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

commit 0d6347bcf45b3671c03f68ec0dabf906a7ba3554
parent 23bc276e52ad4b72483d00e988f165fe956483fb
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Tue,  7 Apr 2026 15:08:01 +0200

Re-eval 222 runs (10 glm-4.5-air, 26 glm-4.7, 9 glm-5.1, 74 haiku, 51 opus, 52 sonnet)

Diffstat:
Mresults/analysis/main_effects_code_quality.json | 296++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_gameplay.json | 312++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_score.json | 342++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_sonarqube.json | 377+++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/index.jsonl | 444++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 41+++++++++++++++++++++++++----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 24++++++++++++------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 25+++++++++++++++++--------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 4++--
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 159++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 21+++++++++++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 4++--
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 107++++++++++++++++++++++++++++++++++++++++---------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 25+++++++++++++++++--------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 8++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 25+++++++++++++++++--------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 8++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 162++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 6+++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 27++++++++++++++++++---------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 10+++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 43++++++++++++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 20++++++++++----------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 64++++++++++++++++++++++++++++++++--------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 161++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 71+++++++++++++++++++++++++++++++++++++++--------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 46++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 47+++++++++++++++++++++++++++--------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 30++++++++++++++----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 10+++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json | 63++++++++++++++++++++++++++++++++++++---------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 40++++++++++++++++++++--------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json | 63++++++++++++++++++++++++++++++++++++---------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json | 40++++++++++++++++++++--------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 35++++++++++++++++++++++-------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 18+++++++++---------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 161+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 163++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 21+++++++++++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 167+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 159++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 37++++++++++++++++++++++++-------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 20+++++++++++---------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json | 31+++++++++++++++++++++----------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 14++++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json | 31++++++++++++++++++++-----------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json | 14+++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json | 159++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json | 164+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 152+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 29+++++++++++++++++++----------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 12++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 162++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 63++++++++++++++++++++++++++++++++++++---------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 40++++++++++++++++++++--------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 21+++++++++++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 4++--
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 162+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 6+++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 92++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 92+++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 59++++++++++++++++++++++++++++++++++-------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 36++++++++++++++++++------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 162+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json | 59++++++++++++++++++++++++++++++++++-------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 36++++++++++++++++++------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json | 164+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json | 80++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json | 162+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 45+++++++++++++++++++++++++++------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 28++++++++++++++--------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 6+++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 162+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 63+++++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 38++++++++++++++++++++------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 45+++++++++++++++++++++++++++------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 28++++++++++++++--------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 105+++++++++++++++++++++++++++++++++++++++++++------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 78+++++++++++++++++++++++++++++++++++++++---------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 161++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 94++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 65+++++++++++++++++++++++++++++++++++++----------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 32++++++++++++++++----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 164+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json | 25+++++++++++++++++--------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 8++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json | 57++++++++++++++++++++++++++++++++-------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 30++++++++++++++----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json | 25+++++++++++++++++--------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json | 8++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json | 6+++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 159++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 92++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 21+++++++++++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 4++--
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 161+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 21+++++++++++++++------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 164+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 64+++++++++++++++++++++++++++++++++++++++++-----------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1/eval_results.json | 63++++++++++++++++++++++++++++++++++++---------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1/gameplay-bot-report.json | 40++++++++++++++++++++--------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3/eval_results.json | 113+++++++++++++++++++++++++++++++++++++++++++------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3/gameplay-bot-report.json | 90++++++++++++++++++++++++++++++++++++++++---------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 78++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 147+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 160++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 87+++++++++++++++++++++++++++++++++++++++++++++----------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 63++++++++++++++++++++++++++++++++++++---------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 40++++++++++++++++++++--------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 61+++++++++++++++++++++++++++++++++++--------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 38+++++++++++++++++++-------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 69+++++++++++++++++++++++++++++++++++++++------------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 46+++++++++++++++++++++++-----------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 65+++++++++++++++++++++++++++++++++++++----------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 42+++++++++++++++++++++---------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 164+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 37+++++++++++++++++++++++--------------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 20++++++++++----------
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 157++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1/eval_results.json | 31++++++++++++++++++++-----------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json | 14+++++++-------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2/eval_results.json | 37++++++++++++++++++++++++-------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json | 20+++++++++++---------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3/eval_results.json | 161++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 27++++++++++++++++++---------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 10+++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 17+++++++++++++----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 57+++++++++++++++++++++++++++++++++------------------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 6+++---
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 163+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 59++++++++++++++++++++++++++++++++++-------------------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 34+++++++++++++++++-----------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json | 59++++++++++++++++++++++++++++++++++-------------------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json | 36++++++++++++++++++------------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1/eval_results.json | 159++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1/gameplay-bot-report.json | 24++++++++++++------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3/eval_results.json | 23++++++++++++++++-------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1/eval_results.json | 33+++++++++++++++++++++------------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1/gameplay-bot-report.json | 16++++++++--------
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2/gameplay-bot-report.json | 2+-
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3/eval_results.json | 19++++++++++++++-----
Mresults/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3/gameplay-bot-report.json | 2+-
412 files changed, 11416 insertions(+), 4401 deletions(-)

diff --git a/results/analysis/main_effects_code_quality.json b/results/analysis/main_effects_code_quality.json @@ -3,300 +3,300 @@ "values": { "creative_validate": { "mean": 0.55, - "effect": -0.2385, + "effect": -0.177, "n": 3 }, "iterate": { "mean": 0.65, - "effect": -0.1385, + "effect": -0.077, "n": 1 }, "none": { - "mean": 0.7505, - "effect": -0.0381, + "mean": 0.6858, + "effect": -0.0412, "n": 65 }, "use_subagents": { - "mean": 0.8103, - "effect": 0.0217, + "mean": 0.7485, + "effect": 0.0215, "n": 153 } }, - "spread": 0.2603 + "spread": 0.1985 }, "model": { "values": { "glm-4.5-air": { - "mean": 0.72, - "effect": -0.0685, + "mean": 0.65, + "effect": -0.077, "n": 10 }, "glm-4.7": { - "mean": 0.7365, - "effect": -0.052, + "mean": 0.6423, + "effect": -0.0847, "n": 26 }, "glm-5.1": { "mean": 0.7667, - "effect": -0.0218, + "effect": 0.0396, "n": 9 }, "haiku": { - "mean": 0.7128, - "effect": -0.0757, + "mean": 0.6419, + "effect": -0.0851, "n": 74 }, "opus": { - "mean": 0.8647, - "effect": 0.0762, + "mean": 0.8304, + "effect": 0.1034, "n": 51 }, "sonnet": { - "mean": 0.8644, - "effect": 0.0759, + "mean": 0.7971, + "effect": 0.0701, "n": 52 } }, - "spread": 0.1519 + "spread": 0.1885 }, "language": { "values": { "javascript": { - "mean": 0.9136, - "effect": 0.1251, + "mean": 0.7545, + "effect": 0.0275, "n": 11 }, "typescript": { - "mean": 0.7739, - "effect": -0.0146, + "mean": 0.7352, + "effect": 0.0081, "n": 199 }, "unspecified": { - "mean": 0.9167, - "effect": 0.1282, + "mean": 0.5667, + "effect": -0.1604, "n": 12 } }, - "spread": 0.1428 + "spread": 0.1878 }, - "playwright": { + "prompt_style": { "values": { - "available": { - "mean": 0.8041, - "effect": 0.0156, - "n": 157 - }, - "instructed": { - "mean": 0.7, - "effect": -0.0885, - "n": 1 + "detailed": { + "mean": 0.6, + "effect": -0.127, + "n": 22 }, - "off": { - "mean": 0.7517, - "effect": -0.0368, - "n": 64 + "simple": { + "mean": 0.741, + "effect": 0.014, + "n": 200 } }, - "spread": 0.1041 + "spread": 0.141 }, "human_language": { "values": { "en": { - "mean": 0.796, - "effect": 0.0075, + "mean": 0.7383, + "effect": 0.0112, "n": 200 }, "es": { - "mean": 0.7205, - "effect": -0.0681, + "mean": 0.625, + "effect": -0.102, "n": 22 } }, - "spread": 0.0755 + "spread": 0.1133 }, - "renderer": { + "playwright": { "values": { - "dom": { - "mean": 0.7667, - "effect": -0.0218, - "n": 3 - }, - "none": { - "mean": 0.789, - "effect": 0.0005, - "n": 218 + "available": { + "mean": 0.7461, + "effect": 0.0191, + "n": 157 }, - "webgl": { - "mean": 0.75, - "effect": -0.0385, + "instructed": { + "mean": 0.7, + "effect": -0.027, "n": 1 + }, + "off": { + "mean": 0.6806, + "effect": -0.0464, + "n": 64 } }, - "spread": 0.039 + "spread": 0.0655 }, "web_search": { "values": { "off": { - "mean": 0.7585, - "effect": -0.03, + "mean": 0.6807, + "effect": -0.0463, "n": 27 }, "on": { - "mean": 0.7927, - "effect": 0.0042, + "mean": 0.7334, + "effect": 0.0064, "n": 195 } }, - "spread": 0.0342 + "spread": 0.0527 }, - "tool_glob": { + "tool_read": { "values": { "off": { - "mean": 0.7583, - "effect": -0.0302, - "n": 18 + "mean": 0.6875, + "effect": -0.0395, + "n": 20 }, "on": { - "mean": 0.7912, - "effect": 0.0027, - "n": 204 + "mean": 0.7309, + "effect": 0.0039, + "n": 202 } }, - "spread": 0.0329 + "spread": 0.0434 }, - "context_file": { + "renderer": { "values": { + "dom": { + "mean": 0.7667, + "effect": 0.0396, + "n": 3 + }, "none": { - "mean": 0.7914, - "effect": 0.0028, - "n": 199 + "mean": 0.7264, + "effect": -0.0007, + "n": 218 }, - "provided": { - "mean": 0.7639, - "effect": -0.0246, - "n": 23 + "webgl": { + "mean": 0.75, + "effect": 0.023, + "n": 1 } }, - "spread": 0.0275 + "spread": 0.0403 }, "effort": { "values": { "high": { - "mean": 0.7897, - "effect": 0.0012, + "mean": 0.7253, + "effect": -0.0017, "n": 212 }, "max": { "mean": 0.764, - "effect": -0.0245, + "effect": 0.037, "n": 10 } }, - "spread": 0.0257 + "spread": 0.0387 }, - "max_budget": { + "linter": { "values": { - "high": { - "mean": 0.7679, - "effect": -0.0206, - "n": 19 + "off": { + "mean": 0.7034, + "effect": -0.0236, + "n": 29 }, - "low": { - "mean": 0.7904, - "effect": 0.0019, - "n": 203 + "on": { + "mean": 0.7306, + "effect": 0.0035, + "n": 193 } }, - "spread": 0.0225 + "spread": 0.0272 }, - "tool_edit": { + "context_file": { "values": { - "off": { - "mean": 0.7696, - "effect": -0.0189, - "n": 24 + "none": { + "mean": 0.7298, + "effect": 0.0028, + "n": 199 }, - "on": { - "mean": 0.7908, - "effect": 0.0023, - "n": 198 + "provided": { + "mean": 0.703, + "effect": -0.024, + "n": 23 } }, - "spread": 0.0212 + "spread": 0.0268 }, - "prompt_style": { + "tool_grep": { "values": { - "detailed": { - "mean": 0.8068, - "effect": 0.0183, + "off": { + "mean": 0.705, + "effect": -0.022, "n": 22 }, - "simple": { - "mean": 0.7865, - "effect": -0.002, + "on": { + "mean": 0.7294, + "effect": 0.0024, "n": 200 } }, - "spread": 0.0203 + "spread": 0.0244 }, - "tool_write": { + "tool_edit": { "values": { "off": { - "mean": 0.7713, - "effect": -0.0172, - "n": 23 + "mean": 0.7113, + "effect": -0.0158, + "n": 24 }, "on": { - "mean": 0.7905, - "effect": 0.002, - "n": 199 + "mean": 0.7289, + "effect": 0.0019, + "n": 198 } }, - "spread": 0.0192 + "spread": 0.0176 }, - "tool_grep": { + "max_budget": { "values": { - "off": { - "mean": 0.8005, - "effect": 0.0119, - "n": 22 + "high": { + "mean": 0.7126, + "effect": -0.0144, + "n": 19 }, - "on": { - "mean": 0.7872, - "effect": -0.0013, - "n": 200 + "low": { + "mean": 0.7284, + "effect": 0.0013, + "n": 203 } }, - "spread": 0.0133 + "spread": 0.0158 }, - "tool_read": { + "tool_glob": { "values": { "off": { - "mean": 0.7925, - "effect": 0.004, - "n": 20 + "mean": 0.7194, + "effect": -0.0076, + "n": 18 }, "on": { - "mean": 0.7881, - "effect": -0.0004, - "n": 202 + "mean": 0.7277, + "effect": 0.0007, + "n": 204 } }, - "spread": 0.0044 + "spread": 0.0083 }, - "linter": { + "tool_write": { "values": { "off": { - "mean": 0.7879, - "effect": -0.0006, - "n": 29 + "mean": 0.7257, + "effect": -0.0014, + "n": 23 }, "on": { - "mean": 0.7886, - "effect": 0.0001, - "n": 193 + "mean": 0.7272, + "effect": 0.0002, + "n": 199 } }, - "spread": 0.0007 + "spread": 0.0015 } } \ No newline at end of file diff --git a/results/analysis/main_effects_gameplay.json b/results/analysis/main_effects_gameplay.json @@ -2,301 +2,301 @@ "renderer": { "values": { "dom": { - "mean": 0.3533, - "effect": 0.2031, + "mean": 0.6867, + "effect": 0.4274, "n": 3 }, "none": { - "mean": 0.1478, - "effect": -0.0024, + "mean": 0.2543, + "effect": -0.005, "n": 218 }, "webgl": { "mean": 0.06, - "effect": -0.0902, + "effect": -0.1993, "n": 1 } }, - "spread": 0.2933 - }, - "effort": { - "values": { - "high": { - "mean": 0.1423, - "effect": -0.008, - "n": 212 - }, - "max": { - "mean": 0.319, - "effect": 0.1688, - "n": 10 - } - }, - "spread": 0.1767 + "spread": 0.6267 }, "model": { "values": { "glm-4.5-air": { "mean": 0.054, - "effect": -0.0962, + "effect": -0.2053, "n": 10 }, "glm-4.7": { - "mean": 0.0896, - "effect": -0.0606, + "mean": 0.1331, + "effect": -0.1262, "n": 26 }, "glm-5.1": { - "mean": 0.1444, - "effect": -0.0058, + "mean": 0.3667, + "effect": 0.1074, "n": 9 }, "haiku": { - "mean": 0.1884, - "effect": 0.0382, + "mean": 0.2715, + "effect": 0.0122, "n": 74 }, "opus": { - "mean": 0.1449, - "effect": -0.0053, + "mean": 0.3549, + "effect": 0.0956, "n": 51 }, "sonnet": { - "mean": 0.151, - "effect": 0.0007, + "mean": 0.2321, + "effect": -0.0272, "n": 52 } }, - "spread": 0.1344 + "spread": 0.3127 }, - "strategy": { + "effort": { "values": { - "creative_validate": { - "mean": 0.06, - "effect": -0.0902, - "n": 3 - }, - "iterate": { - "mean": 0.06, - "effect": -0.0902, - "n": 1 - }, - "none": { - "mean": 0.1151, - "effect": -0.0351, - "n": 65 + "high": { + "mean": 0.2482, + "effect": -0.0111, + "n": 212 }, - "use_subagents": { - "mean": 0.1675, - "effect": 0.0173, - "n": 153 + "max": { + "mean": 0.495, + "effect": 0.2357, + "n": 10 } }, - "spread": 0.1075 + "spread": 0.2468 }, "playwright": { "values": { "available": { - "mean": 0.1632, - "effect": 0.013, + "mean": 0.2846, + "effect": 0.0254, "n": 157 }, "instructed": { "mean": 0.06, - "effect": -0.0902, + "effect": -0.1993, "n": 1 }, "off": { - "mean": 0.1198, - "effect": -0.0304, + "mean": 0.2002, + "effect": -0.0591, "n": 64 } }, - "spread": 0.1032 + "spread": 0.2246 + }, + "strategy": { + "values": { + "creative_validate": { + "mean": 0.06, + "effect": -0.1993, + "n": 3 + }, + "iterate": { + "mean": 0.06, + "effect": -0.1993, + "n": 1 + }, + "none": { + "mean": 0.2155, + "effect": -0.0437, + "n": 65 + }, + "use_subagents": { + "mean": 0.2831, + "effect": 0.0238, + "n": 153 + } + }, + "spread": 0.2231 }, "language": { "values": { "javascript": { - "mean": 0.1355, - "effect": -0.0148, + "mean": 0.2082, + "effect": -0.0511, "n": 11 }, "typescript": { - "mean": 0.1568, - "effect": 0.0066, + "mean": 0.2741, + "effect": 0.0148, "n": 199 }, "unspecified": { - "mean": 0.055, - "effect": -0.0952, + "mean": 0.06, + "effect": -0.1993, "n": 12 } }, - "spread": 0.1018 - }, - "tool_write": { - "values": { - "off": { - "mean": 0.2252, - "effect": 0.075, - "n": 23 - }, - "on": { - "mean": 0.1416, - "effect": -0.0087, - "n": 199 - } - }, - "spread": 0.0836 + "spread": 0.2141 }, "tool_glob": { "values": { "off": { - "mean": 0.2256, - "effect": 0.0753, + "mean": 0.4167, + "effect": 0.1574, "n": 18 }, "on": { - "mean": 0.1436, - "effect": -0.0066, + "mean": 0.2454, + "effect": -0.0139, "n": 204 } }, - "spread": 0.082 + "spread": 0.1713 }, - "tool_edit": { + "tool_write": { "values": { "off": { - "mean": 0.2133, - "effect": 0.0631, - "n": 24 + "mean": 0.3561, + "effect": 0.0968, + "n": 23 }, "on": { - "mean": 0.1426, - "effect": -0.0076, - "n": 198 + "mean": 0.2481, + "effect": -0.0112, + "n": 199 } }, - "spread": 0.0707 + "spread": 0.108 }, "context_file": { "values": { "none": { - "mean": 0.1435, - "effect": -0.0068, + "mean": 0.2516, + "effect": -0.0077, "n": 199 }, "provided": { - "mean": 0.2087, - "effect": 0.0585, + "mean": 0.3261, + "effect": 0.0668, "n": 23 } }, - "spread": 0.0652 + "spread": 0.0745 }, - "prompt_style": { + "tool_grep": { "values": { - "detailed": { - "mean": 0.0927, - "effect": -0.0575, + "off": { + "mean": 0.3182, + "effect": 0.0589, "n": 22 }, - "simple": { - "mean": 0.1566, - "effect": 0.0063, + "on": { + "mean": 0.2528, + "effect": -0.0065, "n": 200 } }, - "spread": 0.0639 + "spread": 0.0654 }, "tool_read": { "values": { "off": { - "mean": 0.0955, - "effect": -0.0547, + "mean": 0.2185, + "effect": -0.0408, "n": 20 }, "on": { - "mean": 0.1556, - "effect": 0.0054, + "mean": 0.2633, + "effect": 0.004, "n": 202 } }, - "spread": 0.0601 + "spread": 0.0448 }, - "max_budget": { + "human_language": { "values": { - "high": { - "mean": 0.1963, - "effect": 0.0461, - "n": 19 + "en": { + "mean": 0.2629, + "effect": 0.0036, + "n": 200 }, - "low": { - "mean": 0.1459, - "effect": -0.0043, - "n": 203 + "es": { + "mean": 0.2268, + "effect": -0.0325, + "n": 22 } }, - "spread": 0.0504 + "spread": 0.0361 }, - "tool_grep": { + "prompt_style": { "values": { - "off": { - "mean": 0.1895, - "effect": 0.0393, + "detailed": { + "mean": 0.2291, + "effect": -0.0302, "n": 22 }, - "on": { - "mean": 0.1459, - "effect": -0.0043, + "simple": { + "mean": 0.2626, + "effect": 0.0033, "n": 200 } }, - "spread": 0.0436 + "spread": 0.0335 }, - "linter": { + "web_search": { "values": { "off": { - "mean": 0.1869, - "effect": 0.0367, - "n": 29 + "mean": 0.2352, + "effect": -0.0241, + "n": 27 }, "on": { - "mean": 0.1447, - "effect": -0.0055, - "n": 193 + "mean": 0.2626, + "effect": 0.0033, + "n": 195 } }, - "spread": 0.0422 + "spread": 0.0274 }, - "human_language": { + "tool_edit": { "values": { - "en": { - "mean": 0.1531, - "effect": 0.0029, - "n": 200 + "off": { + "mean": 0.2812, + "effect": 0.022, + "n": 24 }, - "es": { - "mean": 0.1241, - "effect": -0.0261, - "n": 22 + "on": { + "mean": 0.2566, + "effect": -0.0027, + "n": 198 } }, - "spread": 0.029 + "spread": 0.0246 }, - "web_search": { + "linter": { "values": { "off": { - "mean": 0.1474, - "effect": -0.0028, - "n": 27 + "mean": 0.2797, + "effect": 0.0204, + "n": 29 }, "on": { - "mean": 0.1506, - "effect": 0.0004, - "n": 195 + "mean": 0.2562, + "effect": -0.0031, + "n": 193 + } + }, + "spread": 0.0235 + }, + "max_budget": { + "values": { + "high": { + "mean": 0.2389, + "effect": -0.0203, + "n": 19 + }, + "low": { + "mean": 0.2612, + "effect": 0.0019, + "n": 203 } }, - "spread": 0.0032 + "spread": 0.0223 } } \ No newline at end of file diff --git a/results/analysis/main_effects_score.json b/results/analysis/main_effects_score.json @@ -1,302 +1,302 @@ { - "renderer": { + "playwright": { "values": { - "dom": { - "mean": 0.1767, - "effect": 0.1016, - "n": 3 - }, - "none": { - "mean": 0.0739, - "effect": -0.0012, - "n": 218 + "available": { + "mean": 0.4426, + "effect": 0.0213, + "n": 157 }, - "webgl": { - "mean": 0.03, - "effect": -0.0451, + "instructed": { + "mean": 0.06, + "effect": -0.3614, "n": 1 - } - }, - "spread": 0.1467 - }, - "effort": { - "values": { - "high": { - "mean": 0.0711, - "effect": -0.004, - "n": 212 }, - "max": { - "mean": 0.1595, - "effect": 0.0844, - "n": 10 + "off": { + "mean": 0.3748, + "effect": -0.0465, + "n": 64 } }, - "spread": 0.0884 + "spread": 0.3826 }, "model": { "values": { "glm-4.5-air": { - "mean": 0.027, - "effect": -0.0481, + "mean": 0.262, + "effect": -0.1594, "n": 10 }, "glm-4.7": { - "mean": 0.0448, - "effect": -0.0303, + "mean": 0.3056, + "effect": -0.1158, "n": 26 }, "glm-5.1": { - "mean": 0.0722, - "effect": -0.0029, + "mean": 0.4806, + "effect": 0.0592, "n": 9 }, "haiku": { - "mean": 0.0942, - "effect": 0.0191, + "mean": 0.413, + "effect": -0.0084, "n": 74 }, "opus": { - "mean": 0.0725, - "effect": -0.0027, + "mean": 0.5162, + "effect": 0.0948, "n": 51 }, "sonnet": { - "mean": 0.0755, - "effect": 0.0004, + "mean": 0.4186, + "effect": -0.0028, "n": 52 } }, - "spread": 0.0672 + "spread": 0.2542 + }, + "renderer": { + "values": { + "dom": { + "mean": 0.6033, + "effect": 0.182, + "n": 3 + }, + "none": { + "mean": 0.4191, + "effect": -0.0022, + "n": 218 + }, + "webgl": { + "mean": 0.365, + "effect": -0.0564, + "n": 1 + } + }, + "spread": 0.2383 }, "strategy": { "values": { "creative_validate": { - "mean": 0.03, - "effect": -0.0451, + "mean": 0.2717, + "effect": -0.1497, "n": 3 }, "iterate": { - "mean": 0.03, - "effect": -0.0451, + "mean": 0.34, + "effect": -0.0814, "n": 1 }, "none": { - "mean": 0.0575, - "effect": -0.0176, + "mean": 0.3673, + "effect": -0.054, "n": 65 }, "use_subagents": { - "mean": 0.0838, - "effect": 0.0086, + "mean": 0.4478, + "effect": 0.0264, "n": 153 } }, - "spread": 0.0538 + "spread": 0.1761 }, - "playwright": { + "effort": { "values": { - "available": { - "mean": 0.0816, - "effect": 0.0065, - "n": 157 - }, - "instructed": { - "mean": 0.03, - "effect": -0.0451, - "n": 1 + "high": { + "mean": 0.4171, + "effect": -0.0043, + "n": 212 }, - "off": { - "mean": 0.0599, - "effect": -0.0152, - "n": 64 + "max": { + "mean": 0.5125, + "effect": 0.0911, + "n": 10 } }, - "spread": 0.0516 + "spread": 0.0954 }, "language": { "values": { "javascript": { - "mean": 0.0677, - "effect": -0.0074, + "mean": 0.5041, + "effect": 0.0827, "n": 11 }, "typescript": { - "mean": 0.0784, - "effect": 0.0033, + "mean": 0.4154, + "effect": -0.006, "n": 199 }, "unspecified": { - "mean": 0.0275, - "effect": -0.0476, + "mean": 0.445, + "effect": 0.0236, "n": 12 } }, - "spread": 0.0509 - }, - "tool_write": { - "values": { - "off": { - "mean": 0.1126, - "effect": 0.0375, - "n": 23 - }, - "on": { - "mean": 0.0708, - "effect": -0.0043, - "n": 199 - } - }, - "spread": 0.0418 + "spread": 0.0887 }, "tool_glob": { "values": { "off": { - "mean": 0.1128, - "effect": 0.0377, + "mean": 0.4667, + "effect": 0.0453, "n": 18 }, "on": { - "mean": 0.0718, - "effect": -0.0033, + "mean": 0.4174, + "effect": -0.004, "n": 204 } }, - "spread": 0.041 + "spread": 0.0493 }, - "tool_edit": { + "tool_grep": { "values": { "off": { - "mean": 0.1067, - "effect": 0.0316, - "n": 24 + "mean": 0.4641, + "effect": 0.0427, + "n": 22 }, "on": { - "mean": 0.0713, - "effect": -0.0038, - "n": 198 + "mean": 0.4166, + "effect": -0.0047, + "n": 200 } }, - "spread": 0.0354 + "spread": 0.0475 }, - "context_file": { + "max_budget": { "values": { - "none": { - "mean": 0.0717, - "effect": -0.0034, - "n": 199 + "high": { + "mean": 0.3837, + "effect": -0.0377, + "n": 19 }, - "provided": { - "mean": 0.1043, - "effect": 0.0292, - "n": 23 + "low": { + "mean": 0.4249, + "effect": 0.0035, + "n": 203 } }, - "spread": 0.0326 + "spread": 0.0412 }, - "prompt_style": { + "human_language": { "values": { - "detailed": { - "mean": 0.0464, - "effect": -0.0287, - "n": 22 - }, - "simple": { - "mean": 0.0783, - "effect": 0.0032, + "en": { + "mean": 0.4251, + "effect": 0.0037, "n": 200 + }, + "es": { + "mean": 0.3875, + "effect": -0.0339, + "n": 22 } }, - "spread": 0.0319 + "spread": 0.0376 }, - "tool_read": { + "linter": { "values": { "off": { - "mean": 0.0478, - "effect": -0.0274, - "n": 20 + "mean": 0.4512, + "effect": 0.0299, + "n": 29 }, "on": { - "mean": 0.0778, - "effect": 0.0027, - "n": 202 + "mean": 0.4169, + "effect": -0.0045, + "n": 193 } }, - "spread": 0.03 + "spread": 0.0343 }, - "max_budget": { + "tool_write": { "values": { - "high": { - "mean": 0.0982, - "effect": 0.023, - "n": 19 + "off": { + "mean": 0.4478, + "effect": 0.0265, + "n": 23 }, - "low": { - "mean": 0.073, - "effect": -0.0022, - "n": 203 + "on": { + "mean": 0.4183, + "effect": -0.0031, + "n": 199 } }, - "spread": 0.0252 + "spread": 0.0295 }, - "tool_grep": { + "tool_edit": { "values": { "off": { - "mean": 0.0948, - "effect": 0.0197, - "n": 22 + "mean": 0.3994, + "effect": -0.022, + "n": 24 }, "on": { - "mean": 0.073, - "effect": -0.0022, - "n": 200 + "mean": 0.424, + "effect": 0.0027, + "n": 198 } }, - "spread": 0.0218 + "spread": 0.0246 }, - "linter": { + "context_file": { "values": { - "off": { - "mean": 0.0934, - "effect": 0.0183, - "n": 29 + "none": { + "mean": 0.4193, + "effect": -0.002, + "n": 199 }, - "on": { - "mean": 0.0724, - "effect": -0.0028, - "n": 193 + "provided": { + "mean": 0.4387, + "effect": 0.0173, + "n": 23 } }, - "spread": 0.021 + "spread": 0.0194 }, - "human_language": { + "tool_read": { "values": { - "en": { - "mean": 0.0766, - "effect": 0.0014, - "n": 200 - }, - "es": { - "mean": 0.062, + "off": { + "mean": 0.4083, "effect": -0.0131, - "n": 22 + "n": 20 + }, + "on": { + "mean": 0.4226, + "effect": 0.0013, + "n": 202 } }, - "spread": 0.0146 + "spread": 0.0143 }, "web_search": { "values": { "off": { - "mean": 0.0737, - "effect": -0.0014, + "mean": 0.4131, + "effect": -0.0082, "n": 27 }, "on": { - "mean": 0.0753, - "effect": 0.0002, + "mean": 0.4225, + "effect": 0.0011, "n": 195 } }, - "spread": 0.0016 + "spread": 0.0094 + }, + "prompt_style": { + "values": { + "detailed": { + "mean": 0.4216, + "effect": 0.0002, + "n": 22 + }, + "simple": { + "mean": 0.4213, + "effect": -0.0, + "n": 200 + } + }, + "spread": 0.0003 } } \ No newline at end of file diff --git a/results/analysis/main_effects_sonarqube.json b/results/analysis/main_effects_sonarqube.json @@ -1,302 +1,297 @@ { - "context_file": { - "values": { - "none": { - "mean": 0.0, - "effect": 0.0, - "n": 199 - }, - "provided": { - "mean": 0.0, - "effect": 0.0, - "n": 23 - } - }, - "spread": 0.0 - }, - "effort": { - "values": { - "high": { - "mean": 0.0, - "effect": 0.0, - "n": 212 - }, - "max": { - "mean": 0.0, - "effect": 0.0, - "n": 10 - } - }, - "spread": 0.0 - }, - "human_language": { - "values": { - "en": { - "mean": 0.0, - "effect": 0.0, - "n": 200 - }, - "es": { - "mean": 0.0, - "effect": 0.0, - "n": 22 - } - }, - "spread": 0.0 - }, "language": { "values": { "javascript": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.8, + "effect": 0.2142, "n": 11 }, "typescript": { - "mean": 0.0, - "effect": 0.0, - "n": 199 + "mean": 0.5591, + "effect": -0.0267, + "n": 198 }, "unspecified": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.83, + "effect": 0.2442, "n": 12 } }, - "spread": 0.0 - }, - "linter": { - "values": { - "off": { - "mean": 0.0, - "effect": 0.0, - "n": 29 - }, - "on": { - "mean": 0.0, - "effect": 0.0, - "n": 193 - } - }, - "spread": 0.0 - }, - "max_budget": { - "values": { - "high": { - "mean": 0.0, - "effect": 0.0, - "n": 19 - }, - "low": { - "mean": 0.0, - "effect": 0.0, - "n": 203 - } - }, - "spread": 0.0 + "spread": 0.2709 }, "model": { "values": { "glm-4.5-air": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.47, + "effect": -0.1158, "n": 10 }, "glm-4.7": { - "mean": 0.0, - "effect": 0.0, - "n": 26 + "mean": 0.4948, + "effect": -0.091, + "n": 25 }, "glm-5.1": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.5944, + "effect": 0.0087, "n": 9 }, "haiku": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.5545, + "effect": -0.0313, "n": 74 }, "opus": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.6775, + "effect": 0.0917, "n": 51 }, "sonnet": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.605, + "effect": 0.0192, "n": 52 } }, - "spread": 0.0 - }, - "playwright": { - "values": { - "available": { - "mean": 0.0, - "effect": 0.0, - "n": 157 - }, - "instructed": { - "mean": 0.0, - "effect": 0.0, - "n": 1 - }, - "off": { - "mean": 0.0, - "effect": 0.0, - "n": 64 - } - }, - "spread": 0.0 - }, - "prompt_style": { - "values": { - "detailed": { - "mean": 0.0, - "effect": 0.0, - "n": 22 - }, - "simple": { - "mean": 0.0, - "effect": 0.0, - "n": 200 - } - }, - "spread": 0.0 + "spread": 0.2075 }, "renderer": { "values": { "dom": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.52, + "effect": -0.0658, "n": 3 }, "none": { - "mean": 0.0, - "effect": 0.0, - "n": 218 + "mean": 0.5863, + "effect": 0.0005, + "n": 217 }, "webgl": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.67, + "effect": 0.0842, "n": 1 } }, - "spread": 0.0 + "spread": 0.15 }, "strategy": { "values": { "creative_validate": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.4833, + "effect": -0.1025, "n": 3 }, "iterate": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.62, + "effect": 0.0342, "n": 1 }, "none": { - "mean": 0.0, - "effect": 0.0, - "n": 65 + "mean": 0.5262, + "effect": -0.0595, + "n": 64 }, "use_subagents": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.6125, + "effect": 0.0267, "n": 153 } }, - "spread": 0.0 + "spread": 0.1367 }, "tool_edit": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.5175, + "effect": -0.0683, "n": 24 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 198 + "mean": 0.5941, + "effect": 0.0083, + "n": 197 } }, - "spread": 0.0 + "spread": 0.0766 }, "tool_glob": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.5167, + "effect": -0.0691, "n": 18 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 204 + "mean": 0.5919, + "effect": 0.0061, + "n": 203 } }, - "spread": 0.0 + "spread": 0.0752 }, - "tool_grep": { + "max_budget": { + "values": { + "high": { + "mean": 0.5284, + "effect": -0.0574, + "n": 19 + }, + "low": { + "mean": 0.5912, + "effect": 0.0054, + "n": 202 + } + }, + "spread": 0.0628 + }, + "effort": { + "values": { + "high": { + "mean": 0.5884, + "effect": 0.0026, + "n": 211 + }, + "max": { + "mean": 0.53, + "effect": -0.0558, + "n": 10 + } + }, + "spread": 0.0584 + }, + "tool_write": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, - "n": 22 + "mean": 0.5396, + "effect": -0.0462, + "n": 23 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 200 + "mean": 0.5912, + "effect": 0.0054, + "n": 198 } }, - "spread": 0.0 + "spread": 0.0516 }, - "tool_read": { + "playwright": { "values": { + "available": { + "mean": 0.6006, + "effect": 0.0148, + "n": 157 + }, "off": { - "mean": 0.0, - "effect": 0.0, - "n": 20 + "mean": 0.5495, + "effect": -0.0363, + "n": 64 + } + }, + "spread": 0.0511 + }, + "linter": { + "values": { + "off": { + "mean": 0.6228, + "effect": 0.037, + "n": 29 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 202 + "mean": 0.5802, + "effect": -0.0056, + "n": 192 } }, - "spread": 0.0 + "spread": 0.0426 }, - "tool_write": { + "human_language": { "values": { - "off": { - "mean": 0.0, - "effect": 0.0, + "en": { + "mean": 0.5899, + "effect": 0.0042, + "n": 199 + }, + "es": { + "mean": 0.5482, + "effect": -0.0376, + "n": 22 + } + }, + "spread": 0.0417 + }, + "context_file": { + "values": { + "none": { + "mean": 0.5898, + "effect": 0.004, + "n": 198 + }, + "provided": { + "mean": 0.5513, + "effect": -0.0345, "n": 23 + } + }, + "spread": 0.0385 + }, + "prompt_style": { + "values": { + "detailed": { + "mean": 0.6141, + "effect": 0.0283, + "n": 22 + }, + "simple": { + "mean": 0.5827, + "effect": -0.0031, + "n": 199 + } + }, + "spread": 0.0314 + }, + "tool_grep": { + "values": { + "off": { + "mean": 0.61, + "effect": 0.0242, + "n": 22 }, "on": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.5831, + "effect": -0.0027, "n": 199 } }, - "spread": 0.0 + "spread": 0.0269 + }, + "tool_read": { + "values": { + "off": { + "mean": 0.598, + "effect": 0.0122, + "n": 20 + }, + "on": { + "mean": 0.5846, + "effect": -0.0012, + "n": 201 + } + }, + "spread": 0.0134 }, "web_search": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.5911, + "effect": 0.0053, "n": 27 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 195 + "mean": 0.5851, + "effect": -0.0007, + "n": 194 } }, - "spread": 0.0 + "spread": 0.006 } } \ No newline at end of file diff --git a/results/index.jsonl b/results/index.jsonl @@ -1,222 +1,222 @@ -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "85cfb3b7", "short_cell_id": "503191b4", "completed_at": "2026-04-07T06:40:52.932185+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c530817e", "short_cell_id": "503191b4", "completed_at": "2026-04-07T07:00:02.695067+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e047cf3a", "short_cell_id": "a04d517f", "completed_at": "2026-04-03T19:59:11.076296+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5ae88633", "short_cell_id": "a04d517f", "completed_at": "2026-04-03T19:59:32.351290+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1d08ee76", "short_cell_id": "a04d517f", "completed_at": "2026-04-03T19:59:55.659323+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fe66c902", "short_cell_id": "aa84e15f", "completed_at": "2026-04-05T06:46:14.389007+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f437a754", "short_cell_id": "aa84e15f", "completed_at": "2026-04-05T06:46:36.359954+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6f157de1", "short_cell_id": "aa84e15f", "completed_at": "2026-04-05T06:47:20.748761+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aec24c80", "short_cell_id": "e85710ae", "completed_at": "2026-04-04T21:42:12.786363+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f451b3e8", "short_cell_id": "e85710ae", "completed_at": "2026-04-04T21:58:29.900236+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "59fdb0fc", "short_cell_id": "e85710ae", "completed_at": "2026-04-04T21:57:36.969571+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on", "short_id": "dcbf6400", "short_cell_id": "223b50c4", "completed_at": "2026-04-06T11:12:05.708346+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on", "short_id": "b13fad58", "short_cell_id": "223b50c4", "completed_at": "2026-04-06T11:13:25.219305+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "cbd2d1e2", "short_cell_id": "0318813b", "completed_at": "2026-04-06T17:28:58.615487+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "f76992f1", "short_cell_id": "db2b4edd", "completed_at": "2026-04-06T17:41:07.598957+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "413c1f93", "short_cell_id": "23a09071", "completed_at": "2026-04-06T17:35:26.899056+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9a9774f0", "short_cell_id": "19154aeb", "completed_at": "2026-04-07T09:16:50.008872+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4a154f54", "short_cell_id": "19154aeb", "completed_at": "2026-04-07T09:24:49.967659+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "05601da1", "short_cell_id": "77325cdf", "completed_at": "2026-04-06T18:03:05.716164+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "a6d9fb9c", "short_cell_id": "ae538652", "completed_at": "2026-04-06T17:51:21.325858+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "062f01a0", "short_cell_id": "65bee0d9", "completed_at": "2026-04-03T20:37:10.970114+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "586c6b0a", "short_cell_id": "65bee0d9", "completed_at": "2026-04-03T20:37:09.900301+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71fa204f", "short_cell_id": "65bee0d9", "completed_at": "2026-04-03T20:35:10.729588+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "c151a356", "short_cell_id": "908ef15a", "completed_at": "2026-04-04T20:24:23.986627+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "short_id": "b29d066e", "short_cell_id": "7e05a3fa", "completed_at": "2026-04-03T18:37:03.014208+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "short_id": "1e13c72f", "short_cell_id": "7e05a3fa", "completed_at": "2026-04-03T18:37:23.108082+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "short_id": "56088123", "short_cell_id": "7e05a3fa", "completed_at": "2026-04-03T18:41:13.333121+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "1fdd595b", "short_cell_id": "c09eba14", "completed_at": "2026-04-04T20:17:47.627694+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bd51c309", "short_cell_id": "617518b5", "completed_at": "2026-04-05T21:43:50.904766+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d184704b", "short_cell_id": "617518b5", "completed_at": "2026-04-05T21:45:00.368788+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "135b43a3", "short_cell_id": "617518b5", "completed_at": "2026-04-05T21:48:01.764611+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "05536f95", "short_cell_id": "eec69acb", "completed_at": "2026-04-05T05:43:46.980046+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f8a57948", "short_cell_id": "eec69acb", "completed_at": "2026-04-05T05:44:43.169610+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "69bb8919", "short_cell_id": "eec69acb", "completed_at": "2026-04-05T19:39:10.870002+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1f33a77b", "short_cell_id": "ed58978d", "completed_at": "2026-04-06T20:41:11.429747+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f2b6194f", "short_cell_id": "ed58978d", "completed_at": "2026-04-06T20:45:51.496530+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "004dc1a5", "short_cell_id": "cf9cecb6", "completed_at": "2026-04-03T20:46:26.400041+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "95414e63", "short_cell_id": "cf9cecb6", "completed_at": "2026-04-03T20:44:48.686432+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "805f705d", "short_cell_id": "cf9cecb6", "completed_at": "2026-04-03T20:45:11.072141+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b51daba4", "short_cell_id": "7890cbf1", "completed_at": "2026-04-05T22:00:04.904763+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c946c543", "short_cell_id": "7890cbf1", "completed_at": "2026-04-05T19:56:29.452347+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "66d681fb", "short_cell_id": "7890cbf1", "completed_at": "2026-04-05T19:56:26.634211+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "671816fb", "short_cell_id": "44393a6b", "completed_at": "2026-04-05T06:15:30.738305+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4ba3ba91", "short_cell_id": "44393a6b", "completed_at": "2026-04-05T06:29:48.276358+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d7998414", "short_cell_id": "44393a6b", "completed_at": "2026-04-05T06:34:46.712959+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "50989696", "short_cell_id": "e1167533", "completed_at": "2026-04-06T18:41:25.871351+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1c26e1d8", "short_cell_id": "e1167533", "completed_at": "2026-04-06T18:42:36.778995+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "5141dfbf", "short_cell_id": "319ce6e6", "completed_at": "2026-04-06T18:35:00.836066+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "456d514c", "short_cell_id": "2bb465a6", "completed_at": "2026-04-06T18:17:54.895749+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa2674ac", "short_cell_id": "544657c2", "completed_at": "2026-04-07T09:30:26.934464+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c22109f8", "short_cell_id": "0d2ad982", "completed_at": "2026-04-07T10:02:13.411054+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "56afde62", "short_cell_id": "760f3512", "completed_at": "2026-04-07T06:34:27.157064+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6a743388", "short_cell_id": "1e1c37e8", "completed_at": "2026-04-06T21:38:13.008032+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "af5e84fc", "short_cell_id": "1e1c37e8", "completed_at": "2026-04-06T21:53:59.145803+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2f761815", "short_cell_id": "1e1c37e8", "completed_at": "2026-04-06T21:50:33.427319+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e0237626", "short_cell_id": "bc8005ed", "completed_at": "2026-04-06T21:23:54.623418+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "31a529dc", "short_cell_id": "ae2b0831", "completed_at": "2026-04-07T08:22:54.088254+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "6a018f5e", "short_cell_id": "d5a5cfd4", "completed_at": "2026-04-07T09:00:35.267937+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "ed0b0147", "short_cell_id": "d5a5cfd4", "completed_at": "2026-04-07T09:22:23.004446+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "e8d32946", "short_cell_id": "d3be6bfd", "completed_at": "2026-04-07T08:08:09.733116+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0a030357", "short_cell_id": "4e01e897", "completed_at": "2026-04-07T05:32:35.908202+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "11b37482", "short_cell_id": "86ee3001", "completed_at": "2026-04-07T01:48:05.623201+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63c0c2ab", "short_cell_id": "86ee3001", "completed_at": "2026-04-07T01:48:29.575707+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5da14018", "short_cell_id": "86ee3001", "completed_at": "2026-04-07T02:03:27.157428+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71d588fb", "short_cell_id": "28574c8b", "completed_at": "2026-04-06T18:29:47.257375+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "781c564b", "short_cell_id": "28574c8b", "completed_at": "2026-04-06T18:28:51.570857+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e9975cb", "short_cell_id": "28574c8b", "completed_at": "2026-04-06T18:30:32.314734+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "14486646", "short_cell_id": "cd8ad131", "completed_at": "2026-04-07T02:19:50.929133+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cbbff570", "short_cell_id": "c2189e69", "completed_at": "2026-04-03T19:53:09.020668+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "62c70152", "short_cell_id": "c2189e69", "completed_at": "2026-04-03T19:58:22.294680+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "80f1c3d5", "short_cell_id": "c2189e69", "completed_at": "2026-04-03T19:58:45.116530+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a30100ff", "short_cell_id": "12c78637", "completed_at": "2026-04-03T20:38:46.002214+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b61f8d31", "short_cell_id": "12c78637", "completed_at": "2026-04-03T20:40:37.227520+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "645e0c8f", "short_cell_id": "12c78637", "completed_at": "2026-04-03T20:42:05.384929+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "188635cc", "short_cell_id": "dfa5a30b", "completed_at": "2026-04-03T20:24:31.353521+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9805c24a", "short_cell_id": "dfa5a30b", "completed_at": "2026-04-03T20:28:08.059700+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5cdb89b6", "short_cell_id": "dfa5a30b", "completed_at": "2026-04-03T20:27:54.919444+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4949d521", "short_cell_id": "a811aed0", "completed_at": "2026-04-04T08:51:19.169046+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "165fb66f", "short_cell_id": "a811aed0", "completed_at": "2026-04-04T08:49:47.576163+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "af738eee", "short_cell_id": "a811aed0", "completed_at": "2026-04-03T20:36:54.110927+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "da87903f", "short_cell_id": "df90848f", "completed_at": "2026-04-03T20:36:43.094997+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "49012037", "short_cell_id": "df90848f", "completed_at": "2026-04-03T20:37:39.835213+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "4b5f4543", "short_cell_id": "df90848f", "completed_at": "2026-04-03T20:36:55.359971+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "37c69c60", "short_cell_id": "8aa41c7d", "completed_at": "2026-04-03T20:09:11.289803+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "77c2245c", "short_cell_id": "8aa41c7d", "completed_at": "2026-04-03T20:14:20.080371+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "fe986bd0", "short_cell_id": "8aa41c7d", "completed_at": "2026-04-03T20:13:47.758489+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "0d40c124", "short_cell_id": "a3b01525", "completed_at": "2026-04-03T20:17:45.103375+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "4d6ff9c9", "short_cell_id": "a3b01525", "completed_at": "2026-04-03T20:19:18.568908+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "1a5b849b", "short_cell_id": "a3b01525", "completed_at": "2026-04-03T20:22:17.063412+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "e01fbfa7", "short_cell_id": "0b3898cd", "completed_at": "2026-04-03T20:43:03.409815+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "bf5c394f", "short_cell_id": "0b3898cd", "completed_at": "2026-04-03T20:43:40.282743+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4bdcef51", "short_cell_id": "c1d9b10e", "completed_at": "2026-04-03T19:14:26.851817+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4db28f22", "short_cell_id": "c1d9b10e", "completed_at": "2026-04-03T19:11:09.488782+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6b13f05b", "short_cell_id": "c1d9b10e", "completed_at": "2026-04-03T19:12:36.135542+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "79675074", "short_cell_id": "25036421", "completed_at": "2026-04-06T14:25:53.194123+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c0d3fd49", "short_cell_id": "25036421", "completed_at": "2026-04-06T14:32:23.577315+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1fbd2965", "short_cell_id": "25036421", "completed_at": "2026-04-06T14:39:00.766938+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c9b0a190", "short_cell_id": "5f9e5779", "completed_at": "2026-04-03T20:36:23.056914+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c31b514e", "short_cell_id": "5f9e5779", "completed_at": "2026-04-03T20:39:17.839627+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8de1a3c2", "short_cell_id": "5f9e5779", "completed_at": "2026-04-03T20:41:00.673494+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9cd7d12a", "short_cell_id": "e56a5f02", "completed_at": "2026-04-05T06:41:08.954745+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "28abb304", "short_cell_id": "e56a5f02", "completed_at": "2026-04-05T06:41:10.237903+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "30bc2917", "short_cell_id": "e56a5f02", "completed_at": "2026-04-05T06:43:29.313548+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b9ce8930", "short_cell_id": "a49269f4", "completed_at": "2026-04-05T21:53:52.919817+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6c694ce9", "short_cell_id": "a49269f4", "completed_at": "2026-04-05T21:56:10.524909+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "83b4415b", "short_cell_id": "a49269f4", "completed_at": "2026-04-05T21:56:01.783667+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "37932d12", "short_cell_id": "530658e7", "completed_at": "2026-04-05T21:39:08.458092+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b53d8e6f", "short_cell_id": "530658e7", "completed_at": "2026-04-05T19:51:57.541240+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "53a9f7eb", "short_cell_id": "530658e7", "completed_at": "2026-04-05T21:39:11.755473+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71eeae15", "short_cell_id": "4fe590fd", "completed_at": "2026-04-05T21:39:35.240914+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "868a617f", "short_cell_id": "4fe590fd", "completed_at": "2026-04-05T21:39:36.296175+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8c6cb19c", "short_cell_id": "4fe590fd", "completed_at": "2026-04-05T21:38:59.162109+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "68a6572f", "short_cell_id": "b8c64391", "completed_at": "2026-04-05T21:43:19.539022+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "00b5cb8a", "short_cell_id": "b8c64391", "completed_at": "2026-04-05T21:44:34.164279+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "e2cb7f2b", "short_cell_id": "b8c64391", "completed_at": "2026-04-05T21:45:47.860125+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "4d465534", "short_cell_id": "7a01ba6c", "completed_at": "2026-04-05T19:47:23.981479+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "330aae5e", "short_cell_id": "7a01ba6c", "completed_at": "2026-04-05T19:48:02.042012+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "a59bd13b", "short_cell_id": "7a01ba6c", "completed_at": "2026-04-05T19:46:32.890087+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "6c4adfb0", "short_cell_id": "49742ef4", "completed_at": "2026-04-05T19:47:15.615085+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "e5199e69", "short_cell_id": "49742ef4", "completed_at": "2026-04-05T19:50:03.614395+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "c049fcf5", "short_cell_id": "49742ef4", "completed_at": "2026-04-05T21:43:37.223458+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "feb7d705", "short_cell_id": "ee583d05", "completed_at": "2026-04-05T21:55:43.014791+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "3c9d94f5", "short_cell_id": "ee583d05", "completed_at": "2026-04-05T21:59:19.246820+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "1a10ac67", "short_cell_id": "ee583d05", "completed_at": "2026-04-05T22:02:47.959579+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "67153cc8", "short_cell_id": "237c73d7", "completed_at": "2026-04-04T21:00:53.756188+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cde3d475", "short_cell_id": "237c73d7", "completed_at": "2026-04-04T21:22:28.664145+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b7e96026", "short_cell_id": "237c73d7", "completed_at": "2026-04-04T21:00:10.672556+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "886f5323", "short_cell_id": "806aac25", "completed_at": "2026-04-05T21:48:37.261266+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d6549fa2", "short_cell_id": "806aac25", "completed_at": "2026-04-05T21:49:18.421793+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6ccb77f1", "short_cell_id": "806aac25", "completed_at": "2026-04-05T21:49:30.178832+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "de9c4cc0", "short_cell_id": "954f1321", "completed_at": "2026-04-05T05:05:35.109321+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "536bc021", "short_cell_id": "954f1321", "completed_at": "2026-04-04T21:42:14.345914+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "92665abf", "short_cell_id": "954f1321", "completed_at": "2026-04-04T21:47:38.333466+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d2c1efc6", "short_cell_id": "3f832c89", "completed_at": "2026-04-05T06:05:12.119803+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b9741b31", "short_cell_id": "3f832c89", "completed_at": "2026-04-05T06:15:31.567926+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b683745c", "short_cell_id": "3f832c89", "completed_at": "2026-04-05T06:13:05.102138+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c13f247e", "short_cell_id": "a5028741", "completed_at": "2026-04-05T05:17:55.215229+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0f0815e0", "short_cell_id": "a5028741", "completed_at": "2026-04-05T05:23:27.382997+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f967cca3", "short_cell_id": "a5028741", "completed_at": "2026-04-05T05:13:05.553241+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9378b63f", "short_cell_id": "a7c3af5b", "completed_at": "2026-04-05T05:22:22.970786+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63d07a83", "short_cell_id": "a7c3af5b", "completed_at": "2026-04-05T05:24:29.542398+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "89f5d666", "short_cell_id": "a7c3af5b", "completed_at": "2026-04-05T05:36:44.507712+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "222c497a", "short_cell_id": "ace0bf41", "completed_at": "2026-04-05T05:36:50.072667+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "a0b46dce", "short_cell_id": "ace0bf41", "completed_at": "2026-04-05T05:27:37.222404+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "9d5d71af", "short_cell_id": "ace0bf41", "completed_at": "2026-04-05T05:42:22.469041+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "3bbc243e", "short_cell_id": "03009c4b", "completed_at": "2026-04-04T22:17:05.206931+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "ada76b96", "short_cell_id": "03009c4b", "completed_at": "2026-04-05T19:29:03.407545+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "3ca73775", "short_cell_id": "03009c4b", "completed_at": "2026-04-04T22:18:43.621863+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "225f2763", "short_cell_id": "df15ce64", "completed_at": "2026-04-05T05:18:02.207544+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "0bee082b", "short_cell_id": "df15ce64", "completed_at": "2026-04-05T05:17:28.821271+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "81d1772b", "short_cell_id": "df15ce64", "completed_at": "2026-04-05T05:04:55.065204+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "f91e3319", "short_cell_id": "834205e1", "completed_at": "2026-04-05T06:17:00.182240+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "6a1b6728", "short_cell_id": "834205e1", "completed_at": "2026-04-05T06:20:34.617227+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "5a0dcfdc", "short_cell_id": "834205e1", "completed_at": "2026-04-05T06:24:33.410085+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f333a385", "short_cell_id": "841f3ccb", "completed_at": "2026-04-04T21:04:34.885122+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "edfd3f04", "short_cell_id": "841f3ccb", "completed_at": "2026-04-04T21:36:41.721861+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "dec59666", "short_cell_id": "841f3ccb", "completed_at": "2026-04-04T21:11:17.256644+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "81d56cf5", "short_cell_id": "cbd24a46", "completed_at": "2026-04-06T14:57:48.837614+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6a78fb22", "short_cell_id": "6d2a2231", "completed_at": "2026-04-05T19:38:54.914546+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4b3f7365", "short_cell_id": "6d2a2231", "completed_at": "2026-04-05T19:38:55.252420+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa4f71b7", "short_cell_id": "6d2a2231", "completed_at": "2026-04-05T05:58:46.410223+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "961a7131", "short_cell_id": "0e35a83a", "completed_at": "2026-04-06T18:30:02.568907+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "299b6c41", "short_cell_id": "da9c7a0e", "completed_at": "2026-04-07T07:09:02.374757+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0693e74d", "short_cell_id": "da9c7a0e", "completed_at": "2026-04-07T07:07:55.192621+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "255de2c3", "short_cell_id": "da9c7a0e", "completed_at": "2026-04-07T07:13:33.658784+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7a348b81", "short_cell_id": "0a7c4811", "completed_at": "2026-04-04T08:31:26.255450+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8fe72fce", "short_cell_id": "0a7c4811", "completed_at": "2026-04-04T08:28:47.315460+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8932f117", "short_cell_id": "f9702928", "completed_at": "2026-04-05T06:48:25.182566+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "52f8ab88", "short_cell_id": "f9702928", "completed_at": "2026-04-05T06:48:58.365562+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d6187c89", "short_cell_id": "f9702928", "completed_at": "2026-04-05T06:50:57.420728+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a1f49ced", "short_cell_id": "123941c1", "completed_at": "2026-04-04T21:47:01.274994+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "414139b2", "short_cell_id": "123941c1", "completed_at": "2026-04-04T22:00:40.897695+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ad21bf3b", "short_cell_id": "123941c1", "completed_at": "2026-04-04T21:56:38.633500+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ea686a12", "short_cell_id": "1a05a1cb", "completed_at": "2026-04-06T18:34:08.575979+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa02f9f7", "short_cell_id": "1a05a1cb", "completed_at": "2026-04-06T18:33:38.621190+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7c1248e2", "short_cell_id": "c5dd26c2", "completed_at": "2026-04-07T07:31:19.574335+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c924670c", "short_cell_id": "c5dd26c2", "completed_at": "2026-04-07T07:32:19.471427+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off", "short_id": "0feabf41", "short_cell_id": "d95f230a", "completed_at": "2026-04-06T11:14:52.292482+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off", "short_id": "4c7db3b9", "short_cell_id": "d95f230a", "completed_at": "2026-04-06T11:12:52.023205+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off", "short_id": "40f9a902", "short_cell_id": "d95f230a", "completed_at": "2026-04-06T11:14:09.847134+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e2e04e75", "short_cell_id": "9503631a", "completed_at": "2026-04-03T20:03:41.571216+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b04257bc", "short_cell_id": "9503631a", "completed_at": "2026-04-03T20:05:07.170256+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9b0e0479", "short_cell_id": "9503631a", "completed_at": "2026-04-03T20:09:11.887288+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "daaf1998", "short_cell_id": "08ff16dc", "completed_at": "2026-04-05T19:45:24.239737+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f3f3cd51", "short_cell_id": "08ff16dc", "completed_at": "2026-04-05T06:52:50.645410+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bdd519b4", "short_cell_id": "08ff16dc", "completed_at": "2026-04-05T19:46:38.063853+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "92501938", "short_cell_id": "19f28e41", "completed_at": "2026-04-05T05:12:08.035213+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "12f4a113", "short_cell_id": "19f28e41", "completed_at": "2026-04-04T21:53:14.676366+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6031abcf", "short_cell_id": "19f28e41", "completed_at": "2026-04-04T22:11:07.374754+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d179f825", "short_cell_id": "1fbc3a23", "completed_at": "2026-04-06T18:35:22.981284+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7e61c670", "short_cell_id": "db24182c", "completed_at": "2026-04-03T19:50:12.863462+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6b33ee07", "short_cell_id": "db24182c", "completed_at": "2026-04-03T19:52:07.304632+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "89be04d9", "short_cell_id": "db24182c", "completed_at": "2026-04-03T19:54:56.953646+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "59e8da6e", "short_cell_id": "ebb6cad3", "completed_at": "2026-04-05T06:42:14.154311+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f501a861", "short_cell_id": "ebb6cad3", "completed_at": "2026-04-05T06:46:45.312262+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9720d53e", "short_cell_id": "ebb6cad3", "completed_at": "2026-04-05T06:43:08.609342+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5d88e9c7", "short_cell_id": "6ac26553", "completed_at": "2026-04-04T21:34:54.215164+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "20dc3752", "short_cell_id": "6ac26553", "completed_at": "2026-04-04T21:37:35.722817+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4905874d", "short_cell_id": "6ac26553", "completed_at": "2026-04-04T21:36:09.154037+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "short_id": "1e3f4cdb", "short_cell_id": "7a06a9c5", "completed_at": "2026-04-06T11:05:30.834325+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "short_id": "c7b0bb6b", "short_cell_id": "7a06a9c5", "completed_at": "2026-04-06T11:05:09.726350+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "short_id": "bbb70053", "short_cell_id": "7a06a9c5", "completed_at": "2026-04-06T11:09:25.622402+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "77966846", "short_cell_id": "8ef8eab3", "completed_at": "2026-04-03T18:49:38.321463+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f6426aae", "short_cell_id": "8ef8eab3", "completed_at": "2026-04-03T18:49:48.529132+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f86cae22", "short_cell_id": "8ef8eab3", "completed_at": "2026-04-03T18:53:35.752453+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b13700b7", "short_cell_id": "f5072fb0", "completed_at": "2026-04-06T18:41:35.644789+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8d789027", "short_cell_id": "2b182faa", "completed_at": "2026-04-07T10:10:13.270815+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8bb02c7c", "short_cell_id": "5e972b6c", "completed_at": "2026-04-03T20:40:57.297570+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b1b1424a", "short_cell_id": "5e972b6c", "completed_at": "2026-04-03T20:41:10.072835+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d9899ed8", "short_cell_id": "5e972b6c", "completed_at": "2026-04-03T20:38:44.044823+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "19d7fd45", "short_cell_id": "6b4a8281", "completed_at": "2026-04-05T21:58:12.019082+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e10bfa92", "short_cell_id": "6b4a8281", "completed_at": "2026-04-05T21:50:07.704550+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b060d46a", "short_cell_id": "6b4a8281", "completed_at": "2026-04-05T21:54:23.048656+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7d8d44d6", "short_cell_id": "728557e2", "completed_at": "2026-04-05T06:02:26.660332+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "837ded2f", "short_cell_id": "728557e2", "completed_at": "2026-04-05T06:03:58.503906+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f9d8871e", "short_cell_id": "728557e2", "completed_at": "2026-04-05T05:58:32.199764+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off", "short_id": "195c0c1f", "short_cell_id": "54e291c2", "completed_at": "2026-04-06T11:07:24.704209+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off", "short_id": "18bcc1ad", "short_cell_id": "54e291c2", "completed_at": "2026-04-06T11:06:39.450606+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off", "short_id": "93e8feea", "short_cell_id": "54e291c2", "completed_at": "2026-04-06T11:07:02.723357+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "short_id": "67825cfa", "short_cell_id": "b0ec2d7c", "completed_at": "2026-04-06T11:07:43.412285+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "short_id": "ccc32a02", "short_cell_id": "b0ec2d7c", "completed_at": "2026-04-06T11:06:57.859005+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "short_id": "edcf7c7c", "short_cell_id": "b0ec2d7c", "completed_at": "2026-04-06T11:04:14.817177+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T06:40:52.932185+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T07:00:02.695067+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:59:11.076296+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:59:32.351290+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:59:55.659323+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:46:14.389007+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:46:36.359954+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:47:20.748761+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:42:12.786363+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:58:29.900236+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:57:36.969571+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on", "completed_at": "2026-04-06T11:12:05.708346+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on", "completed_at": "2026-04-06T11:13:25.219305+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-06T17:28:58.615487+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-06T17:41:07.598957+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-06T17:35:26.899056+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T09:16:50.008872+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T09:24:49.967659+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-06T18:03:05.716164+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-06T17:51:21.325858+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:37:10.970114+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:37:09.900301+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:35:10.729588+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-04T20:24:23.986627+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "completed_at": "2026-04-03T18:37:03.014208+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "completed_at": "2026-04-03T18:37:23.108082+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "completed_at": "2026-04-03T18:41:13.333121+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-04T20:17:47.627694+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:43:50.904766+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:45:00.368788+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:48:01.764611+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:43:46.980046+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:44:43.169610+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:39:10.870002+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T20:41:11.429747+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T20:45:51.496530+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:46:26.400041+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:44:48.686432+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:45:11.072141+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T22:00:04.904763+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:56:29.452347+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:56:26.634211+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:15:30.738305+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:29:48.276358+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:34:46.712959+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:41:25.871351+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:42:36.778995+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-06T18:35:00.836066+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:17:54.895749+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T09:30:26.934464+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T10:02:13.411054+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T06:34:27.157064+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T21:38:13.008032+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T21:53:59.145803+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T21:50:33.427319+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T21:23:54.623418+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T08:22:54.088254+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T09:00:35.267937+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T09:22:23.004446+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-07T08:08:09.733116+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T05:32:35.908202+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T01:48:05.623201+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T01:48:29.575707+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T02:03:27.157428+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:29:47.257375+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:28:51.570857+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:30:32.314734+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T02:19:50.929133+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:53:09.020668+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:58:22.294680+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:58:45.116530+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:38:46.002214+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:40:37.227520+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:42:05.384929+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:24:31.353521+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:28:08.059700+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:27:54.919444+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T08:51:19.169046+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T08:49:47.576163+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:36:54.110927+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:36:43.094997+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:37:39.835213+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:36:55.359971+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-03T20:09:11.289803+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-03T20:14:20.080371+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-03T20:13:47.758489+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-03T20:17:45.103375+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-03T20:19:18.568908+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-03T20:22:17.063412+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-03T20:43:03.409815+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-03T20:43:40.282743+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:14:26.851817+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:11:09.488782+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:12:36.135542+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T14:25:53.194123+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T14:32:23.577315+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T14:39:00.766938+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:36:23.056914+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:39:17.839627+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:41:00.673494+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:41:08.954745+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:41:10.237903+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:43:29.313548+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:53:52.919817+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:56:10.524909+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:56:01.783667+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:39:08.458092+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:51:57.541240+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:39:11.755473+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:39:35.240914+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:39:36.296175+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:38:59.162109+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:43:19.539022+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:44:34.164279+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:45:47.860125+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-05T19:47:23.981479+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-05T19:48:02.042012+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-05T19:46:32.890087+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-05T19:47:15.615085+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-05T19:50:03.614395+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-05T21:43:37.223458+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-05T21:55:43.014791+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-05T21:59:19.246820+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-05T22:02:47.959579+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:00:53.756188+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:22:28.664145+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:00:10.672556+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:48:37.261266+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:49:18.421793+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:49:30.178832+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:05:35.109321+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:42:14.345914+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:47:38.333466+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:05:12.119803+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:15:31.567926+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:13:05.102138+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:17:55.215229+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:23:27.382997+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:13:05.553241+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:22:22.970786+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:24:29.542398+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:36:44.507712+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:36:50.072667+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:27:37.222404+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:42:22.469041+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-04T22:17:05.206931+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-05T19:29:03.407545+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "completed_at": "2026-04-04T22:18:43.621863+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-05T05:18:02.207544+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-05T05:17:28.821271+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "completed_at": "2026-04-05T05:04:55.065204+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-05T06:17:00.182240+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-05T06:20:34.617227+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "completed_at": "2026-04-05T06:24:33.410085+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:04:34.885122+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:36:41.721861+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:11:17.256644+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T14:57:48.837614+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:38:54.914546+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:38:55.252420+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:58:46.410223+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:30:02.568907+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T07:09:02.374757+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T07:07:55.192621+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T07:13:33.658784+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T08:31:26.255450+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T08:28:47.315460+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:48:25.182566+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:48:58.365562+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:50:57.420728+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:47:01.274994+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T22:00:40.897695+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:56:38.633500+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:34:08.575979+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:33:38.621190+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T07:31:19.574335+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T07:32:19.471427+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off", "completed_at": "2026-04-06T11:14:52.292482+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off", "completed_at": "2026-04-06T11:12:52.023205+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off", "completed_at": "2026-04-06T11:14:09.847134+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:03:41.571216+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:05:07.170256+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:09:11.887288+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:45:24.239737+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:52:50.645410+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T19:46:38.063853+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:12:08.035213+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:53:14.676366+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T22:11:07.374754+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:35:22.981284+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:50:12.863462+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:52:07.304632+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T19:54:56.953646+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:42:14.154311+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:46:45.312262+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:43:08.609342+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:34:54.215164+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:37:35.722817+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-04T21:36:09.154037+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "completed_at": "2026-04-06T11:05:30.834325+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "completed_at": "2026-04-06T11:05:09.726350+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "completed_at": "2026-04-06T11:09:25.622402+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T18:49:38.321463+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T18:49:48.529132+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T18:53:35.752453+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-06T18:41:35.644789+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-07T10:10:13.270815+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:40:57.297570+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:41:10.072835+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-03T20:38:44.044823+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:58:12.019082+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:50:07.704550+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "opus", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T21:54:23.048656+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:02:26.660332+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T06:03:58.503906+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "sonnet", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "completed_at": "2026-04-05T05:58:32.199764+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off", "completed_at": "2026-04-06T11:07:24.704209+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off", "completed_at": "2026-04-06T11:06:39.450606+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off", "completed_at": "2026-04-06T11:07:02.723357+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "completed_at": "2026-04-06T11:07:43.412285+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "completed_at": "2026-04-06T11:06:57.859005+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3", "task": "tetris", "model": "haiku", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "completed_at": "2026-04-06T11:04:14.817177+00:00"} diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 160 + "load_time_ms": 178 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.33, + "score": 0.33, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 15, + "cognitive_complexity": 129, + "lines_of_code": 983, + "duplication_pct": 6.6, + "tech_debt_minutes": 78, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.6 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 160 + "load_time_ms": 178 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 7 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 13, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 72 + "load_time_ms": 122 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 1019, + "duplication_pct": 6.7, + "tech_debt_minutes": 98, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 72 + "load_time_ms": 122 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -138,7 +138,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -201,17 +201,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "14 pieces placed during play session" + "detail": "21 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "3 line(s) cleared (grid-verified)" + "detail": "1 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 264" + "detail": "score changed from 0 to 336" }, { "name": "game_over", @@ -221,7 +221,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 35 pieces, no crashes" + "detail": "played for 30s, placed 47 pieces, no crashes" } ], "summary": { @@ -231,23 +231,23 @@ "score": 1 }, "gameplay": { - "pieces_placed": 35, - "lines_cleared": 3, - "max_score_observed": 264, + "pieces_placed": 47, + "lines_cleared": 1, + "max_score_observed": 336, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 997, + "frames": 812, "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 14, - "lines_cleared": 3, + "pieces_locked": 21, + "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 63 + "load_time_ms": 420 }, "accessibility": { "issues": [ @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.885, + "score": 0.885, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -78,17 +78,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "14 pieces placed during play session" + "detail": "21 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "3 line(s) cleared (grid-verified)" + "detail": "1 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 264" + "detail": "score changed from 0 to 336" }, { "name": "game_over", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 35 pieces, no crashes" + "detail": "played for 30s, placed 47 pieces, no crashes" } ], "summary": { @@ -108,23 +108,23 @@ "score": 1 }, "gameplay": { - "pieces_placed": 35, - "lines_cleared": 3, - "max_score_observed": 264, + "pieces_placed": 47, + "lines_cleared": 1, + "max_score_observed": 336, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 997, + "frames": 812, "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 14, - "lines_cleared": 3, + "pieces_locked": 21, + "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 63 + "load_time_ms": 420 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 3 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 13, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 35 + "load_time_ms": 62 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 2, + "cognitive_complexity": 0, + "lines_of_code": 554, + "duplication_pct": 0.0, + "tech_debt_minutes": 18, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.94 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 35 + "load_time_ms": 62 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 4 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 13, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 72 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 72 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -117,13 +117,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -138,7 +138,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -150,53 +150,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -226,9 +226,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -238,16 +238,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 203 + "load_time_ms": 161 }, "accessibility": { "issues": [ @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.355, + "score": 0.355, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 203 + "load_time_ms": 161 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 25, @@ -135,7 +135,7 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "z", "drop": "Space" }, "start_mechanism": "unknown", @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 146 + "load_time_ms": 104 }, "accessibility": { "issues": [ @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.47, + "score": 0.47, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -12,7 +12,7 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "z", "drop": "Space" }, "start_mechanism": "unknown", @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 146 + "load_time_ms": 104 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -117,13 +117,160 @@ }, "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": "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": "space", + "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 space" + }, + { + "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": "15 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 32 to 318" + }, + { + "name": "game_over", + "pass": false, + "detail": "could not trigger or detect game over via grid reader" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "2 console error(s), 0 play errors" + } + ], + "summary": { + "total": 16, + "passed": 13, + "failed": 3, + "score": 0.81 + }, + "gameplay": { + "pieces_placed": 17, + "lines_cleared": 1, + "max_score_observed": 318, + "play_duration_seconds": 6, + "errors_during_play": 0 + }, + "session": { + "frames": 672, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 15, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 0.97 + }, + "performance": { + "load_time_ms": 95 + }, + "accessibility": { + "issues": [], + "issue_count": 0, + "pass": true + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.77, + "score": 0.77, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -117,10 +117,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0, + "score": 0.06, "total": 16, - "passed": 0, - "failed": 16, + "passed": 1, + "failed": 15, "report": { "implementation": { "renderer": "unknown", @@ -138,7 +138,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 0 }, @@ -150,53 +150,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via space" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -226,9 +226,9 @@ ], "summary": { "total": 16, - "passed": 0, - "failed": 16, - "score": 0 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -238,7 +238,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 144 + "load_time_ms": 420 }, "accessibility": { "issues": [ @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.425, + "score": 0.425, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 2, + "cognitive_complexity": 109, + "lines_of_code": 629, + "duplication_pct": 0.0, + "tech_debt_minutes": 13, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.79 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 0 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via space" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 0, - "failed": 16, - "score": 0 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 144 + "load_time_ms": 420 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 2 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 45, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 83 + "load_time_ms": 560 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.43, + "score": 0.43, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 83 + "load_time_ms": 560 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 150 + "load_time_ms": 438 }, "accessibility": { "issues": [ @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 150 + "load_time_ms": 438 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 20, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 101 + "load_time_ms": 219 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.53, + "score": 0.53, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 0, + "cognitive_complexity": 0, + "lines_of_code": 775, + "duplication_pct": 0.0, + "tech_debt_minutes": 0, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 1.0 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 101 + "load_time_ms": 219 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3/eval_results.json @@ -91,10 +91,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.75 + "score": 0.4 }, "transcript_analysis": { "total_events": 83, @@ -245,7 +245,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 71 + "load_time_ms": 285 }, "accessibility": { "issues": [], @@ -254,10 +254,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.425, + "score": 0.425, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 2, + "cognitive_complexity": 0, + "lines_of_code": 605, + "duplication_pct": 0.0, + "tech_debt_minutes": 9, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.79 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 71 + "load_time_ms": 285 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -93,10 +93,10 @@ }, "html_validation": { "valid": false, - "errors": 7 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 10, @@ -252,7 +252,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 124 + "load_time_ms": 501 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.35, + "score": 0.35, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 1056, + "duplication_pct": 6.5, + "tech_debt_minutes": 86, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 124 + "load_time_ms": 501 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -93,10 +93,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 60, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 104 + "load_time_ms": 205 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 1165, + "duplication_pct": 5.9, + "tech_debt_minutes": 91, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 104 + "load_time_ms": 205 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -245,7 +245,7 @@ "errors_during_play": 0 }, "session": { - "frames": 955, + "frames": 891, "events_count": 11, "pieces_spawned": 1, "pieces_locked": 17, @@ -256,7 +256,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 38 + "load_time_ms": 461 }, "accessibility": { "issues": [ @@ -268,10 +268,19 @@ } } }, - "outcome_score": 0.47, - "score": 0.47, + "outcome_score": 0.795, + "score": 0.795, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 5, + "cognitive_complexity": 126, + "lines_of_code": 975, + "duplication_pct": 8.8, + "tech_debt_minutes": 53, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 955, + "frames": 891, "events_count": 11, "pieces_spawned": 1, "pieces_locked": 17, @@ -126,7 +126,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 38 + "load_time_ms": 461 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 78 + "load_time_ms": 102 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.37, + "score": 0.37, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 4, + "cognitive_complexity": 163, + "lines_of_code": 961, + "duplication_pct": 6.8, + "tech_debt_minutes": 63, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.68 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 78 + "load_time_ms": 102 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 159 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 41, + "cognitive_complexity": 228, + "lines_of_code": 1432, + "duplication_pct": 18.8, + "tech_debt_minutes": 71, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 159 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -122,13 +122,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 0 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 194 + }, + "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": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 32, + "cognitive_complexity": 310, + "lines_of_code": 2313, + "duplication_pct": 47.5, + "tech_debt_minutes": 116, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,9 +15,9 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "unknown", "score_element_found": true, - "grid_confidence": 1 + "grid_confidence": 0 }, "tests": [ { @@ -27,110 +27,111 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", - "pass": true, - "detail": "grid state changed after 5s with no input (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_left", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "rotate", - "pass": true, - "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", - "pass": true, - "detail": "rotation confirmed but could not identify individual piece types" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "hard_drop", - "pass": true, - "detail": "piece immediately dropped to bottom (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "piece_locks", - "pass": true, - "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) detected at top of grid" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", - "pass": true, - "detail": "9 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", - "pass": true, - "detail": "score changed from 0 to 148" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top (grid-verified)" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 30 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { - "pieces_placed": 30, - "lines_cleared": 1, - "max_score_observed": 148, - "play_duration_seconds": 30, + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 981, - "events_count": 11, - "pieces_spawned": 1, - "pieces_locked": 9, - "lines_cleared": 1, - "piece_types_seen": [ - "unknown" - ], - "grid_read_success_rate": 1 + "frames": 0, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 54 + "load_time_ms": 194 }, "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 70 + "load_time_ms": 159 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.355, + "score": 0.355, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 35, + "cognitive_complexity": 179, + "lines_of_code": 1323, + "duplication_pct": 4.9, + "tech_debt_minutes": 104, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 70 + "load_time_ms": 159 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -138,9 +138,9 @@ "height": 120 }, "controls": { - "left": "a", - "right": "d", - "down": "s", + "left": "ArrowLeft", + "right": "ArrowRight", + "down": "ArrowDown", "rotate": "z", "drop": "Space" }, @@ -253,7 +253,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 104 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.19, + "score": 0.19, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -9,9 +9,9 @@ "height": 120 }, "controls": { - "left": "a", - "right": "d", - "down": "s", + "left": "ArrowLeft", + "right": "ArrowRight", + "down": "ArrowDown", "rotate": "z", "drop": "Space" }, @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 104 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -250,7 +250,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 34 + "load_time_ms": 66 }, "accessibility": { "issues": [], @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 13, + "cognitive_complexity": 65, + "lines_of_code": 812, + "duplication_pct": 2.5, + "tech_debt_minutes": 26, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.75 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 34 + "load_time_ms": 66 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -227,7 +227,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 32 pieces, no crashes" + "detail": "played for 30s, placed 22 pieces, no crashes" } ], "summary": { @@ -237,14 +237,14 @@ "score": 0.81 }, "gameplay": { - "pieces_placed": 32, + "pieces_placed": 22, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 980, + "frames": 905, "events_count": 10, "pieces_spawned": 0, "pieces_locked": 7, @@ -253,7 +253,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 58 + "load_time_ms": 101 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.405, - "score": 0.405, + "outcome_score": 0.68, + "score": 0.68, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 32 pieces, no crashes" + "detail": "played for 30s, placed 22 pieces, no crashes" } ], "summary": { @@ -108,14 +108,14 @@ "score": 0.81 }, "gameplay": { - "pieces_placed": 32, + "pieces_placed": 22, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 980, + "frames": 905, "events_count": 10, "pieces_spawned": 0, "pieces_locked": 7, @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 58 + "load_time_ms": 101 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -245,7 +245,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 55 + "load_time_ms": 216 }, "accessibility": { "issues": [], @@ -254,10 +254,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 55 + "load_time_ms": 216 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 92 + "load_time_ms": 102 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 92 + "load_time_ms": 102 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_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": 80, @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 41 + "load_time_ms": 37 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 3, + "vulnerabilities": 0, + "code_smells": 10, + "cognitive_complexity": 153, + "lines_of_code": 1237, + "duplication_pct": 47.4, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 41 + "load_time_ms": 37 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3/eval_results.json @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 67 + "load_time_ms": 27 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 67 + "load_time_ms": 27 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -253,7 +253,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 56 + "load_time_ms": 59 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.355, + "score": 0.355, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 56 + "load_time_ms": 59 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.49, + "score": 0.49, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,13 +121,163 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.94, + "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 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": "27 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 452" + }, + { + "name": "game_over", + "pass": true, + "detail": "game stopped after stacking to top" + }, + { + "name": "playable_30s", + "pass": true, + "detail": "played for 30s, placed 49 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 15, + "failed": 1, + "score": 0.94 + }, + "gameplay": { + "pieces_placed": 49, + "lines_cleared": 0, + "max_score_observed": 452, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 993, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 27, + "lines_cleared": 0, + "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": 0.915, + "score": 0.915, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "enter", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via enter" + "detail": "started via anykey" }, { "name": "auto_drop", @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 98 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "enter", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via enter" + "detail": "started via anykey" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 98 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -136,10 +136,10 @@ "height": 96 }, "controls": { - "left": "ArrowLeft", - "right": "ArrowRight", - "down": "ArrowDown", - "rotate": "x", + "left": "a", + "right": "d", + "down": "s", + "rotate": "w", "drop": "Space" }, "start_mechanism": "unknown", @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 226 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.37, + "score": 0.37, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -9,10 +9,10 @@ "height": 96 }, "controls": { - "left": "ArrowLeft", - "right": "ArrowRight", - "down": "ArrowDown", - "rotate": "x", + "left": "a", + "right": "d", + "down": "s", + "rotate": "w", "drop": "Space" }, "start_mechanism": "unknown", @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 226 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 171 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 171 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.88, + "score": 0.94, "total": 16, - "passed": 14, - "failed": 2, + "passed": 15, + "failed": 1, "report": { "implementation": { "renderer": "canvas", @@ -219,31 +219,31 @@ }, { "name": "game_over", - "pass": false, - "detail": "could not trigger or detect game over via grid reader" + "pass": true, + "detail": "game stopped after stacking to top (grid-verified)" }, { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 43 pieces, no crashes" + "detail": "played for 30s, placed 45 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 15, + "failed": 1, + "score": 0.94 }, "gameplay": { - "pieces_placed": 43, + "pieces_placed": 45, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 901, - "events_count": 9, + "frames": 830, + "events_count": 10, "pieces_spawned": 1, "pieces_locked": 21, "lines_cleared": 1, @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 136 + "load_time_ms": 86 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.44, - "score": 0.44, + "outcome_score": 0.835, + "score": 0.835, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -92,31 +92,31 @@ }, { "name": "game_over", - "pass": false, - "detail": "could not trigger or detect game over via grid reader" + "pass": true, + "detail": "game stopped after stacking to top (grid-verified)" }, { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 43 pieces, no crashes" + "detail": "played for 30s, placed 45 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 15, + "failed": 1, + "score": 0.94 }, "gameplay": { - "pieces_placed": 43, + "pieces_placed": 45, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 901, - "events_count": 9, + "frames": 830, + "events_count": 10, "pieces_spawned": 1, "pieces_locked": 21, "lines_cleared": 1, @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 136 + "load_time_ms": 86 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 1 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 163 + }, + "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": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 15, + "cognitive_complexity": 248, + "lines_of_code": 1391, + "duplication_pct": 29.6, + "tech_debt_minutes": 111, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,104 +27,104 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via space" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", "pass": false, - "detail": "only 0 piece(s) detected, need at least 3" + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", "pass": false, - "detail": "score stayed at 0" + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 10 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 5, - "failed": 11, - "score": 0.31 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { - "pieces_placed": 10, - "lines_cleared": 1, + "pieces_placed": 0, + "lines_cleared": 0, "max_score_observed": 0, - "play_duration_seconds": 30, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1195, - "events_count": 2, + "frames": 0, + "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, - "lines_cleared": 1, + "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 23 + "load_time_ms": 163 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/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": "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "24 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 44 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 15, + "failed": 1, + "score": 0.94 + }, + "gameplay": { + "pieces_placed": 44, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1029, + "events_count": 11, + "pieces_spawned": 1, + "pieces_locked": 24, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 31 + }, + "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": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 21, + "cognitive_complexity": 226, + "lines_of_code": 1212, + "duplication_pct": 32.9, + "tech_debt_minutes": 98, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -255,7 +255,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 141 + "load_time_ms": 160 }, "accessibility": { "issues": [ @@ -267,10 +267,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 141 + "load_time_ms": 160 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -267,10 +267,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 123 + "load_time_ms": 178 }, "accessibility": { "issues": [], @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 18, + "cognitive_complexity": 99, + "lines_of_code": 939, + "duplication_pct": 0.0, + "tech_debt_minutes": 50, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.75 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 123 + "load_time_ms": 178 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -120,11 +120,11 @@ "score": 1.0 }, "gameplay_bot": { - "pass": true, - "score": 1, + "pass": false, + "score": 0.81, "total": 16, - "passed": 16, - "failed": 0, + "passed": 13, + "failed": 3, "report": { "implementation": { "renderer": "canvas", @@ -142,7 +142,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -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", @@ -205,17 +205,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "20 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "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": true, - "detail": "score changed from 0 to 396" + "detail": "score changed from 0 to 434" }, { "name": "game_over", @@ -225,35 +225,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 32 pieces, no crashes" + "detail": "played for 30s, placed 43 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 13, + "failed": 3, + "score": 0.81 }, "gameplay": { - "pieces_placed": 32, - "lines_cleared": 1, - "max_score_observed": 396, + "pieces_placed": 43, + "lines_cleared": 0, + "max_score_observed": 434, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 902, - "events_count": 11, + "frames": 834, + "events_count": 8, "pieces_spawned": 1, - "pieces_locked": 20, - "lines_cleared": 1, - "piece_types_seen": [ - "unknown" - ], + "pieces_locked": 22, + "lines_cleared": 0, + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 53 + "load_time_ms": 96 }, "accessibility": { "issues": [ @@ -265,10 +263,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.835, + "score": 0.835, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -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", @@ -78,17 +78,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "20 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "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": true, - "detail": "score changed from 0 to 396" + "detail": "score changed from 0 to 434" }, { "name": "game_over", @@ -98,35 +98,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 32 pieces, no crashes" + "detail": "played for 30s, placed 43 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 13, + "failed": 3, + "score": 0.81 }, "gameplay": { - "pieces_placed": 32, - "lines_cleared": 1, - "max_score_observed": 396, + "pieces_placed": 43, + "lines_cleared": 0, + "max_score_observed": 434, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 902, - "events_count": 11, + "frames": 834, + "events_count": 8, "pieces_spawned": 1, - "pieces_locked": 20, - "lines_cleared": 1, - "piece_types_seen": [ - "unknown" - ], + "pieces_locked": 22, + "lines_cleared": 0, + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 53 + "load_time_ms": 96 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.49, + "score": 0.49, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -205,17 +205,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "16 pieces placed during play session" + "detail": "17 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "detail": "2 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 280" + "detail": "score changed from 8 to 310" }, { "name": "game_over", @@ -225,7 +225,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 36 pieces, no crashes" + "detail": "played for 30s, placed 37 pieces, no crashes" } ], "summary": { @@ -235,25 +235,23 @@ "score": 1 }, "gameplay": { - "pieces_placed": 36, - "lines_cleared": 1, - "max_score_observed": 280, + "pieces_placed": 37, + "lines_cleared": 2, + "max_score_observed": 310, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 960, - "events_count": 11, + "frames": 855, + "events_count": 9, "pieces_spawned": 1, - "pieces_locked": 16, - "lines_cleared": 1, - "piece_types_seen": [ - "unknown" - ], + "pieces_locked": 17, + "lines_cleared": 2, + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 78 + "load_time_ms": 79 }, "accessibility": { "issues": [ @@ -265,10 +263,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.835, + "score": 0.835, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -78,17 +78,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "16 pieces placed during play session" + "detail": "17 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "detail": "2 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 280" + "detail": "score changed from 8 to 310" }, { "name": "game_over", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 36 pieces, no crashes" + "detail": "played for 30s, placed 37 pieces, no crashes" } ], "summary": { @@ -108,25 +108,23 @@ "score": 1 }, "gameplay": { - "pieces_placed": 36, - "lines_cleared": 1, - "max_score_observed": 280, + "pieces_placed": 37, + "lines_cleared": 2, + "max_score_observed": 310, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 960, - "events_count": 11, + "frames": 855, + "events_count": 9, "pieces_spawned": 1, - "pieces_locked": 16, - "lines_cleared": 1, - "piece_types_seen": [ - "unknown" - ], + "pieces_locked": 17, + "lines_cleared": 2, + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 78 + "load_time_ms": 79 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 127 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 127 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via button" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 86 + "load_time_ms": 277 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via button" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 86 + "load_time_ms": 277 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { "renderer": "unknown", @@ -142,7 +142,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": false, "grid_confidence": 0 }, @@ -154,53 +154,53 @@ }, { "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": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,7 +242,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 67 + "load_time_ms": 127 }, "accessibility": { "issues": [ @@ -262,10 +262,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.19, + "score": 0.19, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": false, "grid_confidence": 0 }, @@ -27,53 +27,53 @@ }, { "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": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 67 + "load_time_ms": 127 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 76 + "load_time_ms": 147 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 26, + "cognitive_complexity": 208, + "lines_of_code": 1418, + "duplication_pct": 21.7, + "tech_debt_minutes": 94, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 76 + "load_time_ms": 147 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 70 + "load_time_ms": 111 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 8, + "cognitive_complexity": 212, + "lines_of_code": 1334, + "duplication_pct": 33.4, + "tech_debt_minutes": 40, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 70 + "load_time_ms": 111 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json @@ -252,7 +252,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 107 + "load_time_ms": 116 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 30, + "cognitive_complexity": 248, + "lines_of_code": 1341, + "duplication_pct": 35.0, + "tech_debt_minutes": 142, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 107 + "load_time_ms": 116 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -246,7 +246,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 39 + "load_time_ms": 97 }, "accessibility": { "issues": [], @@ -255,10 +255,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 10, + "cognitive_complexity": 174, + "lines_of_code": 1020, + "duplication_pct": 21.1, + "tech_debt_minutes": 43, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 39 + "load_time_ms": 97 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 37 + "load_time_ms": 86 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 20, + "cognitive_complexity": 216, + "lines_of_code": 1381, + "duplication_pct": 26.7, + "tech_debt_minutes": 68, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 37 + "load_time_ms": 86 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -248,7 +248,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 39 + "load_time_ms": 105 }, "accessibility": { "issues": [], @@ -257,10 +257,10 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.06, + "score": 0.06, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "pass": false, + "error": "no output" } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 39 + "load_time_ms": 105 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -93,10 +93,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 66, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 50 + "load_time_ms": 100 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 1144, + "duplication_pct": 6.0, + "tech_debt_minutes": 102, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 50 + "load_time_ms": 100 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -248,7 +248,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 119 + "load_time_ms": 42 }, "accessibility": { "issues": [], @@ -257,10 +257,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 4, + "vulnerabilities": 0, + "code_smells": 78, + "cognitive_complexity": 968, + "lines_of_code": 5627, + "duplication_pct": 53.3, + "tech_debt_minutes": 697, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 119 + "load_time_ms": 42 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 124 + "load_time_ms": 108 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 127, + "cognitive_complexity": 1271, + "lines_of_code": 5704, + "duplication_pct": 58.5, + "tech_debt_minutes": 984, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 124 + "load_time_ms": 108 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 120 + "load_time_ms": 165 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.355, + "score": 0.355, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 37, + "cognitive_complexity": 322, + "lines_of_code": 2039, + "duplication_pct": 3.1, + "tech_debt_minutes": 245, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 120 + "load_time_ms": 165 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -253,7 +253,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 87 + "load_time_ms": 66 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 168, + "lines_of_code": 1004, + "duplication_pct": 6.6, + "tech_debt_minutes": 39, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.62 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 87 + "load_time_ms": 66 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,13 +121,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 0 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 222 + }, + "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": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 230, + "lines_of_code": 1401, + "duplication_pct": 25.8, + "tech_debt_minutes": 66, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 222 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json @@ -123,13 +123,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -141,10 +141,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "ArrowUp", + "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -156,53 +156,53 @@ }, { "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": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -232,9 +232,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -244,16 +244,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 77 + "load_time_ms": 484 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.19, + "score": 0.19, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 18, + "cognitive_complexity": 240, + "lines_of_code": 1604, + "duplication_pct": 32.1, + "tech_debt_minutes": 52, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -12,10 +12,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "ArrowUp", + "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "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": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 77 + "load_time_ms": 484 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json @@ -253,7 +253,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 116 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.255, + "score": 0.255, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 12, + "cognitive_complexity": 136, + "lines_of_code": 976, + "duplication_pct": 6.9, + "tech_debt_minutes": 52, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.45 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 116 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json @@ -123,13 +123,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -144,9 +144,9 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": true, - "grid_confidence": 0 + "grid_confidence": 1 }, "tests": [ { @@ -156,53 +156,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -232,9 +232,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -244,16 +244,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 106 + "load_time_ms": 129 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.29, + "score": 0.29, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 7, + "cognitive_complexity": 136, + "lines_of_code": 1126, + "duplication_pct": 5.9, + "tech_debt_minutes": 27, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.45 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,9 +15,9 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": true, - "grid_confidence": 0 + "grid_confidence": 1 }, "tests": [ { @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 106 + "load_time_ms": 129 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 74 + "load_time_ms": 150 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 13, + "cognitive_complexity": 132, + "lines_of_code": 1387, + "duplication_pct": 30.9, + "tech_debt_minutes": 36, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 74 + "load_time_ms": 150 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via enter" }, { "name": "auto_drop", @@ -205,7 +205,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "25 pieces placed during play session" + "detail": "20 pieces placed during play session" }, { "name": "line_clear", @@ -215,7 +215,7 @@ { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 404" + "detail": "score changed from 0 to 360" }, { "name": "game_over", @@ -225,7 +225,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 53 pieces, no crashes" + "detail": "played for 30s, placed 47 pieces, no crashes" } ], "summary": { @@ -235,17 +235,17 @@ "score": 1 }, "gameplay": { - "pieces_placed": 53, + "pieces_placed": 47, "lines_cleared": 4, - "max_score_observed": 404, + "max_score_observed": 360, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 926, + "frames": 871, "events_count": 11, "pieces_spawned": 1, - "pieces_locked": 25, + "pieces_locked": 20, "lines_cleared": 4, "piece_types_seen": [ "unknown" @@ -253,7 +253,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 154 + "load_time_ms": 213 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.705, + "score": 0.705, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 6, + "vulnerabilities": 0, + "code_smells": 3, + "cognitive_complexity": 187, + "lines_of_code": 1116, + "duplication_pct": 5.9, + "tech_debt_minutes": 35, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.41 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via enter" }, { "name": "auto_drop", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "25 pieces placed during play session" + "detail": "20 pieces placed during play session" }, { "name": "line_clear", @@ -88,7 +88,7 @@ { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 404" + "detail": "score changed from 0 to 360" }, { "name": "game_over", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 53 pieces, no crashes" + "detail": "played for 30s, placed 47 pieces, no crashes" } ], "summary": { @@ -108,17 +108,17 @@ "score": 1 }, "gameplay": { - "pieces_placed": 53, + "pieces_placed": 47, "lines_cleared": 4, - "max_score_observed": 404, + "max_score_observed": 360, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 926, + "frames": 871, "events_count": 11, "pieces_spawned": 1, - "pieces_locked": 25, + "pieces_locked": 20, "lines_cleared": 4, "piece_types_seen": [ "unknown" @@ -126,7 +126,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 154 + "load_time_ms": 213 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -120,14 +120,161 @@ "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": "dom", + "grid_detected": true, + "grid_bounds": { + "x": 391, + "y": 57, + "width": 306, + "height": 606 + }, + "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "26 pieces placed during play session" + }, + { + "name": "line_clear", + "pass": true, + "detail": "14 line(s) cleared (grid-verified)" + }, + { + "name": "score_changes", + "pass": true, + "detail": "score changed from 0 to 986" + }, + { + "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": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 42, + "lines_cleared": 14, + "max_score_observed": 986, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1012, + "events_count": 20, + "pieces_spawned": 1, + "pieces_locked": 26, + "lines_cleared": 14, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 30 + }, + "accessibility": { + "issues": [ + "no focusable elements" + ], + "issue_count": 1, + "pass": false + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.8, + "score": 0.8, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 215, + "lines_of_code": 1153, + "duplication_pct": 7.8, + "tech_debt_minutes": 97, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.6 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 67 + "load_time_ms": 109 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 8, + "cognitive_complexity": 326, + "lines_of_code": 2054, + "duplication_pct": 27.4, + "tech_debt_minutes": 39, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 67 + "load_time_ms": 109 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +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": 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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "20 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 42 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 15, + "failed": 1, + "score": 0.94 + }, + "gameplay": { + "pieces_placed": 42, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1005, + "events_count": 11, + "pieces_spawned": 1, + "pieces_locked": 20, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], + "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" + ], + "issue_count": 3, + "pass": false + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.78, + "score": 0.78, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 239, + "lines_of_code": 1250, + "duplication_pct": 5.5, + "tech_debt_minutes": 74, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.62 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 50 + "load_time_ms": 66 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 5, + "cognitive_complexity": 212, + "lines_of_code": 1344, + "duplication_pct": 5.0, + "tech_debt_minutes": 63, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 50 + "load_time_ms": 66 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -246,7 +246,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 43 + "load_time_ms": 105 }, "accessibility": { "issues": [], @@ -255,10 +255,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.33, + "score": 0.33, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 24, + "cognitive_complexity": 203, + "lines_of_code": 1270, + "duplication_pct": 7.1, + "tech_debt_minutes": 75, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.6 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 43 + "load_time_ms": 105 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 64 + "load_time_ms": 85 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.365, + "score": 0.365, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 312, + "lines_of_code": 1614, + "duplication_pct": 4.1, + "tech_debt_minutes": 149, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.67 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 64 + "load_time_ms": 85 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 24 + "load_time_ms": 64 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.515, + "score": 0.515, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 24 + "load_time_ms": 64 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=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, @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 19, + "cognitive_complexity": 170, + "lines_of_code": 1190, + "duplication_pct": 34.0, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -96,10 +96,10 @@ }, "html_validation": { "valid": false, - "errors": 2 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.7 + "score": 0.35 }, "transcript_analysis": { "total_events": 73, @@ -125,13 +125,164 @@ }, "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: [I]" + }, + { + "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": "20 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 49 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 14, + "failed": 2, + "score": 0.88 + }, + "gameplay": { + "pieces_placed": 49, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 982, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 20, + "lines_cleared": 1, + "piece_types_seen": [ + "I" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 26 + }, + "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": 0.565, + "score": 0.565, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 8, + "cognitive_complexity": 154, + "lines_of_code": 1169, + "duplication_pct": 28.7, + "tech_debt_minutes": 18, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 42 + "load_time_ms": 197 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 42 + "load_time_ms": 197 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -124,13 +124,160 @@ }, "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "9 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 27 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 11, + "failed": 5, + "score": 0.69 + }, + "gameplay": { + "pieces_placed": 27, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1108, + "events_count": 7, + "pieces_spawned": 1, + "pieces_locked": 9, + "lines_cleared": 1, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 21 + }, + "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": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -256,7 +256,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 100 + "load_time_ms": 181 }, "accessibility": { "issues": [ @@ -268,10 +268,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 100 + "load_time_ms": 181 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 85 + "load_time_ms": 78 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 13, + "cognitive_complexity": 116, + "lines_of_code": 932, + "duplication_pct": 25.5, + "tech_debt_minutes": 36, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 85 + "load_time_ms": 78 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -209,7 +209,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "16 pieces placed during play session" + "detail": "4 pieces placed during play session" }, { "name": "line_clear", @@ -229,7 +229,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 40 pieces, no crashes" + "detail": "played for 30s, placed 29 pieces, no crashes" } ], "summary": { @@ -239,23 +239,25 @@ "score": 0.88 }, "gameplay": { - "pieces_placed": 40, + "pieces_placed": 29, "lines_cleared": 0, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 940, - "events_count": 9, + "frames": 342, + "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 16, + "pieces_locked": 4, "lines_cleared": 0, - "piece_types_seen": [], - "grid_read_success_rate": 1 + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 0.96 }, "performance": { - "load_time_ms": 97 + "load_time_ms": 139 }, "accessibility": { "issues": [], @@ -264,10 +266,19 @@ } } }, - "outcome_score": 0.44, - "score": 0.44, + "outcome_score": 0.565, + "score": 0.565, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "16 pieces placed during play session" + "detail": "4 pieces placed during play session" }, { "name": "line_clear", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 40 pieces, no crashes" + "detail": "played for 30s, placed 29 pieces, no crashes" } ], "summary": { @@ -108,23 +108,25 @@ "score": 0.88 }, "gameplay": { - "pieces_placed": 40, + "pieces_placed": 29, "lines_cleared": 0, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 940, - "events_count": 9, + "frames": 342, + "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 16, + "pieces_locked": 4, "lines_cleared": 0, - "piece_types_seen": [], - "grid_read_success_rate": 1 + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 0.96 }, "performance": { - "load_time_ms": 97 + "load_time_ms": 139 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -257,7 +257,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 87 + "load_time_ms": 107 }, "accessibility": { "issues": [ @@ -269,10 +269,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 87 + "load_time_ms": 107 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 60 + "load_time_ms": 68 }, "accessibility": { "issues": [], @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 368, + "lines_of_code": 1318, + "duplication_pct": 37.7, + "tech_debt_minutes": 201, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 60 + "load_time_ms": 68 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 125 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 125 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json @@ -207,7 +207,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "10 pieces placed during play session" + "detail": "11 pieces placed during play session" }, { "name": "line_clear", @@ -244,16 +244,18 @@ "errors_during_play": 0 }, "session": { - "frames": 955, - "events_count": 8, + "frames": 874, + "events_count": 9, "pieces_spawned": 1, - "pieces_locked": 10, + "pieces_locked": 11, "lines_cleared": 1, - "piece_types_seen": [], + "piece_types_seen": [ + "unknown" + ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 49 + "load_time_ms": 71 }, "accessibility": { "issues": [ @@ -264,10 +266,19 @@ } } }, - "outcome_score": 0.405, - "score": 0.405, + "outcome_score": 0.755, + "score": 0.755, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "10 pieces placed during play session" + "detail": "11 pieces placed during play session" }, { "name": "line_clear", @@ -115,16 +115,18 @@ "errors_during_play": 0 }, "session": { - "frames": 955, - "events_count": 8, + "frames": 874, + "events_count": 9, "pieces_spawned": 1, - "pieces_locked": 10, + "pieces_locked": 11, "lines_cleared": 1, - "piece_types_seen": [], + "piece_types_seen": [ + "unknown" + ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 49 + "load_time_ms": 71 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json @@ -253,7 +253,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 69 + "load_time_ms": 140 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 69 + "load_time_ms": 140 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json @@ -255,7 +255,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 46 + "load_time_ms": 65 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 46 + "load_time_ms": 65 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json @@ -124,10 +124,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { "renderer": "unknown", @@ -145,7 +145,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 0 }, @@ -157,53 +157,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via anykey" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -233,9 +233,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -245,7 +245,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 80 + "load_time_ms": 151 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.19, + "score": 0.19, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 0 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via anykey" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 80 + "load_time_ms": 151 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json @@ -250,7 +250,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 37 + "load_time_ms": 252 }, "accessibility": { "issues": [], @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 37 + "load_time_ms": 252 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json @@ -250,7 +250,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 134 + "load_time_ms": 103 }, "accessibility": { "issues": [], @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 134 + "load_time_ms": 103 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json @@ -145,7 +145,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -218,7 +218,7 @@ { "name": "score_changes", "pass": true, - "detail": "score changed from 31 to 173" + "detail": "score changed from 34 to 183" }, { "name": "game_over", @@ -228,7 +228,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 17 pieces, no crashes" + "detail": "played for 30s, placed 16 pieces, no crashes" } ], "summary": { @@ -238,14 +238,14 @@ "score": 0.94 }, "gameplay": { - "pieces_placed": 17, + "pieces_placed": 16, "lines_cleared": 1, - "max_score_observed": 173, + "max_score_observed": 183, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 1000, + "frames": 931, "events_count": 9, "pieces_spawned": 1, "pieces_locked": 6, @@ -254,7 +254,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 189 + "load_time_ms": 191 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.47, - "score": 0.47, + "outcome_score": 0.87, + "score": 0.87, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -88,7 +88,7 @@ { "name": "score_changes", "pass": true, - "detail": "score changed from 31 to 173" + "detail": "score changed from 34 to 183" }, { "name": "game_over", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 17 pieces, no crashes" + "detail": "played for 30s, placed 16 pieces, no crashes" } ], "summary": { @@ -108,14 +108,14 @@ "score": 0.94 }, "gameplay": { - "pieces_placed": 17, + "pieces_placed": 16, "lines_cleared": 1, - "max_score_observed": 173, + "max_score_observed": 183, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 1000, + "frames": 931, "events_count": 9, "pieces_spawned": 1, "pieces_locked": 6, @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 189 + "load_time_ms": 191 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json @@ -267,10 +267,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json @@ -123,13 +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": "could not verify piece locking via grid reader" + }, + { + "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 0 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 10 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 5, + "failed": 11, + "score": 0.31 + }, + "gameplay": { + "pieces_placed": 10, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1180, + "events_count": 2, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 1, + "piece_types_seen": [], + "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": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -250,7 +250,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 97 + "load_time_ms": 165 }, "accessibility": { "issues": [], @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.33, + "score": 0.33, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 83, + "lines_of_code": 663, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 97 + "load_time_ms": 165 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json @@ -123,14 +123,164 @@ "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": "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": 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": "19 pieces placed during play session" + }, + { + "name": "line_clear", + "pass": true, + "detail": "4 line(s) cleared (grid-verified)" + }, + { + "name": "score_changes", + "pass": true, + "detail": "score changed from 0 to 80" + }, + { + "name": "game_over", + "pass": true, + "detail": "game stopped after stacking to top (grid-verified)" + }, + { + "name": "playable_30s", + "pass": true, + "detail": "played for 30s, placed 35 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 35, + "lines_cleared": 4, + "max_score_observed": 80, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 799, + "events_count": 14, + "pieces_spawned": 1, + "pieces_locked": 19, + "lines_cleared": 4, + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 156 + }, + "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": 0.875, + "score": 0.875, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -78,55 +78,55 @@ { "name": "multiple_pieces", "pass": true, - "detail": "18 pieces placed during play session" + "detail": "19 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "detail": "4 line(s) cleared (grid-verified)" }, { "name": "score_changes", - "pass": false, - "detail": "score stayed at 0" + "pass": true, + "detail": "score changed from 0 to 80" }, { "name": "game_over", "pass": true, - "detail": "game stopped after stacking to top" + "detail": "game stopped after stacking to top (grid-verified)" }, { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 38 pieces, no crashes" + "detail": "played for 30s, placed 35 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 15, - "failed": 1, - "score": 0.94 + "passed": 16, + "failed": 0, + "score": 1 }, "gameplay": { - "pieces_placed": 38, - "lines_cleared": 1, - "max_score_observed": 0, + "pieces_placed": 35, + "lines_cleared": 4, + "max_score_observed": 80, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 1060, - "events_count": 11, + "frames": 799, + "events_count": 14, "pieces_spawned": 1, - "pieces_locked": 18, - "lines_cleared": 1, + "pieces_locked": 19, + "lines_cleared": 4, "piece_types_seen": [ "unknown" ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 23 + "load_time_ms": 156 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 126 + "load_time_ms": 216 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 126 + "load_time_ms": 216 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -125,13 +125,153 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "grid_detected": false, + "grid_bounds": null, + "controls": { + "left": "ArrowLeft", + "right": "ArrowRight", + "down": "ArrowDown", + "rotate": "ArrowUp", + "drop": "Space" + }, + "start_mechanism": "unknown", + "score_element_found": false, + "grid_confidence": 0 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 151 + }, + "accessibility": { + "issues": [], + "issue_count": 0, + "pass": true + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 146 + "load_time_ms": 151 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -207,7 +207,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 18 piece(s) detected, need at least 3" + "detail": "only 10 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -227,7 +227,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 44 pieces, no crashes" + "detail": "played for 30s, placed 25 pieces, no crashes" } ], "summary": { @@ -237,23 +237,23 @@ "score": 0.75 }, "gameplay": { - "pieces_placed": 44, + "pieces_placed": 25, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 873, + "frames": 899, "events_count": 9, "pieces_spawned": 0, - "pieces_locked": 18, + "pieces_locked": 10, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 88 + "load_time_ms": 182 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.375, - "score": 0.375, + "outcome_score": 0.675, + "score": 0.675, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 18 piece(s) detected, need at least 3" + "detail": "only 10 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 44 pieces, no crashes" + "detail": "played for 30s, placed 25 pieces, no crashes" } ], "summary": { @@ -108,23 +108,23 @@ "score": 0.75 }, "gameplay": { - "pieces_placed": 44, + "pieces_placed": 25, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 873, + "frames": 899, "events_count": 9, "pieces_spawned": 0, - "pieces_locked": 18, + "pieces_locked": 10, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 88 + "load_time_ms": 182 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 74 + "load_time_ms": 77 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 254, + "lines_of_code": 1622, + "duplication_pct": 24.7, + "tech_debt_minutes": 39, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 74 + "load_time_ms": 77 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -267,10 +267,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 31, + "cognitive_complexity": 200, + "lines_of_code": 1392, + "duplication_pct": 21.0, + "tech_debt_minutes": 118, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -123,10 +123,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { "renderer": "unknown", @@ -144,7 +144,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 0 }, @@ -156,53 +156,53 @@ }, { "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": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -232,9 +232,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -244,7 +244,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -253,7 +253,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 66 + "load_time_ms": 152 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 10, + "cognitive_complexity": 226, + "lines_of_code": 1445, + "duplication_pct": 32.0, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 0 }, @@ -27,53 +27,53 @@ }, { "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": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 66 + "load_time_ms": 152 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.345, - "score": 0.345, + "outcome_score": 0.76, + "score": 0.76, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -124,13 +124,163 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.88, + "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": 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": "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": true, + "detail": "score changed from 0 to 1" + }, + { + "name": "game_over", + "pass": true, + "detail": "game stopped after stacking to top" + }, + { + "name": "playable_30s", + "pass": true, + "detail": "played for 30s, placed 32 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 14, + "failed": 2, + "score": 0.88 + }, + "gameplay": { + "pieces_placed": 32, + "lines_cleared": 1, + "max_score_observed": 1, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1080, + "events_count": 10, + "pieces_spawned": 1, + "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": 0.715, + "score": 0.715, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 93 + "load_time_ms": 118 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.415, + "score": 0.415, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 93 + "load_time_ms": 118 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 59 + "load_time_ms": 53 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 59 + "load_time_ms": 53 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -93,10 +93,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 39, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 63 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.205, + "score": 0.205, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 63 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -252,7 +252,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 188 + "load_time_ms": 149 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 188 + "load_time_ms": 149 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,9 +142,9 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": true, - "grid_confidence": 0 + "grid_confidence": 1 }, "tests": [ { @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 62 + "load_time_ms": 156 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,9 +15,9 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": true, - "grid_confidence": 0 + "grid_confidence": 1 }, "tests": [ { @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 62 + "load_time_ms": 156 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -139,7 +139,7 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "ArrowUp", + "rotate": "x", "drop": "Space" }, "start_mechanism": "unknown", @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 148 + "load_time_ms": 155 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -12,7 +12,7 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "ArrowUp", + "rotate": "x", "drop": "Space" }, "start_mechanism": "unknown", @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 148 + "load_time_ms": 155 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -120,14 +120,162 @@ "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "19 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 0 to 462" + }, + { + "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": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 39, + "lines_cleared": 2, + "max_score_observed": 462, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1045, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 19, + "lines_cleared": 2, + "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": 0.895, + "score": 0.895, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -142,7 +142,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via anykey" }, { "name": "auto_drop", @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 107 + "load_time_ms": 171 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via anykey" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 107 + "load_time_ms": 171 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 101 + "load_time_ms": 302 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 101 + "load_time_ms": 302 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -121,13 +121,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 1 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 231 + }, + "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 not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,104 +27,104 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via auto" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", - "pass": true, - "detail": "grid state changed after 5s with no input (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_left", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "rotate", - "pass": true, - "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", - "pass": true, - "detail": "rotation confirmed but could not identify individual piece types" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "hard_drop", - "pass": true, - "detail": "piece immediately dropped to bottom (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "piece_locks", - "pass": true, - "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) detected at top of grid" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", - "pass": true, - "detail": "21 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "3 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", - "pass": true, - "detail": "score changed from 0 to 396" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 35 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { - "pieces_placed": 35, - "lines_cleared": 3, - "max_score_observed": 396, - "play_duration_seconds": 30, + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1062, - "events_count": 9, - "pieces_spawned": 1, - "pieces_locked": 21, - "lines_cleared": 3, + "frames": 0, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 34 + "load_time_ms": 231 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,161 @@ }, "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": "unknown", + "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": "button", + "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 button" + }, + { + "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": "could not verify piece locking via grid reader" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "could not detect new piece spawning at top via grid reader" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 2, + "failed": 14, + "score": 0.13 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "errors_during_play": 0 + }, + "session": { + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 168 + }, + "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": 0.43, + "score": 0.43, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "button", "score_element_found": true, "grid_confidence": 1 }, @@ -28,105 +28,103 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via button" }, { "name": "auto_drop", - "pass": true, - "detail": "grid state changed after 5s with no input (grid-verified)" + "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)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "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: [I]" + "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))" + "pass": false, + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) 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": "17 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", - "pass": true, - "detail": "score changed from 0 to 318" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 41 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { - "pieces_placed": 41, - "lines_cleared": 1, - "max_score_observed": 318, - "play_duration_seconds": 30, + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1024, - "events_count": 11, - "pieces_spawned": 1, - "pieces_locked": 17, - "lines_cleared": 1, - "piece_types_seen": [ - "I" - ], + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 24 + "load_time_ms": 168 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { "renderer": "unknown", @@ -142,7 +142,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 236 + "load_time_ms": 447 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 10, + "cognitive_complexity": 111, + "lines_of_code": 721, + "duplication_pct": 0.0, + "tech_debt_minutes": 23, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.5 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 236 + "load_time_ms": 447 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -120,14 +120,162 @@ "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": "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": "10 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 0 to 196" + }, + { + "name": "game_over", + "pass": true, + "detail": "game stopped after stacking to top" + }, + { + "name": "playable_30s", + "pass": true, + "detail": "played for 30s, placed 31 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 31, + "lines_cleared": 1, + "max_score_observed": 196, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1079, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 10, + "lines_cleared": 1, + "piece_types_seen": [], + "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": 0.805, + "score": 0.805, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { "renderer": "unknown", @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": false, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 113 + "load_time_ms": 72 }, "accessibility": { "issues": [ @@ -262,10 +262,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.475, + "score": 0.475, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 1, + "cognitive_complexity": 104, + "lines_of_code": 602, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": false, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 113 + "load_time_ms": 72 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 109 + "load_time_ms": 124 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.365, + "score": 0.365, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 126, + "lines_of_code": 621, + "duplication_pct": 0.0, + "tech_debt_minutes": 54, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.67 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 109 + "load_time_ms": 124 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json @@ -120,14 +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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "12 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 0 to 252" + }, + { + "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": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 22, + "lines_cleared": 2, + "max_score_observed": 252, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1073, + "events_count": 12, + "pieces_spawned": 1, + "pieces_locked": 12, + "lines_cleared": 2, + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 33 + }, + "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": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,161 @@ }, "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": 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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "22 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 0 to 362" + }, + { + "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": 14, + "failed": 2, + "score": 0.88 + }, + "gameplay": { + "pieces_placed": 47, + "lines_cleared": 1, + "max_score_observed": 362, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 995, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 22, + "lines_cleared": 1, + "piece_types_seen": [], + "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": 0.765, + "score": 0.765, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 83 + "load_time_ms": 217 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.205, + "score": 0.205, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 83 + "load_time_ms": 217 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json @@ -121,13 +121,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.13, + "total": 16, + "passed": 2, + "failed": 14, + "report": { + "implementation": { + "renderer": "unknown", + "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": "anykey", + "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 anykey" + }, + { + "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": "could not verify piece locking via grid reader" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "could not detect new piece spawning at top via grid reader" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 2, + "failed": 14, + "score": 0.13 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "errors_during_play": 0 + }, + "session": { + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 142 + }, + "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": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -28,27 +28,27 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via anykey" }, { "name": "auto_drop", - "pass": true, - "detail": "grid state changed after 5s with no input (grid-verified)" + "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)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "rotate", @@ -62,69 +62,69 @@ }, { "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))" + "pass": false, + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) 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": "14 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "4 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", - "pass": true, - "detail": "score changed from 0 to 224" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 38 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { - "pieces_placed": 38, - "lines_cleared": 4, - "max_score_observed": 224, - "play_duration_seconds": 30, + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1035, - "events_count": 9, - "pieces_spawned": 1, - "pieces_locked": 14, - "lines_cleared": 4, + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 20 + "load_time_ms": 142 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.865, + "score": 0.865, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json @@ -120,14 +120,162 @@ "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "19 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 0 to 378" + }, + { + "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": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 40, + "lines_cleared": 1, + "max_score_observed": 378, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1043, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 19, + "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": 0.91, + "score": 0.91, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 1, + "cognitive_complexity": 117, + "lines_of_code": 503, + "duplication_pct": 0.0, + "tech_debt_minutes": 28, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.82 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 42 + "load_time_ms": 114 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.245, + "score": 0.245, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 42 + "load_time_ms": 114 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -127,7 +127,7 @@ "failed": 14, "report": { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,9 +142,9 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "space", "score_element_found": true, - "grid_confidence": 1 + "grid_confidence": 0 }, "tests": [ { @@ -155,32 +155,32 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via space" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", @@ -190,12 +190,12 @@ { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 65 + "load_time_ms": 157 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,9 +15,9 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "space", "score_element_found": true, - "grid_confidence": 1 + "grid_confidence": 0 }, "tests": [ { @@ -28,32 +28,32 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via space" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", @@ -63,12 +63,12 @@ { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 65 + "load_time_ms": 157 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 57 + "load_time_ms": 119 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 57 + "load_time_ms": 119 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 112 + "load_time_ms": 118 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.475, + "score": 0.475, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 112 + "load_time_ms": 118 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -142,7 +142,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "anykey", + "start_mechanism": "button", "score_element_found": true, "grid_confidence": 1 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via anykey" + "detail": "started via button" }, { "name": "auto_drop", @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 115 + "load_time_ms": 128 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "anykey", + "start_mechanism": "button", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via anykey" + "detail": "started via button" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 115 + "load_time_ms": 128 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 101 + "load_time_ms": 104 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.385, + "score": 0.385, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 101 + "load_time_ms": 104 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -120,14 +120,162 @@ "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "15 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 0 to 360" + }, + { + "name": "game_over", + "pass": true, + "detail": "game stopped after stacking to top" + }, + { + "name": "playable_30s", + "pass": true, + "detail": "played for 30s, placed 24 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 24, + "lines_cleared": 2, + "max_score_observed": 360, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1063, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 15, + "lines_cleared": 2, + "piece_types_seen": [], + "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": 0.88, + "score": 0.88, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.49, + "score": 0.49, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -120,11 +120,11 @@ "score": 1.0 }, "gameplay_bot": { - "pass": false, - "score": 0.94, + "pass": true, + "score": 1, "total": 16, - "passed": 15, - "failed": 1, + "passed": 16, + "failed": 0, "report": { "implementation": { "renderer": "canvas", @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -205,17 +205,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "21 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "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 2 to 334" + "detail": "score changed from 0 to 386" }, { "name": "game_over", @@ -225,33 +225,35 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 48 pieces, no crashes" + "detail": "played for 30s, placed 47 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 15, - "failed": 1, - "score": 0.94 + "passed": 16, + "failed": 0, + "score": 1 }, "gameplay": { - "pieces_placed": 48, - "lines_cleared": 0, - "max_score_observed": 334, + "pieces_placed": 47, + "lines_cleared": 1, + "max_score_observed": 386, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 861, - "events_count": 9, + "frames": 787, + "events_count": 11, "pieces_spawned": 1, - "pieces_locked": 21, - "lines_cleared": 0, - "piece_types_seen": [], + "pieces_locked": 22, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 71 + "load_time_ms": 76 }, "accessibility": { "issues": [ @@ -263,10 +265,19 @@ } } }, - "outcome_score": 0.47, - "score": 0.47, + "outcome_score": 0.825, + "score": 0.825, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -78,17 +78,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "21 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "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 2 to 334" + "detail": "score changed from 0 to 386" }, { "name": "game_over", @@ -98,33 +98,35 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 48 pieces, no crashes" + "detail": "played for 30s, placed 47 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 15, - "failed": 1, - "score": 0.94 + "passed": 16, + "failed": 0, + "score": 1 }, "gameplay": { - "pieces_placed": 48, - "lines_cleared": 0, - "max_score_observed": 334, + "pieces_placed": 47, + "lines_cleared": 1, + "max_score_observed": 386, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 861, - "events_count": 9, + "frames": 787, + "events_count": 11, "pieces_spawned": 1, - "pieces_locked": 21, - "lines_cleared": 0, - "piece_types_seen": [], + "pieces_locked": 22, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 71 + "load_time_ms": 76 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -127,7 +127,7 @@ "failed": 14, "report": { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,9 +142,9 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "anykey", "score_element_found": true, - "grid_confidence": 1 + "grid_confidence": 0 }, "tests": [ { @@ -155,32 +155,32 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via anykey" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", @@ -190,12 +190,12 @@ { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 164 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.46, + "score": 0.46, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,9 +15,9 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "anykey", "score_element_found": true, - "grid_confidence": 1 + "grid_confidence": 0 }, "tests": [ { @@ -28,32 +28,32 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via anykey" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "grid reader unreliable, cannot verify auto-drop" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "grid reader unreliable, cannot verify movement" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "grid reader unreliable, cannot verify rotation" }, { "name": "all_pieces_rotate", @@ -63,12 +63,12 @@ { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "grid reader unreliable, cannot verify hard drop" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "grid reader unreliable, cannot verify piece locking" }, { "name": "new_piece_spawns", @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 13, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 164 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 133 + "load_time_ms": 100 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 133 + "load_time_ms": 100 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -92,10 +92,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.85 + "score": 0.5 }, "transcript_analysis": { "total_events": 79, @@ -246,7 +246,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 90 + "load_time_ms": 155 }, "accessibility": { "issues": [], @@ -255,10 +255,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.18, + "score": 0.18, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 90 + "load_time_ms": 155 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -93,10 +93,10 @@ }, "html_validation": { "valid": false, - "errors": 4 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.85 + "score": 0.5 }, "transcript_analysis": { "total_events": 74, @@ -122,13 +122,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.88, "total": 16, - "passed": 2, - "failed": 14, + "passed": 14, + "failed": 2, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -160,99 +160,99 @@ }, { "name": "auto_drop", - "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "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" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_right", - "pass": false, - "detail": "no grid change detected after key press" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_down", - "pass": false, - "detail": "no grid change detected after key press" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "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", - "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "pass": true, + "detail": "piece immediately dropped to bottom (grid-verified)" }, { "name": "piece_locks", - "pass": false, - "detail": "could not verify piece locking via grid reader" + "pass": true, + "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" }, { "name": "new_piece_spawns", - "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "pass": true, + "detail": "1 new piece(s) detected at top of grid" }, { "name": "multiple_pieces", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "21 pieces placed during play session" }, { "name": "line_clear", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "1 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": false, - "detail": "skipped: mechanics phase not met" + "detail": "score stayed at 0" }, { "name": "game_over", "pass": false, - "detail": "skipped: gameplay phase not met" + "detail": "could not trigger or detect game over via grid reader" }, { "name": "playable_30s", - "pass": false, - "detail": "skipped: gameplay phase not met" + "pass": true, + "detail": "played for 30s, placed 48 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 14, + "failed": 2, + "score": 0.88 }, "gameplay": { - "pieces_placed": 0, - "lines_cleared": 0, + "pieces_placed": 48, + "lines_cleared": 1, "max_score_observed": 0, - "play_duration_seconds": 0, + "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 15, - "events_count": 0, - "pieces_spawned": 0, - "pieces_locked": 0, - "lines_cleared": 0, + "frames": 782, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 21, + "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 33 + "load_time_ms": 151 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.715, + "score": 0.715, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -32,99 +32,99 @@ }, { "name": "auto_drop", - "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "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" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_right", - "pass": false, - "detail": "no grid change detected after key press" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_down", - "pass": false, - "detail": "no grid change detected after key press" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "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", - "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "pass": true, + "detail": "piece immediately dropped to bottom (grid-verified)" }, { "name": "piece_locks", - "pass": false, - "detail": "could not verify piece locking via grid reader" + "pass": true, + "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" }, { "name": "new_piece_spawns", - "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "pass": true, + "detail": "1 new piece(s) detected at top of grid" }, { "name": "multiple_pieces", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "21 pieces placed during play session" }, { "name": "line_clear", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "1 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": false, - "detail": "skipped: mechanics phase not met" + "detail": "score stayed at 0" }, { "name": "game_over", "pass": false, - "detail": "skipped: gameplay phase not met" + "detail": "could not trigger or detect game over via grid reader" }, { "name": "playable_30s", - "pass": false, - "detail": "skipped: gameplay phase not met" + "pass": true, + "detail": "played for 30s, placed 48 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 14, + "failed": 2, + "score": 0.88 }, "gameplay": { - "pieces_placed": 0, - "lines_cleared": 0, + "pieces_placed": 48, + "lines_cleared": 1, "max_score_observed": 0, - "play_duration_seconds": 0, + "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 15, - "events_count": 0, - "pieces_spawned": 0, - "pieces_locked": 0, - "lines_cleared": 0, + "frames": 782, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 21, + "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 33 + "load_time_ms": 151 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,162 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 1 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 155 + }, + "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": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -12,10 +12,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "ArrowUp", + "rotate": "x", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,104 +27,104 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via auto" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", - "pass": true, - "detail": "grid state changed after 5s with no input (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_left", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "rotate", - "pass": true, - "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", - "pass": true, - "detail": "rotation confirmed but could not identify individual piece types" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "hard_drop", - "pass": true, - "detail": "piece immediately dropped to bottom (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "piece_locks", - "pass": true, - "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) detected at top of grid" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", - "pass": true, - "detail": "19 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", - "pass": true, - "detail": "score changed from 0 to 372" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 30 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { - "pieces_placed": 30, - "lines_cleared": 1, - "max_score_observed": 372, - "play_duration_seconds": 30, + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1045, - "events_count": 9, - "pieces_spawned": 1, - "pieces_locked": 19, - "lines_cleared": 1, + "frames": 0, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 24 + "load_time_ms": 155 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -92,10 +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, @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via auto" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 97 + "load_time_ms": 163 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via auto" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 97 + "load_time_ms": 163 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 114 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.425, + "score": 0.425, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 114 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 70 + "load_time_ms": 151 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.49, + "score": 0.49, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 70 + "load_time_ms": 151 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 68 + "load_time_ms": 106 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.475, + "score": 0.475, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 68 + "load_time_ms": 106 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via anykey" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 62 + "load_time_ms": 97 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.385, + "score": 0.385, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "anykey", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via anykey" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 62 + "load_time_ms": 97 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -120,11 +120,11 @@ "score": 1.0 }, "gameplay_bot": { - "pass": true, - "score": 1, + "pass": false, + "score": 0.94, "total": 16, - "passed": 16, - "failed": 0, + "passed": 15, + "failed": 1, "report": { "implementation": { "renderer": "canvas", @@ -205,17 +205,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "25 pieces placed during play session" + "detail": "27 pieces placed during play session" }, { "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": true, - "detail": "score changed from 2 to 410" + "detail": "score changed from 0 to 454" }, { "name": "game_over", @@ -225,35 +225,35 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 42 pieces, no crashes" + "detail": "played for 30s, placed 54 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 15, + "failed": 1, + "score": 0.94 }, "gameplay": { - "pieces_placed": 42, - "lines_cleared": 1, - "max_score_observed": 410, + "pieces_placed": 54, + "lines_cleared": 0, + "max_score_observed": 454, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 873, - "events_count": 11, + "frames": 731, + "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 25, - "lines_cleared": 1, + "pieces_locked": 27, + "lines_cleared": 0, "piece_types_seen": [ "unknown" ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 60 + "load_time_ms": 101 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.76, + "score": 0.76, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -78,17 +78,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "25 pieces placed during play session" + "detail": "27 pieces placed during play session" }, { "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": true, - "detail": "score changed from 2 to 410" + "detail": "score changed from 0 to 454" }, { "name": "game_over", @@ -98,35 +98,35 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 42 pieces, no crashes" + "detail": "played for 30s, placed 54 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 15, + "failed": 1, + "score": 0.94 }, "gameplay": { - "pieces_placed": 42, - "lines_cleared": 1, - "max_score_observed": 410, + "pieces_placed": 54, + "lines_cleared": 0, + "max_score_observed": 454, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 873, - "events_count": 11, + "frames": 731, + "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 25, - "lines_cleared": 1, + "pieces_locked": 27, + "lines_cleared": 0, "piece_types_seen": [ "unknown" ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 60 + "load_time_ms": 101 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -120,14 +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": "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": 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": "20 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 0 to 298" + }, + { + "name": "game_over", + "pass": true, + "detail": "game stopped after stacking to top" + }, + { + "name": "playable_30s", + "pass": true, + "detail": "played for 30s, placed 32 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 32, + "lines_cleared": 1, + "max_score_observed": 298, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1020, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 20, + "lines_cleared": 1, + "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": 0.75, + "score": 0.75, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 92 + "load_time_ms": 177 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.255, + "score": 0.255, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 92 + "load_time_ms": 177 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/eval_results.json @@ -139,10 +139,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "z", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 0 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 115 + "load_time_ms": 183 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.44, + "score": 0.44, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -12,10 +12,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "z", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 0 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 115 + "load_time_ms": 183 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/eval_results.json @@ -92,10 +92,10 @@ }, "html_validation": { "valid": false, - "errors": 6 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 61, @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.88, + "score": 0.94, "total": 16, - "passed": 14, - "failed": 2, + "passed": 15, + "failed": 1, "report": { "implementation": { "renderer": "canvas", @@ -205,7 +205,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "21 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "name": "line_clear", @@ -214,8 +214,8 @@ }, { "name": "score_changes", - "pass": false, - "detail": "score stayed at 0" + "pass": true, + "detail": "score changed from 0 to 362" }, { "name": "game_over", @@ -225,35 +225,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 42 pieces, no crashes" + "detail": "played for 30s, placed 44 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 15, + "failed": 1, + "score": 0.94 }, "gameplay": { - "pieces_placed": 42, + "pieces_placed": 44, "lines_cleared": 0, - "max_score_observed": 0, + "max_score_observed": 362, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 876, - "events_count": 10, + "frames": 796, + "events_count": 9, "pieces_spawned": 1, - "pieces_locked": 21, + "pieces_locked": 22, "lines_cleared": 0, - "piece_types_seen": [ - "unknown" - ], + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 165 + "load_time_ms": 227 }, "accessibility": { "issues": [ @@ -265,10 +263,19 @@ } } }, - "outcome_score": 0.44, - "score": 0.44, + "outcome_score": 0.72, + "score": 0.72, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "21 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "name": "line_clear", @@ -87,8 +87,8 @@ }, { "name": "score_changes", - "pass": false, - "detail": "score stayed at 0" + "pass": true, + "detail": "score changed from 0 to 362" }, { "name": "game_over", @@ -98,35 +98,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 42 pieces, no crashes" + "detail": "played for 30s, placed 44 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 15, + "failed": 1, + "score": 0.94 }, "gameplay": { - "pieces_placed": 42, + "pieces_placed": 44, "lines_cleared": 0, - "max_score_observed": 0, + "max_score_observed": 362, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 876, - "events_count": 10, + "frames": 796, + "events_count": 9, "pieces_spawned": 1, - "pieces_locked": 21, + "pieces_locked": 22, "lines_cleared": 0, - "piece_types_seen": [ - "unknown" - ], + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 165 + "load_time_ms": 227 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 77 + "load_time_ms": 188 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.41, + "score": 0.41, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 77 + "load_time_ms": 188 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 37 + "load_time_ms": 98 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.365, + "score": 0.365, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "button", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via button" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 37 + "load_time_ms": 98 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 74 + "load_time_ms": 190 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 74 + "load_time_ms": 190 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 64 + "load_time_ms": 111 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.495, + "score": 0.495, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 64 + "load_time_ms": 111 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 91 + "load_time_ms": 125 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.33, + "score": 0.33, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 14, + "cognitive_complexity": 64, + "lines_of_code": 590, + "duplication_pct": 0.0, + "tech_debt_minutes": 46, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.6 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 91 + "load_time_ms": 125 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/eval_results.json @@ -128,7 +128,7 @@ "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -143,7 +143,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -156,7 +156,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -252,7 +252,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 152 + "load_time_ms": 196 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 152 + "load_time_ms": 196 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 73 + "load_time_ms": 141 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 73 + "load_time_ms": 141 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/eval_results.json @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via button" + "detail": "started via space" }, { "name": "auto_drop", @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 130 + "load_time_ms": 119 }, "accessibility": { "issues": [ @@ -268,10 +268,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 7, + "cognitive_complexity": 176, + "lines_of_code": 857, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via button" + "detail": "started via space" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 130 + "load_time_ms": 119 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via space" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 133 + "load_time_ms": 270 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.325, + "score": 0.325, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via space" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 133 + "load_time_ms": 270 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via space" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 76 + "load_time_ms": 162 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via space" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 76 + "load_time_ms": 162 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -122,13 +122,160 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 1 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "performance": { + "load_time_ms": 195 + }, + "accessibility": { + "issues": [ + "canvas without aria-label or role" + ], + "issue_count": 1, + "pass": false + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,104 +27,104 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via auto" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", - "pass": true, - "detail": "grid state changed after 5s with no input (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_left", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "rotate", - "pass": true, - "detail": "piece shape changed after rotate key (grid-verified, 1 rotation(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", - "pass": true, - "detail": "rotation confirmed but could not identify individual piece types" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "hard_drop", - "pass": true, - "detail": "piece immediately dropped to bottom (grid-verified)" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "piece_locks", - "pass": true, - "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) detected at top of grid" + "pass": false, + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", - "pass": true, - "detail": "16 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", - "pass": true, - "detail": "score changed from 0 to 284" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 37 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { - "pieces_placed": 37, - "lines_cleared": 1, - "max_score_observed": 284, - "play_duration_seconds": 30, + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1065, - "events_count": 10, - "pieces_spawned": 1, - "pieces_locked": 16, - "lines_cleared": 1, + "frames": 0, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 27 + "load_time_ms": 195 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -139,7 +139,7 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "ArrowUp", "drop": "Space" }, "start_mechanism": "unknown", @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 91 + "load_time_ms": 202 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.33, + "score": 0.33, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -12,7 +12,7 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "ArrowUp", "drop": "Space" }, "start_mechanism": "unknown", @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 91 + "load_time_ms": 202 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 85 + "load_time_ms": 248 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.41, + "score": 0.41, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 3, + "cognitive_complexity": 161, + "lines_of_code": 695, + "duplication_pct": 0.0, + "tech_debt_minutes": 70, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.76 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 85 + "load_time_ms": 248 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 61 + "load_time_ms": 154 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.42, + "score": 0.42, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 3, + "cognitive_complexity": 169, + "lines_of_code": 1078, + "duplication_pct": 5.8, + "tech_debt_minutes": 37, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.71 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 61 + "load_time_ms": 154 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -120,14 +120,161 @@ "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": "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": 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": "12 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 0 to 208" + }, + { + "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": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 35, + "lines_cleared": 1, + "max_score_observed": 208, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1051, + "events_count": 11, + "pieces_spawned": 1, + "pieces_locked": 12, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 20 + }, + "accessibility": { + "issues": [], + "issue_count": 0, + "pass": true + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.8, + "score": 0.8, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 144 + "load_time_ms": 285 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 144 + "load_time_ms": 285 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -94,10 +94,10 @@ }, "html_validation": { "valid": false, - "errors": 4 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.75 + "score": 0.4 }, "transcript_analysis": { "total_events": 82, @@ -268,10 +268,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.355, + "score": 0.355, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 2 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 29, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 69 + "load_time_ms": 104 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 18, + "cognitive_complexity": 52, + "lines_of_code": 965, + "duplication_pct": 7.0, + "tech_debt_minutes": 105, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 69 + "load_time_ms": 104 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 3 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 16, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 100 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 21, + "cognitive_complexity": 52, + "lines_of_code": 1042, + "duplication_pct": 6.5, + "tech_debt_minutes": 123, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 75 + "load_time_ms": 100 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 10 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 14, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 56 + "load_time_ms": 144 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 1015, + "duplication_pct": 6.7, + "tech_debt_minutes": 98, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 56 + "load_time_ms": 144 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 2 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 17, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 52 + "load_time_ms": 190 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 1103, + "duplication_pct": 6.3, + "tech_debt_minutes": 116, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 52 + "load_time_ms": 190 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -91,10 +91,10 @@ }, "html_validation": { "valid": false, - "errors": 5 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.75 + "score": 0.4 }, "transcript_analysis": { "total_events": 69, @@ -245,7 +245,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 80 }, "accessibility": { "issues": [], @@ -254,10 +254,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.485, + "score": 0.485, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 80 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 4 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 13, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 29 + "load_time_ms": 143 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.515, + "score": 0.515, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 29 + "load_time_ms": 143 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 19, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 67 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.47, + "score": 0.47, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 48 + "load_time_ms": 67 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 20, @@ -117,13 +117,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.06, + "total": 16, + "passed": 1, + "failed": 15, + "report": { + "implementation": { + "renderer": "unknown", + "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": "unknown", + "score_element_found": true, + "grid_confidence": 1 + }, + "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": "skipped: game did not start" + }, + { + "name": "move_left", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_right", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "move_down", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "all_pieces_rotate", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "hard_drop", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "piece_locks", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "skipped: game did not start" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 1, + "failed": 15, + "score": 0.06 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "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 + }, + "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": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -1,8 +1,13 @@ { "implementation": { "renderer": "unknown", - "grid_detected": false, - "grid_bounds": null, + "grid_detected": true, + "grid_bounds": { + "x": 0, + "y": 0, + "width": 300, + "height": 600 + }, "controls": { "left": "ArrowLeft", "right": "ArrowRight", @@ -11,7 +16,8 @@ "drop": "Space" }, "start_mechanism": "unknown", - "score_element_found": false + "score_element_found": true, + "grid_confidence": 1 }, "tests": [ { @@ -22,77 +28,77 @@ { "name": "game_starts", "pass": false, - "detail": "exception: page.screenshot: Timeout 10000ms exceeded.\nCall log:\n\u001b[2m - taking page screenshot\u001b[22m\n" + "detail": "could not start game with any mechanism" }, { "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": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "exception: page.waitForTimeout: Target page, context or browser has been closed" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "exception: page.screenshot: Target page, context or browser has been closed" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", "pass": false, - "detail": "exception: page.evaluate: Target page, context or browser has been closed" + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: gameplay phase not met" } ], "summary": { @@ -102,18 +108,30 @@ "score": 0.06 }, "gameplay": { - "pieces_placed": 4, + "pieces_placed": 0, "lines_cleared": 0, "max_score_observed": 0, "play_duration_seconds": 0, "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 + }, "performance": { - "load_time_ms": 773 + "load_time_ms": 66 }, "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 23, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 79 }, "accessibility": { "issues": [ @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 79 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 3 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 34, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 27 + "load_time_ms": 41 }, "accessibility": { "issues": [ @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.485, + "score": 0.485, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 27 + "load_time_ms": 41 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 43, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 39 + "load_time_ms": 50 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.5, + "score": 0.5, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 39 + "load_time_ms": 50 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -88,10 +88,10 @@ }, "html_validation": { "valid": false, - "errors": 3 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.95 + "score": 0.6 }, "transcript_analysis": { "total_events": 72, @@ -242,7 +242,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 81 + "load_time_ms": 32 }, "accessibility": { "issues": [], @@ -251,10 +251,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.365, + "score": 0.365, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 81 + "load_time_ms": 32 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -252,7 +252,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 84 + "load_time_ms": 77 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 26, + "cognitive_complexity": 216, + "lines_of_code": 1171, + "duplication_pct": 30.7, + "tech_debt_minutes": 115, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 84 + "load_time_ms": 77 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -252,7 +252,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 46 + "load_time_ms": 204 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.18, + "score": 0.18, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 27, + "cognitive_complexity": 132, + "lines_of_code": 995, + "duplication_pct": 6.7, + "tech_debt_minutes": 94, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.3 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 46 + "load_time_ms": 204 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -123,13 +123,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -144,7 +144,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -156,53 +156,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via button" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -232,9 +232,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -244,16 +244,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 102 + "load_time_ms": 145 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 244, + "lines_of_code": 1406, + "duplication_pct": 26.8, + "tech_debt_minutes": 39, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.57 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via button" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "piece did not move down in 5 seconds (grid-verified)" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "no grid change detected after key press" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "no shape change detected after rotate key" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "no grid change with bottom cells detected after hard drop key" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "could not verify piece locking via grid reader" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 15, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 1 + "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 102 + "load_time_ms": 145 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 111 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 12, + "cognitive_complexity": 234, + "lines_of_code": 1568, + "duplication_pct": 31.9, + "tech_debt_minutes": 83, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 111 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1/eval_results.json @@ -123,10 +123,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.88, + "score": 0.69, "total": 16, - "passed": 14, - "failed": 2, + "passed": 11, + "failed": 5, "report": { "implementation": { "renderer": "canvas", @@ -141,10 +141,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "z", + "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -157,7 +157,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via button" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -191,23 +191,23 @@ }, { "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": "1 new piece(s) 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": "12 pieces placed during play session" + "pass": false, + "detail": "only 11 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -227,33 +227,33 @@ { "name": "playable_30s", "pass": false, - "detail": "933 console error(s), 0 play errors" + "detail": "116 console error(s), 0 play errors" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 11, + "failed": 5, + "score": 0.69 }, "gameplay": { - "pieces_placed": 22, + "pieces_placed": 30, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 996, - "events_count": 10, - "pieces_spawned": 1, - "pieces_locked": 12, + "frames": 889, + "events_count": 8, + "pieces_spawned": 0, + "pieces_locked": 11, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 78 + "load_time_ms": 147 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.44, - "score": 0.44, + "outcome_score": 0.47, + "score": 0.47, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 3, + "vulnerabilities": 0, + "code_smells": 19, + "cognitive_complexity": 120, + "lines_of_code": 1984, + "duplication_pct": 63.5, + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1/gameplay-bot-report.json @@ -12,10 +12,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "z", + "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via button" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -62,23 +62,23 @@ }, { "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": "1 new piece(s) 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": "12 pieces placed during play session" + "pass": false, + "detail": "only 11 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -98,33 +98,33 @@ { "name": "playable_30s", "pass": false, - "detail": "933 console error(s), 0 play errors" + "detail": "116 console error(s), 0 play errors" } ], "summary": { "total": 16, - "passed": 14, - "failed": 2, - "score": 0.88 + "passed": 11, + "failed": 5, + "score": 0.69 }, "gameplay": { - "pieces_placed": 22, + "pieces_placed": 30, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 996, - "events_count": 10, - "pieces_spawned": 1, - "pieces_locked": 12, + "frames": 889, + "events_count": 8, + "pieces_spawned": 0, + "pieces_locked": 11, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 78 + "load_time_ms": 147 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2/eval_results.json @@ -90,10 +90,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.85 + "score": 0.5 }, "transcript_analysis": { "total_events": 108, @@ -244,7 +244,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 80 + "load_time_ms": 109 }, "accessibility": { "issues": [], @@ -253,10 +253,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.485, + "score": 0.485, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 3, + "cognitive_complexity": 0, + "lines_of_code": 673, + "duplication_pct": 0.0, + "tech_debt_minutes": 17, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.91 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 80 + "load_time_ms": 109 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3/eval_results.json @@ -125,13 +125,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.81, "total": 16, - "passed": 1, - "failed": 15, + "passed": 13, + "failed": 3, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -146,7 +146,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -158,104 +158,106 @@ }, { "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": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after 5s with no input (grid-verified)" }, { "name": "move_left", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_right", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_down", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "piece immediately dropped to bottom (grid-verified)" }, { "name": "piece_locks", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" }, { "name": "new_piece_spawns", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "1 new piece(s) detected at top of grid" }, { "name": "multiple_pieces", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "25 pieces placed during play session" }, { "name": "line_clear", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "2 line(s) cleared (grid-verified)" }, { "name": "score_changes", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "score changed from 0 to 100" }, { "name": "game_over", "pass": false, - "detail": "skipped: gameplay phase not met" + "detail": "could not trigger or detect game over via grid reader" }, { "name": "playable_30s", - "pass": false, - "detail": "skipped: gameplay phase not met" + "pass": true, + "detail": "played for 30s, placed 44 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 13, + "failed": 3, + "score": 0.81 }, "gameplay": { - "pieces_placed": 0, - "lines_cleared": 0, - "max_score_observed": 0, - "play_duration_seconds": 0, + "pieces_placed": 44, + "lines_cleared": 2, + "max_score_observed": 100, + "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": 760, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 25, + "lines_cleared": 2, + "piece_types_seen": [ + "I" + ], + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 112 + "load_time_ms": 200 }, "accessibility": { "issues": [ @@ -267,10 +269,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.79, + "score": 0.79, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 79, + "lines_of_code": 934, + "duplication_pct": 0.0, + "tech_debt_minutes": 8, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.77 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -27,104 +27,106 @@ }, { "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": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after 5s with no input (grid-verified)" }, { "name": "move_left", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_right", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_down", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "piece immediately dropped to bottom (grid-verified)" }, { "name": "piece_locks", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "filled cells persist at bottom (grid-verified, 2 lock event(s))" }, { "name": "new_piece_spawns", - "pass": false, - "detail": "skipped: game did not start" + "pass": true, + "detail": "1 new piece(s) detected at top of grid" }, { "name": "multiple_pieces", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "25 pieces placed during play session" }, { "name": "line_clear", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "2 line(s) cleared (grid-verified)" }, { "name": "score_changes", - "pass": false, - "detail": "skipped: mechanics phase not met" + "pass": true, + "detail": "score changed from 0 to 100" }, { "name": "game_over", "pass": false, - "detail": "skipped: gameplay phase not met" + "detail": "could not trigger or detect game over via grid reader" }, { "name": "playable_30s", - "pass": false, - "detail": "skipped: gameplay phase not met" + "pass": true, + "detail": "played for 30s, placed 44 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 13, + "failed": 3, + "score": 0.81 }, "gameplay": { - "pieces_placed": 0, - "lines_cleared": 0, - "max_score_observed": 0, - "play_duration_seconds": 0, + "pieces_placed": 44, + "lines_cleared": 2, + "max_score_observed": 100, + "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": 760, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 25, + "lines_cleared": 2, + "piece_types_seen": [ + "I" + ], + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 112 + "load_time_ms": 200 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=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, @@ -250,7 +250,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 77 }, "accessibility": { "issues": [], @@ -259,10 +259,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 47 + "load_time_ms": 77 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -95,10 +95,10 @@ }, "html_validation": { "valid": false, - "errors": 2 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.8 + "score": 0.45 }, "transcript_analysis": { "total_events": 86, @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 36 + "load_time_ms": 50 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 36 + "load_time_ms": 50 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 62 + "load_time_ms": 57 }, "accessibility": { "issues": [], @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 62 + "load_time_ms": 57 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,161 @@ }, "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": "unknown", + "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": "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": "could not verify piece locking via grid reader" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "could not detect new piece spawning at top via grid reader" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 2, + "failed": 14, + "score": 0.13 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "errors_during_play": 0 + }, + "session": { + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], + "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": 0.365, + "score": 0.365, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -28,27 +28,27 @@ { "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 (grid-verified)" + "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)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_right", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_down", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "rotate", @@ -62,71 +62,69 @@ }, { "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))" + "pass": false, + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", - "pass": true, - "detail": "1 new piece(s) 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": "19 pieces placed during play session" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", - "pass": true, - "detail": "1 line(s) cleared (grid-verified)" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", "pass": false, - "detail": "score stayed at 0" + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", "pass": false, - "detail": "could not trigger or detect game over" + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", - "pass": true, - "detail": "played for 30s, placed 43 pieces, no crashes" + "pass": false, + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 12, - "failed": 4, - "score": 0.75 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { - "pieces_placed": 43, - "lines_cleared": 1, + "pieces_placed": 0, + "lines_cleared": 0, "max_score_observed": 0, - "play_duration_seconds": 30, + "play_duration_seconds": 0, "errors_during_play": 0 }, "session": { - "frames": 1025, - "events_count": 9, - "pieces_spawned": 1, - "pieces_locked": 19, - "lines_cleared": 1, - "piece_types_seen": [ - "unknown" - ], + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 19 + "load_time_ms": 43 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,13 +121,148 @@ }, "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": "ArrowUp", + "drop": "Space" + }, + "start_mechanism": "space", + "score_element_found": true + }, + "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 in 5 seconds" + }, + { + "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": false, + "detail": "no change detected after key press" + }, + { + "name": "rotate", + "pass": false, + "detail": "no change detected after rotate key" + }, + { + "name": "all_pieces_rotate", + "pass": true, + "detail": "rotated: [unknown] 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": "grid accumulated cells: 22 -> 44" + }, + { + "name": "line_clear", + "pass": true, + "detail": "line cleared via strategic placement" + }, + { + "name": "score_changes", + "pass": true, + "detail": "score changed from 298 to 342" + }, + { + "name": "game_over", + "pass": false, + "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded." + }, + { + "name": "playable_30s", + "pass": false, + "detail": "exception: keyboard.press: Target page, context or browser has been closed" + } + ], + "summary": { + "total": 16, + "passed": 11, + "failed": 5, + "score": 0.69 + }, + "gameplay": { + "pieces_placed": 24, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 0, + "errors_during_play": 0 + }, + "performance": { + "load_time_ms": 257 + }, + "accessibility": { + "issues": [], + "issue_count": 0, + "pass": true + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.755, + "score": 0.755, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -121,13 +121,161 @@ }, "gameplay_bot": { "pass": false, - "score": 0, - "error": "Gameplay bot timed out after 180 seconds" + "score": 0.13, + "total": 16, + "passed": 2, + "failed": 14, + "report": { + "implementation": { + "renderer": "unknown", + "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": "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": "could not verify piece locking via grid reader" + }, + { + "name": "new_piece_spawns", + "pass": false, + "detail": "could not detect new piece spawning at top via grid reader" + }, + { + "name": "multiple_pieces", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "line_clear", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "score_changes", + "pass": false, + "detail": "skipped: mechanics phase not met" + }, + { + "name": "game_over", + "pass": false, + "detail": "skipped: gameplay phase not met" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "skipped: gameplay phase not met" + } + ], + "summary": { + "total": 16, + "passed": 2, + "failed": 14, + "score": 0.13 + }, + "gameplay": { + "pieces_placed": 0, + "lines_cleared": 0, + "max_score_observed": 0, + "play_duration_seconds": 0, + "errors_during_play": 0 + }, + "session": { + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 166 + }, + "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": 0.46, + "score": 0.46, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "canvas", + "renderer": "unknown", "grid_detected": true, "grid_bounds": { "x": 0, @@ -12,11 +12,12 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "ArrowUp", + "rotate": "x", "drop": "Space" }, - "start_mechanism": "button", - "score_element_found": true + "start_mechanism": "click_canvas", + "score_element_found": true, + "grid_confidence": 1 }, "tests": [ { @@ -27,98 +28,110 @@ { "name": "game_starts", "pass": true, - "detail": "started via button" + "detail": "started via click_canvas" }, { "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": 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": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", - "pass": true, - "detail": "filled cells persist at bottom" + "pass": false, + "detail": "could not verify piece locking via grid reader" }, { "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 -> 40" + "pass": false, + "detail": "skipped: mechanics phase not met" }, { "name": "line_clear", "pass": false, - "detail": "exception: keyboard.press: Test timeout of 180000ms exceeded." + "detail": "skipped: mechanics phase not met" }, { "name": "score_changes", "pass": false, - "detail": "could not read score element" + "detail": "skipped: mechanics phase not met" }, { "name": "game_over", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: gameplay phase not met" }, { "name": "playable_30s", "pass": false, - "detail": "exception: keyboard.press: Target page, context or browser has been closed" + "detail": "skipped: gameplay phase not met" } ], "summary": { "total": 16, - "passed": 12, - "failed": 4, - "score": 0.75 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { - "pieces_placed": 30, + "pieces_placed": 0, "lines_cleared": 0, "max_score_observed": 0, "play_duration_seconds": 0, "errors_during_play": 0 }, + "session": { + "frames": 15, + "events_count": 0, + "pieces_spawned": 0, + "pieces_locked": 0, + "lines_cleared": 0, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, "performance": { - "load_time_ms": 256 + "load_time_ms": 166 }, "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -139,10 +139,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "z", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "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": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 127 + "load_time_ms": 167 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.415, + "score": 0.415, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -12,10 +12,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "x", + "rotate": "z", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "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": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 127 + "load_time_ms": 167 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -92,10 +92,10 @@ }, "html_validation": { "valid": false, - "errors": 5 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.85 + "score": 0.5 }, "transcript_analysis": { "total_events": 47, @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { "renderer": "unknown", @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 0 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via button" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify auto-drop" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "grid reader unreliable, cannot verify rotation" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify hard drop" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "grid reader unreliable, cannot verify piece locking" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -242,7 +242,7 @@ "errors_during_play": 0 }, "session": { - "frames": 13, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 64 + "load_time_ms": 92 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.29, + "score": 0.29, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 6, + "cognitive_complexity": 156, + "lines_of_code": 813, + "duplication_pct": 0.0, + "tech_debt_minutes": 60, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.52 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "button", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 0 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via button" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify auto-drop" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "grid reader unreliable, cannot verify rotation" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify hard drop" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "grid reader unreliable, cannot verify piece locking" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 13, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 64 + "load_time_ms": 92 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via auto" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 121 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via auto" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 45 + "load_time_ms": 121 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -249,7 +249,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 82 + "load_time_ms": 74 }, "accessibility": { "issues": [], @@ -258,10 +258,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.18, + "score": 0.18, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 5, + "cognitive_complexity": 196, + "lines_of_code": 1133, + "duplication_pct": 38.6, + "tech_debt_minutes": 34, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.3 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 82 + "load_time_ms": 74 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -124,10 +124,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.75, + "score": 0.63, "total": 16, - "passed": 12, - "failed": 4, + "passed": 10, + "failed": 6, "report": { "implementation": { "renderer": "canvas", @@ -139,13 +139,13 @@ "height": 600 }, "controls": { - "left": "ArrowLeft", - "right": "ArrowRight", - "down": "ArrowDown", - "rotate": "ArrowUp", + "left": "a", + "right": "d", + "down": "s", + "rotate": "z", "drop": "Space" }, - "start_mechanism": "anykey", + "start_mechanism": "auto", "score_element_found": false, "grid_confidence": 1 }, @@ -167,13 +167,13 @@ }, { "name": "move_left", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_right", - "pass": false, - "detail": "no grid change detected after key press" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_down", @@ -182,13 +182,13 @@ }, { "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", @@ -208,7 +208,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 19 piece(s) detected, need at least 3" + "detail": "only 6 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -228,33 +228,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 33 pieces, no crashes" + "detail": "played for 30s, placed 27 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 12, - "failed": 4, - "score": 0.75 + "passed": 10, + "failed": 6, + "score": 0.63 }, "gameplay": { - "pieces_placed": 33, + "pieces_placed": 27, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 971, - "events_count": 8, + "frames": 927, + "events_count": 7, "pieces_spawned": 0, - "pieces_locked": 19, + "pieces_locked": 6, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 59 + "load_time_ms": 216 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.375, - "score": 0.375, + "outcome_score": 0.715, + "score": 0.715, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -9,13 +9,13 @@ "height": 600 }, "controls": { - "left": "ArrowLeft", - "right": "ArrowRight", - "down": "ArrowDown", - "rotate": "ArrowUp", + "left": "a", + "right": "d", + "down": "s", + "rotate": "z", "drop": "Space" }, - "start_mechanism": "anykey", + "start_mechanism": "auto", "score_element_found": false, "grid_confidence": 1 }, @@ -37,13 +37,13 @@ }, { "name": "move_left", - "pass": true, - "detail": "grid state changed after key press (grid-verified)" + "pass": false, + "detail": "no grid change detected after key press" }, { "name": "move_right", - "pass": false, - "detail": "no grid change detected after key press" + "pass": true, + "detail": "grid state changed after key press (grid-verified)" }, { "name": "move_down", @@ -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", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 19 piece(s) detected, need at least 3" + "detail": "only 6 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -98,33 +98,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 33 pieces, no crashes" + "detail": "played for 30s, placed 27 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 12, - "failed": 4, - "score": 0.75 + "passed": 10, + "failed": 6, + "score": 0.63 }, "gameplay": { - "pieces_placed": 33, + "pieces_placed": 27, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 971, - "events_count": 8, + "frames": 927, + "events_count": 7, "pieces_spawned": 0, - "pieces_locked": 19, + "pieces_locked": 6, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 59 + "load_time_ms": 216 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.34, + "score": 0.34, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -256,7 +256,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 133 + "load_time_ms": 230 }, "accessibility": { "issues": [ @@ -268,10 +268,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 133 + "load_time_ms": 230 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -121,13 +121,13 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -139,12 +139,12 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "z", + "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "enter", "score_element_found": true, - "grid_confidence": 0 + "grid_confidence": 1 }, "tests": [ { @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via enter" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -242,16 +242,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 100 + "load_time_ms": 145 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.39, + "score": 0.39, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "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_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -1,6 +1,6 @@ { "implementation": { - "renderer": "unknown", + "renderer": "canvas", "grid_detected": true, "grid_bounds": { "x": 0, @@ -12,12 +12,12 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "z", + "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "enter", "score_element_found": true, - "grid_confidence": 0 + "grid_confidence": 1 }, "tests": [ { @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": false, - "detail": "could not start game with any mechanism" + "pass": true, + "detail": "started via enter" }, { "name": "auto_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 100 + "load_time_ms": 145 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,10 +121,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.13, + "score": 0.06, "total": 16, - "passed": 2, - "failed": 14, + "passed": 1, + "failed": 15, "report": { "implementation": { "renderer": "unknown", @@ -142,7 +142,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 0 }, @@ -154,53 +154,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify auto-drop" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "grid reader unreliable, cannot verify rotation" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify hard drop" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "grid reader unreliable, cannot verify piece locking" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -230,9 +230,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -242,7 +242,7 @@ "errors_during_play": 0 }, "session": { - "frames": 13, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 116 + "load_time_ms": 158 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.355, + "score": 0.355, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 13, + "cognitive_complexity": 152, + "lines_of_code": 1149, + "duplication_pct": 0.0, + "tech_debt_minutes": 60, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "unknown", "score_element_found": true, "grid_confidence": 0 }, @@ -27,53 +27,53 @@ }, { "name": "game_starts", - "pass": true, - "detail": "started via click_canvas" + "pass": false, + "detail": "could not start game with any mechanism" }, { "name": "auto_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify auto-drop" + "detail": "skipped: game did not start" }, { "name": "move_left", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_right", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "move_down", "pass": false, - "detail": "grid reader unreliable, cannot verify movement" + "detail": "skipped: game did not start" }, { "name": "rotate", "pass": false, - "detail": "grid reader unreliable, cannot verify rotation" + "detail": "skipped: game did not start" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "could not detect any piece rotations via grid reader" + "detail": "skipped: game did not start" }, { "name": "hard_drop", "pass": false, - "detail": "grid reader unreliable, cannot verify hard drop" + "detail": "skipped: game did not start" }, { "name": "piece_locks", "pass": false, - "detail": "grid reader unreliable, cannot verify piece locking" + "detail": "skipped: game did not start" }, { "name": "new_piece_spawns", "pass": false, - "detail": "could not detect new piece spawning at top via grid reader" + "detail": "skipped: game did not start" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 2, - "failed": 14, - "score": 0.13 + "passed": 1, + "failed": 15, + "score": 0.06 }, "gameplay": { "pieces_placed": 0, @@ -115,7 +115,7 @@ "errors_during_play": 0 }, "session": { - "frames": 13, + "frames": 0, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 116 + "load_time_ms": 158 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -120,14 +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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "15 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 0 to 302" + }, + { + "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": 16, + "failed": 0, + "score": 1 + }, + "gameplay": { + "pieces_placed": 39, + "lines_cleared": 1, + "max_score_observed": 302, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1037, + "events_count": 11, + "pieces_spawned": 1, + "pieces_locked": 15, + "lines_cleared": 1, + "piece_types_seen": [ + "unknown" + ], + "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": 0.75, + "score": 0.75, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 15, + "cognitive_complexity": 137, + "lines_of_code": 753, + "duplication_pct": 4.6, + "tech_debt_minutes": 80, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.5 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -142,7 +142,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via auto" }, { "name": "auto_drop", @@ -205,7 +205,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "21 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "name": "line_clear", @@ -215,7 +215,7 @@ { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 376" + "detail": "score changed from 0 to 420" }, { "name": "game_over", @@ -225,7 +225,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 44 pieces, no crashes" + "detail": "played for 30s, placed 43 pieces, no crashes" } ], "summary": { @@ -235,23 +235,23 @@ "score": 1 }, "gameplay": { - "pieces_placed": 44, + "pieces_placed": 43, "lines_cleared": 1, - "max_score_observed": 376, + "max_score_observed": 420, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 948, + "frames": 859, "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 21, + "pieces_locked": 22, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 92 + "load_time_ms": 156 }, "accessibility": { "issues": [ @@ -263,10 +263,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.75, + "score": 0.75, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 5, + "cognitive_complexity": 83, + "lines_of_code": 528, + "duplication_pct": 0.0, + "tech_debt_minutes": 13, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.5 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "z", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "space", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via auto" }, { "name": "auto_drop", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "21 pieces placed during play session" + "detail": "22 pieces placed during play session" }, { "name": "line_clear", @@ -88,7 +88,7 @@ { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 376" + "detail": "score changed from 0 to 420" }, { "name": "game_over", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 44 pieces, no crashes" + "detail": "played for 30s, placed 43 pieces, no crashes" } ], "summary": { @@ -108,23 +108,23 @@ "score": 1 }, "gameplay": { - "pieces_placed": 44, + "pieces_placed": 43, "lines_cleared": 1, - "max_score_observed": 376, + "max_score_observed": 420, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 948, + "frames": 859, "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 21, + "pieces_locked": 22, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 92 + "load_time_ms": 156 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -121,13 +121,158 @@ }, "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": "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "21 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 45 pieces, no crashes" + } + ], + "summary": { + "total": 16, + "passed": 14, + "failed": 2, + "score": 0.88 + }, + "gameplay": { + "pieces_placed": 45, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1000, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 21, + "lines_cleared": 1, + "piece_types_seen": [], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 22 + }, + "accessibility": { + "issues": [], + "issue_count": 0, + "pass": true + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.74, + "score": 0.74, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 74, + "lines_of_code": 562, + "duplication_pct": 0.0, + "tech_debt_minutes": 21, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.6 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.75, + "score": 0.75, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 10, + "cognitive_complexity": 122, + "lines_of_code": 753, + "duplication_pct": 0.0, + "tech_debt_minutes": 49, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.5 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1/eval_results.json @@ -158,7 +158,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via click_canvas" + "detail": "started via auto" }, { "name": "auto_drop", @@ -208,7 +208,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 25 piece(s) detected, need at least 3" + "detail": "only 17 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -228,7 +228,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 41 pieces, no crashes" + "detail": "played for 30s, placed 42 pieces, no crashes" } ], "summary": { @@ -238,23 +238,23 @@ "score": 0.63 }, "gameplay": { - "pieces_placed": 41, + "pieces_placed": 42, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 977, + "frames": 849, "events_count": 8, "pieces_spawned": 0, - "pieces_locked": 25, + "pieces_locked": 17, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 122 + "load_time_ms": 142 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.315, - "score": 0.315, + "outcome_score": 0.59, + "score": 0.59, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 15, + "cognitive_complexity": 142, + "lines_of_code": 756, + "duplication_pct": 36.9, + "tech_debt_minutes": 45, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1/gameplay-bot-report.json @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via click_canvas" + "detail": "started via auto" }, { "name": "auto_drop", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 25 piece(s) detected, need at least 3" + "detail": "only 17 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 41 pieces, no crashes" + "detail": "played for 30s, placed 42 pieces, no crashes" } ], "summary": { @@ -108,23 +108,23 @@ "score": 0.63 }, "gameplay": { - "pieces_placed": 41, + "pieces_placed": 42, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 977, + "frames": 849, "events_count": 8, "pieces_spawned": 0, - "pieces_locked": 25, + "pieces_locked": 17, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 122 + "load_time_ms": 142 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2/eval_results.json @@ -188,7 +188,7 @@ { "name": "all_pieces_rotate", "pass": true, - "detail": "rotation confirmed but could not identify individual piece types" + "detail": "rotation observed, piece types seen: [I]" }, { "name": "hard_drop", @@ -208,7 +208,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "24 pieces placed during play session" + "detail": "25 pieces placed during play session" }, { "name": "line_clear", @@ -228,7 +228,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 46 pieces, no crashes" + "detail": "played for 30s, placed 48 pieces, no crashes" } ], "summary": { @@ -238,23 +238,25 @@ "score": 0.88 }, "gameplay": { - "pieces_placed": 46, + "pieces_placed": 48, "lines_cleared": 0, "max_score_observed": 1, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 894, - "events_count": 9, + "frames": 805, + "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 24, + "pieces_locked": 25, "lines_cleared": 0, - "piece_types_seen": [], + "piece_types_seen": [ + "I" + ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 99 + "load_time_ms": 91 }, "accessibility": { "issues": [ @@ -266,10 +268,19 @@ } } }, - "outcome_score": 0.44, - "score": 0.44, + "outcome_score": 0.565, + "score": 0.565, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 26, + "cognitive_complexity": 154, + "lines_of_code": 1062, + "duplication_pct": 25.5, + "tech_debt_minutes": 105, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=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]" }, { "name": "hard_drop", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": true, - "detail": "24 pieces placed during play session" + "detail": "25 pieces placed during play session" }, { "name": "line_clear", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 46 pieces, no crashes" + "detail": "played for 30s, placed 48 pieces, no crashes" } ], "summary": { @@ -108,23 +108,25 @@ "score": 0.88 }, "gameplay": { - "pieces_placed": 46, + "pieces_placed": 48, "lines_cleared": 0, "max_score_observed": 1, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 894, - "events_count": 9, + "frames": 805, + "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 24, + "pieces_locked": 25, "lines_cleared": 0, - "piece_types_seen": [], + "piece_types_seen": [ + "I" + ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 99 + "load_time_ms": 91 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3/eval_results.json @@ -125,13 +125,162 @@ }, "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": "dom", + "grid_detected": true, + "grid_bounds": { + "x": 316.5, + "y": 0, + "width": 417, + "height": 827 + }, + "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": 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": "19 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 0" + }, + { + "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": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1040, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 19, + "lines_cleared": 0, + "piece_types_seen": [ + "unknown" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 25 + }, + "accessibility": { + "issues": [ + "no headings found" + ], + "issue_count": 1, + "pass": false + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.715, + "score": 0.715, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 156, + "lines_of_code": 1323, + "duplication_pct": 42.0, + "tech_debt_minutes": 52, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -94,10 +94,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.8 + "score": 0.45 }, "transcript_analysis": { "total_events": 85, @@ -253,7 +253,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 98 + "load_time_ms": 148 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.255, + "score": 0.255, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 85, + "lines_of_code": 653, + "duplication_pct": 0.0, + "tech_debt_minutes": 18, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.45 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 98 + "load_time_ms": 148 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -262,10 +262,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 9, + "cognitive_complexity": 96, + "lines_of_code": 618, + "duplication_pct": 4.1, + "tech_debt_minutes": 39, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.75 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -139,10 +139,10 @@ "height": 480 }, "controls": { - "left": "a", - "right": "d", - "down": "s", - "rotate": "x", + "left": "ArrowLeft", + "right": "ArrowRight", + "down": "ArrowDown", + "rotate": "ArrowUp", "drop": "Space" }, "start_mechanism": "unknown", @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 89 + "load_time_ms": 194 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 18, + "cognitive_complexity": 202, + "lines_of_code": 1146, + "duplication_pct": 28.7, + "tech_debt_minutes": 64, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -9,10 +9,10 @@ "height": 480 }, "controls": { - "left": "a", - "right": "d", - "down": "s", - "rotate": "x", + "left": "ArrowLeft", + "right": "ArrowRight", + "down": "ArrowDown", + "rotate": "ArrowUp", "drop": "Space" }, "start_mechanism": "unknown", @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 89 + "load_time_ms": 194 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -252,7 +252,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 52 + "load_time_ms": 199 }, "accessibility": { "issues": [ @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 26, + "cognitive_complexity": 202, + "lines_of_code": 1350, + "duplication_pct": 30.0, + "tech_debt_minutes": 111, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 52 + "load_time_ms": 199 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -93,10 +93,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.9 + "score": 0.55 }, "transcript_analysis": { "total_events": 17, @@ -247,7 +247,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 109 + "load_time_ms": 95 }, "accessibility": { "issues": [], @@ -256,10 +256,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.38, + "score": 0.38, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 16, + "cognitive_complexity": 52, + "lines_of_code": 994, + "duplication_pct": 6.8, + "tech_debt_minutes": 79, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.7 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 109 + "load_time_ms": 95 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -268,10 +268,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.305, + "score": 0.305, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 31, + "cognitive_complexity": 236, + "lines_of_code": 1088, + "duplication_pct": 28.1, + "tech_debt_minutes": 141, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.55 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -255,7 +255,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 98 + "load_time_ms": 113 }, "accessibility": { "issues": [], @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.225, + "score": 0.225, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 7, + "cognitive_complexity": 97, + "lines_of_code": 654, + "duplication_pct": 0.0, + "tech_debt_minutes": 39, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.45 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 98 + "load_time_ms": 113 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -123,10 +123,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.63, + "score": 0.75, "total": 16, - "passed": 10, - "failed": 6, + "passed": 12, + "failed": 4, "report": { "implementation": { "renderer": "canvas", @@ -141,10 +141,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "z", + "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -157,7 +157,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via click_canvas" + "detail": "started via auto" }, { "name": "auto_drop", @@ -181,13 +181,13 @@ }, { "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", @@ -207,7 +207,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 20 piece(s) detected, need at least 3" + "detail": "only 8 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -227,33 +227,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 36 pieces, no crashes" + "detail": "played for 30s, placed 25 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 10, - "failed": 6, - "score": 0.63 + "passed": 12, + "failed": 4, + "score": 0.75 }, "gameplay": { - "pieces_placed": 36, + "pieces_placed": 25, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 987, - "events_count": 8, + "frames": 959, + "events_count": 9, "pieces_spawned": 0, - "pieces_locked": 20, + "pieces_locked": 8, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 121 + "load_time_ms": 214 }, "accessibility": { "issues": [], @@ -262,10 +262,19 @@ } } }, - "outcome_score": 0.315, - "score": 0.315, + "outcome_score": 0.7, + "score": 0.7, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 5, + "cognitive_complexity": 78, + "lines_of_code": 698, + "duplication_pct": 0.0, + "tech_debt_minutes": 25, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -12,10 +12,10 @@ "left": "ArrowLeft", "right": "ArrowRight", "down": "ArrowDown", - "rotate": "z", + "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "click_canvas", + "start_mechanism": "auto", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via click_canvas" + "detail": "started via auto" }, { "name": "auto_drop", @@ -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", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 20 piece(s) detected, need at least 3" + "detail": "only 8 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -98,33 +98,33 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 36 pieces, no crashes" + "detail": "played for 30s, placed 25 pieces, no crashes" } ], "summary": { "total": 16, - "passed": 10, - "failed": 6, - "score": 0.63 + "passed": 12, + "failed": 4, + "score": 0.75 }, "gameplay": { - "pieces_placed": 36, + "pieces_placed": 25, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 987, - "events_count": 8, + "frames": 959, + "events_count": 9, "pieces_spawned": 0, - "pieces_locked": 20, + "pieces_locked": 8, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 121 + "load_time_ms": 214 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -142,7 +142,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "enter", "score_element_found": true, "grid_confidence": 1 }, @@ -155,7 +155,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via enter" }, { "name": "auto_drop", @@ -251,7 +251,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 168 + "load_time_ms": 197 }, "accessibility": { "issues": [], @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.065, - "score": 0.065, + "outcome_score": 0.39, + "score": 0.39, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 17, + "cognitive_complexity": 123, + "lines_of_code": 958, + "duplication_pct": 2.8, + "tech_debt_minutes": 63, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "enter", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via space" + "detail": "started via enter" }, { "name": "auto_drop", @@ -124,7 +124,7 @@ "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 168 + "load_time_ms": 197 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -120,14 +120,163 @@ "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": "1 new piece(s) detected at top of grid" + }, + { + "name": "multiple_pieces", + "pass": true, + "detail": "14 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 0 to 264" + }, + { + "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": 1, + "max_score_observed": 264, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1060, + "events_count": 10, + "pieces_spawned": 1, + "pieces_locked": 14, + "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" + ], + "issue_count": 1, + "pass": false + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.825, + "score": 0.825, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 13, + "cognitive_complexity": 105, + "lines_of_code": 616, + "duplication_pct": 0.0, + "tech_debt_minutes": 46, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -120,11 +120,11 @@ "score": 1.0 }, "gameplay_bot": { - "pass": true, - "score": 1, + "pass": false, + "score": 0.88, "total": 16, - "passed": 16, - "failed": 0, + "passed": 14, + "failed": 2, "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: [I]" + "pass": false, + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", @@ -205,17 +205,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "18 pieces placed during play session" + "detail": "11 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "2 line(s) cleared (grid-verified)" + "detail": "1 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 354" + "detail": "score changed from 0 to 194" }, { "name": "game_over", @@ -230,30 +230,30 @@ ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 14, + "failed": 2, + "score": 0.88 }, "gameplay": { "pieces_placed": 32, - "lines_cleared": 2, - "max_score_observed": 354, + "lines_cleared": 1, + "max_score_observed": 194, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 986, + "frames": 959, "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 18, - "lines_cleared": 2, + "pieces_locked": 11, + "lines_cleared": 1, "piece_types_seen": [ - "I" + "unknown" ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 87 + "load_time_ms": 129 }, "accessibility": { "issues": [], @@ -262,10 +262,19 @@ } } }, - "outcome_score": 0.5, - "score": 0.5, + "outcome_score": 0.765, + "score": 0.765, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 12, + "cognitive_complexity": 144, + "lines_of_code": 826, + "duplication_pct": 0.0, + "tech_debt_minutes": 71, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.65 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=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: [I]" + "pass": false, + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", @@ -78,17 +78,17 @@ { "name": "multiple_pieces", "pass": true, - "detail": "18 pieces placed during play session" + "detail": "11 pieces placed during play session" }, { "name": "line_clear", "pass": true, - "detail": "2 line(s) cleared (grid-verified)" + "detail": "1 line(s) cleared (grid-verified)" }, { "name": "score_changes", "pass": true, - "detail": "score changed from 0 to 354" + "detail": "score changed from 0 to 194" }, { "name": "game_over", @@ -103,30 +103,30 @@ ], "summary": { "total": 16, - "passed": 16, - "failed": 0, - "score": 1 + "passed": 14, + "failed": 2, + "score": 0.88 }, "gameplay": { "pieces_placed": 32, - "lines_cleared": 2, - "max_score_observed": 354, + "lines_cleared": 1, + "max_score_observed": 194, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 986, + "frames": 959, "events_count": 10, "pieces_spawned": 1, - "pieces_locked": 18, - "lines_cleared": 2, + "pieces_locked": 11, + "lines_cleared": 1, "piece_types_seen": [ - "I" + "unknown" ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 87 + "load_time_ms": 129 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 124 + "load_time_ms": 194 }, "accessibility": { "issues": [], @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.28, + "score": 0.28, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 12, + "cognitive_complexity": 148, + "lines_of_code": 734, + "duplication_pct": 0.0, + "tech_debt_minutes": 85, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.5 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 124 + "load_time_ms": 194 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/eval_results.json @@ -251,7 +251,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 128 + "load_time_ms": 176 }, "accessibility": { "issues": [], @@ -260,10 +260,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.43, + "score": 0.43, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 5, + "cognitive_complexity": 94, + "lines_of_code": 623, + "duplication_pct": 0.0, + "tech_debt_minutes": 25, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.8 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 128 + "load_time_ms": 176 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/eval_results.json @@ -122,10 +122,10 @@ }, "gameplay_bot": { "pass": false, - "score": 0.06, + "score": 0.13, "total": 16, - "passed": 1, - "failed": 15, + "passed": 2, + "failed": 14, "report": { "implementation": { "renderer": "unknown", @@ -143,7 +143,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -155,53 +155,53 @@ }, { "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": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -231,9 +231,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -243,16 +243,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 162 + "load_time_ms": 287 }, "accessibility": { "issues": [], @@ -261,10 +261,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.315, + "score": 0.315, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 1, + "vulnerabilities": 0, + "code_smells": 22, + "cognitive_complexity": 120, + "lines_of_code": 811, + "duplication_pct": 0.0, + "tech_debt_minutes": 63, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.5 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "x", "drop": "Space" }, - "start_mechanism": "unknown", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -27,53 +27,53 @@ }, { "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": "skipped: game did not start" + "detail": "piece did not move down in 5 seconds (grid-verified)" }, { "name": "move_left", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_right", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "move_down", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change detected after key press" }, { "name": "rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "no shape change detected after rotate key" }, { "name": "all_pieces_rotate", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect any piece rotations via grid reader" }, { "name": "hard_drop", "pass": false, - "detail": "skipped: game did not start" + "detail": "no grid change with bottom cells detected after hard drop key" }, { "name": "piece_locks", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not verify piece locking via grid reader" }, { "name": "new_piece_spawns", "pass": false, - "detail": "skipped: game did not start" + "detail": "could not detect new piece spawning at top via grid reader" }, { "name": "multiple_pieces", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 1, - "failed": 15, - "score": 0.06 + "passed": 2, + "failed": 14, + "score": 0.13 }, "gameplay": { "pieces_placed": 0, @@ -115,16 +115,16 @@ "errors_during_play": 0 }, "session": { - "frames": 0, + "frames": 15, "events_count": 0, "pieces_spawned": 0, "pieces_locked": 0, "lines_cleared": 0, "piece_types_seen": [], - "grid_read_success_rate": 0 + "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 162 + "load_time_ms": 287 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1/eval_results.json @@ -124,13 +124,160 @@ }, "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": "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": 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]" + }, + { + "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": false, + "detail": "only 2 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 via grid reader" + }, + { + "name": "playable_30s", + "pass": false, + "detail": "3 console error(s), 0 play errors" + } + ], + "summary": { + "total": 16, + "passed": 12, + "failed": 4, + "score": 0.75 + }, + "gameplay": { + "pieces_placed": 12, + "lines_cleared": 1, + "max_score_observed": 0, + "play_duration_seconds": 30, + "errors_during_play": 0 + }, + "session": { + "frames": 1098, + "events_count": 9, + "pieces_spawned": 1, + "pieces_locked": 2, + "lines_cleared": 1, + "piece_types_seen": [ + "S" + ], + "grid_read_success_rate": 1 + }, + "performance": { + "load_time_ms": 110 + }, + "accessibility": { + "issues": [], + "issue_count": 0, + "pass": true + } + } }, - "outcome_score": 0.0, - "score": 0.0, + "outcome_score": 0.65, + "score": 0.65, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 15, + "cognitive_complexity": 103, + "lines_of_code": 1027, + "duplication_pct": 34.6, + "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_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "auto", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -58,7 +58,7 @@ { "name": "all_pieces_rotate", "pass": true, - "detail": "rotation observed, piece types seen: [Z]" + "detail": "rotation observed, piece types seen: [S]" }, { "name": "hard_drop", @@ -92,8 +92,8 @@ }, { "name": "game_over", - "pass": true, - "detail": "game stopped after stacking to top" + "pass": false, + "detail": "could not trigger or detect game over via grid reader" }, { "name": "playable_30s", @@ -103,9 +103,9 @@ ], "summary": { "total": 16, - "passed": 13, - "failed": 3, - "score": 0.81 + "passed": 12, + "failed": 4, + "score": 0.75 }, "gameplay": { "pieces_placed": 12, @@ -115,18 +115,18 @@ "errors_during_play": 0 }, "session": { - "frames": 1176, - "events_count": 10, + "frames": 1098, + "events_count": 9, "pieces_spawned": 1, "pieces_locked": 2, "lines_cleared": 1, "piece_types_seen": [ - "Z" + "S" ], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 21 + "load_time_ms": 110 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2/eval_results.json @@ -90,10 +90,10 @@ }, "html_validation": { "valid": false, - "errors": 2 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.85 + "score": 0.5 }, "transcript_analysis": { "total_events": 63, @@ -244,7 +244,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 57 + "load_time_ms": 74 }, "accessibility": { "issues": [], @@ -253,10 +253,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.47, + "score": 0.47, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 4, + "cognitive_complexity": 0, + "lines_of_code": 705, + "duplication_pct": 0.0, + "tech_debt_minutes": 29, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.88 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2/gameplay-bot-report.json @@ -119,7 +119,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 57 + "load_time_ms": 74 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3/eval_results.json @@ -96,10 +96,10 @@ }, "html_validation": { "valid": false, - "errors": 1 + "errors": 0 }, "duplication_percentage": 0.0, - "score": 0.75 + "score": 0.4 }, "transcript_analysis": { "total_events": 77, @@ -255,7 +255,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 55 + "load_time_ms": 31 }, "accessibility": { "issues": [], @@ -264,10 +264,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.405, + "score": 0.405, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 29, + "cognitive_complexity": 70, + "lines_of_code": 975, + "duplication_pct": 2.3, + "tech_debt_minutes": 45, + "maintainability": "A", + "reliability": "A", + "security": "A", + "score": 0.75 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 55 + "load_time_ms": 31 }, "accessibility": { "issues": [], diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1/eval_results.json @@ -144,7 +144,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -157,7 +157,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -207,7 +207,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 8 piece(s) detected, need at least 3" + "detail": "only 19 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -227,7 +227,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 30 pieces, no crashes" + "detail": "played for 30s, placed 35 pieces, no crashes" } ], "summary": { @@ -237,23 +237,23 @@ "score": 0.75 }, "gameplay": { - "pieces_placed": 30, + "pieces_placed": 35, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 1080, + "frames": 995, "events_count": 9, "pieces_spawned": 0, - "pieces_locked": 8, + "pieces_locked": 19, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 161 }, "accessibility": { "issues": [ @@ -265,10 +265,19 @@ } } }, - "outcome_score": 0.375, - "score": 0.375, + "outcome_score": 0.65, + "score": 0.65, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 0, + "vulnerabilities": 0, + "code_smells": 14, + "cognitive_complexity": 153, + "lines_of_code": 877, + "duplication_pct": 33.4, + "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_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1/gameplay-bot-report.json @@ -15,7 +15,7 @@ "rotate": "ArrowUp", "drop": "Space" }, - "start_mechanism": "space", + "start_mechanism": "click_canvas", "score_element_found": true, "grid_confidence": 1 }, @@ -28,7 +28,7 @@ { "name": "game_starts", "pass": true, - "detail": "started via auto" + "detail": "started via click_canvas" }, { "name": "auto_drop", @@ -78,7 +78,7 @@ { "name": "multiple_pieces", "pass": false, - "detail": "only 8 piece(s) detected, need at least 3" + "detail": "only 19 piece(s) detected, need at least 3" }, { "name": "line_clear", @@ -98,7 +98,7 @@ { "name": "playable_30s", "pass": true, - "detail": "played for 30s, placed 30 pieces, no crashes" + "detail": "played for 30s, placed 35 pieces, no crashes" } ], "summary": { @@ -108,23 +108,23 @@ "score": 0.75 }, "gameplay": { - "pieces_placed": 30, + "pieces_placed": 35, "lines_cleared": 1, "max_score_observed": 0, "play_duration_seconds": 30, "errors_during_play": 0 }, "session": { - "frames": 1080, + "frames": 995, "events_count": 9, "pieces_spawned": 0, - "pieces_locked": 8, + "pieces_locked": 19, "lines_cleared": 1, "piece_types_seen": [], "grid_read_success_rate": 1 }, "performance": { - "load_time_ms": 51 + "load_time_ms": 161 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2/eval_results.json @@ -254,7 +254,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 104 + "load_time_ms": 358 }, "accessibility": { "issues": [ @@ -266,10 +266,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 12, + "cognitive_complexity": 208, + "lines_of_code": 1133, + "duplication_pct": 25.6, + "tech_debt_minutes": 51, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 104 + "load_time_ms": 358 }, "accessibility": { "issues": [ diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3/eval_results.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3/eval_results.json @@ -256,7 +256,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 68 + "load_time_ms": 60 }, "accessibility": { "issues": [ @@ -267,10 +267,19 @@ } } }, - "outcome_score": 0.03, - "score": 0.03, + "outcome_score": 0.155, + "score": 0.155, "sonarqube": { - "error": "SonarQube not running at localhost:9000", - "score": 0 + "bugs": 2, + "vulnerabilities": 0, + "code_smells": 15, + "cognitive_complexity": 166, + "lines_of_code": 1179, + "duplication_pct": 44.0, + "tech_debt_minutes": 26, + "maintainability": "A", + "reliability": "C", + "security": "A", + "score": 0.25 } } \ No newline at end of file diff --git a/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3/gameplay-bot-report.json b/results/runs/tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3/gameplay-bot-report.json @@ -124,7 +124,7 @@ "grid_read_success_rate": 0 }, "performance": { - "load_time_ms": 68 + "load_time_ms": 60 }, "accessibility": { "issues": [

Impressum · Datenschutz