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>
This commit is contained in:
1 parent
539a8bcec8
commit
c493639119
5 files changed
+114
-77
No files matched your search
@@ -214,7 +214,7 @@ skill_evolution:
|
||||
interval_hours: 24
|
||||
review_worker:
|
||||
enabled: true # 被动复盘开关
|
||||
min_tool_calls: 3 # 触发阈值:本轮至少 3 次工具调用
|
||||
min_tool_calls: 5 # 触发阈值:本轮至少 5 次工具调用,与 prompt 中"≥5 步"硬条件一致
|
||||
max_messages: 60 # 传给 LLM 的最大消息条数
|
||||
timeout_seconds: 120 # 单次 review 超时(秒)
|
||||
model_name: # 留空则使用主模型
|
||||
|
||||
Reference in new issue
Block a user