fix(phase26): 打通 Incident→DB→KM 完整鏈路 + namespace 修正
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 1m29s
Type Sync Check / check-type-sync (push) Failing after 52s

問題根因:
1. create_incident_for_approval 只存 Redis,不存 PostgreSQL
   → TTL 7天後消失,Playbook 萃取永遠找不到 Incident
2. ApprovalRecord 無 incident_id 欄位
   → _trigger_playbook_extraction 靠 regex 掃中文文字找 INC-,永遠失敗
3. operation_parser namespace fallback 是 "default"
   → 所有 deployment 在 awoooi-prod,203 次執行全失敗

修復:
- Incident 同時寫入 Redis + PostgreSQL (save_to_episodic_memory)
- ApprovalRecord 加入 incident_id 欄位 (model + ORM + migration)
- alertmanager_webhook 建立 Approval 後回寫 incident_id
- _trigger_playbook_extraction 直接用 approval.incident_id
- operation_parser DEFAULT_NAMESPACE = "awoooi-prod"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
OG T
2026-04-06 11:46:05 +08:00
parent 286a96d1aa
commit 658337ec18
7 changed files with 104 additions and 21 deletions

View File

@@ -161,6 +161,8 @@ class ApprovalRequest(ApprovalRequestBase):
fingerprint: str | None = Field(default=None, description="告警指紋 Hash")
hit_count: int = Field(default=1, description="聚合觸發次數")
last_seen_at: datetime = Field(default_factory=lambda: datetime.now(UTC), description="最後觸發時間")
# 2026-04-06 ogt: 關聯 Incident — 萃取 Playbook 與 KM 寫入必須知道 incident_id
incident_id: str | None = Field(default=None, description="關聯的 Incident ID")
@property
def current_signatures(self) -> int: