sunyuyang
  • Joined on 2026-07-22
sunyuyang pushed to main at sora/evalstone 2026-09-08 07:32:18 +00:00
ad61a2c44e Fix DeepSWE Pier routing and Terminal-Bench context/apt setup.
sunyuyang pushed to main at sora/evalstone 2026-09-03 04:11:37 +00:00
8b0a413cf1 Drop Harbor trial wall-clock from summary perf metrics.
sunyuyang pushed to main at sora/evalstone 2026-09-03 03:54:28 +00:00
44303d8953 Allow resume when only sample limit changes, and keep CSV rows across runs.
sunyuyang pushed to main at sora/evalstone 2026-09-02 09:44:22 +00:00
a37a1165b2 Preload Pier uv and mini-swe-agent wheels so DeepSWE sandbox builds skip GitHub.
sunyuyang pushed to main at sora/evalstone 2026-09-02 08:41:12 +00:00
ee54cd6d5d Rename SciCode preload script away from the K3 sandbox name.
sunyuyang pushed to main at sora/evalstone 2026-09-02 08:24:49 +00:00
70fe0c1d95 Build SciCode sandbox image from local wheels to avoid PyPI timeouts.
sunyuyang pushed to main at sora/evalstone 2026-07-29 07:38:06 +00:00
541b0b477d Improve EvalStone web UI paths, custom suites, and results charts.
7c449d3126 Add local EvalStone web UI for launch and results comparison.
Compare 2 commits »
sunyuyang created branch webui-only in sora/evalstone 2026-07-29 06:49:42 +00:00
sunyuyang pushed to webui-only at sora/evalstone 2026-07-29 06:49:42 +00:00
7c449d3126 Add local EvalStone web UI for launch and results comparison.