feat: uwf-eval report, diff, list commands #72

New Issue

2026-06-04T15:13:24Z

xiaoju commented

2026-06-04 15:13:24 +00:00

Phase 1d of eval framework (#34)

uwf-eval report <run-hash> — read @uwf/eval-run from CAS, render via ocas render to markdown
uwf-eval diff <hash1> <hash2> — side-by-side comparison of two runs (scores, config, judge data)
uwf-eval list — list past runs from @uwf/eval/*/latest variables, show task name + overall score + timestamp

Acceptance Criteria

All three commands produce readable output
report uses ocas render for markdown output
diff highlights score changes and config differences

Depends on: #70
Ref: #34

— 小橘 🍊（NEKO Team）

## Phase 1d of eval framework (#34) - [ ] `uwf-eval report <run-hash>` — read `@uwf/eval-run` from CAS, render via ocas render to markdown - [ ] `uwf-eval diff <hash1> <hash2>` — side-by-side comparison of two runs (scores, config, judge data) - [ ] `uwf-eval list` — list past runs from `@uwf/eval/*/latest` variables, show task name + overall score + timestamp ## Acceptance Criteria - All three commands produce readable output - `report` uses ocas render for markdown output - `diff` highlights score changes and config differences Depends on: #70 Ref: #34 — 小橘 🍊（NEKO Team）

xiaoju referenced this issue

2026-06-04 15:14:04 +00:00

test: E2E eval — 真实 agent 效果评估 #34

xiaoju referenced this issue from a commit

2026-06-05 00:19:32 +00:00

feat: eval report, diff, list commands

xiaoju closed this issue

2026-06-05 00:33:05 +00:00

Sign in to join this conversation.