codex-bot
  • Joined on 2026-09-11
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 15:27:20 +00:00
a1569f3b6a ci: allow cold runner setup to finish
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 15:10:16 +00:00
f0e910cd88 ci: run Python checks in Bookworm container
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 15:07:49 +00:00
fc223263bd ci: provision supported Python on runner
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 15:01:46 +00:00
41cbf44db9 ci: restore Python checks on CODEX runner
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 14:36:52 +00:00
f3dd8f8701 ci: probe Docker through the runner socket
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 14:30:49 +00:00
c3025567c8 ci: inspect persistent storage for uploaded book
codex-bot pushed to main at Zayden-Jung/lean-bench 2026-09-23 14:20:35 +00:00
bde340e414 ci: probe CODEX runner and uploaded book
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-23 02:35:59 +00:00
a06ca45f30 Render dynamic histories in configurable chunks
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-23 02:23:13 +00:00
43aff1e2ee Generate proof-bearing dynamic world histories
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 16:52:39 +00:00
6f929437a2 Score unparseable answers without aborting batches
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 16:42:15 +00:00
06cdd9c556 Preserve and recover solver outputs
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 16:36:48 +00:00
0f0594bc41 Add independent thinking-mode controls
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 16:27:33 +00:00
b645190ea5 Checkpoint rendered cases before solving
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 16:19:37 +00:00
afcd6c614e Harden long-running behavioral evaluations
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 16:11:02 +00:00
9f54f8f5a3 Replace explicit rules with behavioral hidden systems
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 15:23:13 +00:00
3cf3db7b12 Archive first live benchmark as curated report
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 15:07:27 +00:00
fab07f80b0 Capture full solver output in five-case evaluation
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 15:00:15 +00:00
3b50b8201d Require independent renderer and solver clients
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 14:43:00 +00:00
40cbae289e Restore portable evaluation workflow for configured runner
codex-bot pushed to main at Zayden-Jung/logic-skeleton-bench 2026-09-22 13:34:25 +00:00
6d91091bb2 chore: remove CI/CD workflow