Re-eval 159 runs (57 haiku, 51 opus, 51 sonnet) - loop-benchmarking - Controlled experiments across agentic coding configurations. Same task, one variable, what actually works.

commit c7d67a0208000a33a1957c4a7c045a94d3bf9427
parent 1cc1aa1c2d533cc2b3737893c84456794cc80568
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Mon,  6 Apr 2026 12:42:39 +0200

Re-eval 159 runs (57 haiku, 51 opus, 51 sonnet)

Diffstat:
M results/analysis/main_effects_build_quality.json  | 292 ++++++++++++++++++++++++++++++++++++++++----------------------------------------
M results/analysis/main_effects_code_quality.json  | 298 ++++++++++++++++++++++++++++++++++++++++----------------------------------------
M results/analysis/main_effects_gameplay.json  | 304 ++++++++++++++++++++++++++++++++++++++++----------------------------------------
M results/analysis/main_effects_score.json  | 308 ++++++++++++++++++++++++++++++++++++++++----------------------------------------
M results/analysis/main_effects_sonarqube.json  | 320 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/analysis/main_effects_structural.json  | 324 ++++++++++++++++++++++++++++++++++++++++----------------------------------------
M results/analysis/main_effects_transcript.json  | 206 ++++++++++++++++++++++++++++++++++++++++----------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 26 +++++++++++++-------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 2 +-
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 19 ++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 2 +-
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 16 ++++++++--------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 2 +-
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=detailed_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=detailed_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json  | 2 +-
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run1/gameplay-bot-report.json  | 30 +++++++++++++++---------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run2/gameplay-bot-report.json  | 2 +-
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run3/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run3/gameplay-bot-report.json  | 2 +-
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json  | 96 ++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json  | 73 +++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 85 +++++++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 64 +++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 54 ++++++++++++++++++++++++++++++++++--------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 220 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 95 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 217 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 74 ++++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 89 ++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 66 ++++++++++++++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 217 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 62 ++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 220 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 48 +++++++++++++++++++++++++++++++-----------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 85 ++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 62 ++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 129 +++++++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 106 ++++++++++++++++++++++++++++++++++++++++++-------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 73 ++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 218 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 62 +++++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 56 ++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 218 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 58 +++++++++++++++++++++++++++++++++++-----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 217 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 60 +++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 217 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 60 +++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 85 +++++++++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 62 +++++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 163 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 55 ++++++++++++++++++++++++++++++++++---------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 48 ++++++++++++++++++++++++++++++------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 52 +++++++++++++++++++++++++++++++---------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 93 +++++++++++++++++++++++++++++++++++++++++--------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 69 +++++++++++++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 48 ++++++++++++++++++++++++++++++------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 143 +++++++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 120 +++++++++++++++++++++++++++++++++++++++++++------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 65 +++++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 62 +++++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 164 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 63 ++++++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 147 +++++++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 120 +++++++++++++++++++++++++++++++++++++++++++------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 159 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 58 +++++++++++++++++++++++++++++++++++-----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 67 +++++++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 87 ++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 64 +++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 104 +++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 81 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 52 +++++++++++++++++++++++++++++++---------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 68 +++++++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 235 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 66 ++++++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 235 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 78 +++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json  | 240 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 92 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json  | 233 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 69 +++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json  | 233 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 72 ++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json  | 250 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/gameplay-bot-report.json  | 105 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json  | 245 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json  | 66 ++++++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json  | 243 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json  | 42 ++++++++++++++++++++++++++----------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json  | 238 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json  | 69 +++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json  | 154 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json  | 56 ++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 232 +++++++++++++++++++++++++++++++++----------------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 241 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 61 +++++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 245 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 46 +++++++++++++++++++++++++++++-----------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 246 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 56 ++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 244 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 50 +++++++++++++++++++++++++++++++-------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 181 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 58 ++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 179 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 51 ++++++++++++++++++++++++++++++++-------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 34 ++++++++++++++++++++++++++++------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 98 ++++++++++++++++++++++++++++++++++++++++---------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 183 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 46 +++++++++++++++++++++++++++++-----------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 203 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 58 ++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 128 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 61 +++++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 208 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 58 ++++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 203 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 60 +++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 203 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 58 ++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 205 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 53 +++++++++++++++++++++++++++++++++--------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 205 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 57 +++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 209 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 31 ++++++++++++++++---------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 204 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 54 +++++++++++++++++++++++++++++++++---------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 206 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 49 ++++++++++++++++++++++++++++++++-----------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 204 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 54 +++++++++++++++++++++++++++++++++---------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 182 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 52 ++++++++++++++++++++++++++++++++++------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json  | 204 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 48 ++++++++++++++++++++++++++++++------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json  | 203 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 60 +++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json  | 205 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 61 +++++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json  | 205 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/gameplay-bot-report.json  | 59 ++++++++++++++++++++++++++++++++++++-----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json  | 206 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json  | 56 ++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json  | 204 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json  | 62 ++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json  | 129 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json  | 60 +++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json  | 245 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json  | 49 +++++++++++++++++++++++++++++++------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/eval_results.json  | 178 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/gameplay-bot-report.json  | 60 ++++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 243 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 62 ++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 243 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 62 ++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 248 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 60 ++++++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 33 +++++++++++++++++++++++++++------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 244 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 66 ++++++++++++++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 247 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 66 ++++++++++++++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 138 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 98 ++++++++++++++++++++++++++++++++++++++++---------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 166 ++++++++++++++-----------------------------------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 110 ++++++++++++++++++++++++++++++++++++++++---------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 219 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 17 +++++++++--------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 236 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 43 ++++++++++++++++++++++++-------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 181 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 66 ++++++++++++++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 178 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 58 +++++++++++++++++++++++++++++++++++-----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 33 +++++++++++++++++++++++++++------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 183 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 51 ++++++++++++++++++++++++++++++++-------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 203 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 72 +++++++++++++++++++++++++++++++++++++++++++-----------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 183 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 49 +++++++++++++++++++++++++++++++------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 59 ++++++++++++++++++++++++++++++++++++++++++++---------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 197 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 67 +++++++++++++++++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 190 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 59 +++++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 56 ++++++++++++++++++++++++++++++++++----------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 99 +++++++++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 76 +++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 64 +++++++++++++++++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 80 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json  | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 83 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json  | 84 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json  | 141 +++++++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json  | 118 +++++++++++++++++++++++++++++++++++++++++++------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json  | 165 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json  | 75 +++++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json  | 118 +++++++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json  | 95 +++++++++++++++++++++++++++++++++++++++++++------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/gameplay-bot-report.json  | 92 ++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 74 ++++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 21 +++++++++++++++------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 153 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 102 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 58 ++++++++++++++++++++++++++++++++++------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 64 +++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 74 ++++++++++++++++++++++++++++++++++++++++----------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 79 ++++++++++++++++++++++++++++++++++++++++++-------------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 52 +++++++++++++++++++++++++++++++---------------------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 21 +++++++++++++++------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 64 +++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 64 +++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 164 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 71 ++++++++++++++++++++++++++++++++++++++++++++---------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 89 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 148 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 93 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 96 ++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 113 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 17 +++++++++++++----
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 90 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 73 +++++++++++++++++++++++++++++++++++++++++++------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 80 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 95 +++++++++++++++++++++++++++++++++++++++++++++++--------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 153 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 32 ++++++++++++++++----------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 54 ++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 44 +++++++++++++++++++++-----------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 106 ++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 21 +++++++++++----------
M results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 21 +++++++++++----------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 73 ++++++++++++++++++++++++++++++++++++-------------------------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 49 ++++++++++++++++++++++++-------------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 16 ++++++++--------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 16 ++++++++--------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 169 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 40 ++++++++++++++++++++--------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 56 ++++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 30 +++++++++++++++---------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 144 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 4 ++--
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 32 ++++++++++++++++----------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 12 ++++++------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 18 +++++++++---------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 8 ++++----
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 55 +++++++++++++++++++++++++++----------------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 35 +++++++++++++++++------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 52 ++++++++++++++++++++++++++--------------------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 32 ++++++++++++++++----------------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json  | 14 +++++++-------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json  | 6 +++---
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json  | 18 +++++++++---------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json  | 18 +++++++++---------
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json  | 8 ++++----
M results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json  | 8 ++++----

307 files changed, 27096 insertions(+), 6732 deletions(-)
diff --git a/results/analysis/main_effects_build_quality.json b/results/analysis/main_effects_build_quality.json
@@ -3,265 +3,265 @@
     "values": {
       "javascript": {
         "mean": 1.0,
-        "effect": 0.1164,
+        "effect": 0.0913,
         "n": 9
       },
       "typescript": {
-        "mean": 0.8899,
-        "effect": 0.0063,
-        "n": 105
+        "mean": 0.9163,
+        "effect": 0.0077,
+        "n": 142
       },
       "unspecified": {
         "mean": 0.67,
-        "effect": -0.2136,
+        "effect": -0.2387,
         "n": 8
       }
     },
     "spread": 0.33
   },
-  "tool_edit": {
-    "values": {
-      "off": {
-        "mean": 0.67,
-        "effect": -0.2136,
-        "n": 6
-      },
-      "on": {
-        "mean": 0.8947,
-        "effect": 0.011,
-        "n": 116
-      }
-    },
-    "spread": 0.2247
-  },
   "prompt_style": {
     "values": {
       "detailed": {
-        "mean": 0.67,
-        "effect": -0.2136,
-        "n": 5
+        "mean": 0.736,
+        "effect": -0.1727,
+        "n": 10
       },
       "simple": {
-        "mean": 0.8927,
-        "effect": 0.0091,
-        "n": 117
+        "mean": 0.9203,
+        "effect": 0.0116,
+        "n": 149
       }
     },
-    "spread": 0.2227
+    "spread": 0.1843
   },
   "model": {
     "values": {
       "haiku": {
-        "mean": 0.8167,
-        "effect": -0.0669,
-        "n": 54
+        "mean": 0.8205,
+        "effect": -0.0882,
+        "n": 57
       },
       "opus": {
-        "mean": 0.9633,
-        "effect": 0.0797,
-        "n": 27
+        "mean": 0.9676,
+        "effect": 0.059,
+        "n": 51
       },
       "sonnet": {
-        "mean": 0.9193,
-        "effect": 0.0357,
-        "n": 41
+        "mean": 0.9482,
+        "effect": 0.0396,
+        "n": 51
       }
     },
-    "spread": 0.1466
+    "spread": 0.1471
   },
-  "tool_glob": {
+  "claude_version": {
     "values": {
-      "off": {
-        "mean": 0.7512,
-        "effect": -0.1324,
-        "n": 8
+      "2.1.91 (Claude Code)": {
+        "mean": 0.8188,
+        "effect": -0.0899,
+        "n": 51
       },
-      "on": {
-        "mean": 0.8929,
-        "effect": 0.0093,
-        "n": 114
+      "2.1.92 (Claude Code)": {
+        "mean": 0.9511,
+        "effect": 0.0424,
+        "n": 108
       }
     },
-    "spread": 0.1417
+    "spread": 0.1323
   },
-  "sub_agents": {
+  "tool_edit": {
     "values": {
       "off": {
-        "mean": 0.7525,
-        "effect": -0.1311,
-        "n": 8
+        "mean": 0.835,
+        "effect": -0.0737,
+        "n": 12
       },
       "on": {
-        "mean": 0.8928,
-        "effect": 0.0092,
-        "n": 114
+        "mean": 0.9147,
+        "effect": 0.006,
+        "n": 147
       }
     },
-    "spread": 0.1403
+    "spread": 0.0797
   },
-  "claude_version": {
+  "tool_read": {
     "values": {
-      "2.1.91 (Claude Code)": {
-        "mean": 0.8144,
-        "effect": -0.0692,
-        "n": 48
+      "off": {
+        "mean": 0.835,
+        "effect": -0.0737,
+        "n": 12
       },
-      "2.1.92 (Claude Code)": {
-        "mean": 0.9285,
-        "effect": 0.0449,
-        "n": 74
+      "on": {
+        "mean": 0.9147,
+        "effect": 0.006,
+        "n": 147
       }
     },
-    "spread": 0.1141
+    "spread": 0.0797
   },
-  "tool_read": {
+  "sub_agents": {
     "values": {
       "off": {
-        "mean": 0.78,
-        "effect": -0.1036,
-        "n": 9
+        "mean": 0.8586,
+        "effect": -0.0501,
+        "n": 14
       },
       "on": {
-        "mean": 0.8919,
-        "effect": 0.0083,
-        "n": 113
+        "mean": 0.9135,
+        "effect": 0.0048,
+        "n": 145
       }
     },
-    "spread": 0.1119
+    "spread": 0.0549
   },
   "tool_write": {
     "values": {
       "off": {
-        "mean": 0.8167,
-        "effect": -0.0669,
-        "n": 9
+        "mean": 0.8625,
+        "effect": -0.0462,
+        "n": 12
       },
       "on": {
-        "mean": 0.8889,
-        "effect": 0.0053,
-        "n": 113
+        "mean": 0.9124,
+        "effect": 0.0038,
+        "n": 147
       }
     },
-    "spread": 0.0722
+    "spread": 0.0499
   },
   "context_file": {
     "values": {
       "none": {
-        "mean": 0.8769,
-        "effect": -0.0067,
-        "n": 110
+        "mean": 0.9057,
+        "effect": -0.003,
+        "n": 147
       },
       "provided": {
         "mean": 0.945,
-        "effect": 0.0614,
+        "effect": 0.0363,
         "n": 12
       }
     },
-    "spread": 0.0681
+    "spread": 0.0393
   },
-  "effort": {
-    "values": {
-      "high": {
-        "mean": 0.8802,
-        "effect": -0.0034,
-        "n": 113
-      },
-      "max": {
-        "mean": 0.9267,
-        "effect": 0.0431,
-        "n": 9
-      }
-    },
-    "spread": 0.0465
-  },
-  "tool_grep": {
+  "linter": {
     "values": {
       "off": {
-        "mean": 0.8586,
-        "effect": -0.025,
-        "n": 7
+        "mean": 0.8821,
+        "effect": -0.0265,
+        "n": 14
       },
       "on": {
-        "mean": 0.8851,
-        "effect": 0.0015,
-        "n": 115
+        "mean": 0.9112,
+        "effect": 0.0026,
+        "n": 145
       }
     },
-    "spread": 0.0265
+    "spread": 0.0291
   },
   "playwright": {
     "values": {
       "off": {
-        "mean": 0.8625,
-        "effect": -0.0211,
-        "n": 12
+        "mean": 0.8821,
+        "effect": -0.0265,
+        "n": 14
       },
       "on": {
-        "mean": 0.8859,
-        "effect": 0.0023,
-        "n": 110
+        "mean": 0.9112,
+        "effect": 0.0026,
+        "n": 145
       }
     },
-    "spread": 0.0234
+    "spread": 0.0291
   },
-  "web_search": {
+  "max_budget": {
     "values": {
-      "off": {
-        "mean": 0.868,
-        "effect": -0.0156,
-        "n": 10
+      "high": {
+        "mean": 0.89,
+        "effect": -0.0187,
+        "n": 12
       },
-      "on": {
-        "mean": 0.885,
-        "effect": 0.0014,
-        "n": 112
+      "low": {
+        "mean": 0.9102,
+        "effect": 0.0015,
+        "n": 147
       }
     },
-    "spread": 0.017
+    "spread": 0.0202
   },
-  "max_budget": {
+  "tool_grep": {
     "values": {
-      "high": {
+      "off": {
         "mean": 0.89,
-        "effect": 0.0064,
+        "effect": -0.0187,
         "n": 12
       },
-      "low": {
-        "mean": 0.8829,
-        "effect": -0.0007,
-        "n": 110
+      "on": {
+        "mean": 0.9102,
+        "effect": 0.0015,
+        "n": 147
       }
     },
-    "spread": 0.0071
+    "spread": 0.0202
   },
   "human_language": {
     "values": {
       "en": {
-        "mean": 0.8831,
-        "effect": -0.0005,
-        "n": 113
+        "mean": 0.9098,
+        "effect": 0.0011,
+        "n": 150
       },
       "es": {
         "mean": 0.89,
-        "effect": 0.0064,
+        "effect": -0.0187,
         "n": 9
       }
     },
-    "spread": 0.0069
+    "spread": 0.0198
   },
-  "linter": {
+  "effort": {
+    "values": {
+      "high": {
+        "mean": 0.9076,
+        "effect": -0.0011,
+        "n": 150
+      },
+      "max": {
+        "mean": 0.9267,
+        "effect": 0.018,
+        "n": 9
+      }
+    },
+    "spread": 0.0191
+  },
+  "web_search": {
     "values": {
       "off": {
-        "mean": 0.8821,
-        "effect": -0.0015,
-        "n": 14
+        "mean": 0.8985,
+        "effect": -0.0102,
+        "n": 13
       },
       "on": {
-        "mean": 0.8838,
-        "effect": 0.0002,
-        "n": 108
+        "mean": 0.9096,
+        "effect": 0.0009,
+        "n": 146
+      }
+    },
+    "spread": 0.0111
+  },
+  "tool_glob": {
+    "values": {
+      "off": {
+        "mean": 0.9175,
+        "effect": 0.0088,
+        "n": 12
+      },
+      "on": {
+        "mean": 0.908,
+        "effect": -0.0007,
+        "n": 147
       }
     },
-    "spread": 0.0017
+    "spread": 0.0095
   }
 }
 \ No newline at end of file
diff --git a/results/analysis/main_effects_code_quality.json b/results/analysis/main_effects_code_quality.json
@@ -1,267 +1,267 @@
 {
-  "max_budget": {
+  "model": {
     "values": {
-      "high": {
-        "mean": 0.365,
-        "effect": -0.1907,
-        "n": 12
+      "haiku": {
+        "mean": 0.606,
+        "effect": -0.1094,
+        "n": 57
       },
-      "low": {
-        "mean": 0.5713,
-        "effect": 0.0156,
-        "n": 147
+      "opus": {
+        "mean": 0.8235,
+        "effect": 0.1082,
+        "n": 51
+      },
+      "sonnet": {
+        "mean": 0.7294,
+        "effect": 0.0141,
+        "n": 51
       }
     },
-    "spread": 0.2063
+    "spread": 0.2175
+  },
+  "prompt_style": {
+    "values": {
+      "detailed": {
+        "mean": 0.56,
+        "effect": -0.1553,
+        "n": 10
+      },
+      "simple": {
+        "mean": 0.7258,
+        "effect": 0.0104,
+        "n": 149
+      }
+    },
+    "spread": 0.1658
   },
   "language": {
     "values": {
       "javascript": {
         "mean": 0.7389,
-        "effect": 0.1832,
+        "effect": 0.0235,
         "n": 9
       },
       "typescript": {
-        "mean": 0.543,
-        "effect": -0.0127,
+        "mean": 0.7218,
+        "effect": 0.0064,
         "n": 142
       },
       "unspecified": {
         "mean": 0.575,
-        "effect": 0.0193,
+        "effect": -0.1403,
         "n": 8
       }
     },
-    "spread": 0.1959
-  },
-  "tool_edit": {
-    "values": {
-      "off": {
-        "mean": 0.7217,
-        "effect": 0.1659,
-        "n": 12
-      },
-      "on": {
-        "mean": 0.5422,
-        "effect": -0.0135,
-        "n": 147
-      }
-    },
-    "spread": 0.1795
-  },
-  "effort": {
-    "values": {
-      "high": {
-        "mean": 0.5471,
-        "effect": -0.0086,
-        "n": 150
-      },
-      "max": {
-        "mean": 0.6989,
-        "effect": 0.1432,
-        "n": 9
-      }
-    },
-    "spread": 0.1518
+    "spread": 0.1639
   },
   "claude_version": {
     "values": {
       "2.1.91 (Claude Code)": {
-        "mean": 0.4559,
-        "effect": -0.0998,
+        "mean": 0.6094,
+        "effect": -0.1059,
         "n": 51
       },
       "2.1.92 (Claude Code)": {
-        "mean": 0.6029,
-        "effect": 0.0471,
+        "mean": 0.7654,
+        "effect": 0.05,
         "n": 108
       }
     },
-    "spread": 0.147
+    "spread": 0.156
   },
-  "model": {
+  "human_language": {
     "values": {
-      "haiku": {
-        "mean": 0.4686,
-        "effect": -0.0871,
-        "n": 57
-      },
-      "opus": {
-        "mean": 0.6108,
-        "effect": 0.0551,
-        "n": 51
+      "en": {
+        "mean": 0.722,
+        "effect": 0.0067,
+        "n": 150
       },
-      "sonnet": {
-        "mean": 0.598,
-        "effect": 0.0423,
-        "n": 51
+      "es": {
+        "mean": 0.6044,
+        "effect": -0.1109,
+        "n": 9
       }
     },
-    "spread": 0.1422
+    "spread": 0.1176
   },
-  "playwright": {
+  "effort": {
     "values": {
-      "off": {
-        "mean": 0.4286,
-        "effect": -0.1272,
-        "n": 14
+      "high": {
+        "mean": 0.7117,
+        "effect": -0.0037,
+        "n": 150
       },
-      "on": {
-        "mean": 0.568,
-        "effect": 0.0123,
-        "n": 145
+      "max": {
+        "mean": 0.7767,
+        "effect": 0.0613,
+        "n": 9
       }
     },
-    "spread": 0.1394
+    "spread": 0.065
   },
-  "sub_agents": {
+  "tool_grep": {
     "values": {
       "off": {
-        "mean": 0.6807,
-        "effect": 0.125,
-        "n": 14
+        "mean": 0.7675,
+        "effect": 0.0522,
+        "n": 12
       },
       "on": {
-        "mean": 0.5437,
-        "effect": -0.0121,
-        "n": 145
+        "mean": 0.7111,
+        "effect": -0.0043,
+        "n": 147
       }
     },
-    "spread": 0.137
+    "spread": 0.0564
   },
-  "tool_grep": {
+  "tool_read": {
     "values": {
       "off": {
-        "mean": 0.65,
-        "effect": 0.0943,
+        "mean": 0.7667,
+        "effect": 0.0513,
         "n": 12
       },
       "on": {
-        "mean": 0.548,
-        "effect": -0.0077,
+        "mean": 0.7112,
+        "effect": -0.0042,
+        "n": 147
+      }
+    },
+    "spread": 0.0555
+  },
+  "context_file": {
+    "values": {
+      "none": {
+        "mean": 0.7193,
+        "effect": 0.0039,
         "n": 147
+      },
+      "provided": {
+        "mean": 0.6675,
+        "effect": -0.0478,
+        "n": 12
       }
     },
-    "spread": 0.102
+    "spread": 0.0518
   },
   "tool_glob": {
     "values": {
       "off": {
-        "mean": 0.6458,
-        "effect": 0.0901,
+        "mean": 0.7625,
+        "effect": 0.0472,
         "n": 12
       },
       "on": {
-        "mean": 0.5484,
-        "effect": -0.0074,
+        "mean": 0.7115,
+        "effect": -0.0038,
         "n": 147
       }
     },
-    "spread": 0.0974
+    "spread": 0.051
   },
-  "human_language": {
+  "playwright": {
     "values": {
-      "en": {
-        "mean": 0.5505,
-        "effect": -0.0053,
-        "n": 150
+      "off": {
+        "mean": 0.6714,
+        "effect": -0.0439,
+        "n": 14
       },
-      "es": {
-        "mean": 0.6433,
-        "effect": 0.0876,
-        "n": 9
+      "on": {
+        "mean": 0.7196,
+        "effect": 0.0042,
+        "n": 145
       }
     },
-    "spread": 0.0928
+    "spread": 0.0482
   },
-  "context_file": {
+  "max_budget": {
     "values": {
-      "none": {
-        "mean": 0.549,
-        "effect": -0.0067,
-        "n": 147
-      },
-      "provided": {
-        "mean": 0.6383,
-        "effect": 0.0826,
+      "high": {
+        "mean": 0.6775,
+        "effect": -0.0378,
         "n": 12
+      },
+      "low": {
+        "mean": 0.7184,
+        "effect": 0.0031,
+        "n": 147
       }
     },
-    "spread": 0.0893
+    "spread": 0.0409
   },
-  "linter": {
+  "sub_agents": {
     "values": {
       "off": {
-        "mean": 0.4893,
-        "effect": -0.0664,
+        "mean": 0.6914,
+        "effect": -0.0239,
         "n": 14
       },
       "on": {
-        "mean": 0.5621,
-        "effect": 0.0064,
+        "mean": 0.7177,
+        "effect": 0.0023,
         "n": 145
       }
     },
-    "spread": 0.0728
+    "spread": 0.0263
   },
-  "prompt_style": {
+  "web_search": {
     "values": {
-      "detailed": {
-        "mean": 0.505,
-        "effect": -0.0507,
-        "n": 10
+      "off": {
+        "mean": 0.7246,
+        "effect": 0.0093,
+        "n": 13
       },
-      "simple": {
-        "mean": 0.5591,
-        "effect": 0.0034,
-        "n": 149
+      "on": {
+        "mean": 0.7145,
+        "effect": -0.0008,
+        "n": 146
       }
     },
-    "spread": 0.0541
+    "spread": 0.0101
   },
-  "tool_read": {
+  "tool_edit": {
     "values": {
       "off": {
-        "mean": 0.575,
-        "effect": 0.0193,
+        "mean": 0.7217,
+        "effect": 0.0063,
         "n": 12
       },
       "on": {
-        "mean": 0.5541,
-        "effect": -0.0016,
+        "mean": 0.7148,
+        "effect": -0.0005,
         "n": 147
       }
     },
-    "spread": 0.0209
+    "spread": 0.0069
   },
-  "web_search": {
+  "linter": {
     "values": {
       "off": {
-        "mean": 0.5423,
-        "effect": -0.0134,
-        "n": 13
+        "mean": 0.7107,
+        "effect": -0.0046,
+        "n": 14
       },
       "on": {
-        "mean": 0.5569,
-        "effect": 0.0012,
-        "n": 146
+        "mean": 0.7158,
+        "effect": 0.0004,
+        "n": 145
       }
     },
-    "spread": 0.0146
+    "spread": 0.0051
   },
   "tool_write": {
     "values": {
       "off": {
-        "mean": 0.5542,
-        "effect": -0.0016,
+        "mean": 0.7192,
+        "effect": 0.0038,
         "n": 12
       },
       "on": {
-        "mean": 0.5559,
-        "effect": 0.0001,
+        "mean": 0.715,
+        "effect": -0.0003,
         "n": 147
       }
     },
-    "spread": 0.0017
+    "spread": 0.0042
   }
 }
 \ No newline at end of file
diff --git a/results/analysis/main_effects_gameplay.json b/results/analysis/main_effects_gameplay.json
@@ -1,267 +1,267 @@
 {
-  "context_file": {
+  "language": {
     "values": {
-      "none": {
-        "mean": 0.0802,
-        "effect": -0.0396,
-        "n": 147
+      "javascript": {
+        "mean": 0.1956,
+        "effect": -0.313,
+        "n": 9
       },
-      "provided": {
-        "mean": 0.605,
-        "effect": 0.4852,
-        "n": 12
+      "typescript": {
+        "mean": 0.5504,
+        "effect": 0.0418,
+        "n": 142
+      },
+      "unspecified": {
+        "mean": 0.1187,
+        "effect": -0.3898,
+        "n": 8
       }
     },
-    "spread": 0.5248
+    "spread": 0.4317
   },
-  "prompt_style": {
+  "human_language": {
     "values": {
-      "detailed": {
-        "mean": 0.27,
-        "effect": 0.1502,
-        "n": 10
+      "en": {
+        "mean": 0.5249,
+        "effect": 0.0163,
+        "n": 150
       },
-      "simple": {
-        "mean": 0.1097,
-        "effect": -0.0101,
-        "n": 149
+      "es": {
+        "mean": 0.2367,
+        "effect": -0.2719,
+        "n": 9
       }
     },
-    "spread": 0.1603
+    "spread": 0.2882
   },
-  "max_budget": {
+  "tool_grep": {
     "values": {
-      "high": {
-        "mean": 0.25,
-        "effect": 0.1302,
+      "off": {
+        "mean": 0.6842,
+        "effect": 0.1756,
         "n": 12
       },
-      "low": {
-        "mean": 0.1092,
-        "effect": -0.0106,
+      "on": {
+        "mean": 0.4942,
+        "effect": -0.0143,
         "n": 147
       }
     },
-    "spread": 0.1408
+    "spread": 0.19
   },
-  "language": {
+  "model": {
     "values": {
-      "javascript": {
-        "mean": 0.0211,
-        "effect": -0.0987,
-        "n": 9
+      "haiku": {
+        "mean": 0.5023,
+        "effect": -0.0063,
+        "n": 57
       },
-      "typescript": {
-        "mean": 0.1328,
-        "effect": 0.013,
-        "n": 142
+      "opus": {
+        "mean": 0.5976,
+        "effect": 0.0891,
+        "n": 51
       },
-      "unspecified": {
-        "mean": 0.0,
-        "effect": -0.1198,
-        "n": 8
+      "sonnet": {
+        "mean": 0.4265,
+        "effect": -0.0821,
+        "n": 51
       }
     },
-    "spread": 0.1328
+    "spread": 0.1711
   },
-  "tool_edit": {
+  "max_budget": {
     "values": {
-      "off": {
-        "mean": 0.0,
-        "effect": -0.1198,
+      "high": {
+        "mean": 0.6583,
+        "effect": 0.1498,
         "n": 12
       },
-      "on": {
-        "mean": 0.1296,
-        "effect": 0.0098,
+      "low": {
+        "mean": 0.4963,
+        "effect": -0.0122,
         "n": 147
       }
     },
-    "spread": 0.1296
+    "spread": 0.162
   },
-  "tool_read": {
+  "context_file": {
     "values": {
-      "off": {
-        "mean": 0.0,
-        "effect": -0.1198,
-        "n": 12
-      },
-      "on": {
-        "mean": 0.1296,
-        "effect": 0.0098,
+      "none": {
+        "mean": 0.4964,
+        "effect": -0.0122,
         "n": 147
+      },
+      "provided": {
+        "mean": 0.6575,
+        "effect": 0.1489,
+        "n": 12
       }
     },
-    "spread": 0.1296
+    "spread": 0.1611
   },
-  "tool_write": {
+  "web_search": {
     "values": {
       "off": {
-        "mean": 0.0,
-        "effect": -0.1198,
-        "n": 12
+        "mean": 0.4054,
+        "effect": -0.1032,
+        "n": 13
       },
       "on": {
-        "mean": 0.1296,
-        "effect": 0.0098,
-        "n": 147
+        "mean": 0.5177,
+        "effect": 0.0092,
+        "n": 146
       }
     },
-    "spread": 0.1296
+    "spread": 0.1123
   },
-  "human_language": {
+  "tool_glob": {
     "values": {
-      "en": {
-        "mean": 0.127,
-        "effect": 0.0072,
-        "n": 150
+      "off": {
+        "mean": 0.6058,
+        "effect": 0.0973,
+        "n": 12
       },
-      "es": {
-        "mean": 0.0,
-        "effect": -0.1198,
-        "n": 9
+      "on": {
+        "mean": 0.5006,
+        "effect": -0.0079,
+        "n": 147
       }
     },
-    "spread": 0.127
+    "spread": 0.1052
   },
-  "playwright": {
+  "linter": {
     "values": {
       "off": {
-        "mean": 0.0179,
-        "effect": -0.102,
+        "mean": 0.4214,
+        "effect": -0.0871,
         "n": 14
       },
       "on": {
-        "mean": 0.1297,
-        "effect": 0.0098,
+        "mean": 0.517,
+        "effect": 0.0084,
         "n": 145
       }
     },
-    "spread": 0.1118
+    "spread": 0.0956
   },
-  "effort": {
+  "tool_read": {
     "values": {
-      "high": {
-        "mean": 0.1145,
-        "effect": -0.0053,
-        "n": 150
+      "off": {
+        "mean": 0.4392,
+        "effect": -0.0694,
+        "n": 12
       },
-      "max": {
-        "mean": 0.2089,
-        "effect": 0.0891,
-        "n": 9
+      "on": {
+        "mean": 0.5142,
+        "effect": 0.0057,
+        "n": 147
       }
     },
-    "spread": 0.0944
+    "spread": 0.075
   },
-  "tool_grep": {
+  "tool_write": {
     "values": {
       "off": {
-        "mean": 0.0467,
-        "effect": -0.0731,
+        "mean": 0.5742,
+        "effect": 0.0656,
         "n": 12
       },
       "on": {
-        "mean": 0.1258,
-        "effect": 0.006,
+        "mean": 0.5032,
+        "effect": -0.0054,
         "n": 147
       }
     },
-    "spread": 0.0791
+    "spread": 0.071
   },
-  "model": {
+  "playwright": {
     "values": {
-      "haiku": {
-        "mean": 0.1395,
-        "effect": 0.0197,
-        "n": 57
-      },
-      "opus": {
-        "mean": 0.0739,
-        "effect": -0.0459,
-        "n": 51
+      "off": {
+        "mean": 0.4507,
+        "effect": -0.0578,
+        "n": 14
       },
-      "sonnet": {
-        "mean": 0.1437,
-        "effect": 0.0239,
-        "n": 51
+      "on": {
+        "mean": 0.5141,
+        "effect": 0.0056,
+        "n": 145
       }
     },
-    "spread": 0.0698
+    "spread": 0.0634
   },
-  "tool_glob": {
+  "tool_edit": {
     "values": {
       "off": {
-        "mean": 0.0625,
-        "effect": -0.0573,
+        "mean": 0.5425,
+        "effect": 0.0339,
         "n": 12
       },
       "on": {
-        "mean": 0.1245,
-        "effect": 0.0047,
+        "mean": 0.5058,
+        "effect": -0.0028,
         "n": 147
       }
     },
-    "spread": 0.062
+    "spread": 0.0367
   },
-  "sub_agents": {
+  "effort": {
     "values": {
-      "off": {
-        "mean": 0.0807,
-        "effect": -0.0391,
-        "n": 14
+      "high": {
+        "mean": 0.5099,
+        "effect": 0.0014,
+        "n": 150
       },
-      "on": {
-        "mean": 0.1236,
-        "effect": 0.0038,
-        "n": 145
+      "max": {
+        "mean": 0.4856,
+        "effect": -0.023,
+        "n": 9
       }
     },
-    "spread": 0.0429
+    "spread": 0.0243
   },
   "claude_version": {
     "values": {
       "2.1.91 (Claude Code)": {
-        "mean": 0.1363,
-        "effect": 0.0165,
+        "mean": 0.5245,
+        "effect": 0.016,
         "n": 51
       },
       "2.1.92 (Claude Code)": {
-        "mean": 0.112,
-        "effect": -0.0078,
+        "mean": 0.501,
+        "effect": -0.0075,
         "n": 108
       }
     },
-    "spread": 0.0243
+    "spread": 0.0235
   },
-  "web_search": {
+  "prompt_style": {
     "values": {
-      "off": {
-        "mean": 0.14,
-        "effect": 0.0202,
-        "n": 13
+      "detailed": {
+        "mean": 0.49,
+        "effect": -0.0186,
+        "n": 10
       },
-      "on": {
-        "mean": 0.118,
-        "effect": -0.0018,
-        "n": 146
+      "simple": {
+        "mean": 0.5098,
+        "effect": 0.0012,
+        "n": 149
       }
     },
-    "spread": 0.022
+    "spread": 0.0198
   },
-  "linter": {
+  "sub_agents": {
     "values": {
       "off": {
-        "mean": 0.1343,
-        "effect": 0.0145,
+        "mean": 0.5093,
+        "effect": 0.0007,
         "n": 14
       },
       "on": {
-        "mean": 0.1184,
-        "effect": -0.0014,
+        "mean": 0.5085,
+        "effect": -0.0001,
         "n": 145
       }
     },
-    "spread": 0.0159
+    "spread": 0.0008
   }
 }
 \ No newline at end of file
diff --git a/results/analysis/main_effects_score.json b/results/analysis/main_effects_score.json
@@ -1,267 +1,267 @@
 {
-  "context_file": {
-    "values": {
-      "none": {
-        "mean": 0.0638,
-        "effect": -0.0408,
-        "n": 147
-      },
-      "provided": {
-        "mean": 0.6046,
-        "effect": 0.4999,
-        "n": 12
-      }
-    },
-    "spread": 0.5408
-  },
-  "effort": {
+  "human_language": {
     "values": {
-      "high": {
-        "mean": 0.0955,
-        "effect": -0.0092,
+      "en": {
+        "mean": 0.5721,
+        "effect": 0.0092,
         "n": 150
       },
-      "max": {
-        "mean": 0.2572,
-        "effect": 0.1526,
+      "es": {
+        "mean": 0.4089,
+        "effect": -0.154,
         "n": 9
       }
     },
-    "spread": 0.1617
+    "spread": 0.1632
   },
-  "language": {
+  "model": {
     "values": {
-      "javascript": {
-        "mean": 0.0211,
-        "effect": -0.0835,
-        "n": 9
+      "haiku": {
+        "mean": 0.5382,
+        "effect": -0.0247,
+        "n": 57
       },
-      "typescript": {
-        "mean": 0.1158,
-        "effect": 0.0112,
-        "n": 142
+      "opus": {
+        "mean": 0.6375,
+        "effect": 0.0746,
+        "n": 51
       },
-      "unspecified": {
-        "mean": 0.0,
-        "effect": -0.1047,
-        "n": 8
+      "sonnet": {
+        "mean": 0.5159,
+        "effect": -0.047,
+        "n": 51
       }
     },
-    "spread": 0.1158
+    "spread": 0.1216
   },
-  "tool_edit": {
+  "tool_grep": {
     "values": {
       "off": {
-        "mean": 0.0,
-        "effect": -0.1047,
+        "mean": 0.6617,
+        "effect": 0.0988,
         "n": 12
       },
       "on": {
-        "mean": 0.1132,
-        "effect": 0.0085,
+        "mean": 0.5548,
+        "effect": -0.0081,
         "n": 147
       }
     },
-    "spread": 0.1132
+    "spread": 0.1069
   },
   "tool_read": {
     "values": {
       "off": {
-        "mean": 0.0,
-        "effect": -0.1047,
+        "mean": 0.4846,
+        "effect": -0.0783,
         "n": 12
       },
       "on": {
-        "mean": 0.1132,
-        "effect": 0.0085,
+        "mean": 0.5693,
+        "effect": 0.0064,
         "n": 147
       }
     },
-    "spread": 0.1132
+    "spread": 0.0847
   },
-  "tool_write": {
+  "context_file": {
     "values": {
-      "off": {
-        "mean": 0.0,
-        "effect": -0.1047,
-        "n": 12
-      },
-      "on": {
-        "mean": 0.1132,
-        "effect": 0.0085,
+      "none": {
+        "mean": 0.558,
+        "effect": -0.0049,
         "n": 147
+      },
+      "provided": {
+        "mean": 0.6225,
+        "effect": 0.0596,
+        "n": 12
       }
     },
-    "spread": 0.1132
+    "spread": 0.0645
   },
-  "max_budget": {
+  "language": {
     "values": {
-      "high": {
-        "mean": 0.2063,
-        "effect": 0.1016,
-        "n": 12
+      "javascript": {
+        "mean": 0.5228,
+        "effect": -0.0401,
+        "n": 9
       },
-      "low": {
-        "mean": 0.0964,
-        "effect": -0.0083,
-        "n": 147
+      "typescript": {
+        "mean": 0.5686,
+        "effect": 0.0057,
+        "n": 142
+      },
+      "unspecified": {
+        "mean": 0.5069,
+        "effect": -0.056,
+        "n": 8
       }
     },
-    "spread": 0.1099
+    "spread": 0.0617
   },
-  "playwright": {
+  "web_search": {
     "values": {
       "off": {
-        "mean": 0.0179,
-        "effect": -0.0868,
-        "n": 14
+        "mean": 0.5169,
+        "effect": -0.0459,
+        "n": 13
       },
       "on": {
-        "mean": 0.113,
-        "effect": 0.0084,
-        "n": 145
+        "mean": 0.567,
+        "effect": 0.0041,
+        "n": 146
       }
     },
-    "spread": 0.0951
+    "spread": 0.0501
   },
-  "human_language": {
+  "effort": {
     "values": {
-      "en": {
-        "mean": 0.1092,
-        "effect": 0.0045,
+      "high": {
+        "mean": 0.5654,
+        "effect": 0.0025,
         "n": 150
       },
-      "es": {
-        "mean": 0.0289,
-        "effect": -0.0758,
+      "max": {
+        "mean": 0.5206,
+        "effect": -0.0423,
         "n": 9
       }
     },
-    "spread": 0.0803
+    "spread": 0.0448
   },
-  "tool_glob": {
+  "linter": {
     "values": {
       "off": {
-        "mean": 0.0312,
-        "effect": -0.0734,
-        "n": 12
+        "mean": 0.5254,
+        "effect": -0.0375,
+        "n": 14
       },
       "on": {
-        "mean": 0.1106,
-        "effect": 0.006,
+        "mean": 0.5665,
+        "effect": 0.0036,
+        "n": 145
+      }
+    },
+    "spread": 0.0411
+  },
+  "max_budget": {
+    "values": {
+      "high": {
+        "mean": 0.6,
+        "effect": 0.0371,
+        "n": 12
+      },
+      "low": {
+        "mean": 0.5598,
+        "effect": -0.003,
         "n": 147
       }
     },
-    "spread": 0.0794
+    "spread": 0.0402
   },
-  "prompt_style": {
+  "claude_version": {
     "values": {
-      "detailed": {
-        "mean": 0.179,
-        "effect": 0.0743,
-        "n": 10
+      "2.1.91 (Claude Code)": {
+        "mean": 0.5387,
+        "effect": -0.0241,
+        "n": 51
       },
-      "simple": {
-        "mean": 0.0997,
-        "effect": -0.005,
-        "n": 149
+      "2.1.92 (Claude Code)": {
+        "mean": 0.5743,
+        "effect": 0.0114,
+        "n": 108
       }
     },
-    "spread": 0.0793
+    "spread": 0.0356
   },
-  "tool_grep": {
+  "tool_edit": {
     "values": {
       "off": {
-        "mean": 0.0467,
-        "effect": -0.058,
+        "mean": 0.5358,
+        "effect": -0.027,
         "n": 12
       },
       "on": {
-        "mean": 0.1094,
-        "effect": 0.0047,
+        "mean": 0.5651,
+        "effect": 0.0022,
         "n": 147
       }
     },
-    "spread": 0.0627
+    "spread": 0.0293
   },
-  "sub_agents": {
+  "tool_glob": {
     "values": {
       "off": {
-        "mean": 0.0493,
-        "effect": -0.0554,
-        "n": 14
+        "mean": 0.5812,
+        "effect": 0.0184,
+        "n": 12
       },
       "on": {
-        "mean": 0.11,
-        "effect": 0.0053,
-        "n": 145
+        "mean": 0.5614,
+        "effect": -0.0015,
+        "n": 147
       }
     },
-    "spread": 0.0607
+    "spread": 0.0198
   },
-  "model": {
+  "tool_write": {
     "values": {
-      "haiku": {
-        "mean": 0.1214,
-        "effect": 0.0167,
-        "n": 57
-      },
-      "opus": {
-        "mean": 0.0674,
-        "effect": -0.0373,
-        "n": 51
+      "off": {
+        "mean": 0.5783,
+        "effect": 0.0155,
+        "n": 12
       },
-      "sonnet": {
-        "mean": 0.1232,
-        "effect": 0.0186,
-        "n": 51
+      "on": {
+        "mean": 0.5616,
+        "effect": -0.0013,
+        "n": 147
       }
     },
-    "spread": 0.0558
+    "spread": 0.0167
   },
-  "linter": {
+  "sub_agents": {
     "values": {
       "off": {
-        "mean": 0.0761,
-        "effect": -0.0286,
+        "mean": 0.5507,
+        "effect": -0.0121,
         "n": 14
       },
       "on": {
-        "mean": 0.1074,
-        "effect": 0.0028,
+        "mean": 0.564,
+        "effect": 0.0012,
         "n": 145
       }
     },
-    "spread": 0.0313
+    "spread": 0.0133
   },
-  "claude_version": {
+  "prompt_style": {
     "values": {
-      "2.1.91 (Claude Code)": {
-        "mean": 0.1234,
-        "effect": 0.0188,
-        "n": 51
+      "detailed": {
+        "mean": 0.565,
+        "effect": 0.0021,
+        "n": 10
       },
-      "2.1.92 (Claude Code)": {
-        "mean": 0.0958,
-        "effect": -0.0089,
-        "n": 108
+      "simple": {
+        "mean": 0.5627,
+        "effect": -0.0001,
+        "n": 149
       }
     },
-    "spread": 0.0276
+    "spread": 0.0023
   },
-  "web_search": {
+  "playwright": {
     "values": {
       "off": {
-        "mean": 0.1158,
-        "effect": 0.0111,
-        "n": 13
+        "mean": 0.5646,
+        "effect": 0.0018,
+        "n": 14
       },
       "on": {
-        "mean": 0.1037,
-        "effect": -0.001,
-        "n": 146
+        "mean": 0.5627,
+        "effect": -0.0002,
+        "n": 145
       }
     },
-    "spread": 0.0121
+    "spread": 0.0019
   }
 }
 \ No newline at end of file
diff --git a/results/analysis/main_effects_sonarqube.json b/results/analysis/main_effects_sonarqube.json
@@ -1,217 +1,267 @@
 {
-  "context_file": {
+  "language": {
     "values": {
-      "none": {
-        "mean": 0.1089,
-        "effect": -0.1213,
-        "n": 37
+      "javascript": {
+        "mean": 0.85,
+        "effect": 0.2328,
+        "n": 9
       },
-      "provided": {
-        "mean": 0.6042,
-        "effect": 0.374,
-        "n": 12
+      "typescript": {
+        "mean": 0.5868,
+        "effect": -0.0304,
+        "n": 142
+      },
+      "unspecified": {
+        "mean": 0.895,
+        "effect": 0.2778,
+        "n": 8
       }
     },
-    "spread": 0.4953
+    "spread": 0.3082
   },
-  "effort": {
+  "model": {
     "values": {
-      "high": {
-        "mean": 0.1939,
-        "effect": -0.0363,
-        "n": 44
+      "haiku": {
+        "mean": 0.574,
+        "effect": -0.0431,
+        "n": 57
       },
-      "max": {
-        "mean": 0.55,
-        "effect": 0.3198,
-        "n": 5
+      "opus": {
+        "mean": 0.6773,
+        "effect": 0.0601,
+        "n": 51
+      },
+      "sonnet": {
+        "mean": 0.6053,
+        "effect": -0.0119,
+        "n": 51
       }
     },
-    "spread": 0.3561
+    "spread": 0.1033
   },
-  "human_language": {
+  "tool_edit": {
     "values": {
-      "en": {
-        "mean": 0.2242,
-        "effect": -0.006,
-        "n": 48
+      "off": {
+        "mean": 0.5292,
+        "effect": -0.088,
+        "n": 12
       },
-      "es": {
-        "mean": 0.52,
-        "effect": 0.2898,
-        "n": 1
+      "on": {
+        "mean": 0.6244,
+        "effect": 0.0072,
+        "n": 147
       }
     },
-    "spread": 0.2958
+    "spread": 0.0952
   },
-  "linter": {
+  "claude_version": {
     "values": {
-      "off": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 8
+      "2.1.91 (Claude Code)": {
+        "mean": 0.5529,
+        "effect": -0.0642,
+        "n": 51
       },
-      "on": {
-        "mean": 0.2751,
-        "effect": 0.0449,
-        "n": 41
+      "2.1.92 (Claude Code)": {
+        "mean": 0.6475,
+        "effect": 0.0303,
+        "n": 108
       }
     },
-    "spread": 0.2751
+    "spread": 0.0946
   },
-  "language": {
+  "tool_read": {
     "values": {
-      "javascript": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 6
+      "off": {
+        "mean": 0.53,
+        "effect": -0.0872,
+        "n": 12
       },
-      "typescript": {
-        "mean": 0.2623,
-        "effect": 0.0321,
-        "n": 43
+      "on": {
+        "mean": 0.6243,
+        "effect": 0.0071,
+        "n": 147
       }
     },
-    "spread": 0.2623
+    "spread": 0.0943
   },
-  "prompt_style": {
+  "max_budget": {
     "values": {
-      "detailed": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 4
+      "high": {
+        "mean": 0.5417,
+        "effect": -0.0755,
+        "n": 12
       },
-      "simple": {
-        "mean": 0.2507,
-        "effect": 0.0205,
-        "n": 45
+      "low": {
+        "mean": 0.6233,
+        "effect": 0.0062,
+        "n": 147
       }
     },
-    "spread": 0.2507
+    "spread": 0.0816
   },
   "playwright": {
     "values": {
       "off": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 2
+        "mean": 0.6786,
+        "effect": 0.0614,
+        "n": 14
       },
       "on": {
-        "mean": 0.24,
-        "effect": 0.0098,
-        "n": 47
+        "mean": 0.6112,
+        "effect": -0.0059,
+        "n": 145
       }
     },
-    "spread": 0.24
+    "spread": 0.0674
   },
-  "sub_agents": {
+  "tool_glob": {
     "values": {
       "off": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 2
+        "mean": 0.5567,
+        "effect": -0.0605,
+        "n": 12
       },
       "on": {
-        "mean": 0.24,
-        "effect": 0.0098,
-        "n": 47
+        "mean": 0.6221,
+        "effect": 0.0049,
+        "n": 147
       }
     },
-    "spread": 0.24
+    "spread": 0.0654
   },
-  "tool_glob": {
+  "effort": {
     "values": {
-      "off": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 2
+      "high": {
+        "mean": 0.6209,
+        "effect": 0.0037,
+        "n": 150
       },
-      "on": {
-        "mean": 0.24,
-        "effect": 0.0098,
-        "n": 47
+      "max": {
+        "mean": 0.5556,
+        "effect": -0.0616,
+        "n": 9
       }
     },
-    "spread": 0.24
+    "spread": 0.0653
   },
-  "web_search": {
+  "human_language": {
     "values": {
-      "off": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 2
+      "en": {
+        "mean": 0.6193,
+        "effect": 0.0022,
+        "n": 150
       },
-      "on": {
-        "mean": 0.24,
-        "effect": 0.0098,
-        "n": 47
+      "es": {
+        "mean": 0.5811,
+        "effect": -0.0361,
+        "n": 9
       }
     },
-    "spread": 0.24
+    "spread": 0.0382
   },
-  "tool_edit": {
+  "tool_write": {
     "values": {
       "off": {
-        "mean": 0.0,
-        "effect": -0.2302,
-        "n": 1
+        "mean": 0.5825,
+        "effect": -0.0347,
+        "n": 12
       },
       "on": {
-        "mean": 0.235,
-        "effect": 0.0048,
-        "n": 48
+        "mean": 0.62,
+        "effect": 0.0028,
+        "n": 147
       }
     },
-    "spread": 0.235
+    "spread": 0.0375
   },
-  "claude_version": {
+  "context_file": {
     "values": {
-      "2.1.91 (Claude Code)": {
-        "mean": 0.2692,
-        "effect": 0.039,
-        "n": 13
+      "none": {
+        "mean": 0.6196,
+        "effect": 0.0024,
+        "n": 147
       },
-      "2.1.92 (Claude Code)": {
-        "mean": 0.2161,
-        "effect": -0.0141,
-        "n": 36
+      "provided": {
+        "mean": 0.5875,
+        "effect": -0.0297,
+        "n": 12
       }
     },
-    "spread": 0.0531
+    "spread": 0.0321
   },
-  "max_budget": {
+  "sub_agents": {
     "values": {
-      "high": {
-        "mean": 0.195,
-        "effect": -0.0352,
+      "off": {
+        "mean": 0.5921,
+        "effect": -0.025,
+        "n": 14
+      },
+      "on": {
+        "mean": 0.6196,
+        "effect": 0.0024,
+        "n": 145
+      }
+    },
+    "spread": 0.0275
+  },
+  "prompt_style": {
+    "values": {
+      "detailed": {
+        "mean": 0.64,
+        "effect": 0.0228,
         "n": 10
       },
-      "low": {
-        "mean": 0.2392,
-        "effect": 0.009,
-        "n": 39
+      "simple": {
+        "mean": 0.6156,
+        "effect": -0.0015,
+        "n": 149
       }
     },
-    "spread": 0.0442
+    "spread": 0.0244
   },
-  "model": {
+  "tool_grep": {
     "values": {
-      "haiku": {
-        "mean": 0.2188,
-        "effect": -0.0115,
-        "n": 16
+      "off": {
+        "mean": 0.6392,
+        "effect": 0.022,
+        "n": 12
       },
-      "opus": {
-        "mean": 0.2214,
-        "effect": -0.0088,
+      "on": {
+        "mean": 0.6154,
+        "effect": -0.0018,
+        "n": 147
+      }
+    },
+    "spread": 0.0238
+  },
+  "linter": {
+    "values": {
+      "off": {
+        "mean": 0.6293,
+        "effect": 0.0121,
         "n": 14
       },
-      "sonnet": {
-        "mean": 0.2463,
-        "effect": 0.0161,
-        "n": 19
+      "on": {
+        "mean": 0.616,
+        "effect": -0.0012,
+        "n": 145
       }
     },
-    "spread": 0.0275
+    "spread": 0.0133
+  },
+  "web_search": {
+    "values": {
+      "off": {
+        "mean": 0.6285,
+        "effect": 0.0113,
+        "n": 13
+      },
+      "on": {
+        "mean": 0.6162,
+        "effect": -0.001,
+        "n": 146
+      }
+    },
+    "spread": 0.0123
   }
 }
 \ No newline at end of file
diff --git a/results/analysis/main_effects_structural.json b/results/analysis/main_effects_structural.json
@@ -1,267 +1,267 @@
 {
-  "tool_read": {
-    "values": {
-      "off": {
-        "mean": 0.6944,
-        "effect": -0.1649,
-        "n": 9
-      },
-      "on": {
-        "mean": 0.8724,
-        "effect": 0.013,
-        "n": 114
-      }
-    },
-    "spread": 0.178
-  },
   "model": {
     "values": {
       "haiku": {
-        "mean": 0.7798,
-        "effect": -0.0795,
-        "n": 51
+        "mean": 0.7986,
+        "effect": -0.0895,
+        "n": 57
       },
       "opus": {
-        "mean": 0.9507,
-        "effect": 0.0914,
-        "n": 27
+        "mean": 0.9739,
+        "effect": 0.0859,
+        "n": 51
       },
       "sonnet": {
-        "mean": 0.8947,
-        "effect": 0.0353,
-        "n": 45
+        "mean": 0.9022,
+        "effect": 0.0141,
+        "n": 51
       }
     },
-    "spread": 0.1709
+    "spread": 0.1753
   },
-  "tool_edit": {
+  "prompt_style": {
+    "values": {
+      "detailed": {
+        "mean": 0.759,
+        "effect": -0.1291,
+        "n": 10
+      },
+      "simple": {
+        "mean": 0.8967,
+        "effect": 0.0087,
+        "n": 149
+      }
+    },
+    "spread": 0.1377
+  },
+  "tool_read": {
     "values": {
       "off": {
-        "mean": 0.7188,
-        "effect": -0.1406,
-        "n": 8
+        "mean": 0.7708,
+        "effect": -0.1172,
+        "n": 12
       },
       "on": {
-        "mean": 0.8691,
-        "effect": 0.0098,
-        "n": 115
+        "mean": 0.8976,
+        "effect": 0.0096,
+        "n": 147
       }
     },
-    "spread": 0.1503
+    "spread": 0.1268
   },
   "claude_version": {
     "values": {
       "2.1.91 (Claude Code)": {
-        "mean": 0.7836,
-        "effect": -0.0758,
-        "n": 45
+        "mean": 0.8041,
+        "effect": -0.0839,
+        "n": 51
       },
       "2.1.92 (Claude Code)": {
-        "mean": 0.9031,
-        "effect": 0.0437,
-        "n": 78
+        "mean": 0.9277,
+        "effect": 0.0396,
+        "n": 108
       }
     },
-    "spread": 0.1195
+    "spread": 0.1236
   },
   "tool_grep": {
     "values": {
       "off": {
-        "mean": 0.75,
-        "effect": -0.1093,
-        "n": 9
+        "mean": 0.7917,
+        "effect": -0.0964,
+        "n": 12
       },
       "on": {
-        "mean": 0.868,
-        "effect": 0.0086,
-        "n": 114
+        "mean": 0.8959,
+        "effect": 0.0079,
+        "n": 147
       }
     },
-    "spread": 0.118
+    "spread": 0.1042
   },
-  "tool_glob": {
+  "language": {
+    "values": {
+      "javascript": {
+        "mean": 0.89,
+        "effect": 0.0019,
+        "n": 9
+      },
+      "typescript": {
+        "mean": 0.8932,
+        "effect": 0.0052,
+        "n": 142
+      },
+      "unspecified": {
+        "mean": 0.7938,
+        "effect": -0.0943,
+        "n": 8
+      }
+    },
+    "spread": 0.0994
+  },
+  "tool_edit": {
     "values": {
       "off": {
-        "mean": 0.75,
-        "effect": -0.1093,
-        "n": 7
+        "mean": 0.8125,
+        "effect": -0.0756,
+        "n": 12
       },
       "on": {
-        "mean": 0.8659,
-        "effect": 0.0066,
-        "n": 116
+        "mean": 0.8942,
+        "effect": 0.0062,
+        "n": 147
       }
     },
-    "spread": 0.1159
+    "spread": 0.0817
   },
-  "prompt_style": {
+  "linter": {
     "values": {
-      "detailed": {
-        "mean": 0.759,
-        "effect": -0.1003,
-        "n": 10
+      "off": {
+        "mean": 0.8157,
+        "effect": -0.0723,
+        "n": 14
       },
-      "simple": {
-        "mean": 0.8682,
-        "effect": 0.0089,
-        "n": 113
+      "on": {
+        "mean": 0.895,
+        "effect": 0.007,
+        "n": 145
       }
     },
-    "spread": 0.1092
+    "spread": 0.0793
   },
   "playwright": {
     "values": {
       "off": {
-        "mean": 0.767,
-        "effect": -0.0923,
-        "n": 10
+        "mean": 0.8336,
+        "effect": -0.0545,
+        "n": 14
       },
       "on": {
-        "mean": 0.8675,
-        "effect": 0.0082,
-        "n": 113
+        "mean": 0.8933,
+        "effect": 0.0053,
+        "n": 145
       }
     },
-    "spread": 0.1005
+    "spread": 0.0597
   },
-  "language": {
+  "human_language": {
     "values": {
-      "javascript": {
-        "mean": 0.89,
-        "effect": 0.0307,
-        "n": 9
-      },
-      "typescript": {
-        "mean": 0.8617,
-        "effect": 0.0023,
-        "n": 106
+      "en": {
+        "mean": 0.8913,
+        "effect": 0.0033,
+        "n": 150
       },
-      "unspecified": {
-        "mean": 0.7938,
-        "effect": -0.0656,
-        "n": 8
+      "es": {
+        "mean": 0.8333,
+        "effect": -0.0547,
+        "n": 9
       }
     },
-    "spread": 0.0962
+    "spread": 0.058
   },
-  "tool_write": {
+  "sub_agents": {
     "values": {
       "off": {
-        "mean": 0.7917,
-        "effect": -0.0677,
-        "n": 6
+        "mean": 0.8514,
+        "effect": -0.0366,
+        "n": 14
       },
       "on": {
-        "mean": 0.8628,
+        "mean": 0.8916,
         "effect": 0.0035,
-        "n": 117
+        "n": 145
       }
     },
-    "spread": 0.0711
+    "spread": 0.0402
   },
-  "effort": {
+  "max_budget": {
     "values": {
       "high": {
-        "mean": 0.8548,
-        "effect": -0.0045,
-        "n": 114
+        "mean": 0.8542,
+        "effect": -0.0339,
+        "n": 12
       },
-      "max": {
-        "mean": 0.9167,
-        "effect": 0.0573,
-        "n": 9
+      "low": {
+        "mean": 0.8908,
+        "effect": 0.0028,
+        "n": 147
       }
     },
-    "spread": 0.0619
+    "spread": 0.0366
   },
-  "sub_agents": {
+  "tool_glob": {
     "values": {
       "off": {
-        "mean": 0.8109,
-        "effect": -0.0484,
-        "n": 11
+        "mean": 0.8542,
+        "effect": -0.0339,
+        "n": 12
       },
       "on": {
-        "mean": 0.8641,
-        "effect": 0.0048,
-        "n": 112
+        "mean": 0.8908,
+        "effect": 0.0028,
+        "n": 147
       }
     },
-    "spread": 0.0532
+    "spread": 0.0366
   },
-  "linter": {
+  "web_search": {
     "values": {
       "off": {
-        "mean": 0.8157,
-        "effect": -0.0436,
-        "n": 14
+        "mean": 0.8592,
+        "effect": -0.0288,
+        "n": 13
       },
       "on": {
-        "mean": 0.865,
-        "effect": 0.0056,
-        "n": 109
+        "mean": 0.8906,
+        "effect": 0.0026,
+        "n": 146
       }
     },
-    "spread": 0.0493
+    "spread": 0.0314
   },
-  "web_search": {
+  "effort": {
+    "values": {
+      "high": {
+        "mean": 0.8863,
+        "effect": -0.0017,
+        "n": 150
+      },
+      "max": {
+        "mean": 0.9167,
+        "effect": 0.0286,
+        "n": 9
+      }
+    },
+    "spread": 0.0304
+  },
+  "tool_write": {
     "values": {
       "off": {
-        "mean": 0.817,
-        "effect": -0.0423,
-        "n": 10
+        "mean": 0.875,
+        "effect": -0.0131,
+        "n": 12
       },
       "on": {
-        "mean": 0.8631,
-        "effect": 0.0037,
-        "n": 113
+        "mean": 0.8891,
+        "effect": 0.0011,
+        "n": 147
       }
     },
-    "spread": 0.0461
+    "spread": 0.0141
   },
   "context_file": {
     "values": {
       "none": {
-        "mean": 0.8554,
-        "effect": -0.0039,
-        "n": 111
+        "mean": 0.8874,
+        "effect": -0.0006,
+        "n": 147
       },
       "provided": {
         "mean": 0.8958,
-        "effect": 0.0365,
+        "effect": 0.0078,
         "n": 12
       }
     },
-    "spread": 0.0404
-  },
-  "human_language": {
-    "values": {
-      "en": {
-        "mean": 0.8614,
-        "effect": 0.0021,
-        "n": 114
-      },
-      "es": {
-        "mean": 0.8333,
-        "effect": -0.026,
-        "n": 9
-      }
-    },
-    "spread": 0.0281
-  },
-  "max_budget": {
-    "values": {
-      "high": {
-        "mean": 0.8542,
-        "effect": -0.0052,
-        "n": 12
-      },
-      "low": {
-        "mean": 0.8599,
-        "effect": 0.0006,
-        "n": 111
-      }
-    },
-    "spread": 0.0057
+    "spread": 0.0084
   }
 }
 \ No newline at end of file
diff --git a/results/analysis/main_effects_transcript.json b/results/analysis/main_effects_transcript.json
@@ -2,266 +2,266 @@
   "model": {
     "values": {
       "haiku": {
-        "mean": 0.7368,
-        "effect": -0.1638,
+        "mean": 0.7895,
+        "effect": -0.13,
         "n": 57
       },
       "opus": {
         "mean": 1.0,
-        "effect": 0.0994,
+        "effect": 0.0805,
         "n": 51
       },
       "sonnet": {
         "mean": 0.9843,
-        "effect": 0.0837,
+        "effect": 0.0648,
         "n": 51
       }
     },
-    "spread": 0.2632
+    "spread": 0.2105
   },
   "claude_version": {
     "values": {
       "2.1.91 (Claude Code)": {
-        "mean": 0.7255,
-        "effect": -0.1751,
+        "mean": 0.7843,
+        "effect": -0.1352,
         "n": 51
       },
       "2.1.92 (Claude Code)": {
         "mean": 0.9833,
-        "effect": 0.0827,
+        "effect": 0.0638,
         "n": 108
       }
     },
-    "spread": 0.2578
-  },
-  "tool_read": {
-    "values": {
-      "off": {
-        "mean": 0.6875,
-        "effect": -0.2131,
-        "n": 12
-      },
-      "on": {
-        "mean": 0.918,
-        "effect": 0.0174,
-        "n": 147
-      }
-    },
-    "spread": 0.2305
+    "spread": 0.199
   },
   "language": {
     "values": {
       "javascript": {
         "mean": 1.0,
-        "effect": 0.0994,
+        "effect": 0.0805,
         "n": 9
       },
       "typescript": {
-        "mean": 0.8905,
-        "effect": -0.0101,
+        "mean": 0.9116,
+        "effect": -0.0079,
         "n": 142
       },
       "unspecified": {
         "mean": 0.9688,
-        "effect": 0.0681,
+        "effect": 0.0493,
         "n": 8
       }
     },
-    "spread": 0.1095
+    "spread": 0.0884
   },
   "playwright": {
     "values": {
       "off": {
         "mean": 0.8643,
-        "effect": -0.0363,
+        "effect": -0.0552,
         "n": 14
       },
       "on": {
-        "mean": 0.9041,
-        "effect": 0.0035,
+        "mean": 0.9248,
+        "effect": 0.0053,
         "n": 145
       }
     },
-    "spread": 0.0398
+    "spread": 0.0605
   },
   "linter": {
     "values": {
       "off": {
         "mean": 0.8679,
-        "effect": -0.0328,
+        "effect": -0.0516,
         "n": 14
       },
       "on": {
-        "mean": 0.9038,
-        "effect": 0.0032,
+        "mean": 0.9245,
+        "effect": 0.005,
         "n": 145
       }
     },
-    "spread": 0.0359
+    "spread": 0.0566
+  },
+  "tool_read": {
+    "values": {
+      "off": {
+        "mean": 0.875,
+        "effect": -0.0445,
+        "n": 12
+      },
+      "on": {
+        "mean": 0.9231,
+        "effect": 0.0036,
+        "n": 147
+      }
+    },
+    "spread": 0.0481
   },
   "max_budget": {
     "values": {
       "high": {
         "mean": 0.8792,
-        "effect": -0.0215,
+        "effect": -0.0403,
         "n": 12
       },
       "low": {
-        "mean": 0.9024,
-        "effect": 0.0018,
+        "mean": 0.9228,
+        "effect": 0.0033,
         "n": 147
       }
     },
-    "spread": 0.0232
+    "spread": 0.0436
   },
   "tool_edit": {
     "values": {
       "off": {
         "mean": 0.8792,
-        "effect": -0.0215,
+        "effect": -0.0403,
         "n": 12
       },
       "on": {
-        "mean": 0.9024,
-        "effect": 0.0018,
+        "mean": 0.9228,
+        "effect": 0.0033,
         "n": 147
       }
     },
-    "spread": 0.0232
+    "spread": 0.0436
   },
   "tool_write": {
     "values": {
       "off": {
         "mean": 0.8792,
-        "effect": -0.0215,
+        "effect": -0.0403,
         "n": 12
       },
       "on": {
-        "mean": 0.9024,
-        "effect": 0.0018,
+        "mean": 0.9228,
+        "effect": 0.0033,
         "n": 147
       }
     },
-    "spread": 0.0232
-  },
-  "human_language": {
-    "values": {
-      "en": {
-        "mean": 0.8993,
-        "effect": -0.0013,
-        "n": 150
-      },
-      "es": {
-        "mean": 0.9222,
-        "effect": 0.0216,
-        "n": 9
-      }
-    },
-    "spread": 0.0229
+    "spread": 0.0436
   },
   "sub_agents": {
     "values": {
       "off": {
         "mean": 0.8821,
-        "effect": -0.0185,
+        "effect": -0.0374,
         "n": 14
       },
       "on": {
-        "mean": 0.9024,
-        "effect": 0.0018,
+        "mean": 0.9231,
+        "effect": 0.0036,
         "n": 145
       }
     },
-    "spread": 0.0203
+    "spread": 0.041
   },
   "tool_glob": {
     "values": {
       "off": {
         "mean": 0.8833,
-        "effect": -0.0173,
+        "effect": -0.0362,
         "n": 12
       },
       "on": {
-        "mean": 0.902,
-        "effect": 0.0014,
+        "mean": 0.9224,
+        "effect": 0.003,
         "n": 147
       }
     },
-    "spread": 0.0187
-  },
-  "effort": {
-    "values": {
-      "high": {
-        "mean": 0.8997,
-        "effect": -0.001,
-        "n": 150
-      },
-      "max": {
-        "mean": 0.9167,
-        "effect": 0.016,
-        "n": 9
-      }
-    },
-    "spread": 0.017
+    "spread": 0.0391
   },
   "tool_grep": {
     "values": {
       "off": {
         "mean": 0.8875,
-        "effect": -0.0131,
+        "effect": -0.032,
         "n": 12
       },
       "on": {
-        "mean": 0.9017,
-        "effect": 0.0011,
+        "mean": 0.9221,
+        "effect": 0.0026,
         "n": 147
       }
     },
-    "spread": 0.0142
+    "spread": 0.0346
   },
   "context_file": {
     "values": {
       "none": {
-        "mean": 0.9014,
-        "effect": 0.0007,
+        "mean": 0.9218,
+        "effect": 0.0023,
         "n": 147
       },
       "provided": {
         "mean": 0.8917,
-        "effect": -0.009,
+        "effect": -0.0278,
         "n": 12
       }
     },
-    "spread": 0.0097
+    "spread": 0.0301
   },
   "web_search": {
     "values": {
       "off": {
         "mean": 0.8923,
-        "effect": -0.0083,
+        "effect": -0.0272,
         "n": 13
       },
       "on": {
-        "mean": 0.9014,
-        "effect": 0.0007,
+        "mean": 0.9219,
+        "effect": 0.0024,
         "n": 146
       }
     },
-    "spread": 0.0091
+    "spread": 0.0296
   },
   "prompt_style": {
     "values": {
       "detailed": {
         "mean": 0.895,
-        "effect": -0.0056,
+        "effect": -0.0245,
         "n": 10
       },
       "simple": {
-        "mean": 0.901,
-        "effect": 0.0004,
+        "mean": 0.9211,
+        "effect": 0.0016,
         "n": 149
       }
     },
-    "spread": 0.006
+    "spread": 0.0261
+  },
+  "effort": {
+    "values": {
+      "high": {
+        "mean": 0.9197,
+        "effect": 0.0002,
+        "n": 150
+      },
+      "max": {
+        "mean": 0.9167,
+        "effect": -0.0028,
+        "n": 9
+      }
+    },
+    "spread": 0.003
+  },
+  "human_language": {
+    "values": {
+      "en": {
+        "mean": 0.9193,
+        "effect": -0.0002,
+        "n": 150
+      },
+      "es": {
+        "mean": 0.9222,
+        "effect": 0.0027,
+        "n": 9
+      }
+    },
+    "spread": 0.0029
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -117,13 +117,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 196"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 39 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 39,
+        "lines_cleared": 0,
+        "max_score_observed": 196,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 304,
+        "events_count": 10,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 26
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.825,
+  "score": 0.825,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 90,
+    "lines_of_code": 591,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 9,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.77
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "2 new piece(s) detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -82,13 +82,13 @@
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "1 line(s) cleared (grid-verified)"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score stayed at 250"
+      "detail": "score stayed at 196"
     },
     {
       "name": "game_over",
@@ -103,30 +103,30 @@
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
     "pieces_placed": 39,
-    "lines_cleared": 1,
-    "max_score_observed": 250,
+    "lines_cleared": 0,
+    "max_score_observed": 196,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 305,
+    "frames": 304,
     "events_count": 10,
-    "pieces_spawned": 2,
+    "pieces_spawned": 4,
     "pieces_locked": 11,
-    "lines_cleared": 1,
+    "lines_cleared": 0,
     "piece_types_seen": [
       "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 30
+    "load_time_ms": 26
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 20
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.565,
+  "score": 0.565,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 604,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 23,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -119,7 +119,7 @@
     "grid_read_success_rate": 0
   },
   "performance": {
-    "load_time_ms": 47
+    "load_time_ms": 20
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -242,7 +242,7 @@
         "grid_read_success_rate": 0
       },
       "performance": {
-        "load_time_ms": 42
+        "load_time_ms": 25
       },
       "accessibility": {
         "issues": [],
@@ -251,10 +251,19 @@
       }
     }
   },
-  "outcome_score": 0.19,
-  "score": 0.19,
+  "outcome_score": 0.565,
+  "score": 0.565,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 604,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 23,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -119,7 +119,7 @@
     "grid_read_success_rate": 0
   },
   "performance": {
-    "load_time_ms": 42
+    "load_time_ms": 25
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -117,13 +117,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 50,
+          "height": 100
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 168"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 168,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 347,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 262
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.48,
+  "score": 0.48,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 137,
+    "lines_of_code": 867,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 56,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.65
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -87,8 +87,8 @@
     },
     {
       "name": "score_changes",
-      "pass": true,
-      "detail": "score changed from 194 to 222"
+      "pass": false,
+      "detail": "score stayed at 168"
     },
     {
       "name": "game_over",
@@ -103,19 +103,19 @@
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
     "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 222,
+    "max_score_observed": 168,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 349,
+    "frames": 347,
     "events_count": 2,
     "pieces_spawned": 0,
     "pieces_locked": 10,
@@ -124,7 +124,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 50
+    "load_time_ms": 262
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 651,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 10,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.365,
+  "score": 0.365,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 101,
+    "lines_of_code": 655,
+    "duplication_pct": 3.4,
+    "tech_debt_minutes": 34,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 486,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 16,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 61
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.495,
+  "score": 0.495,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 0,
+    "lines_of_code": 787,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 232,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.8
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -119,7 +119,7 @@
     "grid_read_success_rate": 0
   },
   "performance": {
-    "load_time_ms": 20
+    "load_time_ms": 61
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=javascript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 486,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 16,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=detailed_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=detailed_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json
@@ -123,10 +123,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 840,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 13,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=detailed_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=detailed_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json
@@ -119,7 +119,7 @@
     "grid_read_success_rate": 0
   },
   "performance": {
-    "load_time_ms": 59
+    "load_time_ms": 72
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run1/eval_results.json
@@ -124,13 +124,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.69,
+    "total": 16,
+    "passed": 11,
+    "failed": 5,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 152"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 35 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 11,
+        "failed": 5,
+        "score": 0.69
+      },
+      "gameplay": {
+        "pieces_placed": 35,
+        "lines_cleared": 1,
+        "max_score_observed": 152,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 313,
+        "events_count": 7,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 72
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.62,
+  "score": 0.62,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 168,
+    "lines_of_code": 785,
+    "duplication_pct": 43.1,
+    "tech_debt_minutes": 73,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run1/gameplay-bot-report.json
@@ -12,7 +12,7 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "1 new piece(s) detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -88,45 +88,45 @@
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score stayed at 155"
+      "detail": "score stayed at 152"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "could not trigger or detect game over"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 33 pieces, no crashes"
+      "detail": "played for 30s, placed 35 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 11,
+    "failed": 5,
+    "score": 0.69
   },
   "gameplay": {
-    "pieces_placed": 33,
+    "pieces_placed": 35,
     "lines_cleared": 1,
-    "max_score_observed": 155,
+    "max_score_observed": 152,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 319,
+    "frames": 313,
     "events_count": 7,
-    "pieces_spawned": 1,
+    "pieces_spawned": 2,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
-      "I"
+      "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 204
+    "load_time_ms": 72
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run2/eval_results.json
@@ -124,13 +124,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 46
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.37,
+  "score": 0.37,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 160,
+    "lines_of_code": 1029,
+    "duplication_pct": 39.4,
+    "tech_debt_minutes": 55,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run2/gameplay-bot-report.json
@@ -119,7 +119,7 @@
     "grid_read_success_rate": 0
   },
   "performance": {
-    "load_time_ms": 20
+    "load_time_ms": 46
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run3/eval_results.json
@@ -124,13 +124,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 40
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.37,
+  "score": 0.37,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 160,
+    "lines_of_code": 1029,
+    "duplication_pct": 39.4,
+    "tech_debt_minutes": 55,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=off_tool_glob=off_tool_grep=off_tool_read=off_tool_write=off_web_search=off_run3/gameplay-bot-report.json
@@ -119,7 +119,7 @@
     "grid_read_success_rate": 0
   },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 40
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json
@@ -123,10 +123,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.25,
+    "score": 0.31,
     "total": 16,
-    "passed": 4,
-    "failed": 12,
+    "passed": 5,
+    "failed": 11,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -145,7 +145,8 @@
           "drop": "Space"
         },
         "start_mechanism": "click_canvas",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -161,101 +162,122 @@
         {
           "name": "auto_drop",
           "pass": false,
-          "detail": "piece did not move in 5 seconds"
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": false,
-          "detail": "no change detected after key press"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
           "pass": false,
-          "detail": "no change detected after key press"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "could not detect any piece rotations"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
           "pass": false,
-          "detail": "no change detected after hard drop key"
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": false,
-          "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
           "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "could not read score element"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 4,
-        "failed": 12,
-        "score": 0.25
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
       },
       "gameplay": {
-        "pieces_placed": 60,
-        "lines_cleared": 0,
+        "pieces_placed": 20,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 345,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 750
+        "load_time_ms": 31
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.25,
-  "score": 0.25,
+  "outcome_score": 0.48,
+  "score": 0.48,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 5,
+    "cognitive_complexity": 90,
+    "lines_of_code": 708,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 20,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.65
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,105 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 4,
-    "failed": 12,
-    "score": 0.25
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 60,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 750
+    "load_time_ms": 31
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -123,13 +123,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 27
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.28,
+  "score": 0.28,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 16,
+    "cognitive_complexity": 190,
+    "lines_of_code": 992,
+    "duplication_pct": 35.2,
+    "tech_debt_minutes": 73,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -9,14 +9,15 @@
       "height": 120
     },
     "controls": {
-      "left": "a",
-      "right": "d",
-      "down": "s",
-      "rotate": "z",
+      "left": "ArrowLeft",
+      "right": "ArrowRight",
+      "down": "ArrowDown",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,94 +32,106 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded."
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 60,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1515
+    "load_time_ms": 27
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -125,13 +125,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 62
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.37,
+  "score": 0.37,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 190,
+    "lines_of_code": 985,
+    "duplication_pct": 31.8,
+    "tech_debt_minutes": 76,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -10,106 +10,116 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:38155/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 4052
+    "load_time_ms": 62
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -123,10 +123,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.88,
+    "score": 0.94,
     "total": 16,
-    "passed": 14,
-    "failed": 2,
+    "passed": 15,
+    "failed": 1,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -145,7 +145,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -161,62 +162,62 @@
         {
           "name": "auto_drop",
           "pass": true,
-          "detail": "grid state changed after 5s with no input"
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
           "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "rotated: [] failed: [unknown] (tested 1 piece types in 60 attempts)"
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [I, J, unknown]"
         },
         {
           "name": "hard_drop",
           "pass": true,
-          "detail": "piece immediately dropped and new piece appeared"
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom"
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "visual change suggests new piece spawned"
+          "detail": "6 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
           "pass": true,
-          "detail": "grid accumulated cells: 8 -> 12"
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "line cleared via strategic placement"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score did not increase: [0] -> no change after polling"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
@@ -226,24 +227,37 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 78 pieces, no crashes"
+          "detail": "played for 30s, placed 37 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 14,
-        "failed": 2,
-        "score": 0.88
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 137,
+        "pieces_placed": 37,
         "lines_cleared": 1,
         "max_score_observed": 0,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 300,
+        "events_count": 11,
+        "pieces_spawned": 6,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "I",
+          "J",
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 68
+        "load_time_ms": 40
       },
       "accessibility": {
         "issues": [
@@ -254,10 +268,19 @@
       }
     }
   },
-  "outcome_score": 0.44,
-  "score": 0.44,
+  "outcome_score": 0.745,
+  "score": 0.745,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 190,
+    "lines_of_code": 985,
+    "duplication_pct": 31.8,
+    "tech_debt_minutes": 76,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "rotated: [] failed: [unknown] (tested 1 piece types in 60 attempts)"
+      "pass": true,
+      "detail": "rotation observed, piece types seen: [I, J, unknown]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "detail": "6 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 8 -> 12"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,37 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 137,
+    "pieces_placed": 37,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 300,
+    "events_count": 11,
+    "pieces_spawned": 6,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "I",
+      "J",
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 68
+    "load_time_ms": 40
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -124,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.46,
+  "score": 0.46,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 100,
+    "lines_of_code": 608,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.92
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-pf5imcma/loop-bench-y7z0amb9', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 943,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 26,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 55,
+      "average": 6.8,
+      "max": 26,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 8,
+    "global_declarations": 62,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 297,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 39,
+      "source_lines": 681,
+      "ratio_pct": 5.7
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.9
   },
   "transcript_analysis": {
     "total_events": 46,
@@ -68,14 +120,164 @@
     "score": 1.0
   },
   "gameplay_bot": {
-    "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "pass": true,
+    "score": 1,
+    "total": 16,
+    "passed": 16,
+    "failed": 0,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "2 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 376 to 458"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 33 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 16,
+        "failed": 0,
+        "score": 1
+      },
+      "gameplay": {
+        "pieces_placed": 33,
+        "lines_cleared": 2,
+        "max_score_observed": 458,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 287,
+        "events_count": 11,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 2,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 23
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.945,
+  "score": 0.945,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 87,
+    "lines_of_code": 487,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 22,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.89
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,94 +32,108 @@
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "exception: page.reload: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "2 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "could not read score element"
+      "pass": true,
+      "detail": "score changed from 376 to 458"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 33 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 2,
-    "failed": 14,
-    "score": 0.13
+    "passed": 16,
+    "failed": 0,
+    "score": 1
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 33,
+    "lines_cleared": 2,
+    "max_score_observed": 458,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 287,
+    "events_count": 11,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 2,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 23
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-traf_u58/loop-bench-drho0eka', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1526,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 36,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 67,
+      "average": 7.4,
+      "max": 48,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 14,
+    "global_declarations": 38,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 526,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 86,
+      "source_lines": 1180,
+      "ratio_pct": 7.3
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 8
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 47,
@@ -69,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 172 to 194"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 194,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 342,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 26
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.44,
+  "score": 0.44,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 164,
+    "lines_of_code": 746,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 82,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,106 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: page.reload: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "could not read score element"
+      "pass": true,
+      "detail": "score changed from 172 to 194"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 2,
-    "failed": 14,
-    "score": 0.13
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 194,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 342,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 75
+    "load_time_ms": 26
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -121,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.75,
+    "score": 0.38,
     "total": 16,
-    "passed": 12,
-    "failed": 4,
+    "passed": 6,
+    "failed": 10,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -143,7 +143,8 @@
           "drop": "Space"
         },
         "start_mechanism": "enter",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -158,63 +159,63 @@
         },
         {
           "name": "auto_drop",
-          "pass": true,
-          "detail": "pixels changed after 5s with no input"
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "could not detect any piece rotations"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
-          "pass": true,
-          "detail": "visual change detected after hard drop"
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": false,
-          "detail": "could not verify piece locking at bottom"
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "could not detect new piece at top"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
-          "pass": true,
-          "detail": "game still responding after 10 piece drops"
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "line cleared via strategic placement"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
-          "pass": false,
-          "detail": "score did not increase: [188] -> no change after polling"
+          "pass": true,
+          "detail": "score changed from 164 to 168"
         },
         {
           "name": "game_over",
@@ -224,24 +225,33 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 76 pieces, no crashes"
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 12,
-        "failed": 4,
-        "score": 0.75
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
       },
       "gameplay": {
-        "pieces_placed": 186,
+        "pieces_placed": 20,
         "lines_cleared": 1,
-        "max_score_observed": 180,
+        "max_score_observed": 168,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 349,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 29
+        "load_time_ms": 43
       },
       "accessibility": {
         "issues": [
@@ -255,10 +265,19 @@
       }
     }
   },
-  "outcome_score": 0.375,
-  "score": 0.375,
+  "outcome_score": 0.53,
+  "score": 0.53,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 90,
+    "lines_of_code": 667,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 19,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.68
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [188] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 164 to 168"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 76 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 12,
-    "failed": 4,
-    "score": 0.75
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 186,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 180,
+    "max_score_observed": 168,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 349,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 29
+    "load_time_ms": 43
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-ivkll6nh/loop-bench-e35s4mjy', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 7,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1723,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 36,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 59,
+      "average": 9.5,
+      "max": 45,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 32,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 556,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 132,
+      "source_lines": 1194,
+      "ratio_pct": 11.1
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 0
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.5
   },
   "transcript_analysis": {
     "total_events": 57,
@@ -69,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 50,
+          "height": 100
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 202 to 226"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 226,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 348,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 106
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.44,
+  "score": 0.44,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 165,
+    "lines_of_code": 835,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 92,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [268] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 202 to 226"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 200,
+    "max_score_observed": 226,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 348,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 44
+    "load_time_ms": 106
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-1mwrka44/loop-bench-294r5yrr', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 7,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1376,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 58,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 69,
+      "average": 5.9,
+      "max": 17,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 84,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 538,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 71,
+      "source_lines": 995,
+      "ratio_pct": 7.1
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 8
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 41,
@@ -69,13 +121,165 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, I, J]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 47 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 47,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 278,
+        "events_count": 11,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "I",
+          "J"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 56
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.835,
+  "score": 0.835,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 126,
+    "lines_of_code": 688,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 38,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=off_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, I, J]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "11 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 86 pieces, no crashes"
+      "detail": "played for 30s, placed 47 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,27 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 127,
-    "lines_cleared": 41,
+    "pieces_placed": 47,
+    "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 278,
+    "events_count": 11,
+    "pieces_spawned": 5,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "I",
+      "J"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 79
+    "load_time_ms": 56
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -125,10 +125,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.56,
+    "score": 0.38,
     "total": 16,
-    "passed": 9,
-    "failed": 7,
+    "passed": 6,
+    "failed": 10,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -147,7 +147,8 @@
           "drop": "Space"
         },
         "start_mechanism": "click_canvas",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -163,62 +164,62 @@
         {
           "name": "auto_drop",
           "pass": false,
-          "detail": "piece did not move in 5 seconds"
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "could not detect any piece rotations"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
           "pass": false,
-          "detail": "no change detected after hard drop key"
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
-          "pass": false,
-          "detail": "could not verify piece locking at bottom"
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "could not detect new piece at top"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
           "pass": false,
-          "detail": "grid did not accumulate filled cells"
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "2 line(s) cleared during AI play"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score did not increase: [0] -> no change after polling"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
@@ -228,24 +229,33 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 26s, placed 100 pieces, no crashes"
+          "detail": "played for 30s, placed 22 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 9,
-        "failed": 7,
-        "score": 0.56
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
       },
       "gameplay": {
-        "pieces_placed": 200,
-        "lines_cleared": 6,
+        "pieces_placed": 22,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 26,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 339,
+        "events_count": 3,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 168
+        "load_time_ms": 92
       },
       "accessibility": {
         "issues": [
@@ -257,10 +267,19 @@
       }
     }
   },
-  "outcome_score": 0.28,
-  "score": 0.28,
+  "outcome_score": 0.315,
+  "score": 0.315,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 20,
+    "cognitive_complexity": 186,
+    "lines_of_code": 1056,
+    "duplication_pct": 35.3,
+    "tech_debt_minutes": 72,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "2 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 26s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 22 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 9,
-    "failed": 7,
-    "score": 0.56
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 200,
-    "lines_cleared": 6,
+    "pieces_placed": 22,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 26,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 339,
+    "events_count": 3,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 168
+    "load_time_ms": 92
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -125,15 +125,20 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
+    "score": 0.69,
     "total": 16,
-    "passed": 0,
-    "failed": 16,
+    "passed": 11,
+    "failed": 5,
     "report": {
       "implementation": {
-        "renderer": "unknown",
-        "grid_detected": false,
-        "grid_bounds": null,
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
         "controls": {
           "left": "ArrowLeft",
           "right": "ArrowRight",
@@ -141,128 +146,140 @@
           "rotate": "ArrowUp",
           "drop": "Space"
         },
-        "start_mechanism": "unknown",
-        "score_element_found": false,
-        "grid_confidence": 0
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
           "name": "game_loads",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "no console errors"
         },
         {
           "name": "game_starts",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "started via auto"
         },
         {
           "name": "auto_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "1 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "played for 30s, placed 30 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 0,
-        "failed": 16,
-        "score": 0
+        "passed": 11,
+        "failed": 5,
+        "score": 0.69
       },
       "gameplay": {
-        "pieces_placed": 0,
-        "lines_cleared": 0,
+        "pieces_placed": 30,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 0,
-        "events_count": 0,
-        "pieces_spawned": 0,
-        "pieces_locked": 0,
-        "lines_cleared": 0,
+        "frames": 324,
+        "events_count": 6,
+        "pieces_spawned": 1,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
         "piece_types_seen": [],
-        "grid_read_success_rate": 0
+        "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": -1
+        "load_time_ms": 80
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.62,
+  "score": 0.62,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 170,
+    "lines_of_code": 881,
+    "duplication_pct": 21.8,
+    "tech_debt_minutes": 41,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,8 +1,13 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
@@ -10,120 +15,123 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false,
-    "grid_confidence": 0
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40141/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "played for 30s, placed 30 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 11,
+    "failed": 5,
+    "score": 0.69
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 30,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 0,
-    "events_count": 0,
-    "pieces_spawned": 0,
-    "pieces_locked": 0,
-    "lines_cleared": 0,
+    "frames": 324,
+    "events_count": 6,
+    "pieces_spawned": 1,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
     "piece_types_seen": [],
-    "grid_read_success_rate": 0
+    "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 80
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -126,13 +126,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 38
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.22,
+  "score": 0.22,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 20,
+    "cognitive_complexity": 186,
+    "lines_of_code": 1056,
+    "duplication_pct": 35.3,
+    "tech_debt_minutes": 72,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -10,113 +10,120 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "1 console error(s): Unexpected token '<'"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 165
+    "load_time_ms": 38
   },
   "accessibility": {
-    "issues": [
-      "canvas without aria-label or role",
-      "canvas without aria-label or role"
-    ],
-    "issue_count": 2,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-trbyqbmh/loop-bench-dwwdc2bs', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1043,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 28,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 53,
+      "average": 7.2,
+      "max": 26,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 54,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 367,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 67,
+      "source_lines": 756,
+      "ratio_pct": 8.9
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 6
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 42,
@@ -69,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.81,
+    "total": 16,
+    "passed": 13,
+    "failed": 3,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 292"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 34 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
+      },
+      "gameplay": {
+        "pieces_placed": 34,
+        "lines_cleared": 1,
+        "max_score_observed": 292,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 312,
+        "events_count": 10,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 35
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.835,
+  "score": 0.835,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 86,
+    "lines_of_code": 520,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 16,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.86
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 49"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [158] -> no change after polling"
+      "detail": "score stayed at 292"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 34 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 121,
-    "lines_cleared": 2,
-    "max_score_observed": 164,
+    "pieces_placed": 34,
+    "lines_cleared": 1,
+    "max_score_observed": 292,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 312,
+    "events_count": 10,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 32
+    "load_time_ms": 35
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -121,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 310"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 43 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 43,
+        "lines_cleared": 0,
+        "max_score_observed": 310,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 286,
+        "events_count": 10,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 45
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.9,
+  "score": 0.9,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 77,
+    "lines_of_code": 486,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.92
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 40"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "line cleared via strategic placement"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [160] -> no change after polling"
+      "detail": "score stayed at 310"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 43 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 130,
-    "lines_cleared": 1,
-    "max_score_observed": 222,
+    "pieces_placed": 43,
+    "lines_cleared": 0,
+    "max_score_observed": 310,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 286,
+    "events_count": 10,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 0,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 31
+    "load_time_ms": 45
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-8enzhjux/loop-bench-qyww_eoe', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 11,
+      "code": 5,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1339,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 40,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 53,
+      "average": 8.5,
+      "max": 48,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 16,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 532,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 99,
+      "source_lines": 1000,
+      "ratio_pct": 9.9
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 3,
+      "files_with_logic": 3,
+      "files_with_both": 3
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 49,
@@ -69,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.81,
+    "total": 16,
+    "passed": 13,
+    "failed": 3,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 252"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 252,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 295,
+        "events_count": 10,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 27
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.74,
+  "score": 0.74,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 112,
+    "lines_of_code": 688,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.67
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 43"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [214] -> no change after polling"
+      "detail": "score stayed at 252"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 120,
+    "pieces_placed": 37,
     "lines_cleared": 1,
-    "max_score_observed": 182,
+    "max_score_observed": 252,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 295,
+    "events_count": 10,
+    "pieces_spawned": 5,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 35
+    "load_time_ms": 27
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-82_506qo/loop-bench-5vcsw5m5', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 7,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1441,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 34,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 77,
+      "average": 6.8,
+      "max": 50,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 18,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 576,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 115,
+      "source_lines": 1022,
+      "ratio_pct": 11.3
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 98,
@@ -69,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 26"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 26,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 347,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 32
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 20,
+    "cognitive_complexity": 123,
+    "lines_of_code": 698,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 52,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [210] -> no change after polling"
+      "detail": "score stayed at 26"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 176,
+    "max_score_observed": 26,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 347,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 60
+    "load_time_ms": 32
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -42,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-9ibz17n0/loop-bench-fffti9wy', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 9,
+      "code": 4,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1471,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 72,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 60,
+      "average": 7.9,
+      "max": 44,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 18,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 464,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 136,
+      "source_lines": 983,
+      "ratio_pct": 13.8
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 5
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 46,
@@ -69,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 52,
+          "height": 104
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 186 to 208"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 208,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 350,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 31
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.44,
+  "score": 0.44,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 16,
+    "cognitive_complexity": 111,
+    "lines_of_code": 696,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 56,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [208] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 186 to 208"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 9,
-    "failed": 7,
-    "score": 0.56
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 190,
+    "max_score_observed": 208,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 350,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 82
+    "load_time_ms": 31
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -121,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.69,
+    "score": 0.94,
     "total": 16,
-    "passed": 11,
-    "failed": 5,
+    "passed": 15,
+    "failed": 1,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -143,7 +143,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": false
+        "score_element_found": false,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -159,62 +160,62 @@
         {
           "name": "auto_drop",
           "pass": true,
-          "detail": "pixels changed after 5s with no input"
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
-          "pass": false,
-          "detail": "no change detected after key press"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
           "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "could not detect any piece rotations"
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
         },
         {
           "name": "hard_drop",
-          "pass": false,
-          "detail": "no change detected after hard drop key"
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom"
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "new piece detected at top of grid"
+          "detail": "2 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
-          "pass": false,
-          "detail": "grid did not accumulate filled cells"
+          "pass": true,
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "1 line(s) cleared during AI play"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "no score element found and no number changed"
+          "detail": "no score element found"
         },
         {
           "name": "game_over",
@@ -224,24 +225,35 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 26s, placed 100 pieces, no crashes"
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 11,
-        "failed": 5,
-        "score": 0.69
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 200,
-        "lines_cleared": 2,
+        "pieces_placed": 20,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 26,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 350,
+        "events_count": 9,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 43
+        "load_time_ms": 44
       },
       "accessibility": {
         "issues": [
@@ -252,10 +264,19 @@
       }
     }
   },
-  "outcome_score": 0.345,
-  "score": 0.345,
+  "outcome_score": 0.595,
+  "score": 0.595,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 140,
+    "lines_of_code": 961,
+    "duplication_pct": 33.6,
+    "tech_debt_minutes": 107,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": false
+    "score_element_found": false,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "could not detect any piece rotations"
+      "pass": true,
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "no change detected after hard drop key"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "no score element found and no number changed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 26s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 11,
-    "failed": 5,
-    "score": 0.69
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 200,
-    "lines_cleared": 2,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 26,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 350,
+    "events_count": 9,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 43
+    "load_time_ms": 44
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -124,13 +124,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.81,
+    "total": 16,
+    "passed": 13,
+    "failed": 3,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "10 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 35 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
+      },
+      "gameplay": {
+        "pieces_placed": 35,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 315,
+        "events_count": 8,
+        "pieces_spawned": 10,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "I"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 141
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.82,
+  "score": 0.82,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 79,
+    "lines_of_code": 564,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 18,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.83
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [I, other] failed: [] (tested 2 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "detail": "10 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,36 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 35 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 167,
+    "pieces_placed": 35,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 315,
+    "events_count": 8,
+    "pieces_spawned": 10,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "I"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 29
+    "load_time_ms": 141
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -124,13 +124,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 40 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 40,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 297,
+        "events_count": 10,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 120
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.745,
+  "score": 0.745,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 18,
+    "cognitive_complexity": 164,
+    "lines_of_code": 996,
+    "duplication_pct": 17.0,
+    "tech_debt_minutes": 48,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 38"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 26s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 40 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,25 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 151,
+    "pieces_placed": 40,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 26,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 297,
+    "events_count": 10,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 49
+    "load_time_ms": 120
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -124,13 +124,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 75,
+          "height": 150
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 42
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.54,
+  "score": 0.54,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 6,
+    "cognitive_complexity": 85,
+    "lines_of_code": 721,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 18,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.77
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 76 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 7,
-    "failed": 9,
-    "score": 0.44
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 186,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 42
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 26
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.58,
+  "score": 0.58,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 0,
+    "lines_of_code": 657,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 12,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.97
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -1,22 +1,18 @@
 {
   "implementation": {
-    "renderer": "dom",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 360.5,
-      "y": 50,
-      "width": 329,
-      "height": 639
-    },
+    "renderer": "unknown",
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "auto",
-    "score_element_found": true
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -27,67 +23,67 @@
     {
       "name": "game_starts",
       "pass": true,
-      "detail": "started via auto"
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
-      "pass": true,
-      "detail": "filled cells persist at bottom"
+      "pass": false,
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "new piece detected at top of grid"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "line cleared via strategic placement"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -97,30 +93,37 @@
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "390 console errors, 0 play errors during 30s"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 11,
-    "failed": 5,
-    "score": 0.69
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 188,
-    "lines_cleared": 1,
+    "pieces_placed": 26,
+    "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 30,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 27
+    "load_time_ms": 26
   },
   "accessibility": {
-    "issues": [
-      "no headings found"
-    ],
-    "issue_count": 1,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -95,10 +95,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 1
+      "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.8
+    "score": 0.45
   },
   "transcript_analysis": {
     "total_events": 91,
@@ -146,7 +146,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -162,62 +163,62 @@
         {
           "name": "auto_drop",
           "pass": true,
-          "detail": "grid state changed after 5s with no input"
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
-          "pass": false,
-          "detail": "no change detected after key press"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
           "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
           "pass": true,
-          "detail": "rotated: [I] failed: [] (tested 1 piece types in 60 attempts)"
+          "detail": "rotation confirmed but could not identify individual piece types"
         },
         {
           "name": "hard_drop",
           "pass": true,
-          "detail": "piece immediately dropped and new piece appeared"
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom"
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "new piece detected at top of grid"
+          "detail": "2 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
           "pass": true,
-          "detail": "grid accumulated cells: 16 -> 40"
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "line cleared via strategic placement"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score did not increase: [0] -> no change after polling"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
@@ -227,7 +228,7 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 94 pieces, no crashes"
+          "detail": "played for 30s, placed 33 pieces, no crashes"
         }
       ],
       "summary": {
@@ -237,14 +238,25 @@
         "score": 0.88
       },
       "gameplay": {
-        "pieces_placed": 145,
+        "pieces_placed": 33,
         "lines_cleared": 1,
         "max_score_observed": 0,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 314,
+        "events_count": 10,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 21
+        "load_time_ms": 32
       },
       "accessibility": {
         "issues": [
@@ -256,10 +268,19 @@
       }
     }
   },
-  "outcome_score": 0.88,
-  "score": 0.88,
+  "outcome_score": 0.925,
+  "score": 0.925,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 0,
+    "lines_of_code": 657,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 12,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.97
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [I] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 40"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 94 pieces, no crashes"
+      "detail": "played for 30s, placed 33 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,25 @@
     "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 145,
+    "pieces_placed": 33,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 314,
+    "events_count": 10,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 32
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -125,144 +125,165 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
+    "score": 0.88,
     "total": 16,
-    "passed": 0,
-    "failed": 16,
+    "passed": 14,
+    "failed": 2,
     "report": {
       "implementation": {
-        "renderer": "unknown",
-        "grid_detected": false,
-        "grid_bounds": null,
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
         "controls": {
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "ArrowUp",
+          "rotate": "z",
           "drop": "Space"
         },
-        "start_mechanism": "unknown",
-        "score_element_found": false,
-        "grid_confidence": 0
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
           "name": "game_loads",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "no console errors"
         },
         {
           "name": "game_starts",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "started via auto"
         },
         {
           "name": "auto_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, L]"
         },
         {
           "name": "hard_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "could not trigger or detect game over"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "played for 30s, placed 45 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 0,
-        "failed": 16,
-        "score": 0
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
       },
       "gameplay": {
-        "pieces_placed": 0,
-        "lines_cleared": 0,
+        "pieces_placed": 45,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 0,
-        "events_count": 0,
-        "pieces_spawned": 0,
-        "pieces_locked": 0,
-        "lines_cleared": 0,
-        "piece_types_seen": [],
-        "grid_read_success_rate": 0
+        "frames": 278,
+        "events_count": 10,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "L"
+        ],
+        "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": -1
+        "load_time_ms": 36
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.925,
+  "score": 0.925,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 0,
+    "lines_of_code": 657,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 12,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.97
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -1,129 +1,141 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "z",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false,
-    "grid_confidence": 0
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "rotation observed, piece types seen: [unknown, L]"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:34125/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "played for 30s, placed 45 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 45,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 0,
-    "events_count": 0,
-    "pieces_spawned": 0,
-    "pieces_locked": 0,
-    "lines_cleared": 0,
-    "piece_types_seen": [],
-    "grid_read_success_rate": 0
+    "frames": 278,
+    "events_count": 10,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "L"
+    ],
+    "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 36
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "no headings found",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -124,13 +124,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 37
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.28,
+  "score": 0.28,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 3,
+    "vulnerabilities": 0,
+    "code_smells": 13,
+    "cognitive_complexity": 162,
+    "lines_of_code": 1064,
+    "duplication_pct": 16.2,
+    "tech_debt_minutes": 48,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -96,29 +97,41 @@
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 110,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 39
+    "load_time_ms": 37
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -124,13 +124,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.69,
+    "total": 16,
+    "passed": 11,
+    "failed": 5,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "a",
+          "right": "d",
+          "down": "s",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 41 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 11,
+        "failed": 5,
+        "score": 0.69
+      },
+      "gameplay": {
+        "pieces_placed": 41,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 293,
+        "events_count": 7,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 30
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.68,
+  "score": 0.68,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 6,
+    "cognitive_complexity": 103,
+    "lines_of_code": 612,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 32,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.67
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -9,14 +9,15 @@
       "height": 600
     },
     "controls": {
-      "left": "ArrowLeft",
-      "right": "ArrowRight",
-      "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "left": "a",
+      "right": "d",
+      "down": "s",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 51"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 41 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 11,
+    "failed": 5,
+    "score": 0.69
   },
   "gameplay": {
-    "pieces_placed": 129,
+    "pieces_placed": 41,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 293,
+    "events_count": 7,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 531
+    "load_time_ms": 30
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -97,10 +97,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 4
+      "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.58
+    "score": 0.23
   },
   "transcript_analysis": {
     "total_events": 117,
@@ -126,13 +126,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "space",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via space"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 349,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 44
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.28,
+  "score": 0.28,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 164,
+    "lines_of_code": 1102,
+    "duplication_pct": 31.6,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "space",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,72 +33,72 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded."
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,18 +108,30 @@
     "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 110,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 349,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 310
+    "load_time_ms": 44
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -95,10 +95,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 1
+      "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.8
+    "score": 0.45
   },
   "transcript_analysis": {
     "total_events": 115,
@@ -124,144 +124,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
+    "score": 0.94,
     "total": 16,
-    "passed": 0,
-    "failed": 16,
+    "passed": 15,
+    "failed": 1,
     "report": {
       "implementation": {
-        "renderer": "unknown",
-        "grid_detected": false,
-        "grid_bounds": null,
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
         "controls": {
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "ArrowUp",
+          "rotate": "x",
           "drop": "Space"
         },
-        "start_mechanism": "unknown",
-        "score_element_found": false,
-        "grid_confidence": 0
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
           "name": "game_loads",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "no console errors"
         },
         {
           "name": "game_starts",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "started via auto"
         },
         {
           "name": "auto_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
         },
         {
           "name": "hard_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "played for 31s, placed 43 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 0,
-        "failed": 16,
-        "score": 0
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 0,
-        "lines_cleared": 0,
+        "pieces_placed": 43,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 31,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 0,
-        "events_count": 0,
-        "pieces_spawned": 0,
-        "pieces_locked": 0,
-        "lines_cleared": 0,
-        "piece_types_seen": [],
-        "grid_read_success_rate": 0
+        "frames": 295,
+        "events_count": 11,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": -1
+        "load_time_ms": 40
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.595,
+  "score": 0.595,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 182,
+    "lines_of_code": 936,
+    "duplication_pct": 26.8,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -1,129 +1,139 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false,
-    "grid_confidence": 0
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "page load failed: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37589/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "played for 31s, placed 43 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 43,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 31,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 0,
-    "events_count": 0,
-    "pieces_spawned": 0,
-    "pieces_locked": 0,
-    "lines_cleared": 0,
-    "piece_types_seen": [],
-    "grid_read_success_rate": 0
+    "frames": 295,
+    "events_count": 11,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 40
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -125,13 +125,160 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.81,
+    "total": 16,
+    "passed": 13,
+    "failed": 3,
+    "report": {
+      "implementation": {
+        "renderer": "dom",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 375,
+          "y": 30,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "2 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 38 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
+      },
+      "gameplay": {
+        "pieces_placed": 38,
+        "lines_cleared": 2,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 301,
+        "events_count": 8,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 2,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 25
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.53,
+  "score": 0.53,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 182,
+    "lines_of_code": 936,
+    "duplication_pct": 26.8,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected after drop"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 41"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "2 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 43s, placed 39 pieces, no crashes"
+      "detail": "played for 30s, placed 38 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 80,
-    "lines_cleared": 1,
+    "pieces_placed": 38,
+    "lines_cleared": 2,
     "max_score_observed": 0,
-    "play_duration_seconds": 43,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 301,
+    "events_count": 8,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 2,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 745
+    "load_time_ms": 25
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -127,13 +127,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 280 to 288"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 22 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 22,
+        "lines_cleared": 1,
+        "max_score_observed": 288,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 343,
+        "events_count": 9,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 70
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.595,
+  "score": 0.595,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 184,
+    "lines_of_code": 1132,
+    "duplication_pct": 33.1,
+    "tech_debt_minutes": 24,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 38"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [190] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 280 to 288"
     },
     {
       "name": "game_over",
@@ -96,29 +97,43 @@
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 22 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 41,
+    "pieces_placed": 22,
     "lines_cleared": 1,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "max_score_observed": 288,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 343,
+    "events_count": 9,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 5790
+    "load_time_ms": 70
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -124,10 +124,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.25,
+    "score": 0.31,
     "total": 16,
-    "passed": 4,
-    "failed": 12,
+    "passed": 5,
+    "failed": 11,
     "report": {
       "implementation": {
         "renderer": "dom",
@@ -146,7 +146,8 @@
           "drop": "Space"
         },
         "start_mechanism": "click_canvas",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -162,89 +163,98 @@
         {
           "name": "auto_drop",
           "pass": false,
-          "detail": "piece did not move in 5 seconds"
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": false,
-          "detail": "no change detected after key press"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
           "pass": false,
-          "detail": "no change detected after key press"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "could not detect any piece rotations"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
           "pass": false,
-          "detail": "no change detected after hard drop key"
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": false,
-          "detail": "could not verify piece locking at bottom"
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "could not detect new piece at top"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
           "pass": false,
-          "detail": "exception: page.waitForTimeout: Test timeout of 180000ms exceeded."
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "could not read score element"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 4,
-        "failed": 12,
-        "score": 0.25
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
       },
       "gameplay": {
-        "pieces_placed": 60,
-        "lines_cleared": 0,
+        "pieces_placed": 20,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 349,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 9051
+        "load_time_ms": 24
       },
       "accessibility": {
         "issues": [],
@@ -253,10 +263,19 @@
       }
     }
   },
-  "outcome_score": 0.125,
-  "score": 0.125,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 105,
+    "lines_of_code": 764,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 18,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,89 +33,98 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: page.waitForTimeout: Test timeout of 180000ms exceeded."
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 4,
-    "failed": 12,
-    "score": 0.25
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 60,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 349,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 9051
+    "load_time_ms": 24
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -123,10 +123,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.5,
+    "score": 0.88,
     "total": 16,
-    "passed": 8,
-    "failed": 8,
+    "passed": 14,
+    "failed": 2,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -145,7 +145,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": false
+        "score_element_found": false,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -161,101 +162,124 @@
         {
           "name": "auto_drop",
           "pass": true,
-          "detail": "pixels changed after 5s with no input"
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
           "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "could not detect any piece rotations"
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [J, unknown]"
         },
         {
           "name": "hard_drop",
-          "pass": true,
-          "detail": "visual change detected after hard drop"
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
-          "pass": false,
-          "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n\u001b[2m  - fonts loaded\u001b[22m\n"
+          "pass": true,
+          "detail": "10 piece(s) locked during play"
         },
         {
           "name": "new_piece_spawns",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "10 pieces placed during play session"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "exception: page.evaluate: Target page, context or browser has been closed"
+          "detail": "no score element found"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "played for 30s, placed 33 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 8,
-        "failed": 8,
-        "score": 0.5
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
       },
       "gameplay": {
-        "pieces_placed": 60,
-        "lines_cleared": 0,
+        "pieces_placed": 33,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 319,
+        "events_count": 7,
+        "pieces_spawned": 5,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "J",
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 2815
+        "load_time_ms": 34
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.25,
-  "score": 0.25,
+  "outcome_score": 0.715,
+  "score": 0.715,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 166,
+    "lines_of_code": 1039,
+    "duplication_pct": 28.5,
+    "tech_debt_minutes": 32,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": false
+    "score_element_found": false,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,107 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "could not detect any piece rotations"
+      "pass": true,
+      "detail": "rotation observed, piece types seen: [J, unknown]"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n\u001b[2m  - fonts loaded\u001b[22m\n"
+      "pass": true,
+      "detail": "10 piece(s) locked during play"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "10 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "exception: page.evaluate: Target page, context or browser has been closed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 33 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 8,
-    "failed": 8,
-    "score": 0.5
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 60,
-    "lines_cleared": 0,
+    "pieces_placed": 33,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 319,
+    "events_count": 7,
+    "pieces_spawned": 5,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "J",
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 2815
+    "load_time_ms": 34
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -124,13 +124,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 240,
+          "height": 400
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 344,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 36
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 105,
+    "lines_of_code": 764,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 18,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 7,
-    "failed": 9,
-    "score": 0.44
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 344,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 39
+    "load_time_ms": 36
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -123,13 +123,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.81,
+    "total": 16,
+    "passed": 13,
+    "failed": 3,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "1 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 307,
+        "events_count": 8,
+        "pieces_spawned": 1,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 56
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.755,
+  "score": 0.755,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 93,
+    "lines_of_code": 641,
+    "duplication_pct": 6.0,
+    "tech_debt_minutes": 39,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.7
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 42"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "20 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -96,29 +97,42 @@
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 12,
-    "failed": 4,
-    "score": 0.75
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 30,
-    "lines_cleared": 20,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 307,
+    "events_count": 8,
+    "pieces_spawned": 1,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1053
+    "load_time_ms": 56
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -26,12 +26,78 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-4v0qdx8e/loop-bench-ktrmyvlb', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 131616,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-4v0qdx8e/loop-bench-ktrmyvlb', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 14,
+      "code": 3,
+      "docs": 7,
+      "unnecessary": 1,
+      "unnecessary_list": [
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1308,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 22,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 52,
+      "average": 7.1,
+      "max": 30,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 0,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 629,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 32,
+      "source_lines": 1083,
+      "ratio_pct": 3.0
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.75
   },
   "transcript_analysis": {
     "total_events": 120,
@@ -57,13 +123,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": false,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 39 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 39,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 296,
+        "events_count": 11,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 38
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.755,
+  "score": 0.755,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 6,
+    "cognitive_complexity": 130,
+    "lines_of_code": 1187,
+    "duplication_pct": 35.2,
+    "tech_debt_minutes": 20,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.57
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": false
+    "score_element_found": false,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other, unknown] failed: [] (tested 2 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 22"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "9 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "no score element found and no number changed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -96,29 +97,42 @@
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 39 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 42,
-    "lines_cleared": 9,
+    "pieces_placed": 39,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 296,
+    "events_count": 11,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 219
+    "load_time_ms": 38
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -26,12 +26,80 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-g_6vs4uj/loop-bench-v_scnslz', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": false,
+      "error": "no tsconfig.json"
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 94776,
+      "size_under_512kb": true
+    },
+    "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-g_6vs4uj/loop-bench-v_scnslz', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 12,
+      "code": 4,
+      "docs": 6,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "server.js",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 984,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 2,
+    "magic_numbers": {
+      "count": 17,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 54,
+      "average": 5.1,
+      "max": 12,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 20,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 311,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 32,
+      "source_lines": 711,
+      "ratio_pct": 4.5
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.66
   },
   "transcript_analysis": {
     "total_events": 95,
@@ -57,13 +125,160 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.5,
+    "total": 16,
+    "passed": 8,
+    "failed": 8,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "10 piece(s) locked during play"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "1 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "10 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 8,
+        "failed": 8,
+        "score": 0.5
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 341,
+        "events_count": 2,
+        "pieces_spawned": 1,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 28
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.525,
+  "score": 0.525,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 141,
+    "lines_of_code": 873,
+    "duplication_pct": 27.8,
+    "tech_debt_minutes": 51,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,104 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: page.waitForTimeout: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "10 piece(s) locked during play"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "10 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 4,
-    "failed": 12,
-    "score": 0.25
+    "passed": 8,
+    "failed": 8,
+    "score": 0.5
   },
   "gameplay": {
-    "pieces_placed": 50,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 341,
+    "events_count": 2,
+    "pieces_spawned": 1,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1117
+    "load_time_ms": 28
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json
@@ -43,22 +43,242 @@
     "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-u6jryf6_/loop-bench-fx9t030l', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 11,
+      "code": 3,
+      "docs": 5,
+      "unnecessary": 1,
+      "unnecessary_list": [
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1145,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 12,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 50,
+      "average": 7.5,
+      "max": 30,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 12,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 748,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 26,
+      "source_lines": 823,
+      "ratio_pct": 3.2
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.8
   },
   "transcript_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/transcript-analysis.py', '/root/loop-benchmarking/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1']' timed out after 30 seconds",
-    "score": 0
+    "total_events": 110,
+    "tool_calls": {
+      "total": 28,
+      "bash": 21,
+      "write": 0,
+      "edit": 3,
+      "read": 4
+    },
+    "wasted_turns": {
+      "total": 18,
+      "docs": 3,
+      "ascii_art": 5,
+      "server_starts": 10
+    },
+    "errors_encountered": 0,
+    "thinking_blocks": 29,
+    "text_blocks": 21,
+    "productivity_ratio": 0.36,
+    "self_tested": false,
+    "score": 0.75
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.5,
+    "total": 16,
+    "passed": 8,
+    "failed": 8,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "10 piece(s) locked during play"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "1 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "10 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 22 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 8,
+        "failed": 8,
+        "score": 0.5
+      },
+      "gameplay": {
+        "pieces_placed": 22,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 336,
+        "events_count": 2,
+        "pieces_spawned": 1,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 26
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.375,
+  "score": 0.375,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 13,
+    "cognitive_complexity": 162,
+    "lines_of_code": 1022,
+    "duplication_pct": 37.4,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -1,8 +1,13 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
@@ -10,8 +15,9 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -21,99 +27,111 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "pass": true,
+      "detail": "10 piece(s) locked during play"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "could not detect new piece at top"
+      "pass": true,
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "10 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "exception: page.evaluate: Target page, context or browser has been closed"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 22 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 1,
-    "failed": 15,
-    "score": 0.06
+    "passed": 8,
+    "failed": 8,
+    "score": 0.5
   },
   "gameplay": {
-    "pieces_placed": 70,
-    "lines_cleared": 0,
+    "pieces_placed": 22,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 336,
+    "events_count": 2,
+    "pieces_spawned": 1,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1237
+    "load_time_ms": 26
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json
@@ -43,22 +43,235 @@
     "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-23oypf3d/loop-bench-v114tywh', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 15,
+      "code": 3,
+      "docs": 6,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "QUICK_START.txt",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1138,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 14,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 47,
+      "average": 7.6,
+      "max": 28,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 7,
+    "global_declarations": 8,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 564,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 60,
+      "source_lines": 766,
+      "ratio_pct": 7.8
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 5
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.75
   },
   "transcript_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/transcript-analysis.py', '/root/loop-benchmarking/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2']' timed out after 30 seconds",
-    "score": 0
+    "total_events": 124,
+    "tool_calls": {
+      "total": 35,
+      "bash": 32,
+      "write": 0,
+      "edit": 2,
+      "read": 1
+    },
+    "wasted_turns": {
+      "total": 14,
+      "docs": 6,
+      "ascii_art": 3,
+      "server_starts": 5
+    },
+    "errors_encountered": 0,
+    "thinking_blocks": 36,
+    "text_blocks": 14,
+    "productivity_ratio": 0.6,
+    "self_tested": false,
+    "score": 0.75
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 23
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.22,
+  "score": 0.22,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 4,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 174,
+    "lines_of_code": 931,
+    "duplication_pct": 57.3,
+    "tech_debt_minutes": 60,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,13 +1,8 @@
 {
   "implementation": {
-    "renderer": "canvas",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 0,
-      "y": 0,
-      "width": 75,
-      "height": 150
-    },
+    "renderer": "unknown",
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
@@ -16,7 +11,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -32,89 +28,98 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 4,
-    "failed": 12,
-    "score": 0.25
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 46,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 39
+    "load_time_ms": 23
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json
@@ -43,22 +43,235 @@
     "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-oyxhf1b6/loop-bench-n9n73btm', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 20,
+      "code": 4,
+      "docs": 8,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "QUICK_START.txt",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1157,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 10,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 55,
+      "average": 4.9,
+      "max": 17,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 14,
+    "global_declarations": 2,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 520,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 20,
+      "source_lines": 813,
+      "ratio_pct": 2.5
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 3,
+      "files_with_logic": 3,
+      "files_with_both": 3
+    },
+    "html_validation": {
+      "valid": true,
+      "errors": 0
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.75
   },
   "transcript_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/transcript-analysis.py', '/root/loop-benchmarking/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3']' timed out after 30 seconds",
-    "score": 0
+    "total_events": 134,
+    "tool_calls": {
+      "total": 36,
+      "bash": 32,
+      "write": 0,
+      "edit": 2,
+      "read": 2
+    },
+    "wasted_turns": {
+      "total": 13,
+      "docs": 3,
+      "ascii_art": 5,
+      "server_starts": 5
+    },
+    "errors_encountered": 0,
+    "thinking_blocks": 37,
+    "text_blocks": 21,
+    "productivity_ratio": 0.64,
+    "self_tested": false,
+    "score": 0.75
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 31
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 94,
+    "lines_of_code": 593,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 29,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.75
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -10,112 +10,120 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "1 console error(s): Unexpected token '<'"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 1915
+    "load_time_ms": 31
   },
   "accessibility": {
-    "issues": [
-      "canvas without aria-label or role"
-    ],
-    "issue_count": 1,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-2crbjsnw/loop-bench-npum8frs', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,63 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-2crbjsnw/loop-bench-npum8frs', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 42,
+      "code": 20,
+      "docs": 7,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "FEATURES.md",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 2098,
+    "dependencies": {
+      "production": 0,
+      "dev": 6,
+      "total": 6
+    },
+    "complexity": "over-engineered",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 36,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 125,
+      "average": 6.1,
+      "max": 34,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 14,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 98.8,
+      "camel_case": 1165,
+      "snake_case": 14
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 50,
+      "source_lines": 1736,
+      "ratio_pct": 2.9
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 6,
+      "files_with_logic": 10,
+      "files_with_both": 5
+    },
+    "html_validation": {
+      "valid": true,
+      "errors": 0
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.6
   },
   "transcript_analysis": {
     "total_events": 152,
@@ -46,14 +123,165 @@
     "score": 0.75
   },
   "gameplay_bot": {
-    "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "pass": true,
+    "score": 1,
+    "total": 16,
+    "passed": 16,
+    "failed": 0,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 49 to 53"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 25 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 16,
+        "failed": 0,
+        "score": 1
+      },
+      "gameplay": {
+        "pieces_placed": 25,
+        "lines_cleared": 1,
+        "max_score_observed": 53,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 329,
+        "events_count": 9,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "O"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 135
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.9,
+  "score": 0.9,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 21,
+    "cognitive_complexity": 49,
+    "lines_of_code": 741,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 75,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.8
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/gameplay-bot-report.json
@@ -1,17 +1,23 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "z",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -21,99 +27,114 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "exception: page.waitForTimeout: Test timeout of 180000ms exceeded."
+      "pass": true,
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "exception: page.evaluate: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "score changed from 49 to 53"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 25 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 16,
+    "failed": 0,
+    "score": 1
   },
   "gameplay": {
-    "pieces_placed": 28,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 25,
+    "lines_cleared": 1,
+    "max_score_observed": 53,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 329,
+    "events_count": 9,
+    "pieces_spawned": 5,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "O"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 979
+    "load_time_ms": 135
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
     "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-h0p8kpvx/loop-bench-5dl5qz_l', 'typescript']' timed out after 120 seconds"
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": false,
+        "detail": "TypeScript files found but no tsconfig.json"
+      }
+    ],
+    "score": 0.75
   },
   "quality": {
     "lint": {
@@ -21,8 +43,64 @@
     "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-h0p8kpvx/loop-bench-5dl5qz_l', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 11,
+      "code": 4,
+      "docs": 5,
+      "unnecessary": 3,
+      "unnecessary_list": [
+        "FEATURES.md",
+        "server.js",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1092,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 1,
+    "magic_numbers": {
+      "count": 18,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 52,
+      "average": 6.6,
+      "max": 28,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 17,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 457,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 37,
+      "source_lines": 749,
+      "ratio_pct": 4.9
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 3,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 3
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.58
   },
   "transcript_analysis": {
     "total_events": 94,
@@ -48,13 +126,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "1 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 38 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 38,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 297,
+        "events_count": 11,
+        "pieces_spawned": 1,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 98
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.745,
+  "score": 0.745,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 168,
+    "lines_of_code": 963,
+    "duplication_pct": 34.9,
+    "tech_debt_minutes": 38,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,106 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 46"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 38 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 51,
+    "pieces_placed": 38,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 297,
+    "events_count": 11,
+    "pieces_spawned": 1,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 747
+    "load_time_ms": 98
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-bdk2kxg3/loop-bench-opdim046', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,62 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-bdk2kxg3/loop-bench-opdim046', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 18,
+      "code": 5,
+      "docs": 7,
+      "unnecessary": 1,
+      "unnecessary_list": [
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1363,
+    "dependencies": {
+      "production": 0,
+      "dev": 3,
+      "total": 3
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 10,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 63,
+      "average": 5.3,
+      "max": 15,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 10,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 573,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 40,
+      "source_lines": 968,
+      "ratio_pct": 4.1
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 3,
+      "files_with_logic": 3,
+      "files_with_both": 3
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 8
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.8
   },
   "transcript_analysis": {
     "total_events": 120,
@@ -47,13 +123,160 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 346,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 91
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 105,
+    "lines_of_code": 691,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 21,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,23 @@
     "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 189,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 346,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 40
+    "load_time_ms": 91
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-33yz4i_u/loop-bench-jvbn5i1r', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "dist/index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,64 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-33yz4i_u/loop-bench-jvbn5i1r', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 19,
+      "code": 7,
+      "docs": 9,
+      "unnecessary": 3,
+      "unnecessary_list": [
+        "FEATURES.md",
+        "server.js",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1444,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "over-engineered",
+    "console_logs": 2,
+    "magic_numbers": {
+      "count": 13,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 52,
+      "average": 5.2,
+      "max": 15,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 15,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 393,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 20,
+      "source_lines": 784,
+      "ratio_pct": 2.6
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 3
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.46
   },
   "transcript_analysis": {
     "total_events": 107,
@@ -47,13 +125,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 52
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 57,
+    "lines_of_code": 629,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 18,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.75
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json
@@ -1,13 +1,8 @@
 {
   "implementation": {
     "renderer": "unknown",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 0,
-      "y": 0,
-      "width": 75,
-      "height": 150
-    },
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
@@ -15,8 +10,9 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": true
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -26,95 +22,104 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "could not start game with any mechanism"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 1,
-    "failed": 15,
-    "score": 0.06
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 70,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 79
+    "load_time_ms": 52
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json
@@ -26,12 +26,79 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-0x3y75v_/loop-bench-tirri_jo', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 12744,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-0x3y75v_/loop-bench-tirri_jo', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 15,
+      "code": 4,
+      "docs": 7,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "server.js",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1098,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 2,
+    "magic_numbers": {
+      "count": 16,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 45,
+      "average": 8.0,
+      "max": 35,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 11,
+    "global_declarations": 10,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 396,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 34,
+      "source_lines": 744,
+      "ratio_pct": 4.6
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": true,
+      "errors": 0
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.71
   },
   "transcript_analysis": {
     "total_events": 134,
@@ -57,10 +124,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.94,
+    "score": 0.88,
     "total": 16,
-    "passed": 15,
-    "failed": 1,
+    "passed": 14,
+    "failed": 2,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -79,7 +146,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -95,62 +163,62 @@
         {
           "name": "auto_drop",
           "pass": true,
-          "detail": "grid state changed after 5s with no input"
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
           "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
           "pass": true,
-          "detail": "rotated: [unknown] failed: [] (tested 1 piece types in 60 attempts)"
+          "detail": "rotation confirmed but could not identify individual piece types"
         },
         {
           "name": "hard_drop",
           "pass": true,
-          "detail": "piece immediately dropped and new piece appeared"
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom"
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "new piece detected at top of grid"
+          "detail": "2 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
           "pass": true,
-          "detail": "grid accumulated cells: 28 -> 47"
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
-          "pass": true,
-          "detail": "line cleared via strategic placement"
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score did not increase: [0] -> no change after polling"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
@@ -160,24 +228,35 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 29s, placed 100 pieces, no crashes"
+          "detail": "played for 30s, placed 39 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 15,
-        "failed": 1,
-        "score": 0.94
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
       },
       "gameplay": {
-        "pieces_placed": 154,
-        "lines_cleared": 1,
+        "pieces_placed": 39,
+        "lines_cleared": 0,
         "max_score_observed": 0,
-        "play_duration_seconds": 29,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 297,
+        "events_count": 10,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": -1
+        "load_time_ms": 35
       },
       "accessibility": {
         "issues": [
@@ -189,10 +268,19 @@
       }
     }
   },
-  "outcome_score": 0.94,
-  "score": 0.94,
+  "outcome_score": 0.815,
+  "score": 0.815,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 57,
+    "lines_of_code": 629,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 18,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.75
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [unknown] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 28 -> 47"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "line cleared via strategic placement"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 29s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 39 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 154,
-    "lines_cleared": 1,
+    "pieces_placed": 39,
+    "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 29,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 297,
+    "events_count": 10,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 0,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 35
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-me5_pdo3/loop-bench-sdqv7jk5', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,63 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-me5_pdo3/loop-bench-sdqv7jk5', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 38,
+      "code": 20,
+      "docs": 9,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "server.js",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1642,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "over-engineered",
+    "console_logs": 2,
+    "magic_numbers": {
+      "count": 19,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 75,
+      "average": 6.1,
+      "max": 35,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 29,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 685,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 42,
+      "source_lines": 1296,
+      "ratio_pct": 3.2
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 5,
+      "files_with_logic": 9,
+      "files_with_both": 4
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 1
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.56
   },
   "transcript_analysis": {
     "total_events": 123,
@@ -47,139 +124,22 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.13,
-    "total": 16,
-    "passed": 2,
-    "failed": 14,
-    "report": {
-      "implementation": {
-        "renderer": "unknown",
-        "grid_detected": true,
-        "grid_bounds": {
-          "x": 0,
-          "y": 0,
-          "width": 75,
-          "height": 150
-        },
-        "controls": {
-          "left": "ArrowLeft",
-          "right": "ArrowRight",
-          "down": "ArrowDown",
-          "rotate": "ArrowUp",
-          "drop": "Space"
-        },
-        "start_mechanism": "unknown",
-        "score_element_found": false
-      },
-      "tests": [
-        {
-          "name": "game_loads",
-          "pass": true,
-          "detail": "no console errors"
-        },
-        {
-          "name": "game_starts",
-          "pass": false,
-          "detail": "could not start game with any mechanism"
-        },
-        {
-          "name": "auto_drop",
-          "pass": false,
-          "detail": "piece did not move in 5 seconds"
-        },
-        {
-          "name": "move_left",
-          "pass": false,
-          "detail": "no change detected after key press"
-        },
-        {
-          "name": "move_right",
-          "pass": false,
-          "detail": "no change detected after key press"
-        },
-        {
-          "name": "move_down",
-          "pass": false,
-          "detail": "no change detected after key press"
-        },
-        {
-          "name": "rotate",
-          "pass": false,
-          "detail": "no change detected after rotate key"
-        },
-        {
-          "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "could not detect any piece rotations"
-        },
-        {
-          "name": "hard_drop",
-          "pass": false,
-          "detail": "no change detected after hard drop key"
-        },
-        {
-          "name": "piece_locks",
-          "pass": false,
-          "detail": "could not verify piece locking at bottom"
-        },
-        {
-          "name": "new_piece_spawns",
-          "pass": false,
-          "detail": "could not detect new piece at top"
-        },
-        {
-          "name": "multiple_pieces",
-          "pass": false,
-          "detail": "grid did not accumulate filled cells"
-        },
-        {
-          "name": "line_clear",
-          "pass": true,
-          "detail": "line cleared via strategic placement"
-        },
-        {
-          "name": "score_changes",
-          "pass": false,
-          "detail": "score did not increase: [0] -> no change after polling"
-        },
-        {
-          "name": "game_over",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
-        },
-        {
-          "name": "playable_30s",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
-        }
-      ],
-      "summary": {
-        "total": 16,
-        "passed": 2,
-        "failed": 14,
-        "score": 0.13
-      },
-      "gameplay": {
-        "pieces_placed": 110,
-        "lines_cleared": 1,
-        "max_score_observed": 0,
-        "play_duration_seconds": 0,
-        "errors_during_play": 0
-      },
-      "performance": {
-        "load_time_ms": 117
-      },
-      "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
-      }
-    }
+    "score": 0,
+    "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.13,
-  "score": 0.13,
+  "outcome_score": 0.275,
+  "score": 0.275,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 12,
+    "cognitive_complexity": 101,
+    "lines_of_code": 806,
+    "duplication_pct": 15.0,
+    "tech_debt_minutes": 30,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -43,22 +43,243 @@
     "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-dg9g3bx_/loop-bench-eenai5fl', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 11,
+      "code": 5,
+      "docs": 3,
+      "unnecessary": 2,
+      "unnecessary_list": [
+        "server.js",
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1390,
+    "dependencies": {
+      "production": 0,
+      "dev": 5,
+      "total": 5
+    },
+    "complexity": "moderate",
+    "console_logs": 2,
+    "magic_numbers": {
+      "count": 15,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 50,
+      "average": 8.1,
+      "max": 40,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 16,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 830,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 33,
+      "source_lines": 921,
+      "ratio_pct": 3.6
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 4
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.66
   },
   "transcript_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/transcript-analysis.py', '/root/loop-benchmarking/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2']' timed out after 30 seconds",
-    "score": 0
+    "total_events": 69,
+    "tool_calls": {
+      "total": 18,
+      "bash": 13,
+      "write": 0,
+      "edit": 0,
+      "read": 5
+    },
+    "wasted_turns": {
+      "total": 6,
+      "docs": 2,
+      "ascii_art": 0,
+      "server_starts": 4
+    },
+    "errors_encountered": 0,
+    "thinking_blocks": 19,
+    "text_blocks": 10,
+    "productivity_ratio": 0.67,
+    "self_tested": false,
+    "score": 0.75
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 343,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 101
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.28,
+  "score": 0.28,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 128,
+    "lines_of_code": 1228,
+    "duplication_pct": 32.5,
+    "tech_debt_minutes": 35,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,28 +98,40 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 77 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 7,
-    "failed": 9,
-    "score": 0.44
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 187,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 343,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 40
+    "load_time_ms": 101
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-jz1t_adw/loop-bench-ud3ikw5f', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,62 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-jz1t_adw/loop-bench-ud3ikw5f', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 12,
+      "code": 5,
+      "docs": 2,
+      "unnecessary": 1,
+      "unnecessary_list": [
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1207,
+    "dependencies": {
+      "production": 0,
+      "dev": 3,
+      "total": 3
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 14,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 50,
+      "average": 6.3,
+      "max": 26,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 16,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 455,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 31,
+      "source_lines": 848,
+      "ratio_pct": 3.7
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 3,
+      "files_with_logic": 3,
+      "files_with_both": 3
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 5
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.8
   },
   "transcript_analysis": {
     "total_events": 52,
@@ -47,13 +123,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "6 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 307,
+        "events_count": 10,
+        "pieces_spawned": 6,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 110
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.77,
+  "score": 0.77,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 9,
+    "cognitive_complexity": 86,
+    "lines_of_code": 614,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.6
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [I, other] failed: [] (tested 2 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "detail": "6 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 24"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 28s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,25 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 210,
+    "pieces_placed": 37,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 28,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 307,
+    "events_count": 10,
+    "pieces_spawned": 6,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 159
+    "load_time_ms": 110
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-loagbwpu/loop-bench-xt9_gk40', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-loagbwpu/loop-bench-xt9_gk40', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 895,
+    "dependencies": {
+      "production": 0,
+      "dev": 6,
+      "total": 6
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 16,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 61,
+      "average": 6.6,
+      "max": 22,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 8,
+    "global_declarations": 48,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 275,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 37,
+      "source_lines": 688,
+      "ratio_pct": 5.4
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 7
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.95
   },
   "transcript_analysis": {
     "total_events": 40,
@@ -46,14 +120,164 @@
     "score": 1.0
   },
   "gameplay_bot": {
-    "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "pass": true,
+    "score": 1,
+    "total": 16,
+    "passed": 16,
+    "failed": 0,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "2 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 254 to 364"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 34 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 16,
+        "failed": 0,
+        "score": 1
+      },
+      "gameplay": {
+        "pieces_placed": 34,
+        "lines_cleared": 2,
+        "max_score_observed": 364,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 287,
+        "events_count": 11,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 2,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 35
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.96,
+  "score": 0.96,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 93,
+    "lines_of_code": 446,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.92
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 40"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "2 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [210] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 254 to 364"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 76 pieces, no crashes"
+      "detail": "played for 30s, placed 34 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 16,
+    "failed": 0,
+    "score": 1
   },
   "gameplay": {
-    "pieces_placed": 127,
-    "lines_cleared": 1,
-    "max_score_observed": 158,
+    "pieces_placed": 34,
+    "lines_cleared": 2,
+    "max_score_observed": 364,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 287,
+    "events_count": 11,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 2,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 22
+    "load_time_ms": 35
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-de89ue8t/loop-bench-3ur6qash', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-de89ue8t/loop-bench-3ur6qash', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1292,
+    "dependencies": {
+      "production": 0,
+      "dev": 6,
+      "total": 6
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 30,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 59,
+      "average": 7.3,
+      "max": 27,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 34,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 435,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 96,
+      "source_lines": 991,
+      "ratio_pct": 9.7
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 8
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 41,
@@ -47,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 256"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 44 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 44,
+        "lines_cleared": 1,
+        "max_score_observed": 256,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 289,
+        "events_count": 11,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 94
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.795,
+  "score": 0.795,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 108,
+    "lines_of_code": 595,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 39,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.65
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 46"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [132] -> no change after polling"
+      "detail": "score stayed at 256"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 44 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,25 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 119,
-    "lines_cleared": 2,
-    "max_score_observed": 200,
+    "pieces_placed": 44,
+    "lines_cleared": 1,
+    "max_score_observed": 256,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 289,
+    "events_count": 11,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 26
+    "load_time_ms": 94
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -26,8 +26,20 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-kdaj92n_/loop-bench-afsfv6ek', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 17548,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -80,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 2
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 44,
@@ -109,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 160"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 160,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 343,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 54
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.55,
+  "score": 0.55,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 123,
+    "lines_of_code": 644,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 16,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.79
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [128] -> no change after polling"
+      "detail": "score stayed at 160"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 160,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 343,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 34
+    "load_time_ms": 54
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -26,8 +26,20 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-_3aet_ww/loop-bench-ztizwjzj', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 145626,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -109,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [S, unknown]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "3 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 34 to 160"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 41 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 41,
+        "lines_cleared": 3,
+        "max_score_observed": 160,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 291,
+        "events_count": 9,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 3,
+        "piece_types_seen": [
+          "S",
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 67
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.745,
+  "score": 0.745,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 19,
+    "cognitive_complexity": 120,
+    "lines_of_code": 1411,
+    "duplication_pct": 53.1,
+    "tech_debt_minutes": 74,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [S, unknown]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "10 line(s) cleared during AI play"
+      "detail": "3 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 0 to 122"
+      "detail": "score changed from 34 to 160"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 28s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 41 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,26 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 141,
-    "lines_cleared": 46,
-    "max_score_observed": 0,
-    "play_duration_seconds": 28,
+    "pieces_placed": 41,
+    "lines_cleared": 3,
+    "max_score_observed": 160,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 291,
+    "events_count": 9,
+    "pieces_spawned": 5,
+    "pieces_locked": 11,
+    "lines_cleared": 3,
+    "piece_types_seen": [
+      "S",
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 617
+    "load_time_ms": 67
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -26,8 +26,21 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-3a9i8rmm/loop-bench-jymd_531', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": false,
+      "errors": 1
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 15037,
+      "size_under_512kb": true
+    },
+    "score": 0.67
   },
   "code_analysis": {
     "files": {
@@ -112,10 +125,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.175,
+  "score": 0.175,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 91,
+    "lines_of_code": 937,
+    "duplication_pct": 12.6,
+    "tech_debt_minutes": 75,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.35
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,22 +1,18 @@
 {
   "implementation": {
-    "renderer": "canvas",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 0,
-      "y": 0,
-      "width": 320,
-      "height": 640
-    },
+    "renderer": "unknown",
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "auto",
-    "score_element_found": true
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -27,67 +23,67 @@
     {
       "name": "game_starts",
       "pass": true,
-      "detail": "started via auto"
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "rotated: [] failed: [I] (tested 1 piece types in 60 attempts)"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
-      "pass": true,
-      "detail": "filled cells persist at bottom"
+      "pass": false,
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "new piece detected at top of grid"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "grid accumulated cells: 20 -> 44"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "2 line(s) cleared during AI play"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -96,32 +92,38 @@
     },
     {
       "name": "playable_30s",
-      "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "pass": false,
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 119,
-    "lines_cleared": 4,
+    "pieces_placed": 26,
+    "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 30,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 497
+    "load_time_ms": 27
   },
   "accessibility": {
-    "issues": [
-      "canvas without aria-label or role",
-      "canvas without aria-label or role"
-    ],
-    "issue_count": 2,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -26,8 +26,21 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-mzmf8qdj/loop-bench-amrtiyou', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": false,
+      "errors": 2
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 151804,
+      "size_under_512kb": true
+    },
+    "score": 0.67
   },
   "code_analysis": {
     "files": {
@@ -79,11 +92,11 @@
       "files_with_both": 2
     },
     "html_validation": {
-      "valid": false,
+      "valid": true,
       "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.9
   },
   "transcript_analysis": {
     "total_events": 56,
@@ -109,13 +122,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 280"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 46 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 46,
+        "lines_cleared": 1,
+        "max_score_observed": 280,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 279,
+        "events_count": 11,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 21
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.745,
+  "score": 0.745,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 16,
+    "cognitive_complexity": 176,
+    "lines_of_code": 1794,
+    "duplication_pct": 44.8,
+    "tech_debt_minutes": 62,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 40"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [130] -> no change after polling"
+      "detail": "score stayed at 280"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 46 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,25 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 129,
+    "pieces_placed": 46,
     "lines_cleared": 1,
-    "max_score_observed": 162,
+    "max_score_observed": 280,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 279,
+    "events_count": 11,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 27
+    "load_time_ms": 21
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-38mshnpy/loop-bench-dzgab_lb', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-38mshnpy/loop-bench-dzgab_lb', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 49197,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 25,
+          "height": 50
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 150"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 150,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 347,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 25
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 12,
+    "cognitive_complexity": 117,
+    "lines_of_code": 635,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 44,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [240] -> no change after polling"
+      "detail": "score stayed at 150"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 77 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 9,
-    "failed": 7,
-    "score": 0.56
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 187,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 186,
+    "max_score_observed": 150,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 347,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 60
+    "load_time_ms": 25
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-0n45h12w/loop-bench-p92ynomw', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-0n45h12w/loop-bench-p92ynomw', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 48079,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -86,11 +120,11 @@
     "score": 1.0
   },
   "gameplay_bot": {
-    "pass": false,
-    "score": 0.88,
+    "pass": true,
+    "score": 1,
     "total": 16,
-    "passed": 14,
-    "failed": 2,
+    "passed": 16,
+    "failed": 0,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -105,11 +139,12 @@
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "ArrowUp",
+          "rotate": "x",
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -125,62 +160,62 @@
         {
           "name": "auto_drop",
           "pass": true,
-          "detail": "grid state changed after 5s with no input"
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
           "pass": true,
-          "detail": "grid state changed after key press"
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
-          "pass": false,
-          "detail": "no change detected after rotate key"
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
           "pass": true,
-          "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+          "detail": "rotation observed, piece types seen: [unknown, S]"
         },
         {
           "name": "hard_drop",
           "pass": true,
-          "detail": "piece immediately dropped and new piece appeared"
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom"
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "new piece detected at top of grid"
+          "detail": "4 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
           "pass": true,
-          "detail": "grid accumulated cells: 20 -> 45"
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "1 line(s) cleared during AI play"
+          "detail": "2 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
-          "pass": false,
-          "detail": "score did not increase: [202] -> no change after polling"
+          "pass": true,
+          "detail": "score changed from 342 to 360"
         },
         {
           "name": "game_over",
@@ -190,24 +225,36 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 26s, placed 100 pieces, no crashes"
+          "detail": "played for 30s, placed 37 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 14,
-        "failed": 2,
-        "score": 0.88
+        "passed": 16,
+        "failed": 0,
+        "score": 1
       },
       "gameplay": {
-        "pieces_placed": 141,
+        "pieces_placed": 37,
         "lines_cleared": 2,
-        "max_score_observed": 238,
-        "play_duration_seconds": 26,
+        "max_score_observed": 360,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 305,
+        "events_count": 8,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 2,
+        "piece_types_seen": [
+          "unknown",
+          "S"
+        ],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 82
+        "load_time_ms": 34
       },
       "accessibility": {
         "issues": [
@@ -219,10 +266,19 @@
       }
     }
   },
-  "outcome_score": 0.44,
-  "score": 0.44,
+  "outcome_score": 0.875,
+  "score": 0.875,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 76,
+    "lines_of_code": 819,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 28,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.75
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "no change detected after rotate key"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, S]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 45"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "2 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [202] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 342 to 360"
     },
     {
       "name": "game_over",
@@ -97,24 +98,36 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 26s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 16,
+    "failed": 0,
+    "score": 1
   },
   "gameplay": {
-    "pieces_placed": 141,
+    "pieces_placed": 37,
     "lines_cleared": 2,
-    "max_score_observed": 238,
-    "play_duration_seconds": 26,
+    "max_score_observed": 360,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 305,
+    "events_count": 8,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 2,
+    "piece_types_seen": [
+      "unknown",
+      "S"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 82
+    "load_time_ms": 34
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-ex80o7g1/loop-bench-mjng5_fj', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-ex80o7g1/loop-bench-mjng5_fj', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 28619,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -86,14 +120,166 @@
     "score": 1.0
   },
   "gameplay_bot": {
-    "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "pass": true,
+    "score": 1,
+    "total": 16,
+    "passed": 16,
+    "failed": 0,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [S, L, J]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 302 to 310"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 16,
+        "failed": 0,
+        "score": 1
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 310,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 302,
+        "events_count": 10,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "S",
+          "L",
+          "J"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 49
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.895,
+  "score": 0.895,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 107,
+    "lines_of_code": 672,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 32,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.79
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other, unknown] failed: [] (tested 2 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [S, L, J]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 32 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [200] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 302 to 310"
     },
     {
       "name": "game_over",
@@ -97,24 +98,37 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 77 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 16,
+    "failed": 0,
+    "score": 1
   },
   "gameplay": {
-    "pieces_placed": 122,
-    "lines_cleared": 2,
-    "max_score_observed": 182,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
+    "max_score_observed": 310,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 302,
+    "events_count": 10,
+    "pieces_spawned": 5,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "S",
+      "L",
+      "J"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 348
+    "load_time_ms": 49
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-9ieawh2c/loop-bench-6s2flshh', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "no build script defined (static project)"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-9ieawh2c/loop-bench-6s2flshh', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 50041,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 164"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 164,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 350,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 29
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 13,
+    "cognitive_complexity": 153,
+    "lines_of_code": 704,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 69,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [154] -> no change after polling"
+      "detail": "score stayed at 164"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 222,
+    "max_score_observed": 164,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 350,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 34
+    "load_time_ms": 29
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-f54mliyx/loop-bench-pc2ap4ay', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "no build script defined (static project)"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-f54mliyx/loop-bench-pc2ap4ay', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 44999,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 340,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 78
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 140,
+    "lines_of_code": 709,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 58,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 340,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 35
+    "load_time_ms": 78
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-0ywraxje/loop-bench-q46nchnj', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-0ywraxje/loop-bench-q46nchnj', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 47466,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, S]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 260"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 38 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 38,
+        "lines_cleared": 0,
+        "max_score_observed": 260,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 300,
+        "events_count": 9,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown",
+          "S"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 43
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.69,
+  "score": 0.69,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 106,
+    "lines_of_code": 604,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 44,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, S]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 41"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "line cleared via strategic placement"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [272] -> no change after polling"
+      "detail": "score stayed at 260"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 38 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,26 @@
     "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 131,
-    "lines_cleared": 1,
-    "max_score_observed": 174,
+    "pieces_placed": 38,
+    "lines_cleared": 0,
+    "max_score_observed": 260,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 300,
+    "events_count": 9,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 0,
+    "piece_types_seen": [
+      "unknown",
+      "S"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 43
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-egdg4quh/loop-bench-amkr12d_', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-egdg4quh/loop-bench-amkr12d_', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 38300,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, S]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 350"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 43 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 43,
+        "lines_cleared": 1,
+        "max_score_observed": 350,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 279,
+        "events_count": 11,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "S"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 51
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.835,
+  "score": 0.835,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 128,
+    "lines_of_code": 602,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 53,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, S]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 41"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [162] -> no change after polling"
+      "detail": "score stayed at 350"
     },
     {
       "name": "game_over",
@@ -97,24 +98,36 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 43 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 130,
+    "pieces_placed": 43,
     "lines_cleared": 1,
-    "max_score_observed": 192,
+    "max_score_observed": 350,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 279,
+    "events_count": 11,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "S"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 51
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-cy1ouzsu/loop-bench-t_rwtfd6', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-cy1ouzsu/loop-bench-t_rwtfd6', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 38664,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -58,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 3
     },
     "duplication_percentage": 0.0,
-    "score": 0.4
+    "score": 0.75
   },
   "transcript_analysis": {
     "total_events": 73,
@@ -87,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [I, unknown]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "6 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 302"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 41 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 41,
+        "lines_cleared": 1,
+        "max_score_observed": 302,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 284,
+        "events_count": 11,
+        "pieces_spawned": 6,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "I",
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 66
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.775,
+  "score": 0.775,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 156,
+    "lines_of_code": 686,
+    "duplication_pct": 3.5,
+    "tech_debt_minutes": 33,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.61
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -58,7 +58,7 @@
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotation confirmed but could not identify individual piece types"
+      "detail": "rotation observed, piece types seen: [I, unknown]"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "5 new piece(s) detected at top of grid"
+      "detail": "6 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -82,13 +82,13 @@
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "could not trigger or detect a line clear via grid reader"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score stayed at 308"
+      "detail": "score stayed at 302"
     },
     {
       "name": "game_over",
@@ -103,30 +103,31 @@
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
     "pieces_placed": 41,
-    "lines_cleared": 0,
-    "max_score_observed": 308,
+    "lines_cleared": 1,
+    "max_score_observed": 302,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 179,
-    "events_count": 10,
-    "pieces_spawned": 5,
+    "frames": 284,
+    "events_count": 11,
+    "pieces_spawned": 6,
     "pieces_locked": 11,
-    "lines_cleared": 0,
+    "lines_cleared": 1,
     "piece_types_seen": [
+      "I",
       "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 1458
+    "load_time_ms": 66
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-1ryr7fh0/loop-bench-g913qn5g', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-1ryr7fh0/loop-bench-g913qn5g', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 42269,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 188"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 36 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 36,
+        "lines_cleared": 1,
+        "max_score_observed": 188,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 303,
+        "events_count": 9,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 28
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.775,
+  "score": 0.775,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 156,
+    "lines_of_code": 686,
+    "duplication_pct": 3.5,
+    "tech_debt_minutes": 33,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.61
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [178] -> no change after polling"
+      "detail": "score stayed at 188"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 36 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 120,
-    "lines_cleared": 2,
+    "pieces_placed": 36,
+    "lines_cleared": 1,
     "max_score_observed": 188,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 303,
+    "events_count": 9,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 26
+    "load_time_ms": 28
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-dr_6_3of/loop-bench-xwpci4l5', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-dr_6_3of/loop-bench-xwpci4l5', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 42258,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,165 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": false,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, T, L, S]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "10 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 304,
+        "events_count": 10,
+        "pieces_spawned": 10,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "T",
+          "L",
+          "S"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 48
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.835,
+  "score": 0.835,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 132,
+    "lines_of_code": 685,
+    "duplication_pct": 2.8,
+    "tech_debt_minutes": 23,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": false
+    "score_element_found": false,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, T, L, S]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "10 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 43"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "no score element found and no number changed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,28 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 121,
-    "lines_cleared": 2,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 304,
+    "events_count": 10,
+    "pieces_spawned": 10,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "T",
+      "L",
+      "S"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 22
+    "load_time_ms": 48
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-vqyy1j1m/loop-bench-io7ugig5', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-vqyy1j1m/loop-bench-io7ugig5', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 45625,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.81,
+    "total": 16,
+    "passed": 13,
+    "failed": 3,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": false,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "9 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 302,
+        "events_count": 9,
+        "pieces_spawned": 9,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 29
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.77,
+  "score": 0.77,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 132,
+    "lines_of_code": 685,
+    "duplication_pct": 2.8,
+    "tech_debt_minutes": 23,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": false
+    "score_element_found": false,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "9 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 41"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "no score element found and no number changed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 130,
+    "pieces_placed": 37,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 302,
+    "events_count": 9,
+    "pieces_spawned": 9,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 29
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -26,8 +26,20 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-_e4j35hj/loop-bench-wyg6e789', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 36796,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -109,13 +121,167 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [L, S, unknown, T, Z]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "9 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 278"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 36 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 36,
+        "lines_cleared": 1,
+        "max_score_observed": 278,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 306,
+        "events_count": 10,
+        "pieces_spawned": 9,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "L",
+          "S",
+          "unknown",
+          "T",
+          "Z"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 67
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.835,
+  "score": 0.835,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 132,
+    "lines_of_code": 685,
+    "duplication_pct": 2.8,
+    "tech_debt_minutes": 23,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [L, S, unknown, T, Z]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "9 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [240] -> no change after polling"
+      "detail": "score stayed at 278"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 36 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,29 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 121,
-    "lines_cleared": 2,
-    "max_score_observed": 152,
+    "pieces_placed": 36,
+    "lines_cleared": 1,
+    "max_score_observed": 278,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 306,
+    "events_count": 10,
+    "pieces_spawned": 9,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "L",
+      "S",
+      "unknown",
+      "T",
+      "Z"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 35
+    "load_time_ms": 67
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-60ygqx7w/loop-bench-l6roqn5z', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "no build script defined (static project)"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-60ygqx7w/loop-bench-l6roqn5z', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 36505,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 304"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 44 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 44,
+        "lines_cleared": 1,
+        "max_score_observed": 304,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 278,
+        "events_count": 10,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 34
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.795,
+  "score": 0.795,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 104,
+    "lines_of_code": 760,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 42,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.65
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [154] -> no change after polling"
+      "detail": "score stayed at 304"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 44 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,25 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 120,
-    "lines_cleared": 2,
-    "max_score_observed": 182,
+    "pieces_placed": 44,
+    "lines_cleared": 1,
+    "max_score_observed": 304,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 278,
+    "events_count": 10,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 28
+    "load_time_ms": 34
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-3gvujmf9/loop-bench-k3paesnr', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "no build script defined (static project)"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-3gvujmf9/loop-bench-k3paesnr', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 48614,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 64,
+          "height": 128
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 188 to 212"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 212,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 346,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 71
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.365,
+  "score": 0.365,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 121,
+    "lines_of_code": 829,
+    "duplication_pct": 2.8,
+    "tech_debt_minutes": 52,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.35
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [138] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 188 to 212"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 9,
-    "failed": 7,
-    "score": 0.56
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 168,
+    "max_score_observed": 212,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 346,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 24
+    "load_time_ms": 71
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-9kxwf7dz/loop-bench-j7p5ruqx', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-9kxwf7dz/loop-bench-j7p5ruqx', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 45822,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, J]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 290"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 43 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 43,
+        "lines_cleared": 1,
+        "max_score_observed": 290,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 284,
+        "events_count": 11,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "J"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 118
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.72,
+  "score": 0.72,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 125,
+    "lines_of_code": 763,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 48,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [I] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, J]"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "no change detected after hard drop key"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [154] -> no change after polling"
+      "detail": "score stayed at 290"
     },
     {
       "name": "game_over",
@@ -97,24 +98,36 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 43 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 12,
-    "failed": 4,
-    "score": 0.75
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 180,
-    "lines_cleared": 2,
-    "max_score_observed": 172,
+    "pieces_placed": 43,
+    "lines_cleared": 1,
+    "max_score_observed": 290,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 284,
+    "events_count": 11,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "J"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 29
+    "load_time_ms": 118
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-fw_9cpgu/loop-bench-sx5ep9jz', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-fw_9cpgu/loop-bench-sx5ep9jz', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 11827,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, Z]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 278"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 46 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 46,
+        "lines_cleared": 1,
+        "max_score_observed": 278,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 279,
+        "events_count": 10,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "Z"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 72
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.835,
+  "score": 0.835,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 101,
+    "lines_of_code": 534,
+    "duplication_pct": 4.5,
+    "tech_debt_minutes": 16,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "could not detect any piece rotations"
+      "pass": true,
+      "detail": "rotation observed, piece types seen: [unknown, Z]"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "no change detected after hard drop key"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [156] -> no change after polling"
+      "detail": "score stayed at 278"
     },
     {
       "name": "game_over",
@@ -97,24 +98,36 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 46 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 12,
-    "failed": 4,
-    "score": 0.75
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 189,
+    "pieces_placed": 46,
     "lines_cleared": 1,
-    "max_score_observed": 230,
+    "max_score_observed": 278,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 279,
+    "events_count": 10,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "Z"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 28
+    "load_time_ms": 72
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-5j34pz8r/loop-bench-t34c4nm0', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-5j34pz8r/loop-bench-t34c4nm0', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 32578,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -86,14 +120,164 @@
     "score": 1.0
   },
   "gameplay_bot": {
-    "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "pass": true,
+    "score": 1,
+    "total": 16,
+    "passed": 16,
+    "failed": 0,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 304 to 312"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 16,
+        "failed": 0,
+        "score": 1
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 312,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 299,
+        "events_count": 9,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 50
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.865,
+  "score": 0.865,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 101,
+    "lines_of_code": 534,
+    "duplication_pct": 4.5,
+    "tech_debt_minutes": 16,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.73
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [164] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 304 to 312"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 16,
+    "failed": 0,
+    "score": 1
   },
   "gameplay": {
-    "pieces_placed": 119,
-    "lines_cleared": 2,
-    "max_score_observed": 186,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
+    "max_score_observed": 312,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 299,
+    "events_count": 9,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 26
+    "load_time_ms": 50
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-0_q053vs/loop-bench-1oqz1n2q', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-0_q053vs/loop-bench-1oqz1n2q', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 47946,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 64,
+          "height": 128
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 162"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 162,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 28
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 4,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.37,
+  "score": 0.37,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 161,
+    "lines_of_code": 840,
+    "duplication_pct": 3.4,
+    "tech_debt_minutes": 38,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.43
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [168] -> no change after polling"
+      "detail": "score stayed at 162"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 232,
+    "max_score_observed": 162,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 21
+    "load_time_ms": 28
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-iuedekw4/loop-bench-ste9dw4l', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-iuedekw4/loop-bench-ste9dw4l', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 46717,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -58,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 2
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 42,
@@ -87,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.63,
+    "score": 0.31,
     "total": 16,
-    "passed": 10,
-    "failed": 6,
+    "passed": 5,
+    "failed": 11,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -109,7 +143,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -124,63 +159,63 @@
         },
         {
           "name": "auto_drop",
-          "pass": true,
-          "detail": "pixels changed after 5s with no input"
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "could not detect any piece rotations"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
           "pass": false,
-          "detail": "no change detected after hard drop key"
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": false,
-          "detail": "could not verify piece locking at bottom"
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "could not detect new piece at top"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
           "pass": false,
-          "detail": "grid did not accumulate filled cells"
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "line cleared via strategic placement"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score did not increase: [166] -> no change after polling"
+          "detail": "score stayed at 148"
         },
         {
           "name": "game_over",
@@ -190,24 +225,33 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 77 pieces, no crashes"
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 10,
-        "failed": 6,
-        "score": 0.63
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
       },
       "gameplay": {
-        "pieces_placed": 187,
+        "pieces_placed": 20,
         "lines_cleared": 1,
-        "max_score_observed": 234,
+        "max_score_observed": 148,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 346,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 157
+        "load_time_ms": 39
       },
       "accessibility": {
         "issues": [
@@ -220,10 +264,19 @@
       }
     }
   },
-  "outcome_score": 0.315,
-  "score": 0.315,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 126,
+    "lines_of_code": 721,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 41,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [166] -> no change after polling"
+      "detail": "score stayed at 148"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 77 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 187,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 234,
+    "max_score_observed": 148,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 346,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 157
+    "load_time_ms": 39
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-r8vyc4_o/loop-bench-s2o7c9uv', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-r8vyc4_o/loop-bench-s2o7c9uv', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 9,
+      "code": 4,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1468,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 26,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 59,
+      "average": 6.4,
+      "max": 23,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 14,
+    "global_declarations": 18,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 517,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 71,
+      "source_lines": 1176,
+      "ratio_pct": 6.0
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 3,
+      "files_with_logic": 3,
+      "files_with_both": 3
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 7
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 52,
@@ -47,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [J, Z]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 264"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 39 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 39,
+        "lines_cleared": 1,
+        "max_score_observed": 264,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 293,
+        "events_count": 10,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "J",
+          "Z"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 71
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.72,
+  "score": 0.72,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 16,
+    "cognitive_complexity": 152,
+    "lines_of_code": 685,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 93,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [J, Z]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 40"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [162] -> no change after polling"
+      "detail": "score stayed at 264"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 39 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,26 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 129,
-    "lines_cleared": 2,
-    "max_score_observed": 180,
+    "pieces_placed": 39,
+    "lines_cleared": 1,
+    "max_score_observed": 264,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 293,
+    "events_count": 10,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "J",
+      "Z"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 125
+    "load_time_ms": 71
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/eval_results.json
@@ -26,8 +26,20 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-dzqt_mrd/loop-bench-exsc6g82', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 36162,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -109,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "8 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 274"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 40 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 40,
+        "lines_cleared": 0,
+        "max_score_observed": 274,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 293,
+        "events_count": 9,
+        "pieces_spawned": 8,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 50
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.885,
+  "score": 0.885,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 90,
+    "lines_of_code": 637,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 15,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.89
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "no change detected after rotate key"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "8 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [160] -> no change after polling"
+      "detail": "score stayed at 274"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 80 pieces, no crashes"
+      "detail": "played for 30s, placed 40 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 121,
-    "lines_cleared": 2,
-    "max_score_observed": 144,
+    "pieces_placed": 40,
+    "lines_cleared": 0,
+    "max_score_observed": 274,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 293,
+    "events_count": 9,
+    "pieces_spawned": 8,
+    "pieces_locked": 11,
+    "lines_cleared": 0,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 28
+    "load_time_ms": 50
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-05r17q0m/loop-bench-doqfpofi', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-05r17q0m/loop-bench-doqfpofi', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 11,
+      "code": 5,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1624,
+    "dependencies": {
+      "production": 0,
+      "dev": 8,
+      "total": 8
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 42,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 68,
+      "average": 7.4,
+      "max": 43,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 20,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 549,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 84,
+      "source_lines": 1269,
+      "ratio_pct": 6.6
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 3,
+      "files_with_logic": 3,
+      "files_with_both": 3
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 9
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 48,
@@ -47,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 196 to 234"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 234,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 344,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 38
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.44,
+  "score": 0.44,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 152,
+    "lines_of_code": 830,
+    "duplication_pct": 3.1,
+    "tech_debt_minutes": 65,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [166] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 196 to 234"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 208,
+    "max_score_observed": 234,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 344,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 85
+    "load_time_ms": 38
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-idtri8by/loop-bench-9b42xbl4', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-idtri8by/loop-bench-9b42xbl4', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1199,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 54,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 69,
+      "average": 6.0,
+      "max": 27,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 24,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 459,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 80,
+      "source_lines": 892,
+      "ratio_pct": 9.0
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 9
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 53,
@@ -47,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 36,
+          "height": 72
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 218 to 256"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 256,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 343,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 29
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.545,
+  "score": 0.545,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 71,
+    "lines_of_code": 575,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 9,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.71
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [210] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 218 to 256"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 140,
+    "max_score_observed": 256,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 343,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 30
+    "load_time_ms": 29
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-dvwvbo88/loop-bench-amzysv_v', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-dvwvbo88/loop-bench-amzysv_v', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1134,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 20,
+      "excessive": false
+    },
+    "function_length": {
+      "count": 56,
+      "average": 7.4,
+      "max": 43,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 66,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 385,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 55,
+      "source_lines": 899,
+      "ratio_pct": 6.1
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 8
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.9
   },
   "transcript_analysis": {
     "total_events": 43,
@@ -47,13 +121,167 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, S, J, T, L]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "8 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 298"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 298,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 306,
+        "events_count": 9,
+        "pieces_spawned": 8,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "S",
+          "J",
+          "T",
+          "L"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 152
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.85,
+  "score": 0.85,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 130,
+    "lines_of_code": 562,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 44,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.76
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [I] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, S, J, T, L]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "8 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 42"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [226] -> no change after polling"
+      "detail": "score stayed at 298"
     },
     {
       "name": "game_over",
@@ -97,24 +98,39 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 120,
-    "lines_cleared": 2,
-    "max_score_observed": 196,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
+    "max_score_observed": 298,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 306,
+    "events_count": 9,
+    "pieces_spawned": 8,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "S",
+      "J",
+      "T",
+      "L"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 23
+    "load_time_ms": 152
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -26,8 +26,20 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-cfq1fa7e/loop-bench-kncx228p', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 15602,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -112,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.3,
+  "score": 0.3,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 13,
+    "cognitive_complexity": 64,
+    "lines_of_code": 592,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 29,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.6
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-le3rczwj/loop-bench-6c3p0wr6', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,60 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-le3rczwj/loop-bench-6c3p0wr6', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 9,
+      "code": 4,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1647,
+    "dependencies": {
+      "production": 0,
+      "dev": 6,
+      "total": 6
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 58,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 89,
+      "average": 7.7,
+      "max": 45,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 15,
+    "global_declarations": 24,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 567,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 119,
+      "source_lines": 1195,
+      "ratio_pct": 10.0
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 7
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 64,
@@ -47,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "space",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via space"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 96 to 176"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 96,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 348,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 47
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 4,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 152,
+    "lines_of_code": 767,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 52,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "space",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [214] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 96 to 176"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 11,
-    "failed": 5,
-    "score": 0.69
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 72,
+    "max_score_observed": 96,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 348,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 41
+    "load_time_ms": 47
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-2zfhi3g8/loop-bench-9r05i_lq', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -20,8 +42,62 @@
     "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-2zfhi3g8/loop-bench-9r05i_lq', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 8,
+      "code": 3,
+      "docs": 1,
+      "unnecessary": 1,
+      "unnecessary_list": [
+        "README.md"
+      ]
+    },
+    "lines_of_code": 1535,
+    "dependencies": {
+      "production": 0,
+      "dev": 6,
+      "total": 6
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 64,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 75,
+      "average": 6.7,
+      "max": 30,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 12,
+    "global_declarations": 22,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 534,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 136,
+      "source_lines": 1078,
+      "ratio_pct": 12.6
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 0
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.4
   },
   "transcript_analysis": {
     "total_events": 82,
@@ -47,13 +123,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 42,
+          "height": 84
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 184 to 218"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 218,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 347,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 44
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 5,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.48,
+  "score": 0.48,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 112,
+    "lines_of_code": 750,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 52,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.65
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=off_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 184 to 284"
+      "detail": "score changed from 184 to 218"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 78 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 188,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 100,
+    "max_score_observed": 218,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 347,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 25
+    "load_time_ms": 44
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -26,8 +26,21 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-oqdanj22/loop-bench-zhl3wjhq', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": false,
+      "errors": 1
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 0,
+      "size_under_512kb": true
+    },
+    "score": 0.67
   },
   "code_analysis": {
     "files": {
@@ -109,29 +122,25 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.88,
+    "score": 0.19,
     "total": 16,
-    "passed": 14,
-    "failed": 2,
+    "passed": 3,
+    "failed": 13,
     "report": {
       "implementation": {
-        "renderer": "canvas",
-        "grid_detected": true,
-        "grid_bounds": {
-          "x": 0,
-          "y": 0,
-          "width": 320,
-          "height": 640
-        },
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
         "controls": {
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "z",
+          "rotate": "ArrowUp",
           "drop": "Space"
         },
-        "start_mechanism": "auto",
-        "score_element_found": true
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
       },
       "tests": [
         {
@@ -142,67 +151,67 @@
         {
           "name": "game_starts",
           "pass": true,
-          "detail": "started via auto"
+          "detail": "started via click_canvas"
         },
         {
           "name": "auto_drop",
-          "pass": true,
-          "detail": "grid state changed after 5s with no input"
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
         },
         {
           "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
         },
         {
           "name": "move_right",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
         },
         {
           "name": "move_down",
           "pass": false,
-          "detail": "no change detected after key press"
+          "detail": "grid reader unreliable, cannot verify movement"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": true,
-          "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
-          "pass": true,
-          "detail": "piece immediately dropped and new piece appeared"
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
         },
         {
           "name": "piece_locks",
-          "pass": true,
-          "detail": "filled cells persist at bottom"
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
-          "pass": true,
-          "detail": "new piece detected at top of grid"
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
-          "pass": true,
-          "detail": "game still responding after 10 piece drops"
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
-          "pass": true,
-          "detail": "51 line(s) cleared during AI play"
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score did not increase: [0] -> no change after polling"
+          "detail": "no score element found"
         },
         {
           "name": "game_over",
@@ -211,40 +220,55 @@
         },
         {
           "name": "playable_30s",
-          "pass": true,
-          "detail": "played for 30s, placed 82 pieces, no crashes"
+          "pass": false,
+          "detail": "only played for 7s"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 14,
-        "failed": 2,
-        "score": 0.88
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
       },
       "gameplay": {
-        "pieces_placed": 123,
-        "lines_cleared": 175,
+        "pieces_placed": 26,
+        "lines_cleared": 0,
         "max_score_observed": 0,
-        "play_duration_seconds": 30,
+        "play_duration_seconds": 7,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
       "performance": {
         "load_time_ms": 19
       },
       "accessibility": {
-        "issues": [
-          "canvas without aria-label or role",
-          "canvas without aria-label or role"
-        ],
-        "issue_count": 2,
-        "pass": false
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
       }
     }
   },
-  "outcome_score": 0.44,
-  "score": 0.44,
+  "outcome_score": 0.22,
+  "score": 0.22,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 3,
+    "vulnerabilities": 0,
+    "code_smells": 21,
+    "cognitive_complexity": 184,
+    "lines_of_code": 1499,
+    "duplication_pct": 55.8,
+    "tech_debt_minutes": 147,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -1,22 +1,18 @@
 {
   "implementation": {
-    "renderer": "canvas",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 0,
-      "y": 0,
-      "width": 320,
-      "height": 640
-    },
+    "renderer": "unknown",
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "auto",
-    "score_element_found": true
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -27,67 +23,67 @@
     {
       "name": "game_starts",
       "pass": true,
-      "detail": "started via auto"
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
-      "pass": true,
-      "detail": "filled cells persist at bottom"
+      "pass": false,
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "new piece detected at top of grid"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "51 line(s) cleared during AI play"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -96,32 +92,38 @@
     },
     {
       "name": "playable_30s",
-      "pass": true,
-      "detail": "played for 30s, placed 82 pieces, no crashes"
+      "pass": false,
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 123,
-    "lines_cleared": 175,
+    "pieces_placed": 26,
+    "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 30,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
     "load_time_ms": 19
   },
   "accessibility": {
-    "issues": [
-      "canvas without aria-label or role",
-      "canvas without aria-label or role"
-    ],
-    "issue_count": 2,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -26,8 +26,20 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-eb26nye_/loop-bench-_a_0urqo', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 20120,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -109,142 +121,22 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.94,
-    "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "report": {
-      "implementation": {
-        "renderer": "canvas",
-        "grid_detected": true,
-        "grid_bounds": {
-          "x": 0,
-          "y": 0,
-          "width": 300,
-          "height": 600
-        },
-        "controls": {
-          "left": "ArrowLeft",
-          "right": "ArrowRight",
-          "down": "ArrowDown",
-          "rotate": "z",
-          "drop": "Space"
-        },
-        "start_mechanism": "auto",
-        "score_element_found": true
-      },
-      "tests": [
-        {
-          "name": "game_loads",
-          "pass": true,
-          "detail": "no console errors"
-        },
-        {
-          "name": "game_starts",
-          "pass": true,
-          "detail": "started via auto"
-        },
-        {
-          "name": "auto_drop",
-          "pass": true,
-          "detail": "grid state changed after 5s with no input"
-        },
-        {
-          "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
-        },
-        {
-          "name": "move_right",
-          "pass": true,
-          "detail": "grid state changed after key press"
-        },
-        {
-          "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
-        },
-        {
-          "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
-        },
-        {
-          "name": "all_pieces_rotate",
-          "pass": true,
-          "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
-        },
-        {
-          "name": "hard_drop",
-          "pass": true,
-          "detail": "piece immediately dropped and new piece appeared"
-        },
-        {
-          "name": "piece_locks",
-          "pass": true,
-          "detail": "filled cells persist at bottom"
-        },
-        {
-          "name": "new_piece_spawns",
-          "pass": true,
-          "detail": "new piece detected at top of grid"
-        },
-        {
-          "name": "multiple_pieces",
-          "pass": true,
-          "detail": "game still responding after 10 piece drops"
-        },
-        {
-          "name": "line_clear",
-          "pass": true,
-          "detail": "9 line(s) cleared during AI play"
-        },
-        {
-          "name": "score_changes",
-          "pass": true,
-          "detail": "score changed from 192 to 200"
-        },
-        {
-          "name": "game_over",
-          "pass": false,
-          "detail": "could not trigger or detect game over"
-        },
-        {
-          "name": "playable_30s",
-          "pass": true,
-          "detail": "played for 30s, placed 83 pieces, no crashes"
-        }
-      ],
-      "summary": {
-        "total": 16,
-        "passed": 15,
-        "failed": 1,
-        "score": 0.94
-      },
-      "gameplay": {
-        "pieces_placed": 124,
-        "lines_cleared": 36,
-        "max_score_observed": 238,
-        "play_duration_seconds": 30,
-        "errors_during_play": 0
-      },
-      "performance": {
-        "load_time_ms": 35
-      },
-      "accessibility": {
-        "issues": [
-          "canvas without aria-label or role",
-          "canvas without aria-label or role"
-        ],
-        "issue_count": 2,
-        "pass": false
-      }
-    }
+    "score": 0,
+    "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.47,
-  "score": 0.47,
+  "outcome_score": 0.15,
+  "score": 0.15,
   "sonarqube": {
-    "error": "SonarQube scan timed out",
-    "score": 0
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 145,
+    "lines_of_code": 1250,
+    "duplication_pct": 5.9,
+    "tech_debt_minutes": 170,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.3
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,22 +1,18 @@
 {
   "implementation": {
-    "renderer": "canvas",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 0,
-      "y": 0,
-      "width": 300,
-      "height": 600
-    },
+    "renderer": "unknown",
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "auto",
-    "score_element_found": true
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -27,101 +23,107 @@
     {
       "name": "game_starts",
       "pass": true,
-      "detail": "started via auto"
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
-      "pass": true,
-      "detail": "filled cells persist at bottom"
+      "pass": false,
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "new piece detected at top of grid"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "9 line(s) cleared during AI play"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
-      "pass": true,
-      "detail": "score changed from 192 to 200"
+      "pass": false,
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "could not trigger or detect game over"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": true,
-      "detail": "played for 30s, placed 83 pieces, no crashes"
+      "pass": false,
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 124,
-    "lines_cleared": 36,
-    "max_score_observed": 238,
-    "play_duration_seconds": 30,
+    "pieces_placed": 26,
+    "lines_cleared": 0,
+    "max_score_observed": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 35
+    "load_time_ms": 22
   },
   "accessibility": {
-    "issues": [
-      "canvas without aria-label or role",
-      "canvas without aria-label or role"
-    ],
-    "issue_count": 2,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -43,8 +43,60 @@
     "score": 0.67
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-x_a00wq5/loop-bench-gmilst_1', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 7,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1657,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 28,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 55,
+      "average": 6.6,
+      "max": 26,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 10,
+    "global_declarations": 18,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 100.0,
+      "camel_case": 328,
+      "snake_case": 0
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 101,
+      "source_lines": 781,
+      "ratio_pct": 12.9
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 0
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.5
   },
   "transcript_analysis": {
     "total_events": 74,
@@ -70,13 +122,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, Z]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 44 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 44,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 279,
+        "events_count": 9,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "Z"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 19
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.715,
+  "score": 0.715,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 16,
+    "cognitive_complexity": 170,
+    "lines_of_code": 1440,
+    "duplication_pct": 49.3,
+    "tech_debt_minutes": 48,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=detailed_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -58,7 +58,7 @@
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotation confirmed but could not identify individual piece types"
+      "detail": "rotation observed, piece types seen: [unknown, Z]"
     },
     {
       "name": "hard_drop",
@@ -68,7 +68,7 @@
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
@@ -98,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 31s, placed 37 pieces, no crashes"
+      "detail": "played for 30s, placed 44 pieces, no crashes"
     }
   ],
   "summary": {
@@ -108,25 +108,26 @@
     "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 37,
+    "pieces_placed": 44,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 31,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 145,
+    "frames": 279,
     "events_count": 9,
     "pieces_spawned": 5,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
-      "unknown"
+      "unknown",
+      "Z"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 447
+    "load_time_ms": 19
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -26,12 +26,76 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-t3fuj7u6/loop-bench-_7ks5zgn', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 16947,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
-    "error": "Command '['python3', '/root/loop-benchmarking/tasks/tetris/eval/code-analysis.py', '/tmp/reeval-t3fuj7u6/loop-bench-_7ks5zgn', 'typescript']' timed out after 120 seconds",
-    "score": 0
+    "files": {
+      "total": 7,
+      "code": 3,
+      "docs": 0,
+      "unnecessary": 0,
+      "unnecessary_list": []
+    },
+    "lines_of_code": 1375,
+    "dependencies": {
+      "production": 0,
+      "dev": 7,
+      "total": 7
+    },
+    "complexity": "moderate",
+    "console_logs": 0,
+    "magic_numbers": {
+      "count": 66,
+      "excessive": true
+    },
+    "function_length": {
+      "count": 58,
+      "average": 7.6,
+      "max": 27,
+      "long_functions": 0
+    },
+    "max_nesting_depth": 14,
+    "global_declarations": 30,
+    "naming": {
+      "dominant_style": "camelCase",
+      "consistency_pct": 92.4,
+      "camel_case": 363,
+      "snake_case": 30
+    },
+    "error_handling": {
+      "try_catch_blocks": 0,
+      "has_error_handling": false
+    },
+    "comments": {
+      "comment_lines": 72,
+      "source_lines": 1035,
+      "ratio_pct": 7.0
+    },
+    "separation_of_concerns": {
+      "verdict": "mixed",
+      "files_with_rendering": 2,
+      "files_with_logic": 2,
+      "files_with_both": 2
+    },
+    "html_validation": {
+      "valid": false,
+      "errors": 2
+    },
+    "duplication_percentage": 0.0,
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 55,
@@ -57,13 +121,165 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "6 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 324 to 342"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 342,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 299,
+        "events_count": 10,
+        "pieces_spawned": 6,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "I",
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 89
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.715,
+  "score": 0.715,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 5,
+    "cognitive_complexity": 144,
+    "lines_of_code": 638,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 45,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -12,7 +12,7 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -52,13 +52,13 @@
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotation confirmed but could not identify individual piece types"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
@@ -87,8 +87,8 @@
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score stayed at 296"
+      "pass": true,
+      "detail": "score changed from 324 to 342"
     },
     {
       "name": "game_over",
@@ -98,39 +98,44 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 31 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 31,
+    "pieces_placed": 37,
     "lines_cleared": 1,
-    "max_score_observed": 296,
+    "max_score_observed": 342,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 159,
-    "events_count": 11,
+    "frames": 299,
+    "events_count": 10,
     "pieces_spawned": 6,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
+      "I",
       "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 4276
+    "load_time_ms": 89
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "no headings found",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -26,8 +26,20 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-i4ymkfiq/loop-bench-hdcmmx_h', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 25381,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -80,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 6
+      "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.85
+    "score": 0.5
   },
   "transcript_analysis": {
     "total_events": 57,
@@ -109,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 0 to 144"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 144,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 32
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 144,
+    "lines_of_code": 780,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 35,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 138 to 246"
+      "detail": "score changed from 0 to 144"
     },
     {
       "name": "game_over",
@@ -97,24 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 77 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 187,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 66,
+    "max_score_observed": 144,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 28
+    "load_time_ms": 32
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -26,8 +26,20 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-d59z4ylb/loop-bench-udnn4aje', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 17708,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -109,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "5 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 0 to 368"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 303,
+        "events_count": 10,
+        "pieces_spawned": 5,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 34
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.865,
+  "score": 0.865,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 136,
+    "lines_of_code": 653,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 48,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.79
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=off_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "5 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "11 line(s) cleared during AI play"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 96 to 192"
+      "detail": "score changed from 0 to 368"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 83 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 16,
-    "failed": 0,
-    "score": 1
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 124,
-    "lines_cleared": 42,
-    "max_score_observed": 216,
+    "pieces_placed": 37,
+    "lines_cleared": 0,
+    "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 303,
+    "events_count": 10,
+    "pieces_spawned": 5,
+    "pieces_locked": 11,
+    "lines_cleared": 0,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 40
+    "load_time_ms": 34
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -26,8 +26,20 @@
     "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-wnxcksi7/loop-bench-ymvhffsl', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 13233,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -112,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.46,
+  "score": 0.46,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 61,
+    "lines_of_code": 478,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.92
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -26,8 +26,20 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-4g5vr4fy/loop-bench-9osp3kim', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 15345,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -80,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 2
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 52,
@@ -109,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [I, unknown]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 246"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 246,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 305,
+        "events_count": 11,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "I",
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 87
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.915,
+  "score": 0.915,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 73,
+    "lines_of_code": 555,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 6,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.89
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -12,11 +12,12 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [I, unknown]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "1 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [166] -> no change after polling"
+      "detail": "score stayed at 246"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,26 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 120,
-    "lines_cleared": 2,
-    "max_score_observed": 142,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
+    "max_score_observed": 246,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 305,
+    "events_count": 11,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "I",
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 76
+    "load_time_ms": 87
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,11 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-0_h4aplp/loop-bench-5xgkq0xm', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-0_h4aplp/loop-bench-5xgkq0xm', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 22016,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -87,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 60,
+          "height": 120
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 178"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 178,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 346,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 111
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.475,
+  "score": 0.475,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 111,
+    "lines_of_code": 754,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 10,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.64
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=off_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "enter",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [356] -> no change after polling"
+      "detail": "score stayed at 178"
     },
     {
       "name": "game_over",
@@ -97,28 +98,41 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 31s, placed 48 pieces, no crashes"
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 10,
-    "failed": 6,
-    "score": 0.63
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 158,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 0,
-    "play_duration_seconds": 31,
+    "max_score_observed": 178,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 346,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1092
+    "load_time_ms": 111
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -26,8 +26,20 @@
     "score": 0.75
   },
   "quality": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/quality.sh', '/tmp/reeval-6xzte1vr/loop-bench-05evwwhn', 'typescript']' timed out after 120 seconds"
+    "lint": {
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
+    },
+    "typecheck": {
+      "pass": true
+    },
+    "performance": {
+      "pass": true,
+      "bundle_size_bytes": 16576,
+      "size_under_512kb": true
+    },
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -80,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 2
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 61,
@@ -109,13 +121,164 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, L]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "3 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 332"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 46 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 46,
+        "lines_cleared": 1,
+        "max_score_observed": 332,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 279,
+        "events_count": 11,
+        "pieces_spawned": 3,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "L"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 42
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.76,
+  "score": 0.76,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 113,
+    "lines_of_code": 541,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.58
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, L]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected after drop"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 20 -> 40"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [162] -> no change after polling"
+      "detail": "score stayed at 332"
     },
     {
       "name": "game_over",
@@ -97,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 26s, placed 100 pieces, no crashes"
+      "detail": "played for 30s, placed 46 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,14 +108,26 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 151,
+    "pieces_placed": 46,
     "lines_cleared": 1,
-    "max_score_observed": 132,
-    "play_duration_seconds": 26,
+    "max_score_observed": 332,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 279,
+    "events_count": 11,
+    "pieces_spawned": 3,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "L"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 937
+    "load_time_ms": 42
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -1,25 +1,45 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-ldeahnr5/loop-bench-_vpevx35', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
-      "pass": false,
-      "errors": -1,
-      "warnings": 0,
-      "error": "eslint failed to run"
+      "pass": true,
+      "errors": 0,
+      "warnings": 0
     },
     "typecheck": {
-      "pass": false,
-      "errors": 0
+      "pass": true
     },
     "performance": {
       "pass": true,
       "bundle_size_bytes": 21434,
       "size_under_512kb": true
     },
-    "score": 0.33
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -72,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 2
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 63,
@@ -104,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.25,
+  "score": 0.25,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 16,
+    "cognitive_complexity": 133,
+    "lines_of_code": 687,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 82,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
-    "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-r14ej_nz/loop-bench-ofmivkls', 'typescript']' timed out after 120 seconds"
+    "pass": true,
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "npm run build completed successfully"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": true,
+        "detail": "tsc --noEmit passed"
+      }
+    ],
+    "score": 1.0
   },
   "quality": {
     "lint": {
@@ -10,15 +32,14 @@
       "warnings": 0
     },
     "typecheck": {
-      "pass": false,
-      "errors": 0
+      "pass": true
     },
     "performance": {
       "pass": true,
       "bundle_size_bytes": 15383,
       "size_under_512kb": true
     },
-    "score": 0.67
+    "score": 1.0
   },
   "code_analysis": {
     "files": {
@@ -71,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 3
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 49,
@@ -100,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 305,
+        "events_count": 10,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 40
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.695,
+  "score": 0.695,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 10,
+    "cognitive_complexity": 69,
+    "lines_of_code": 594,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 34,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.45
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=off_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "no change detected after key press"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [unknown] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 36 -> 44"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "10 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
@@ -96,29 +97,43 @@
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 92,
-    "lines_cleared": 10,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 305,
+    "events_count": 10,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1356
+    "load_time_ms": 40
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -1,7 +1,29 @@
 {
   "structural": {
     "pass": false,
-    "error": "Command '['bash', '/root/loop-benchmarking/tasks/tetris/eval/structural.sh', '/tmp/reeval-wuh6htkd/loop-bench-q0okqwr1', 'typescript']' timed out after 120 seconds"
+    "checks": [
+      {
+        "name": "entry_point_exists",
+        "pass": true,
+        "detail": "index.html found"
+      },
+      {
+        "name": "package_json_exists",
+        "pass": true,
+        "detail": "package.json found"
+      },
+      {
+        "name": "build_succeeds",
+        "pass": true,
+        "detail": "no build script defined (static project)"
+      },
+      {
+        "name": "typescript_compiles",
+        "pass": false,
+        "detail": "tsc --noEmit failed"
+      }
+    ],
+    "score": 0.75
   },
   "quality": {
     "lint": {
@@ -99,13 +121,167 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, T, Z, J]"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "6 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 394"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 42 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 42,
+        "lines_cleared": 1,
+        "max_score_observed": 394,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 294,
+        "events_count": 10,
+        "pieces_spawned": 6,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "T",
+          "Z",
+          "J"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 31
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.845,
+  "score": 0.845,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 80,
+    "lines_of_code": 516,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 33,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.75
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "no change detected after rotate key"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation observed, piece types seen: [unknown, T, Z, J]"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "6 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 49"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "2 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [222] -> no change after polling"
+      "detail": "score stayed at 394"
     },
     {
       "name": "game_over",
@@ -97,24 +98,38 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 79 pieces, no crashes"
+      "detail": "played for 30s, placed 42 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 14,
-    "failed": 2,
-    "score": 0.88
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 120,
-    "lines_cleared": 2,
-    "max_score_observed": 222,
+    "pieces_placed": 42,
+    "lines_cleared": 1,
+    "max_score_observed": 394,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 294,
+    "events_count": 10,
+    "pieces_spawned": 6,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "T",
+      "Z",
+      "J"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 2944
+    "load_time_ms": 31
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -121,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.88,
+    "total": 16,
+    "passed": 14,
+    "failed": 2,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "1 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 302"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 14,
+        "failed": 2,
+        "score": 0.88
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 0,
+        "max_score_observed": 302,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 304,
+        "events_count": 9,
+        "pieces_spawned": 1,
+        "pieces_locked": 11,
+        "lines_cleared": 0,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 29
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.69,
+  "score": 0.69,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 12,
+    "cognitive_complexity": 101,
+    "lines_of_code": 680,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 50,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,62 +33,62 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [I] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "grid accumulated cells: 16 -> 36"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "line cleared via strategic placement"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [294] -> no change after polling"
+      "detail": "score stayed at 302"
     },
     {
       "name": "game_over",
@@ -97,24 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 70 pieces, no crashes"
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 121,
-    "lines_cleared": 1,
-    "max_score_observed": 186,
+    "pieces_placed": 37,
+    "lines_cleared": 0,
+    "max_score_observed": 302,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 304,
+    "events_count": 9,
+    "pieces_spawned": 1,
+    "pieces_locked": 11,
+    "lines_cleared": 0,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 358
+    "load_time_ms": 29
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -121,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.56,
+    "score": 0.38,
     "total": 16,
-    "passed": 9,
-    "failed": 7,
+    "passed": 6,
+    "failed": 10,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -143,7 +143,8 @@
           "drop": "Space"
         },
         "start_mechanism": "auto",
-        "score_element_found": true
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
@@ -158,63 +159,63 @@
         },
         {
           "name": "auto_drop",
-          "pass": true,
-          "detail": "pixels changed after 5s with no input"
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
-          "pass": true,
-          "detail": "grid state changed after key press"
+          "pass": false,
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "could not detect any piece rotations"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
           "pass": false,
-          "detail": "no change detected after hard drop key"
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": false,
-          "detail": "could not verify piece locking at bottom"
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "could not detect new piece at top"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
           "pass": false,
-          "detail": "grid did not accumulate filled cells"
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "line cleared via strategic placement"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
-          "pass": false,
-          "detail": "score did not increase: [176] -> no change after polling"
+          "pass": true,
+          "detail": "score changed from 168 to 186"
         },
         {
           "name": "game_over",
@@ -223,37 +224,59 @@
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 9,
-        "failed": 7,
-        "score": 0.56
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
       },
       "gameplay": {
-        "pieces_placed": 104,
+        "pieces_placed": 20,
         "lines_cleared": 1,
-        "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "max_score_observed": 186,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
+      "session": {
+        "frames": 346,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
       "performance": {
-        "load_time_ms": 1405
+        "load_time_ms": 48
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.56,
-  "score": 0.56,
+  "outcome_score": 0.57,
+  "score": 0.57,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 151,
+    "lines_of_code": 668,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 30,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.76
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=off_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,63 +32,63 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [176] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 168 to 186"
     },
     {
       "name": "game_over",
@@ -96,29 +97,42 @@
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 9,
-    "failed": 7,
-    "score": 0.56
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 104,
+    "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "max_score_observed": 186,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 346,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1405
+    "load_time_ms": 48
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/eval_results.json
@@ -121,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "space",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via space"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 349,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 27
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.455,
+  "score": 0.455,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 12,
+    "cognitive_complexity": 72,
+    "lines_of_code": 574,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 41,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.6
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "space",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,72 +33,72 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
@@ -107,18 +108,31 @@
     "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 101,
+    "pieces_placed": 20,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 349,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 702
+    "load_time_ms": 27
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/eval_results.json
@@ -121,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 33,
+          "height": 66
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 0 to 182"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 349,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 37
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 18,
+    "cognitive_complexity": 137,
+    "lines_of_code": 806,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 51,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,106 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
-      "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "pass": false,
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded."
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "could not read score element"
+      "pass": true,
+      "detail": "score changed from 0 to 182"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 7,
-    "failed": 9,
-    "score": 0.44
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 100,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 349,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1304
+    "load_time_ms": 37
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/eval_results.json
@@ -121,13 +121,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.44,
+    "total": 16,
+    "passed": 7,
+    "failed": 9,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 56,
+          "height": 112
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 202 to 226"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 7,
+        "failed": 9,
+        "score": 0.44
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 226,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 350,
+        "events_count": 3,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 38
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.65,
+  "score": 0.65,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 72,
+    "lines_of_code": 647,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 20,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.86
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=off_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,94 +32,106 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "151 line(s) cleared during AI play"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "score did not increase: [360] -> no change after polling"
+      "pass": true,
+      "detail": "score changed from 202 to 226"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 8,
-    "failed": 8,
-    "score": 0.5
+    "passed": 7,
+    "failed": 9,
+    "score": 0.44
   },
   "gameplay": {
-    "pieces_placed": 100,
-    "lines_cleared": 151,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 226,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 350,
+    "events_count": 3,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 3913
+    "load_time_ms": 38
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run1/eval_results.json
@@ -124,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.275,
+  "score": 0.275,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 271,
+    "lines_of_code": 1230,
+    "duplication_pct": 14.9,
+    "tech_debt_minutes": 101,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/eval_results.json
@@ -122,13 +122,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 200 to 232"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 232,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 351,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 91
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.465,
+  "score": 0.465,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 271,
+    "lines_of_code": 1230,
+    "duplication_pct": 14.9,
+    "tech_debt_minutes": 101,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run2/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,94 +32,107 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded."
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "could not read score element"
+      "pass": true,
+      "detail": "score changed from 200 to 232"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 7,
-    "failed": 9,
-    "score": 0.44
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 80,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 232,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 351,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 1061
+    "load_time_ms": 91
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/eval_results.json
@@ -121,15 +121,20 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
+    "score": 0.94,
     "total": 16,
-    "passed": 0,
-    "failed": 16,
+    "passed": 15,
+    "failed": 1,
     "report": {
       "implementation": {
-        "renderer": "unknown",
-        "grid_detected": false,
-        "grid_bounds": null,
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
         "controls": {
           "left": "ArrowLeft",
           "right": "ArrowRight",
@@ -137,128 +142,144 @@
           "rotate": "ArrowUp",
           "drop": "Space"
         },
-        "start_mechanism": "unknown",
+        "start_mechanism": "auto",
         "score_element_found": false,
-        "grid_confidence": 0
+        "grid_confidence": 1
       },
       "tests": [
         {
           "name": "game_loads",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "no console errors"
         },
         {
           "name": "game_starts",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "started via auto"
         },
         {
           "name": "auto_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
         },
         {
           "name": "move_left",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_right",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "move_down",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
         },
         {
           "name": "rotate",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "rotation observed, piece types seen: [unknown, J, Z]"
         },
         {
           "name": "hard_drop",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
         },
         {
           "name": "piece_locks",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "11 pieces placed during play session"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no score element found"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "played for 30s, placed 42 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 0,
-        "failed": 16,
-        "score": 0
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 0,
-        "lines_cleared": 0,
+        "pieces_placed": 42,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 0,
-        "events_count": 0,
-        "pieces_spawned": 0,
-        "pieces_locked": 0,
-        "lines_cleared": 0,
-        "piece_types_seen": [],
-        "grid_read_success_rate": 0
+        "frames": 289,
+        "events_count": 10,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "J",
+          "Z"
+        ],
+        "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": -1
+        "load_time_ms": 62
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.72,
+  "score": 0.72,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 12,
+    "cognitive_complexity": 102,
+    "lines_of_code": 588,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 72,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=off_web_search=on_run3/gameplay-bot-report.json
@@ -1,8 +1,13 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
@@ -10,120 +15,127 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
+    "start_mechanism": "auto",
     "score_element_found": false,
-    "grid_confidence": 0
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "rotation observed, piece types seen: [unknown, J, Z]"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:33953/\" is interrupted by another navigation to \"http://127.0.0.1:33953/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33953/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "played for 30s, placed 42 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 42,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 0,
-    "events_count": 0,
-    "pieces_spawned": 0,
-    "pieces_locked": 0,
-    "lines_cleared": 0,
-    "piece_types_seen": [],
-    "grid_read_success_rate": 0
+    "frames": 289,
+    "events_count": 10,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "J",
+      "Z"
+    ],
+    "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 62
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/eval_results.json
@@ -121,13 +121,166 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.13,
+    "total": 16,
+    "passed": 2,
+    "failed": 14,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 36,
+          "height": 72
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": false,
+          "detail": "1 console error(s): Cannot read properties of undefined (reading '0')"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "5 console error(s), 0 play errors"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 2,
+        "failed": 14,
+        "score": 0.13
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 348,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 61
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 7,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.325,
+  "score": 0.325,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 6,
+    "cognitive_complexity": 152,
+    "lines_of_code": 686,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 62,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.52
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run1/gameplay-bot-report.json
@@ -1,17 +1,23 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 36,
+      "height": 72
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -21,95 +27,104 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "5 console error(s), 0 play errors"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 2,
+    "failed": 14,
+    "score": 0.13
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 348,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 5864
+    "load_time_ms": 61
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/eval_results.json
@@ -121,144 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
+    "score": 0.31,
     "total": 16,
-    "passed": 0,
-    "failed": 16,
+    "passed": 5,
+    "failed": 11,
     "report": {
       "implementation": {
-        "renderer": "unknown",
-        "grid_detected": false,
-        "grid_bounds": null,
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 42,
+          "height": 84
+        },
         "controls": {
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "ArrowUp",
+          "rotate": "x",
           "drop": "Space"
         },
-        "start_mechanism": "unknown",
-        "score_element_found": false,
-        "grid_confidence": 0
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
       },
       "tests": [
         {
           "name": "game_loads",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "no console errors"
         },
         {
           "name": "game_starts",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "started via auto"
         },
         {
           "name": "auto_drop",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
         },
         {
           "name": "move_left",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_right",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "move_down",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no grid change detected after key press"
         },
         {
           "name": "rotate",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
         },
         {
           "name": "new_piece_spawns",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "could not detect new piece spawning at top via grid reader"
         },
         {
           "name": "multiple_pieces",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "only 10 piece(s) detected, need at least 3"
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "detail": "score stayed at 0"
         },
         {
           "name": "game_over",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "game stopped after stacking to top"
         },
         {
           "name": "playable_30s",
-          "pass": false,
-          "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 0,
-        "failed": 16,
-        "score": 0
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
       },
       "gameplay": {
-        "pieces_placed": 0,
-        "lines_cleared": 0,
+        "pieces_placed": 20,
+        "lines_cleared": 1,
         "max_score_observed": 0,
-        "play_duration_seconds": 0,
+        "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 0,
-        "events_count": 0,
+        "frames": 347,
+        "events_count": 2,
         "pieces_spawned": 0,
-        "pieces_locked": 0,
-        "lines_cleared": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
         "piece_types_seen": [],
-        "grid_read_success_rate": 0
+        "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": -1
+        "load_time_ms": 55
       },
       "accessibility": {
-        "issues": [],
-        "issue_count": 0,
-        "pass": true
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
       }
     }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.415,
+  "score": 0.415,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 6,
+    "cognitive_complexity": 152,
+    "lines_of_code": 686,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 62,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.52
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run2/gameplay-bot-report.json
@@ -1,129 +1,138 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 42,
+      "height": 84
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false,
-    "grid_confidence": 0
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "page load failed: page.goto: Navigation to \"http://127.0.0.1:41317/\" is interrupted by another navigation to \"http://127.0.0.1:41317/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:41317/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 0,
-    "events_count": 0,
+    "frames": 347,
+    "events_count": 2,
     "pieces_spawned": 0,
-    "pieces_locked": 0,
-    "lines_cleared": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
     "piece_types_seen": [],
-    "grid_read_success_rate": 0
+    "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 55
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/eval_results.json
@@ -121,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.25,
+    "total": 16,
+    "passed": 4,
+    "failed": 12,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 4,
+        "failed": 12,
+        "score": 0.25
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 22
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 4,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.375,
+  "score": 0.375,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 15,
+    "cognitive_complexity": 117,
+    "lines_of_code": 741,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 66,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=off_run3/gameplay-bot-report.json
@@ -1,119 +1,139 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 40,
+      "height": 80
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "enter",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:36761/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via enter"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 4,
+    "failed": 12,
+    "score": 0.25
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 345,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 4258
+    "load_time_ms": 22
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "no headings found",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 4,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -122,13 +122,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "6 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 226"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 37 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 37,
+        "lines_cleared": 1,
+        "max_score_observed": 226,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 299,
+        "events_count": 11,
+        "pieces_spawned": 6,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 34
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.595,
+  "score": 0.595,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 8,
+    "cognitive_complexity": 208,
+    "lines_of_code": 1260,
+    "duplication_pct": 21.7,
+    "tech_debt_minutes": 54,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,106 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotated: [other] failed: [] (tested 1 piece types in 60 attempts)"
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "6 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "exception: page.waitForTimeout: Test timeout of 180000ms exceeded."
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 226"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 37 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 11,
-    "failed": 5,
-    "score": 0.69
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 1,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 37,
+    "lines_cleared": 1,
+    "max_score_observed": 226,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 299,
+    "events_count": 11,
+    "pieces_spawned": 6,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 7547
+    "load_time_ms": 34
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -92,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 9
+      "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.85
+    "score": 0.5
   },
   "transcript_analysis": {
     "total_events": 45,
@@ -124,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.3,
+  "score": 0.3,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 93,
+    "lines_of_code": 638,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 33,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.6
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -92,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 3
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 74,
@@ -121,11 +121,152 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 64,
+          "height": 128
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 1"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 1,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 348,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 77
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 4,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.38,
-  "score": 0.38,
+  "outcome_score": 0.535,
+  "score": 0.535,
   "sonarqube": {
     "bugs": 0,
     "vulnerabilities": 0,
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -1,17 +1,23 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 64,
+      "height": 128
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -21,99 +27,113 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "exception: page.evaluate: Target page, context or browser has been closed"
+      "detail": "score stayed at 1"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 19,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 1,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 348,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 3882
+    "load_time_ms": 77
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "no headings found",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 4,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -120,13 +120,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 22
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.55,
+  "score": 0.55,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 3,
+    "lines_of_code": 700,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 15,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.91
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -10,8 +10,9 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -21,78 +22,78 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n\u001b[2m  - fonts loaded\u001b[22m\n"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded."
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "exception: page.evaluate: Target page, context or browser has been closed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
@@ -102,14 +103,23 @@
     "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 21,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 3622
+    "load_time_ms": 22
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 33
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.58,
+  "score": 0.58,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 0,
+    "lines_of_code": 625,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.97
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -10,106 +10,116 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "1 console error(s): Cannot read properties of undefined (reading '0')"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 1604
+    "load_time_ms": 33
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 37
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.535,
+  "score": 0.535,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 4,
+    "cognitive_complexity": 0,
+    "lines_of_code": 558,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 23,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.88
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -10,114 +10,120 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "1 console error(s): Cannot read properties of undefined (reading '0')"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 1604
+    "load_time_ms": 37
   },
   "accessibility": {
-    "issues": [
-      "canvas without aria-label or role",
-      "canvas without aria-label or role",
-      "canvas without aria-label or role"
-    ],
-    "issue_count": 3,
-    "pass": false
+    "issues": [],
+    "issue_count": 0,
+    "pass": true
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 557,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 40,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.47,
+  "score": 0.47,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 2,
+    "lines_of_code": 678,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 29,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -120,10 +120,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.455,
+  "score": 0.455,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 3,
+    "cognitive_complexity": 0,
+    "lines_of_code": 632,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 45,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.91
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 21
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.565,
+  "score": 0.565,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 0,
+    "lines_of_code": 678,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 76,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.94
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,22 +1,18 @@
 {
   "implementation": {
-    "renderer": "canvas",
-    "grid_detected": true,
-    "grid_bounds": {
-      "x": 0,
-      "y": 0,
-      "width": 32,
-      "height": 64
-    },
+    "renderer": "unknown",
+    "grid_detected": false,
+    "grid_bounds": null,
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "auto",
-    "score_element_found": true
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -27,94 +23,103 @@
     {
       "name": "game_starts",
       "pass": true,
-      "detail": "started via auto"
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: page.waitForTimeout: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 11,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 535
+    "load_time_ms": 21
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -117,13 +117,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 20
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.43,
+  "score": 0.43,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 6,
+    "cognitive_complexity": 0,
+    "lines_of_code": 961,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 208,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.67
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=en_language=unspecified_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -10,8 +10,9 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
@@ -21,68 +22,68 @@
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "could not start game with any mechanism"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "no change detected after rotate key"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "could not detect any piece rotations"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "no change detected after hard drop key"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "could not verify piece locking at bottom"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "could not detect new piece at top"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "could not trigger or detect a line clear"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "no score element found and no number changed"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
@@ -91,8 +92,8 @@
     },
     {
       "name": "playable_30s",
-      "pass": true,
-      "detail": "played for 30s, placed 11 pieces, no crashes"
+      "pass": false,
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
@@ -102,14 +103,23 @@
     "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 102,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 30,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 19
+    "load_time_ms": 20
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -96,10 +96,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 3
+      "errors": 0
     },
     "duplication_percentage": 0.0,
-    "score": 0.68
+    "score": 0.33
   },
   "transcript_analysis": {
     "total_events": 84,
@@ -128,10 +128,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.275,
+  "score": 0.275,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 18,
+    "cognitive_complexity": 185,
+    "lines_of_code": 1106,
+    "duplication_pct": 28.6,
+    "tech_debt_minutes": 59,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -124,13 +124,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 39
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.345,
+  "score": 0.345,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 7,
+    "cognitive_complexity": 99,
+    "lines_of_code": 841,
+    "duplication_pct": 21.4,
+    "tech_debt_minutes": 20,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -10,106 +10,116 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Navigation to \"http://127.0.0.1:44091/\" is interrupted by another navigation to \"http://127.0.0.1:44091/public/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:44091/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 39
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -126,13 +126,153 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "unknown",
+        "grid_detected": false,
+        "grid_bounds": null,
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": false,
+        "grid_confidence": 0
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify auto-drop"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify movement"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify rotation"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "grid reader unreliable, cannot verify hard drop"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "only played for 7s"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 26,
+        "lines_cleared": 0,
+        "max_score_observed": 0,
+        "play_duration_seconds": 7,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 33,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 0,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 0
+      },
+      "performance": {
+        "load_time_ms": 33
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.22,
+  "score": 0.22,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 14,
+    "cognitive_complexity": 174,
+    "lines_of_code": 1014,
+    "duplication_pct": 30.6,
+    "tech_debt_minutes": 28,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -10,106 +10,116 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "click_canvas",
+    "score_element_found": false,
+    "grid_confidence": 0
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "1 console error(s): Unexpected token '<'"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via click_canvas"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify auto-drop"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify movement"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify rotation"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "grid reader unreliable, cannot verify hard drop"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only played for 7s"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 3,
+    "failed": 13,
+    "score": 0.19
   },
   "gameplay": {
-    "pieces_placed": 0,
+    "pieces_placed": 26,
     "lines_cleared": 0,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 7,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 33,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 0,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 0
+  },
   "performance": {
-    "load_time_ms": 97
+    "load_time_ms": 33
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -121,13 +121,165 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.75,
+    "total": 16,
+    "passed": 12,
+    "failed": 4,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 43 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 12,
+        "failed": 4,
+        "score": 0.75
+      },
+      "gameplay": {
+        "pieces_placed": 43,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 290,
+        "events_count": 9,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown",
+          "J",
+          "Z"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 21
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.675,
+  "score": 0.675,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 12,
+    "cognitive_complexity": 82,
+    "lines_of_code": 612,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 42,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.6
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,109 @@
     {
       "name": "auto_drop",
       "pass": true,
-      "detail": "grid state changed after 5s with no input"
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
       "pass": true,
-      "detail": "grid state changed after key press"
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotated: [unknown] failed: [] (tested 1 piece types in 60 attempts)"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": true,
-      "detail": "piece immediately dropped and new piece appeared"
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom"
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "new piece detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "game still responding after 10 piece drops"
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "line cleared via strategic placement"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score did not increase: [0] -> no change after polling"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded."
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 43 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 12,
+    "failed": 4,
+    "score": 0.75
   },
   "gameplay": {
-    "pieces_placed": 32,
+    "pieces_placed": 43,
     "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 290,
+    "events_count": 9,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown",
+      "J",
+      "Z"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 256
+    "load_time_ms": 21
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -124,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.41,
+  "score": 0.41,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 1,
+    "cognitive_complexity": 106,
+    "lines_of_code": 715,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 5,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.82
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -124,10 +124,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.395,
+  "score": 0.395,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 2,
+    "cognitive_complexity": 143,
+    "lines_of_code": 929,
+    "duplication_pct": 3.1,
+    "tech_debt_minutes": 12,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.79
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -121,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.38,
+    "total": 16,
+    "passed": 6,
+    "failed": 10,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 48,
+          "height": 96
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 160 to 162"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 6,
+        "failed": 10,
+        "score": 0.38
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 162,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 348,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 25
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 4,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.54,
+  "score": 0.54,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 5,
+    "cognitive_complexity": 117,
+    "lines_of_code": 867,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 13,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.7
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,94 +32,108 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: page.reload: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - waiting for navigation until \"load\"\u001b[22m\n\u001b[2m    - navigated to \"http://127.0.0.1:42027/index.html\"\u001b[22m\n"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "visual change detected after hard drop"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m  - taking page screenshot\u001b[22m\n\u001b[2m  - waiting for fonts to load...\u001b[22m\n"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
-      "pass": true,
-      "detail": "visual change suggests new piece spawned"
+      "pass": false,
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "grid did not accumulate filled cells"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "could not read score element"
+      "pass": true,
+      "detail": "score changed from 160 to 162"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 9,
-    "failed": 7,
-    "score": 0.56
+    "passed": 6,
+    "failed": 10,
+    "score": 0.38
   },
   "gameplay": {
-    "pieces_placed": 10,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 162,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 348,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 5657
+    "load_time_ms": 25
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "no headings found",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 4,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -121,11 +121,151 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 343,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 60
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.26,
-  "score": 0.26,
+  "outcome_score": 0.415,
+  "score": 0.415,
   "sonarqube": {
     "bugs": 1,
     "vulnerabilities": 0,
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,119 +1,138 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:38503/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 343,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 60
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -121,13 +121,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 50,
+          "height": 100
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 222 to 246"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 246,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 338,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 31
+      },
+      "accessibility": {
+        "issues": [
+          "no headings found",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 4,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.405,
+  "score": 0.405,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 1,
+    "vulnerabilities": 0,
+    "code_smells": 11,
+    "cognitive_complexity": 119,
+    "lines_of_code": 726,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 41,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.5
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=high_human_language=es_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -1,119 +1,139 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 50,
+      "height": 100
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "auto",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:33367/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "score changed from 222 to 246"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 246,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 338,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 7033
+    "load_time_ms": 31
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "no headings found",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 4,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -124,13 +124,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.75,
+    "total": 16,
+    "passed": 12,
+    "failed": 4,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 300,
+          "height": 600
+        },
+        "controls": {
+          "left": "a",
+          "right": "d",
+          "down": "s",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": false,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "2 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "no score element found"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 36 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 12,
+        "failed": 4,
+        "score": 0.75
+      },
+      "gameplay": {
+        "pieces_placed": 36,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 308,
+        "events_count": 6,
+        "pieces_spawned": 2,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 32
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 1,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.775,
+  "score": 0.775,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 5,
+    "cognitive_complexity": 88,
+    "lines_of_code": 528,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 17,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.8
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -1,119 +1,138 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
-      "left": "ArrowLeft",
-      "right": "ArrowRight",
-      "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "left": "a",
+      "right": "d",
+      "down": "s",
+      "rotate": "z",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "auto",
+    "score_element_found": false,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:46525/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via auto"
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "2 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no score element found"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 36 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 12,
+    "failed": 4,
+    "score": 0.75
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 36,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 308,
+    "events_count": 6,
+    "pieces_spawned": 2,
+    "pieces_locked": 11,
+    "lines_cleared": 1,
+    "piece_types_seen": [
+      "unknown"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 7299
+    "load_time_ms": 32
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 1,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -127,10 +127,19 @@
     "score": 0,
     "error": "Gameplay bot timed out after 180 seconds"
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.275,
+  "score": 0.275,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 17,
+    "cognitive_complexity": 198,
+    "lines_of_code": 1055,
+    "duplication_pct": 34.3,
+    "tech_debt_minutes": 58,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,8 +1,13 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 300,
+      "height": 600
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
@@ -10,110 +15,123 @@
       "rotate": "ArrowUp",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "space",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:37507/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via space"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 344,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 51
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -126,13 +126,161 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 50,
+          "height": 100
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 339,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 73
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.28,
+  "score": 0.28,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 2,
+    "vulnerabilities": 0,
+    "code_smells": 19,
+    "cognitive_complexity": 198,
+    "lines_of_code": 1205,
+    "duplication_pct": 26.5,
+    "tech_debt_minutes": 55,
+    "maintainability": "A",
+    "reliability": "C",
+    "security": "A",
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "click_canvas",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -32,93 +33,105 @@
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "piece did not move in 5 seconds"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: page.waitForTimeout: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 0"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 4,
-    "failed": 12,
-    "score": 0.25
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 11,
-    "lines_cleared": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
     "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 339,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 123
+    "load_time_ms": 73
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 2,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -121,13 +121,162 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 40,
+          "height": 80
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 138"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 138,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 343,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 57
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.0,
-  "score": 0.0,
+  "outcome_score": 0.48,
+  "score": 0.48,
   "sonarqube": {
-    "pass": false,
-    "error": "no output"
+    "bugs": 0,
+    "vulnerabilities": 0,
+    "code_smells": 44,
+    "cognitive_complexity": 124,
+    "lines_of_code": 809,
+    "duplication_pct": 2.8,
+    "tech_debt_minutes": 86,
+    "maintainability": "A",
+    "reliability": "A",
+    "security": "A",
+    "score": 0.65
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -16,7 +16,8 @@
       "drop": "Space"
     },
     "start_mechanism": "auto",
-    "score_element_found": true
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
@@ -31,94 +32,107 @@
     },
     {
       "name": "auto_drop",
-      "pass": true,
-      "detail": "pixels changed after 5s with no input"
+      "pass": false,
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
-      "pass": true,
-      "detail": "grid state changed after key press"
+      "pass": false,
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "no change detected after key press"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "exception: page.waitForTimeout: Target page, context or browser has been closed"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "exception: page.screenshot: Target page, context or browser has been closed"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "could not read score element"
+      "detail": "score stayed at 138"
     },
     {
       "name": "game_over",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "game stopped after stacking to top"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "exception: keyboard.press: Target page, context or browser has been closed"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 6,
-    "failed": 10,
-    "score": 0.38
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 8,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 138,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 343,
+    "events_count": 2,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 3482
+    "load_time_ms": 57
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -92,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 8
     },
     "duplication_percentage": 0.0,
-    "score": 0.4
+    "score": 0.75
   },
   "transcript_analysis": {
     "total_events": 112,
@@ -121,11 +121,151 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.31,
+    "total": 16,
+    "passed": 5,
+    "failed": 11,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 54,
+          "height": 108
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "enter",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via enter"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 38 to 194"
+        },
+        {
+          "name": "game_over",
+          "pass": false,
+          "detail": "could not trigger or detect game over"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 20 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 5,
+        "failed": 11,
+        "score": 0.31
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 194,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 338,
+        "events_count": 1,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 63
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 3,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.325,
-  "score": 0.325,
+  "outcome_score": 0.48,
+  "score": 0.48,
   "sonarqube": {
     "bugs": 0,
     "vulnerabilities": 0,
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,119 +1,138 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 54,
+      "height": 108
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "z",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "enter",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Timeout 5000ms exceeded.\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:35703/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via enter"
     },
     {
       "name": "auto_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "piece did not move down in 5 seconds (grid-verified)"
     },
     {
       "name": "move_left",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_right",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "move_down",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change detected after key press"
     },
     {
       "name": "rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
     },
     {
       "name": "new_piece_spawns",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not detect new piece spawning at top via grid reader"
     },
     {
       "name": "multiple_pieces",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "only 10 piece(s) detected, need at least 3"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "score changed from 38 to 194"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 20 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 5,
+    "failed": 11,
+    "score": 0.31
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 20,
+    "lines_cleared": 1,
+    "max_score_observed": 194,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 338,
+    "events_count": 1,
+    "pieces_spawned": 0,
+    "pieces_locked": 10,
+    "lines_cleared": 1,
+    "piece_types_seen": [],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": 5999
+    "load_time_ms": 63
   },
   "accessibility": {
-    "issues": [],
-    "issue_count": 0,
-    "pass": true
+    "issues": [
+      "canvas without aria-label or role",
+      "canvas without aria-label or role",
+      "canvas without aria-label or role"
+    ],
+    "issue_count": 3,
+    "pass": false
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -92,10 +92,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 8
     },
     "duplication_percentage": 0.0,
-    "score": 0.5
+    "score": 0.85
   },
   "transcript_analysis": {
     "total_events": 71,
@@ -121,11 +121,152 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 320,
+          "height": 640
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "z",
+          "drop": "Space"
+        },
+        "start_mechanism": "auto",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via auto"
+        },
+        {
+          "name": "auto_drop",
+          "pass": true,
+          "detail": "grid state changed after 5s with no input (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "4 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 354"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 44 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 44,
+        "lines_cleared": 1,
+        "max_score_observed": 354,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 289,
+        "events_count": 11,
+        "pieces_spawned": 4,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 106
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.25,
-  "score": 0.25,
+  "outcome_score": 0.72,
+  "score": 0.72,
   "sonarqube": {
     "bugs": 1,
     "vulnerabilities": 0,
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -52,13 +52,13 @@
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "no shape change detected after rotate key"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "could not detect any piece rotations via grid reader"
+      "pass": true,
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "6 new piece(s) detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -88,7 +88,7 @@
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score stayed at 212"
+      "detail": "score stayed at 354"
     },
     {
       "name": "game_over",
@@ -98,26 +98,26 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 41 pieces, no crashes"
+      "detail": "played for 30s, placed 44 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 41,
+    "pieces_placed": 44,
     "lines_cleared": 1,
-    "max_score_observed": 212,
+    "max_score_observed": 354,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 204,
-    "events_count": 10,
-    "pieces_spawned": 6,
+    "frames": 289,
+    "events_count": 11,
+    "pieces_spawned": 4,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
@@ -126,7 +126,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 280
+    "load_time_ms": 106
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -121,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.94,
+    "score": 0.81,
     "total": 16,
-    "passed": 15,
-    "failed": 1,
+    "passed": 13,
+    "failed": 3,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -179,13 +179,13 @@
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": true,
-          "detail": "rotation confirmed but could not identify individual piece types"
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
@@ -200,7 +200,7 @@
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "2 new piece(s) detected at top of grid"
+          "detail": "1 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
@@ -209,13 +209,13 @@
         },
         {
           "name": "line_clear",
-          "pass": false,
-          "detail": "could not trigger or detect a line clear via grid reader"
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
-          "pass": true,
-          "detail": "score changed from 362 to 372"
+          "pass": false,
+          "detail": "score stayed at 276"
         },
         {
           "name": "game_over",
@@ -225,35 +225,33 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 39 pieces, no crashes"
+          "detail": "played for 30s, placed 38 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 15,
-        "failed": 1,
-        "score": 0.94
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
       },
       "gameplay": {
-        "pieces_placed": 39,
-        "lines_cleared": 0,
-        "max_score_observed": 372,
+        "pieces_placed": 38,
+        "lines_cleared": 1,
+        "max_score_observed": 276,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 298,
+        "frames": 303,
         "events_count": 9,
-        "pieces_spawned": 2,
+        "pieces_spawned": 1,
         "pieces_locked": 11,
-        "lines_cleared": 0,
-        "piece_types_seen": [
-          "unknown"
-        ],
+        "lines_cleared": 1,
+        "piece_types_seen": [],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 181
+        "load_time_ms": 92
       },
       "accessibility": {
         "issues": [
@@ -265,8 +263,8 @@
       }
     }
   },
-  "outcome_score": 0.72,
-  "score": 0.72,
+  "outcome_score": 0.655,
+  "score": 0.655,
   "sonarqube": {
     "bugs": 2,
     "vulnerabilities": 0,
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -52,13 +52,13 @@
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotation confirmed but could not identify individual piece types"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "2 new piece(s) detected at top of grid"
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -82,13 +82,13 @@
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "could not trigger or detect a line clear via grid reader"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
-      "pass": true,
-      "detail": "score changed from 362 to 372"
+      "pass": false,
+      "detail": "score stayed at 276"
     },
     {
       "name": "game_over",
@@ -98,35 +98,33 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 39 pieces, no crashes"
+      "detail": "played for 30s, placed 38 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 39,
-    "lines_cleared": 0,
-    "max_score_observed": 372,
+    "pieces_placed": 38,
+    "lines_cleared": 1,
+    "max_score_observed": 276,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 298,
+    "frames": 303,
     "events_count": 9,
-    "pieces_spawned": 2,
+    "pieces_spawned": 1,
     "pieces_locked": 11,
-    "lines_cleared": 0,
-    "piece_types_seen": [
-      "unknown"
-    ],
+    "lines_cleared": 1,
+    "piece_types_seen": [],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 181
+    "load_time_ms": 92
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -1,115 +1,133 @@
 {
   "implementation": {
-    "renderer": "unknown",
-    "grid_detected": false,
-    "grid_bounds": null,
+    "renderer": "canvas",
+    "grid_detected": true,
+    "grid_bounds": {
+      "x": 0,
+      "y": 0,
+      "width": 320,
+      "height": 640
+    },
     "controls": {
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "x",
       "drop": "Space"
     },
-    "start_mechanism": "unknown",
-    "score_element_found": false
+    "start_mechanism": "enter",
+    "score_element_found": true,
+    "grid_confidence": 1
   },
   "tests": [
     {
       "name": "game_loads",
-      "pass": false,
-      "detail": "exception: page.goto: Navigation to \"http://127.0.0.1:40031/\" is interrupted by another navigation to \"http://127.0.0.1:40031/public/index.html\"\nCall log:\n\u001b[2m  - navigating to \"http://127.0.0.1:40031/\", waiting until \"domcontentloaded\"\u001b[22m\n"
+      "pass": true,
+      "detail": "no console errors"
     },
     {
       "name": "game_starts",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "started via enter"
     },
     {
       "name": "auto_drop",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after 5s with no input (grid-verified)"
     },
     {
       "name": "move_left",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_right",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "move_down",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "grid state changed after key press (grid-verified)"
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "rotation observed, piece types seen: [unknown, I]"
     },
     {
       "name": "hard_drop",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "piece immediately dropped to bottom (grid-verified)"
     },
     {
       "name": "piece_locks",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "11 pieces placed during play session"
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "3 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "score stayed at 414"
     },
     {
       "name": "game_over",
       "pass": false,
-      "detail": "skipped: page did not load"
+      "detail": "could not trigger or detect game over"
     },
     {
       "name": "playable_30s",
-      "pass": false,
-      "detail": "skipped: page did not load"
+      "pass": true,
+      "detail": "played for 30s, placed 31 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 0,
-    "failed": 16,
-    "score": 0
+    "passed": 14,
+    "failed": 2,
+    "score": 0.88
   },
   "gameplay": {
-    "pieces_placed": 0,
-    "lines_cleared": 0,
-    "max_score_observed": 0,
-    "play_duration_seconds": 0,
+    "pieces_placed": 31,
+    "lines_cleared": 3,
+    "max_score_observed": 414,
+    "play_duration_seconds": 30,
     "errors_during_play": 0
   },
+  "session": {
+    "frames": 288,
+    "events_count": 12,
+    "pieces_spawned": 4,
+    "pieces_locked": 11,
+    "lines_cleared": 3,
+    "piece_types_seen": [
+      "unknown",
+      "I"
+    ],
+    "grid_read_success_rate": 1
+  },
   "performance": {
-    "load_time_ms": -1
+    "load_time_ms": 101
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -139,7 +139,7 @@
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "x",
+          "rotate": "z",
           "drop": "Space"
         },
         "start_mechanism": "auto",
@@ -185,7 +185,7 @@
         {
           "name": "all_pieces_rotate",
           "pass": true,
-          "detail": "rotation confirmed but could not identify individual piece types"
+          "detail": "rotation observed, piece types seen: [I, unknown]"
         },
         {
           "name": "hard_drop",
@@ -200,7 +200,7 @@
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "5 new piece(s) detected at top of grid"
+          "detail": "7 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
@@ -215,7 +215,7 @@
         {
           "name": "score_changes",
           "pass": true,
-          "detail": "score changed from 0 to 144"
+          "detail": "score changed from 98 to 364"
         },
         {
           "name": "game_over",
@@ -225,7 +225,7 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 43 pieces, no crashes"
+          "detail": "played for 30s, placed 42 pieces, no crashes"
         }
       ],
       "summary": {
@@ -235,25 +235,26 @@
         "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 43,
+        "pieces_placed": 42,
         "lines_cleared": 1,
-        "max_score_observed": 144,
+        "max_score_observed": 98,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 288,
+        "frames": 286,
         "events_count": 10,
-        "pieces_spawned": 5,
+        "pieces_spawned": 7,
         "pieces_locked": 11,
         "lines_cleared": 1,
         "piece_types_seen": [
+          "I",
           "unknown"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 231
+        "load_time_ms": 27
       },
       "accessibility": {
         "issues": [
diff --git a/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=none_effort=max_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -12,7 +12,7 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "z",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -58,7 +58,7 @@
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotation confirmed but could not identify individual piece types"
+      "detail": "rotation observed, piece types seen: [I, unknown]"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "5 new piece(s) detected at top of grid"
+      "detail": "7 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -88,7 +88,7 @@
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 0 to 144"
+      "detail": "score changed from 98 to 364"
     },
     {
       "name": "game_over",
@@ -98,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 43 pieces, no crashes"
+      "detail": "played for 30s, placed 42 pieces, no crashes"
     }
   ],
   "summary": {
@@ -108,25 +108,26 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 43,
+    "pieces_placed": 42,
     "lines_cleared": 1,
-    "max_score_observed": 144,
+    "max_score_observed": 98,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 288,
+    "frames": 286,
     "events_count": 10,
-    "pieces_spawned": 5,
+    "pieces_spawned": 7,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
+      "I",
       "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 231
+    "load_time_ms": 27
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -123,10 +123,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.81,
+    "score": 0.63,
     "total": 16,
-    "passed": 13,
-    "failed": 3,
+    "passed": 10,
+    "failed": 6,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -138,10 +138,10 @@
           "height": 400
         },
         "controls": {
-          "left": "a",
-          "right": "d",
-          "down": "s",
-          "rotate": "z",
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
           "drop": "Space"
         },
         "start_mechanism": "auto",
@@ -181,33 +181,33 @@
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": true,
-          "detail": "rotation observed, piece types seen: [O, L, unknown]"
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
-          "pass": true,
-          "detail": "piece immediately dropped to bottom (grid-verified)"
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
         },
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "4 new piece(s) detected at top of grid"
+          "detail": "3 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
           "pass": true,
-          "detail": "11 pieces placed during play session"
+          "detail": "10 pieces placed during play session"
         },
         {
           "name": "line_clear",
@@ -227,37 +227,36 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 35 pieces, no crashes"
+          "detail": "played for 30s, placed 34 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 13,
-        "failed": 3,
-        "score": 0.81
+        "passed": 10,
+        "failed": 6,
+        "score": 0.63
       },
       "gameplay": {
-        "pieces_placed": 35,
+        "pieces_placed": 34,
         "lines_cleared": 1,
         "max_score_observed": 0,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 304,
-        "events_count": 9,
-        "pieces_spawned": 4,
-        "pieces_locked": 11,
+        "frames": 309,
+        "events_count": 4,
+        "pieces_spawned": 3,
+        "pieces_locked": 10,
         "lines_cleared": 1,
         "piece_types_seen": [
-          "O",
-          "L",
+          "S",
           "unknown"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 216
+        "load_time_ms": 35
       },
       "accessibility": {
         "issues": [
@@ -270,19 +269,19 @@
       }
     }
   },
-  "outcome_score": 0.63,
-  "score": 0.63,
+  "outcome_score": 0.69,
+  "score": 0.69,
   "sonarqube": {
-    "bugs": 2,
+    "bugs": 0,
     "vulnerabilities": 0,
     "code_smells": 9,
-    "cognitive_complexity": 85,
-    "lines_of_code": 653,
-    "duplication_pct": 0.0,
-    "tech_debt_minutes": 18,
+    "cognitive_complexity": 96,
+    "lines_of_code": 618,
+    "duplication_pct": 4.1,
+    "tech_debt_minutes": 39,
     "maintainability": "A",
-    "reliability": "C",
+    "reliability": "A",
     "security": "A",
-    "score": 0.45
+    "score": 0.75
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -9,10 +9,10 @@
       "height": 400
     },
     "controls": {
-      "left": "a",
-      "right": "d",
-      "down": "s",
-      "rotate": "z",
+      "left": "ArrowLeft",
+      "right": "ArrowRight",
+      "down": "ArrowDown",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -52,33 +52,33 @@
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotation observed, piece types seen: [O, L, unknown]"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
-      "pass": true,
-      "detail": "piece immediately dropped to bottom (grid-verified)"
+      "pass": false,
+      "detail": "no grid change with bottom cells detected after hard drop key"
     },
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "4 new piece(s) detected at top of grid"
+      "detail": "3 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
       "pass": true,
-      "detail": "11 pieces placed during play session"
+      "detail": "10 pieces placed during play session"
     },
     {
       "name": "line_clear",
@@ -98,37 +98,36 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 35 pieces, no crashes"
+      "detail": "played for 30s, placed 34 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 10,
+    "failed": 6,
+    "score": 0.63
   },
   "gameplay": {
-    "pieces_placed": 35,
+    "pieces_placed": 34,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 304,
-    "events_count": 9,
-    "pieces_spawned": 4,
-    "pieces_locked": 11,
+    "frames": 309,
+    "events_count": 4,
+    "pieces_spawned": 3,
+    "pieces_locked": 10,
     "lines_cleared": 1,
     "piece_types_seen": [
-      "O",
-      "L",
+      "S",
       "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 216
+    "load_time_ms": 35
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -197,12 +197,12 @@
         {
           "name": "piece_locks",
           "pass": true,
-          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+          "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
         },
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "4 new piece(s) detected at top of grid"
+          "detail": "1 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
@@ -227,7 +227,7 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 39 pieces, no crashes"
+          "detail": "played for 30s, placed 38 pieces, no crashes"
         }
       ],
       "summary": {
@@ -237,16 +237,16 @@
         "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 39,
+        "pieces_placed": 38,
         "lines_cleared": 1,
         "max_score_observed": 0,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 298,
-        "events_count": 11,
-        "pieces_spawned": 4,
+        "frames": 295,
+        "events_count": 10,
+        "pieces_spawned": 1,
         "pieces_locked": 11,
         "lines_cleared": 1,
         "piece_types_seen": [
@@ -255,7 +255,7 @@
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 303
+        "load_time_ms": 31
       },
       "accessibility": {
         "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -68,12 +68,12 @@
     {
       "name": "piece_locks",
       "pass": true,
-      "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+      "detail": "filled cells persist at bottom (grid-verified, 1 lock event(s))"
     },
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "4 new piece(s) detected at top of grid"
+      "detail": "1 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -98,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 39 pieces, no crashes"
+      "detail": "played for 30s, placed 38 pieces, no crashes"
     }
   ],
   "summary": {
@@ -108,16 +108,16 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 39,
+    "pieces_placed": 38,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 298,
-    "events_count": 11,
-    "pieces_spawned": 4,
+    "frames": 295,
+    "events_count": 10,
+    "pieces_spawned": 1,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
@@ -126,7 +126,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 303
+    "load_time_ms": 31
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -95,10 +95,10 @@
     },
     "html_validation": {
       "valid": false,
-      "errors": 0
+      "errors": 14
     },
     "duplication_percentage": 0.0,
-    "score": 0.4
+    "score": 0.75
   },
   "transcript_analysis": {
     "total_events": 124,
@@ -124,22 +124,163 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.94,
+    "total": 16,
+    "passed": 15,
+    "failed": 1,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 240,
+          "height": 480
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "x",
+          "drop": "Space"
+        },
+        "start_mechanism": "click_canvas",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": true,
+          "detail": "no console errors"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via click_canvas"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_right",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "move_down",
+          "pass": true,
+          "detail": "grid state changed after key press (grid-verified)"
+        },
+        {
+          "name": "rotate",
+          "pass": true,
+          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": true,
+          "detail": "rotation confirmed but could not identify individual piece types"
+        },
+        {
+          "name": "hard_drop",
+          "pass": true,
+          "detail": "piece immediately dropped to bottom (grid-verified)"
+        },
+        {
+          "name": "piece_locks",
+          "pass": true,
+          "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": true,
+          "detail": "8 new piece(s) detected at top of grid"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": true,
+          "detail": "11 pieces placed during play session"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": true,
+          "detail": "score changed from 322 to 332"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": true,
+          "detail": "played for 30s, placed 23 pieces, no crashes"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 15,
+        "failed": 1,
+        "score": 0.94
+      },
+      "gameplay": {
+        "pieces_placed": 23,
+        "lines_cleared": 1,
+        "max_score_observed": 332,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 340,
+        "events_count": 9,
+        "pieces_spawned": 8,
+        "pieces_locked": 11,
+        "lines_cleared": 1,
+        "piece_types_seen": [
+          "unknown"
+        ],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 77
+      },
+      "accessibility": {
+        "issues": [
+          "canvas without aria-label or role",
+          "canvas without aria-label or role"
+        ],
+        "issue_count": 2,
+        "pass": false
+      }
+    }
   },
-  "outcome_score": 0.375,
-  "score": 0.375,
+  "outcome_score": 0.595,
+  "score": 0.595,
   "sonarqube": {
-    "bugs": 0,
+    "bugs": 2,
     "vulnerabilities": 0,
-    "code_smells": 9,
-    "cognitive_complexity": 96,
-    "lines_of_code": 618,
-    "duplication_pct": 4.1,
-    "tech_debt_minutes": 39,
+    "code_smells": 18,
+    "cognitive_complexity": 202,
+    "lines_of_code": 1146,
+    "duplication_pct": 28.7,
+    "tech_debt_minutes": 64,
     "maintainability": "A",
-    "reliability": "A",
+    "reliability": "C",
     "security": "A",
-    "score": 0.75
+    "score": 0.25
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=high_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -52,13 +52,13 @@
     },
     {
       "name": "rotate",
-      "pass": false,
-      "detail": "no shape change detected after rotate key"
+      "pass": true,
+      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": false,
-      "detail": "could not detect any piece rotations via grid reader"
+      "pass": true,
+      "detail": "rotation confirmed but could not identify individual piece types"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "4 new piece(s) detected at top of grid"
+      "detail": "8 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -82,13 +82,13 @@
     },
     {
       "name": "line_clear",
-      "pass": false,
-      "detail": "could not trigger or detect a line clear via grid reader"
+      "pass": true,
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 304 to 318"
+      "detail": "score changed from 322 to 332"
     },
     {
       "name": "game_over",
@@ -98,35 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 22 pieces, no crashes"
+      "detail": "played for 30s, placed 23 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 12,
-    "failed": 4,
-    "score": 0.75
+    "passed": 15,
+    "failed": 1,
+    "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 22,
-    "lines_cleared": 0,
-    "max_score_observed": 318,
+    "pieces_placed": 23,
+    "lines_cleared": 1,
+    "max_score_observed": 332,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 341,
-    "events_count": 7,
-    "pieces_spawned": 4,
+    "frames": 340,
+    "events_count": 9,
+    "pieces_spawned": 8,
     "pieces_locked": 11,
-    "lines_cleared": 0,
+    "lines_cleared": 1,
     "piece_types_seen": [
       "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 214
+    "load_time_ms": 77
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -125,10 +125,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.81,
+    "score": 0.75,
     "total": 16,
-    "passed": 13,
-    "failed": 3,
+    "passed": 12,
+    "failed": 4,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -204,7 +204,7 @@
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "2 new piece(s) detected at top of grid"
+          "detail": "4 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
@@ -213,8 +213,8 @@
         },
         {
           "name": "line_clear",
-          "pass": true,
-          "detail": "1 line(s) cleared (grid-verified)"
+          "pass": false,
+          "detail": "could not trigger or detect a line clear via grid reader"
         },
         {
           "name": "score_changes",
@@ -229,35 +229,35 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 22 pieces, no crashes"
+          "detail": "played for 30s, placed 28 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 13,
-        "failed": 3,
-        "score": 0.81
+        "passed": 12,
+        "failed": 4,
+        "score": 0.75
       },
       "gameplay": {
-        "pieces_placed": 22,
-        "lines_cleared": 1,
+        "pieces_placed": 28,
+        "lines_cleared": 0,
         "max_score_observed": 0,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 331,
-        "events_count": 9,
-        "pieces_spawned": 2,
+        "frames": 328,
+        "events_count": 8,
+        "pieces_spawned": 4,
         "pieces_locked": 11,
-        "lines_cleared": 1,
+        "lines_cleared": 0,
         "piece_types_seen": [
-          "I"
+          "unknown"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 222
+        "load_time_ms": 66
       },
       "accessibility": {
         "issues": [
@@ -270,19 +270,19 @@
       }
     }
   },
-  "outcome_score": 0.63,
-  "score": 0.63,
+  "outcome_score": 0.65,
+  "score": 0.65,
   "sonarqube": {
-    "bugs": 2,
+    "bugs": 0,
     "vulnerabilities": 0,
-    "code_smells": 7,
-    "cognitive_complexity": 97,
-    "lines_of_code": 654,
-    "duplication_pct": 0.0,
-    "tech_debt_minutes": 39,
+    "code_smells": 31,
+    "cognitive_complexity": 236,
+    "lines_of_code": 1088,
+    "duplication_pct": 28.1,
+    "tech_debt_minutes": 141,
     "maintainability": "A",
-    "reliability": "C",
+    "reliability": "A",
     "security": "A",
-    "score": 0.45
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "2 new piece(s) detected at top of grid"
+      "detail": "4 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -82,8 +82,8 @@
     },
     {
       "name": "line_clear",
-      "pass": true,
-      "detail": "1 line(s) cleared (grid-verified)"
+      "pass": false,
+      "detail": "could not trigger or detect a line clear via grid reader"
     },
     {
       "name": "score_changes",
@@ -98,35 +98,35 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 22 pieces, no crashes"
+      "detail": "played for 30s, placed 28 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 13,
-    "failed": 3,
-    "score": 0.81
+    "passed": 12,
+    "failed": 4,
+    "score": 0.75
   },
   "gameplay": {
-    "pieces_placed": 22,
-    "lines_cleared": 1,
+    "pieces_placed": 28,
+    "lines_cleared": 0,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 331,
-    "events_count": 9,
-    "pieces_spawned": 2,
+    "frames": 328,
+    "events_count": 8,
+    "pieces_spawned": 4,
     "pieces_locked": 11,
-    "lines_cleared": 1,
+    "lines_cleared": 0,
     "piece_types_seen": [
-      "I"
+      "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 222
+    "load_time_ms": 66
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -125,11 +125,147 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0,
-    "error": "Gameplay bot timed out after 180 seconds"
+    "score": 0.19,
+    "total": 16,
+    "passed": 3,
+    "failed": 13,
+    "report": {
+      "implementation": {
+        "renderer": "canvas",
+        "grid_detected": true,
+        "grid_bounds": {
+          "x": 0,
+          "y": 0,
+          "width": 75,
+          "height": 150
+        },
+        "controls": {
+          "left": "ArrowLeft",
+          "right": "ArrowRight",
+          "down": "ArrowDown",
+          "rotate": "ArrowUp",
+          "drop": "Space"
+        },
+        "start_mechanism": "space",
+        "score_element_found": true,
+        "grid_confidence": 1
+      },
+      "tests": [
+        {
+          "name": "game_loads",
+          "pass": false,
+          "detail": "1 console error(s): Unexpected token 'export'"
+        },
+        {
+          "name": "game_starts",
+          "pass": true,
+          "detail": "started via space"
+        },
+        {
+          "name": "auto_drop",
+          "pass": false,
+          "detail": "piece did not move down in 5 seconds (grid-verified)"
+        },
+        {
+          "name": "move_left",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_right",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "move_down",
+          "pass": false,
+          "detail": "no grid change detected after key press"
+        },
+        {
+          "name": "rotate",
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
+        },
+        {
+          "name": "all_pieces_rotate",
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
+        },
+        {
+          "name": "hard_drop",
+          "pass": false,
+          "detail": "no grid change with bottom cells detected after hard drop key"
+        },
+        {
+          "name": "piece_locks",
+          "pass": false,
+          "detail": "10 lock event(s) but 0 spawns detected - likely false positive from UI misread"
+        },
+        {
+          "name": "new_piece_spawns",
+          "pass": false,
+          "detail": "could not detect new piece spawning at top via grid reader"
+        },
+        {
+          "name": "multiple_pieces",
+          "pass": false,
+          "detail": "only 10 piece(s) detected, need at least 3"
+        },
+        {
+          "name": "line_clear",
+          "pass": true,
+          "detail": "1 line(s) cleared (grid-verified)"
+        },
+        {
+          "name": "score_changes",
+          "pass": false,
+          "detail": "score stayed at 0"
+        },
+        {
+          "name": "game_over",
+          "pass": true,
+          "detail": "game stopped after stacking to top"
+        },
+        {
+          "name": "playable_30s",
+          "pass": false,
+          "detail": "5 console error(s), 0 play errors"
+        }
+      ],
+      "summary": {
+        "total": 16,
+        "passed": 3,
+        "failed": 13,
+        "score": 0.19
+      },
+      "gameplay": {
+        "pieces_placed": 20,
+        "lines_cleared": 1,
+        "max_score_observed": 0,
+        "play_duration_seconds": 30,
+        "errors_during_play": 0
+      },
+      "session": {
+        "frames": 345,
+        "events_count": 2,
+        "pieces_spawned": 0,
+        "pieces_locked": 10,
+        "lines_cleared": 1,
+        "piece_types_seen": [],
+        "grid_read_success_rate": 1
+      },
+      "performance": {
+        "load_time_ms": 20
+      },
+      "accessibility": {
+        "issues": [],
+        "issue_count": 0,
+        "pass": true
+      }
+    }
   },
-  "outcome_score": 0.225,
-  "score": 0.225,
+  "outcome_score": 0.32,
+  "score": 0.32,
   "sonarqube": {
     "bugs": 2,
     "vulnerabilities": 0,
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -115,7 +115,7 @@
     "errors_during_play": 0
   },
   "session": {
-    "frames": 323,
+    "frames": 345,
     "events_count": 2,
     "pieces_spawned": 0,
     "pieces_locked": 10,
@@ -124,7 +124,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 290
+    "load_time_ms": 20
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -141,7 +141,7 @@
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "z",
+          "rotate": "x",
           "drop": "Space"
         },
         "start_mechanism": "auto",
@@ -227,7 +227,7 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 36 pieces, no crashes"
+          "detail": "played for 30s, placed 33 pieces, no crashes"
         }
       ],
       "summary": {
@@ -237,26 +237,26 @@
         "score": 0.81
       },
       "gameplay": {
-        "pieces_placed": 36,
+        "pieces_placed": 33,
         "lines_cleared": 1,
         "max_score_observed": 0,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 306,
+        "frames": 309,
         "events_count": 8,
         "pieces_spawned": 9,
         "pieces_locked": 11,
         "lines_cleared": 1,
         "piece_types_seen": [
           "unknown",
-          "O"
+          "T"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 163
+        "load_time_ms": 32
       },
       "accessibility": {
         "issues": [],
@@ -265,19 +265,19 @@
       }
     }
   },
-  "outcome_score": 0.73,
-  "score": 0.73,
+  "outcome_score": 0.68,
+  "score": 0.68,
   "sonarqube": {
-    "bugs": 1,
+    "bugs": 0,
     "vulnerabilities": 0,
-    "code_smells": 5,
-    "cognitive_complexity": 78,
-    "lines_of_code": 698,
-    "duplication_pct": 0.0,
-    "tech_debt_minutes": 25,
+    "code_smells": 31,
+    "cognitive_complexity": 236,
+    "lines_of_code": 1088,
+    "duplication_pct": 28.1,
+    "tech_debt_minutes": 141,
     "maintainability": "A",
-    "reliability": "C",
+    "reliability": "A",
     "security": "A",
-    "score": 0.65
+    "score": 0.55
   }
 }
 \ No newline at end of file
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=haiku_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -12,7 +12,7 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "z",
+      "rotate": "x",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -98,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 36 pieces, no crashes"
+      "detail": "played for 30s, placed 33 pieces, no crashes"
     }
   ],
   "summary": {
@@ -108,26 +108,26 @@
     "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 36,
+    "pieces_placed": 33,
     "lines_cleared": 1,
     "max_score_observed": 0,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 306,
+    "frames": 309,
     "events_count": 8,
     "pieces_spawned": 9,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
       "unknown",
-      "O"
+      "T"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 163
+    "load_time_ms": 32
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -215,7 +215,7 @@
         {
           "name": "score_changes",
           "pass": true,
-          "detail": "score changed from 160 to 162"
+          "detail": "score changed from 194 to 216"
         },
         {
           "name": "game_over",
@@ -237,12 +237,12 @@
       "gameplay": {
         "pieces_placed": 20,
         "lines_cleared": 1,
-        "max_score_observed": 162,
+        "max_score_observed": 216,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 336,
+        "frames": 351,
         "events_count": 2,
         "pieces_spawned": 0,
         "pieces_locked": 10,
@@ -251,7 +251,7 @@
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 402
+        "load_time_ms": 86
       },
       "accessibility": {
         "issues": [],
@@ -265,11 +265,11 @@
   "sonarqube": {
     "bugs": 0,
     "vulnerabilities": 0,
-    "code_smells": 17,
-    "cognitive_complexity": 123,
-    "lines_of_code": 958,
-    "duplication_pct": 2.8,
-    "tech_debt_minutes": 63,
+    "code_smells": 12,
+    "cognitive_complexity": 144,
+    "lines_of_code": 826,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 71,
     "maintainability": "A",
     "reliability": "A",
     "security": "A",
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -88,7 +88,7 @@
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 160 to 162"
+      "detail": "score changed from 194 to 216"
     },
     {
       "name": "game_over",
@@ -110,12 +110,12 @@
   "gameplay": {
     "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 162,
+    "max_score_observed": 216,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 336,
+    "frames": 351,
     "events_count": 2,
     "pieces_spawned": 0,
     "pieces_locked": 10,
@@ -124,7 +124,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 402
+    "load_time_ms": 86
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -121,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.94,
+    "score": 0.81,
     "total": 16,
-    "passed": 15,
-    "failed": 1,
+    "passed": 13,
+    "failed": 3,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -139,7 +139,7 @@
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "ArrowUp",
+          "rotate": "z",
           "drop": "Space"
         },
         "start_mechanism": "auto",
@@ -179,13 +179,13 @@
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": true,
-          "detail": "rotation observed, piece types seen: [unknown, S]"
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
@@ -210,12 +210,12 @@
         {
           "name": "line_clear",
           "pass": true,
-          "detail": "2 line(s) cleared (grid-verified)"
+          "detail": "1 line(s) cleared (grid-verified)"
         },
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score stayed at 282"
+          "detail": "score stayed at 216"
         },
         {
           "name": "game_over",
@@ -230,31 +230,30 @@
       ],
       "summary": {
         "total": 16,
-        "passed": 15,
-        "failed": 1,
-        "score": 0.94
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
       },
       "gameplay": {
         "pieces_placed": 37,
-        "lines_cleared": 2,
-        "max_score_observed": 282,
+        "lines_cleared": 1,
+        "max_score_observed": 216,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 296,
-        "events_count": 11,
+        "frames": 309,
+        "events_count": 9,
         "pieces_spawned": 4,
         "pieces_locked": 11,
-        "lines_cleared": 2,
+        "lines_cleared": 1,
         "piece_types_seen": [
-          "unknown",
-          "S"
+          "unknown"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 141
+        "load_time_ms": 38
       },
       "accessibility": {
         "issues": [
@@ -265,16 +264,16 @@
       }
     }
   },
-  "outcome_score": 0.795,
-  "score": 0.795,
+  "outcome_score": 0.73,
+  "score": 0.73,
   "sonarqube": {
     "bugs": 0,
     "vulnerabilities": 0,
-    "code_smells": 17,
-    "cognitive_complexity": 123,
-    "lines_of_code": 958,
-    "duplication_pct": 2.8,
-    "tech_debt_minutes": 63,
+    "code_smells": 13,
+    "cognitive_complexity": 105,
+    "lines_of_code": 616,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 46,
     "maintainability": "A",
     "reliability": "A",
     "security": "A",
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -12,7 +12,7 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "ArrowUp",
+      "rotate": "z",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -52,13 +52,13 @@
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotation observed, piece types seen: [unknown, S]"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
@@ -83,12 +83,12 @@
     {
       "name": "line_clear",
       "pass": true,
-      "detail": "2 line(s) cleared (grid-verified)"
+      "detail": "1 line(s) cleared (grid-verified)"
     },
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score stayed at 282"
+      "detail": "score stayed at 216"
     },
     {
       "name": "game_over",
@@ -103,31 +103,30 @@
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
     "pieces_placed": 37,
-    "lines_cleared": 2,
-    "max_score_observed": 282,
+    "lines_cleared": 1,
+    "max_score_observed": 216,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 296,
-    "events_count": 11,
+    "frames": 309,
+    "events_count": 9,
     "pieces_spawned": 4,
     "pieces_locked": 11,
-    "lines_cleared": 2,
+    "lines_cleared": 1,
     "piece_types_seen": [
-      "unknown",
-      "S"
+      "unknown"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 141
+    "load_time_ms": 38
   },
   "accessibility": {
     "issues": [
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -121,10 +121,10 @@
   },
   "gameplay_bot": {
     "pass": false,
-    "score": 0.94,
+    "score": 0.81,
     "total": 16,
-    "passed": 15,
-    "failed": 1,
+    "passed": 13,
+    "failed": 3,
     "report": {
       "implementation": {
         "renderer": "canvas",
@@ -179,13 +179,13 @@
         },
         {
           "name": "rotate",
-          "pass": true,
-          "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+          "pass": false,
+          "detail": "no shape change detected after rotate key"
         },
         {
           "name": "all_pieces_rotate",
-          "pass": true,
-          "detail": "rotation observed, piece types seen: [unknown, T, S, I]"
+          "pass": false,
+          "detail": "could not detect any piece rotations via grid reader"
         },
         {
           "name": "hard_drop",
@@ -200,7 +200,7 @@
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "8 new piece(s) detected at top of grid"
+          "detail": "7 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
@@ -215,7 +215,7 @@
         {
           "name": "score_changes",
           "pass": false,
-          "detail": "score stayed at 350"
+          "detail": "score stayed at 298"
         },
         {
           "name": "game_over",
@@ -225,38 +225,38 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 41 pieces, no crashes"
+          "detail": "played for 30s, placed 40 pieces, no crashes"
         }
       ],
       "summary": {
         "total": 16,
-        "passed": 15,
-        "failed": 1,
-        "score": 0.94
+        "passed": 13,
+        "failed": 3,
+        "score": 0.81
       },
       "gameplay": {
-        "pieces_placed": 41,
+        "pieces_placed": 40,
         "lines_cleared": 1,
-        "max_score_observed": 350,
+        "max_score_observed": 298,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 289,
+        "frames": 300,
         "events_count": 10,
-        "pieces_spawned": 8,
+        "pieces_spawned": 7,
         "pieces_locked": 11,
         "lines_cleared": 1,
         "piece_types_seen": [
           "unknown",
-          "T",
+          "Z",
           "S",
           "I"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 100
+        "load_time_ms": 39
       },
       "accessibility": {
         "issues": [],
@@ -265,16 +265,16 @@
       }
     }
   },
-  "outcome_score": 0.795,
-  "score": 0.795,
+  "outcome_score": 0.73,
+  "score": 0.73,
   "sonarqube": {
     "bugs": 0,
     "vulnerabilities": 0,
-    "code_smells": 17,
-    "cognitive_complexity": 123,
-    "lines_of_code": 958,
-    "duplication_pct": 2.8,
-    "tech_debt_minutes": 63,
+    "code_smells": 12,
+    "cognitive_complexity": 144,
+    "lines_of_code": 826,
+    "duplication_pct": 0.0,
+    "tech_debt_minutes": 71,
     "maintainability": "A",
     "reliability": "A",
     "security": "A",
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=opus_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -52,13 +52,13 @@
     },
     {
       "name": "rotate",
-      "pass": true,
-      "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))"
+      "pass": false,
+      "detail": "no shape change detected after rotate key"
     },
     {
       "name": "all_pieces_rotate",
-      "pass": true,
-      "detail": "rotation observed, piece types seen: [unknown, T, S, I]"
+      "pass": false,
+      "detail": "could not detect any piece rotations via grid reader"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "8 new piece(s) detected at top of grid"
+      "detail": "7 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -88,7 +88,7 @@
     {
       "name": "score_changes",
       "pass": false,
-      "detail": "score stayed at 350"
+      "detail": "score stayed at 298"
     },
     {
       "name": "game_over",
@@ -98,38 +98,38 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 41 pieces, no crashes"
+      "detail": "played for 30s, placed 40 pieces, no crashes"
     }
   ],
   "summary": {
     "total": 16,
-    "passed": 15,
-    "failed": 1,
-    "score": 0.94
+    "passed": 13,
+    "failed": 3,
+    "score": 0.81
   },
   "gameplay": {
-    "pieces_placed": 41,
+    "pieces_placed": 40,
     "lines_cleared": 1,
-    "max_score_observed": 350,
+    "max_score_observed": 298,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 289,
+    "frames": 300,
     "events_count": 10,
-    "pieces_spawned": 8,
+    "pieces_spawned": 7,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
       "unknown",
-      "T",
+      "Z",
       "S",
       "I"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 100
+    "load_time_ms": 39
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/eval_results.json
@@ -139,7 +139,7 @@
           "left": "ArrowLeft",
           "right": "ArrowRight",
           "down": "ArrowDown",
-          "rotate": "x",
+          "rotate": "ArrowUp",
           "drop": "Space"
         },
         "start_mechanism": "auto",
@@ -242,7 +242,7 @@
         "errors_during_play": 0
       },
       "session": {
-        "frames": 327,
+        "frames": 346,
         "events_count": 2,
         "pieces_spawned": 0,
         "pieces_locked": 10,
@@ -251,7 +251,7 @@
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 133
+        "load_time_ms": 46
       },
       "accessibility": {
         "issues": [],
@@ -265,11 +265,11 @@
   "sonarqube": {
     "bugs": 1,
     "vulnerabilities": 0,
-    "code_smells": 22,
-    "cognitive_complexity": 120,
-    "lines_of_code": 811,
+    "code_smells": 12,
+    "cognitive_complexity": 148,
+    "lines_of_code": 734,
     "duplication_pct": 0.0,
-    "tech_debt_minutes": 63,
+    "tech_debt_minutes": 85,
     "maintainability": "A",
     "reliability": "C",
     "security": "A",
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run1/gameplay-bot-report.json
@@ -12,7 +12,7 @@
       "left": "ArrowLeft",
       "right": "ArrowRight",
       "down": "ArrowDown",
-      "rotate": "x",
+      "rotate": "ArrowUp",
       "drop": "Space"
     },
     "start_mechanism": "auto",
@@ -115,7 +115,7 @@
     "errors_during_play": 0
   },
   "session": {
-    "frames": 327,
+    "frames": 346,
     "events_count": 2,
     "pieces_spawned": 0,
     "pieces_locked": 10,
@@ -124,7 +124,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 133
+    "load_time_ms": 46
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/eval_results.json
@@ -185,7 +185,7 @@
         {
           "name": "all_pieces_rotate",
           "pass": true,
-          "detail": "rotation observed, piece types seen: [unknown, J]"
+          "detail": "rotation observed, piece types seen: [unknown, Z]"
         },
         {
           "name": "hard_drop",
@@ -200,7 +200,7 @@
         {
           "name": "new_piece_spawns",
           "pass": true,
-          "detail": "8 new piece(s) detected at top of grid"
+          "detail": "10 new piece(s) detected at top of grid"
         },
         {
           "name": "multiple_pieces",
@@ -215,7 +215,7 @@
         {
           "name": "score_changes",
           "pass": true,
-          "detail": "score changed from 126 to 266"
+          "detail": "score changed from 36 to 176"
         },
         {
           "name": "game_over",
@@ -225,7 +225,7 @@
         {
           "name": "playable_30s",
           "pass": true,
-          "detail": "played for 30s, placed 43 pieces, no crashes"
+          "detail": "played for 30s, placed 44 pieces, no crashes"
         }
       ],
       "summary": {
@@ -235,26 +235,26 @@
         "score": 0.94
       },
       "gameplay": {
-        "pieces_placed": 43,
+        "pieces_placed": 44,
         "lines_cleared": 1,
-        "max_score_observed": 266,
+        "max_score_observed": 176,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
         "frames": 281,
         "events_count": 10,
-        "pieces_spawned": 8,
+        "pieces_spawned": 10,
         "pieces_locked": 11,
         "lines_cleared": 1,
         "piece_types_seen": [
           "unknown",
-          "J"
+          "Z"
         ],
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 146
+        "load_time_ms": 37
       },
       "accessibility": {
         "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run2/gameplay-bot-report.json
@@ -58,7 +58,7 @@
     {
       "name": "all_pieces_rotate",
       "pass": true,
-      "detail": "rotation observed, piece types seen: [unknown, J]"
+      "detail": "rotation observed, piece types seen: [unknown, Z]"
     },
     {
       "name": "hard_drop",
@@ -73,7 +73,7 @@
     {
       "name": "new_piece_spawns",
       "pass": true,
-      "detail": "8 new piece(s) detected at top of grid"
+      "detail": "10 new piece(s) detected at top of grid"
     },
     {
       "name": "multiple_pieces",
@@ -88,7 +88,7 @@
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 126 to 266"
+      "detail": "score changed from 36 to 176"
     },
     {
       "name": "game_over",
@@ -98,7 +98,7 @@
     {
       "name": "playable_30s",
       "pass": true,
-      "detail": "played for 30s, placed 43 pieces, no crashes"
+      "detail": "played for 30s, placed 44 pieces, no crashes"
     }
   ],
   "summary": {
@@ -108,26 +108,26 @@
     "score": 0.94
   },
   "gameplay": {
-    "pieces_placed": 43,
+    "pieces_placed": 44,
     "lines_cleared": 1,
-    "max_score_observed": 266,
+    "max_score_observed": 176,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
     "frames": 281,
     "events_count": 10,
-    "pieces_spawned": 8,
+    "pieces_spawned": 10,
     "pieces_locked": 11,
     "lines_cleared": 1,
     "piece_types_seen": [
       "unknown",
-      "J"
+      "Z"
     ],
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 146
+    "load_time_ms": 37
   },
   "accessibility": {
     "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/eval_results.json
@@ -216,7 +216,7 @@
         {
           "name": "score_changes",
           "pass": true,
-          "detail": "score changed from 196 to 216"
+          "detail": "score changed from 230 to 262"
         },
         {
           "name": "game_over",
@@ -238,12 +238,12 @@
       "gameplay": {
         "pieces_placed": 20,
         "lines_cleared": 1,
-        "max_score_observed": 216,
+        "max_score_observed": 262,
         "play_duration_seconds": 30,
         "errors_during_play": 0
       },
       "session": {
-        "frames": 325,
+        "frames": 351,
         "events_count": 2,
         "pieces_spawned": 0,
         "pieces_locked": 10,
@@ -252,7 +252,7 @@
         "grid_read_success_rate": 1
       },
       "performance": {
-        "load_time_ms": 160
+        "load_time_ms": 44
       },
       "accessibility": {
         "issues": [],
diff --git a/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json b/results/runs/tetris_context_file=provided_effort=high_human_language=en_language=typescript_linter=on_max_budget=low_model=sonnet_playwright=on_prompt_style=simple_sub_agents=on_tool_edit=on_tool_glob=on_tool_grep=on_tool_read=on_tool_write=on_web_search=on_run3/gameplay-bot-report.json
@@ -88,7 +88,7 @@
     {
       "name": "score_changes",
       "pass": true,
-      "detail": "score changed from 196 to 216"
+      "detail": "score changed from 230 to 262"
     },
     {
       "name": "game_over",
@@ -110,12 +110,12 @@
   "gameplay": {
     "pieces_placed": 20,
     "lines_cleared": 1,
-    "max_score_observed": 216,
+    "max_score_observed": 262,
     "play_duration_seconds": 30,
     "errors_during_play": 0
   },
   "session": {
-    "frames": 325,
+    "frames": 351,
     "events_count": 2,
     "pieces_spawned": 0,
     "pieces_locked": 10,
@@ -124,7 +124,7 @@
     "grid_read_success_rate": 1
   },
   "performance": {
-    "load_time_ms": 160
+    "load_time_ms": 44
   },
   "accessibility": {
     "issues": [],

	loop-benchmarking Controlled experiments across agentic coding configurations. Same task, one variable, what actually works.
	git clone https://git.shiptheloop.com/loop-benchmarking.git
	Log \| Files \| Refs \| README