feat(auto-repair): 打通自動修復閉環 (ADR-058)
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Type Sync Check / check-type-sync (push) Failing after 53s

問題: 告警鏈路從未呼叫 auto_repair_service,機制完全死路
修正:
1. webhooks.py: alertmanager_webhook 建立 Incident 後觸發 _try_auto_repair_background
2. playbook.py: is_high_quality 門檻降低 (冷啟動期)
   - success_count: 10 → 3
   - success_rate: 95% → 80%
3. tests: test_evaluate_not_high_quality 更新為新門檻

流程: Alertmanager → API → Incident → evaluate → P2以下+高品質Playbook → 自動執行 → Telegram通知

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
OG T
2026-04-05 22:08:08 +08:00
parent 9629367bc2
commit 5499169996
3 changed files with 107 additions and 6 deletions

View File

@@ -237,13 +237,16 @@ class Playbook(BaseModel):
條件:
- 狀態為 APPROVED
- 成功率 >= 95%
- 成功次數 >= 10
- 成功率 >= 80% (冷啟動期: 原 95%2026-04-05 ogt 降低以打破零執行惡性循環)
- 成功次數 >= 3 (冷啟動期: 原 10累積足夠後再收緊)
待成熟後收緊為: success_rate >= 0.95, success_count >= 10
"""
# 2026-04-05 ogt: 冷啟動調整,打破 zero-execution 惡性循環
return (
self.status == PlaybookStatus.APPROVED
and self.success_rate >= 0.95
and self.success_count >= 10
and self.success_rate >= 0.80
and self.success_count >= 3
)
@property