commit 00055378a50253cc949795147e20b64ed2a2767f
parent 42321c004e708af0b099db58e9cbedf54e03e145
Author: Brian Graham <brian@buildingbetterteams.de>
Date: Sun, 12 Apr 2026 17:38:24 +0200
Update calibration: cbbff570 CW rotation works, e2e04e75 scores on clear,
9805c24a has game over overlay
cbbff570: CW rotation (Up) works, CCW (Z) is broken. Updated rotate=true.
e2e04e75: Bot was right, score increases by 100 on line clear. Updated
score_increases_on_clear=true.
9805c24a: Game over shows overlay with GAME OVER text + Play Again button.
Updated game_over_display=true.
V2 agreement now 95% (102/107). 5 remaining disagreements: 3 from trail
rendering bug (4949d521), 1 game_over_display detection (9805c24a), 1
all_pieces_rotate edge case (cbbff570).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat:
3 files changed, 14 insertions(+), 11 deletions(-)
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/9805c24a.json b/tasks/tetris/eval/gameplay-bot/calibration/9805c24a.json
@@ -2,8 +2,8 @@
"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
"short_id": "9805c24a",
"label": "DOM game (haiku-4.5, en)",
- "notes": "Very ugly misaligned UI. Rotation partially broken: only does 1 of 4 rotations for some blocks. Poor randomizer: first 8-10 blocks were only 2 different tetrominoes. Next piece preview and game over display present. Soft drop works correctly.",
- "human_tested_at": "2026-04-09",
+ "notes": "Very ugly misaligned UI. Rotation partially broken: only 1 of 4 states for some blocks. Poor randomizer. Play starts instantly (no start button). Game over shows overlay with GAME OVER text and Play Again button.",
+ "human_tested_at": "2026-04-12",
"human_tests": {
"game_loads": true,
"game_starts": true,
@@ -31,4 +31,4 @@
"counter_clockwise_rotation": false,
"soft_drop_distinct": true
}
-}
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/cbbff570.json b/tasks/tetris/eval/gameplay-bot/calibration/cbbff570.json
@@ -2,8 +2,8 @@
"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
"short_id": "cbbff570",
"label": "DOM game (haiku-4.5, en)",
- "notes": "Rotation is flaky: at best rotates once per piece, sometimes stalls the game or causes blocks to vanish. Next piece preview shows a shaded box outline instead of the actual upcoming block shape. Line clear works but at one point randomly cleared a line incorrectly (spurious clear). Game over can be triggered by spamming space and shows a proper game_over_modal with restart button. Multi-line clear and soft drop work.",
- "human_tested_at": "2026-04-11",
+ "notes": "CW rotation (Up arrow) works normally. CCW rotation (Z key) is buggy: at best once, sometimes stalls or causes blocks to vanish. Next piece preview shows a shaded box outline. Line clear works but at one point randomly cleared incorrectly.",
+ "human_tested_at": "2026-04-12",
"human_tests": {
"game_loads": true,
"game_starts": true,
@@ -11,7 +11,7 @@
"move_left": true,
"move_right": true,
"move_down": true,
- "rotate": false,
+ "rotate": true,
"hard_drop": true,
"all_pieces_rotate": false,
"piece_locks": true,
@@ -31,4 +31,4 @@
"counter_clockwise_rotation": false,
"soft_drop_distinct": true
}
-}
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/e2e04e75.json b/tasks/tetris/eval/gameplay-bot/calibration/e2e04e75.json
@@ -2,8 +2,8 @@
"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
"short_id": "e2e04e75",
"label": "Spanish basic play",
- "notes": "Spanish game. Basic play works fine. Score does not change during play.",
- "human_tested_at": "2026-04-09",
+ "notes": "Spanish game. Basic play works fine. Score increases by 100 on line clear (bot was right, human was wrong on initial test).",
+ "human_tested_at": "2026-04-12",
"human_tests": {
"game_loads": true,
"game_starts": true,
@@ -18,7 +18,7 @@
"new_piece_spawns": true,
"multiple_pieces": true,
"line_clear": null,
- "score_increases_on_clear": false,
+ "score_increases_on_clear": true,
"score_element_visible": null,
"game_over": true,
"playable_30s": true,
@@ -31,4 +31,4 @@
"counter_clockwise_rotation": null,
"soft_drop_distinct": null
}
-}
+}
+\ No newline at end of file
