Hunter B c8fcef7f1e feat(benchmarks): add CodeWhale-native PinchBench runner ...

Runs PinchBench tasks directly through codewhale exec --auto instead
of going through OpenClaw. Loads task markdown, creates workspace,
runs the prompt, and grades using PinchBench's embedded automated
checks.

No external agent framework dependency — just codewhale + pyyaml.

2026-06-04 20:26:05 -07:00

..

benchmarks

feat(benchmarks): add CodeWhale-native PinchBench runner

2026-06-04 20:26:05 -07:00

installer

fix(release): ship NSIS installer artifact

2026-06-01 19:34:25 -07:00

release

chore(release): harden deepseek-tui deprecation path

2026-06-01 06:01:03 -07:00

tencent-lighthouse

chore(release): v0.8.53 — Arcee support, telegram bridge, provider fixes

2026-06-03 16:12:38 -07:00

check-provider-registry.py

fix(provider): expose siliconflow-cn registry coverage

2026-06-03 02:51:42 -07:00

measure-tool-catalog.py

feat: defer low-value native tools by default, reduce catalog tokens 73% (#2076)

2026-05-26 10:08:09 -05:00

mobile-smoke.sh

fix(runtime): harden mobile QR smoke output (#2417)

2026-05-31 02:48:41 -07:00

verify_task.sh

chore: add DeepSWE task verification script

2026-05-26 16:40:16 -05:00