Files
deerflow-code/offline-backend-20260512/backend/packages/harness/deerflow/agents
xuhdandClaude Opus 4.7 c493639119 feat(skill-review): strict-mode prompt + raise min_tool_calls 3 to 5
The review agent was creating too many low-value skills. Three changes
tighten the funnel:

- review_worker prompt: rewritten in "保守模式". Default decision is
  do-nothing. To create, all five AND conditions must hold (>=5 tool
  calls with step dependencies, an explicit fail->fix->success episode,
  cross-scenario reusability, no >=70% overlap with skill_list, can
  produce >=300 chars of substance). Adds 7 explicit NO categories
  (single-tool loops, one-off queries, LLM common knowledge, etc.)
  and a 4-question self-check before any create. Hard cap of 1 new
  skill per review, with patch preferred over create.
- min_tool_calls: 3 -> 5. Matches the prompt's ">=5 steps" hard
  condition so trivial turns never reach the LLM reviewer.
- Updated config.yaml, the default-value assertion in
  test_skill_review_worker, and the middleware docstring's "(default
  3)" annotation to keep all three references in sync.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-09 16:00:29 +08:00
..
2026-05-16 22:00:34 +08:00
2026-05-13 14:36:44 +08:00
2026-05-13 14:36:44 +08:00
2026-05-13 14:36:44 +08:00
2026-06-03 18:57:49 +08:00