Garry Tan 03a6270b9c feat: eval efficiency metrics — turns, duration, commentary across all surfaces ...

Add generateCommentary() for natural-language delta interpretation,
per-test turns/duration in comparison and summary output, judgePassed
unit tests, 3 new E2E tests (qa-only, qa fix loop, plan artifact).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-15 21:17:12 -05:00

..

dev-skill.ts

feat: SKILL.md template system, 3-tier testing, DX tools (v0.3.3) (#41)

2026-03-13 21:08:12 -07:00

eval-compare.ts

feat: eval CLI tools + docs cleanup

2026-03-14 03:49:57 -05:00

eval-list.ts

feat: eval efficiency metrics — turns, duration, commentary across all surfaces

2026-03-15 21:17:12 -05:00

eval-summary.ts

feat: eval efficiency metrics — turns, duration, commentary across all surfaces

2026-03-15 21:17:12 -05:00

eval-watch.ts

fix: auto-clear stale heartbeat when process is dead

2026-03-14 12:55:40 -05:00

gen-skill-docs.ts

feat: qa-only skill, qa fix loop, plan-to-QA artifact flow

2026-03-15 21:17:06 -05:00

skill-check.ts

feat: qa-only skill, qa fix loop, plan-to-QA artifact flow

2026-03-15 21:17:06 -05:00