Your Name
f2f5148ca6
fix(awooop): Phase 2 第二批 P0 安全強化 + Redis key 命名空間修正
...
## P0-05 Callback Nonce 防偽造(ADR-116)
- security_interceptor.py:generate_callback_nonce() 新增 HMAC-SHA256[:16] 附加
- 新 5-part 格式:{action}:{short_id}:{ts}:{rand}:{hmac16}
- CALLBACK_HMAC_SECRET 未設定時降級 warning(向後相容)
- security_interceptor.py:parse_callback_data() 新增 5-part 分支 + HMAC 驗證
- config.py:新增 CALLBACK_HMAC_SECRET: str = Field(default="")
## P0-06 Webhook HMAC Replay 防護(ADR-116)
- security_interceptor.py:新增 check_webhook_nonce()(Service 層,get_redis 在此層合法)
- webhooks.py:verify_webhook_signature() 新增兩個可選 Header
- X-Webhook-Timestamp:±300s 窗口驗證(若提供)
- X-Webhook-Nonce:呼叫 check_webhook_nonce()(Redis NX dedup,fail open)
- 移除直接 get_redis import(leWOOOgo 積木化修正)
## P0-11 ollama:current_primary Redis key 遷移 Phase A(ADR-110)
- ollama_auto_recovery.py:_REDIS_PRIMARY_KEY = "platform:ollama:current_primary"
- 雙寫舊 key "ollama:current_primary"(Phase A 30 天)
- 讀取以新 key 為主,fallback 舊 key
## P0-12 consensus Redis key 加 project namespace Phase A
- consensus_engine.py:新增 _consensus_key() / _consensus_legacy_key() helper
- 新 key:{project_id}:consensus:{consensus_id}
- project_id=None 時 fallback __platform__:consensus:{consensus_id}
- Phase A 雙寫 + fallback 讀取,現有呼叫方零修改
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-04 13:54:38 +08:00
Your Name
2b2359e367
fix(ai-router): ADR-110 GCP 三層容災 — 修復 Ollama 直跳 Gemini 根因
...
Code Review / ai-code-review (push) Successful in 55s
run-migration / migrate (push) Successful in 41s
根因(所有告警 Ollama 失敗直接跳 Gemini 的原因):
AIProviderEnum 缺少 ollama_gcp_a / ollama_gcp_b / ollama_local
→ AIProviderEnum("ollama_gcp_a") 拋 ValueError
→ fallback chain 清空(所有 GCP 端點轉換全失敗)
→ failover_fallback = [](空 list,非 None)
→ fallback_chain 被覆寫為 [] 而非走 Gemini 備援
→ AIProviderRegistry.get("ollama_gcp_a") 回傳 None → not_registered → 跳過
→ 整條 Ollama 鏈(GCP-A → GCP-B → 111)全部略過,直接跳 Gemini
修復:
1. AIProviderEnum 新增 OLLAMA_GCP_A / OLLAMA_GCP_B / OLLAMA_LOCAL
2. PROVIDER_LATENCY_BUDGET 補齊三個新 enum
3. ollama.py 新增 OllamaGcpBProvider(OLLAMA_SECONDARY_URL = GCP-B 34.21.145.224)
4. _init_registry() 補登:
- "ollama_gcp_a" alias → OllamaProvider(GCP-A,OLLAMA_URL)
- OllamaGcpBProvider("ollama_gcp_b",OLLAMA_SECONDARY_URL)
- "ollama_local" alias → Ollama188Provider(111,OLLAMA_FALLBACK_URL)
修復後路由順序:GCP-A → GCP-B → Local(111) → Gemini → Claude
2026-05-04 ogt + Claude Sonnet 4.6
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-04 13:49:32 +08:00
Your Name
14bf86a462
fix(awooop): Phase 2 初批 P0 修正 + Phase 1 Task 1.7 integration tests
...
## P0 安全 / 架構修正
### P0-08 telemetry.py — 移除硬碼 IP assert(ADR-121)
- config.py:新增 OTEL_ALLOWED_ENDPOINTS(預設 192.168.0.188)+ OTEL_FORBIDDEN_ENDPOINTS
- telemetry.py:_validate_endpoint() 改為 config-driven allowlist/forbidlist
- EwoooC 可用 env 覆寫 OTEL_ALLOWED_ENDPOINTS 指向自己的 SigNoz host
### P0-13 mcp_bridge.py — K8s namespace 由 settings 提供
- config.py:新增 AWOOOI_K8S_NAMESPACE(預設 "awoooi-prod")
- mcp_bridge.py:5 處 parameters.get("namespace", "awoooi-prod") → settings.AWOOOI_K8S_NAMESPACE
- EwoooC/Tsenyang 可設自己的 namespace
### P1-24 decision_manager.py — silence key 常數統一
- 新增 from src.services.telegram_gateway import SILENCE_KEY_PREFIX
- f"telegram_silence:{target}" → f"{SILENCE_KEY_PREFIX}{target}"
- 消除跨兩處重複定義(ADR-118 No Island Coding 原則)
## Phase 1 Task 1.7 Integration Tests
- tests/integration/test_awooop_phase1_schema.py:31 個測試案例
- awooop_projects CHECK 約束(4 cases)
- revision 不可變性 trigger(5 cases:draft 可改、published 鎖住、身份欄不可改、非法流轉、DELETE 禁止)
- awooop_published_revisions VIEW draft/published 隔離(2 cases)
- active_pointer_guard(3 cases:不可指向 draft、可指向 active、跨租戶 mismatch)
- RLS fail-closed(3 cases:未設/錯設/正確設 project_id)
- outbox FK + dedup(2 cases)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-04 13:46:19 +08:00
Your Name
b4055c5915
feat(embedding): ADR-110 升級 bge-m3:latest 1024 維向量
...
Code Review / ai-code-review (push) Successful in 57s
run-migration / migrate (push) Failing after 44s
GCP-A (34.143.170.20) 無 nomic-embed-text,改用 bge-m3:latest(專用
多語言 embedding 模型),產生 1024 維向量。
變更:
- embedding_service.py: 加入 bge-m3:latest=1024 維到 MODEL_DIMENSIONS,
預設模型改為 bge-m3:latest,更新文件說明
- playbook_embedding_repository.py + interfaces.py: 更新維度說明
- migrations/embedding_bge_m3_1024.sql: pgvector schema 遷移
rag_chunks + playbook_embeddings vector(768) → vector(1024)
- scripts/reembed_bge_m3.py: 遷移後重新嵌入現有資料的 script
遷移步驟:
1. 執行 embedding_bge_m3_1024.sql(清空現有 768 維向量,變更維度)
2. 執行 python scripts/reembed_bge_m3.py 重新嵌入
2026-05-04 ogt + Claude Sonnet 4.6
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-04 11:18:20 +08:00
Your Name
0068440388
fix(failover): Gemini 永遠附在 Ollama fallback 鏈尾(ADR-110 漏加)
...
Code Review / ai-code-review (push) Successful in 54s
CD Pipeline / tests (push) Successful in 1m55s
CD Pipeline / build-and-deploy (push) Successful in 41m6s
CD Pipeline / post-deploy-checks (push) Successful in 3m36s
GCP-A HEALTHY → fallback=[GCP-B, Local, Gemini]
GCP-B HEALTHY → fallback=[Local, Gemini]
與舊 111 HEALTHY → fallback=[Gemini] 行為一致,保留雲端最後防線。
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 23:03:34 +08:00
Your Name
4461c2778d
fix(model-probe): 補回 ollama_188 provider 判斷(ADR-110 漏刪)
...
Code Review / ai-code-review (push) Successful in 51s
CD Pipeline / tests (push) Failing after 1m13s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
188 CPU-only 主機雖移出 routing chain,但 probe 仍可被呼叫。
保留 192.168.0.188 → "ollama_188" 映射,避免 test_success_188_provider 失敗。
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 22:52:24 +08:00
Your Name
b1ef05fa8c
feat(ollama): ADR-110 GCP 三層容災架構(GCP-A → GCP-B → Local → Gemini)
...
Code Review / ai-code-review (push) Successful in 50s
CD Pipeline / tests (push) Failing after 1m14s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
## 變更摘要
- Primary: http://34.143.170.20:11434 (GCP-A SSD, 9x 載速 + 2x 推理)
- Secondary: http://34.21.145.224:11434 (GCP-B SSD)
- Fallback: http://192.168.0.111:11434 (M1 Pro Local HDD,最後防線)
- 廢止 ADR-105「111 唯一鐵律」,新建 ADR-110
## 核心改動
- config.py: 新增 OLLAMA_SECONDARY_URL;validator 加 GCP IP 白名單(34.143.170.20, 34.21.145.224)
- ollama_failover_manager.py: 三層 Ollama 決策矩陣;並行健康檢查三台;health_111 → health_gcp_a
- ollama_health_monitor.py: host label 萃取改為通用版(支援 GCP 公網 IP)
- failover_alerter.py: 故障/恢復主機動態顯示,不再硬編碼「Ollama 111 (GPU)」
- ollama_auto_recovery.py: notify_recovery 改為 ollama_gcp_a;recovered_host 動態
- k8s/awoooi-prod: configmap + deployment + network-policy 同步更新(egress 加 GCP /32)
- 服務層: 10 個服務檔案硬編碼 192.168.0.111 改為讀 settings.OLLAMA_URL
- 測試: URL 常數更新,新增三層容災場景,GCP IP 白名單驗證測試
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 22:49:23 +08:00
Your Name
e45b055e0e
feat(governance): AI 治理事件處理鏈四軌交付(C/D/B/A)
...
Code Review / ai-code-review (push) Successful in 48s
run-migration / migrate (push) Failing after 45s
CD Pipeline / tests (push) Successful in 3m46s
Type Sync Check / check-type-sync (push) Successful in 2m8s
CD Pipeline / build-and-deploy (push) Failing after 31m14s
CD Pipeline / post-deploy-checks (push) Has been skipped
【十二人專家團隊全景掃描 + 並行四軌實施】
統帥質疑「有讓 12-agent 一起協作嗎」後,依照團隊規則完成全鏈路交付:
onboarder + critic + db-expert + debugger + frontend-designer 並行掃描,
找到 6 大 Gap,再由 fullstack-engineer × 4、refactor-specialist 協作落地。
【Track C — trust_drift 雙寫整併】
兩條獨立寫 event_type=trust_drift 路徑互不呼叫,下游 consumer 拿到雙份資料
無法判定 source-of-truth。整併保留 governance_agent.check_trust_drift(功能
更全:auto-deprecate + Telegram + PG),TrustDriftDetector 降為純統計 lib,
W-6 watchdog 改呼叫 governance_agent。新增 TestSinglePgWritePerDriftScenario
驗證同一 drift 場景只觸發一次 PG 寫入。
變更:
- apps/api/src/services/trust_drift_detector.py(lib only,不再寫 PG)
- apps/api/tests/test_trust_drift_watchdog.py(W-6 改 mock governance_agent)
【Track D — governance_remediation_dispatch 派遣表】
ai_governance_events 是不可變 Event Sourcing,不能塞執行狀態。新建派遣表
作為投影層:1 event → 0..N dispatches,狀態可變、可重試、可審計。
- PgEnum 5 種 event_type + 7 階段狀態機(pending → dispatched → executing →
succeeded/failed/cancelled/skipped)
- 失敗重試 INSERT 新 row(不改舊 row 的 status,保留審計痕跡)
- Partial unique index ux_grd_one_active_per_event 強制「同事件唯一活躍」
- 4 個複合 index 支援 worker poll、去重查詢、觀測面板
- FK 對應 ai_governance_events / playbooks / incidents / approval_records
全部 SET NULL(avoid cascade lock,但 governance_event 用 RESTRICT)
變更:
- apps/api/src/db/models.py(GovernanceRemediationDispatch ORM class)
- apps/api/migrations/governance_remediation_dispatch_2026-05-03.sql
- apps/api/src/repositories/governance_remediation_dispatch_repo.py
(6 個 async 函式 + 3 個自訂例外:DispatchAlreadyActive /
InvalidStatusTransition / DispatchNotFound)
- apps/api/src/models/governance_dispatch.py(DecisionContextV1 等 4 schema)
- apps/api/tests/test_governance_remediation_dispatch.py(29 tests)
【Track B — /governance 頁面】
後端 PR1 三個 endpoint + 前端 PR2-5 完整三 Tab。
PR1 後端:
- GET /api/v1/ai/governance/events(events_tab,含 event_type/severity/
狀態/時間範圍篩選 + 分頁)
- GET /api/v1/ai/governance/queue(queue_tab,含 graceful fallback:
dispatch 表不存在時回 table_pending=True 不拋 500)
- GET /api/v1/ai/governance/summary(slo_tab 30d 違反時序圖)
- severity 映射規則寫死(critic 建議未來移 settings)
PR2-5 前端:
- /governance 路由 + AppLayout + Compliance Badge 橫幅 + PageTabs
- SLO Tab:3 KPI 卡片(Syne 28px + StatusOrb + 7d sparkline)+
30d 違反 stacked BarChart
- Events Tab:篩選列 + 表格 + inline 展開行(JSON / 修復建議 / 派遣記錄)
- Queue Tab:HITL 待辦卡片 + 信任度進度條 + 批准/拒絕按鈕(本 PR console.log)
- Sidebar 加入「AI 治理」入口(ShieldCheck icon)
- i18n 雙語完整(governance namespace + nav.governance)
- 7 個新元件:slo-kpi-card / slo-violation-chart / events-table /
events-filter-bar / event-detail-drawer / queue-item-card / queue-history-tabs
變更:
- apps/api/src/api/v1/ai_governance.py(router)
- apps/api/src/services/governance_query_service.py
- apps/api/src/models/governance.py(Pydantic V2 schemas)
- apps/api/tests/test_ai_governance_endpoints.py(21 tests)
- apps/web/src/app/[locale]/governance/(page + 3 tabs)
- apps/web/src/components/governance/(7 元件)
- apps/web/messages/{zh-TW,en}.json(governance namespace)
- apps/web/src/components/layout/sidebar.tsx(+1 行)
- apps/api/src/main.py(router include)
【Track A — GovernanceDispatcher 決策融合】
把治理事件接到 remediation 執行器,走北極星方向決策融合(LLM × Playbook trust
× MCP),符合「禁寫死規則」鐵律。
- 設計鐵律:DecisionFusionAdapter 是新增 wrapper,**不修改任何 Tier 3 檔**
(decision_manager / learning_service / trust_engine),只 consume 既有 API
- 三維融合公式:confidence = 0.4×llm + 0.3×playbook_trust + 0.3×mcp_consistency
(權重加 TODO 標明未來由 AI 自學調整)
- 三分支決策路徑:
confidence ≥ 0.85 → auto_dispatch(status=dispatched)
0.65 ≤ confidence < 0.85 → pending_approval(HITL)
confidence < 0.65 → skip + log
- decision_context JSONB 完整記錄三維輸入快照(給未來 fine-tune 用)
- poll 30s 掃 unresolved 事件,仿 governance loop 模式
- 重複事件擋去重(呼叫 get_active_for_event)
變更:
- apps/api/src/services/governance_dispatcher.py
- apps/api/src/services/decision_fusion_adapter.py
- apps/api/tests/test_governance_dispatcher.py(14 tests)
- apps/api/src/main.py(lifespan task 接 run_governance_dispatcher_loop)
【驗證】
1836 個 unit test 全過(29 skipped 為既有 PG integration env 問題)
【調度教訓 — 已記入 memory】
- vuln-verifier 應在 fullstack-engineer **之前**跑(避免並行讀到已修代碼誤判)
- critic 雙輪審查不可省(第二輪抓到 NaN sentinel + Prom rule 連鎖)
- 北極星「禁寫死規則」搭配 decision-fusion 確實實施
【未動 Tier 3 — 已驗證】
git diff 確認本 commit 完全沒改 decision_manager.py / learning_service.py /
trust_engine.py,只新增 wrapper service consume 既有 API。
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 12:42:40 +08:00
Your Name
8fb0c5df33
feat(heartbeat): noise reduction — silent 6h + warnings hash dedup
...
Code Review / ai-code-review (push) Successful in 47s
CD Pipeline / tests (push) Successful in 2m11s
CD Pipeline / build-and-deploy (push) Failing after 31m12s
CD Pipeline / post-deploy-checks (push) Has been skipped
P0 #4 (徹底長期修系列) — 統帥鐵證:「INFO | AWOOOI 系統報告」每 30 分鐘
推一次,一天 48 條同樣內容,即使我修了 P0 #3 假警報,每天的「全系統正常」
重複推送本身就是噪音,讓統帥誤以為告警還在重複。
修法(不違反「監控工具必須被監控」鐵律 — 健康狀態仍每 6h 推 1 次「我活著」):
| 狀況 | 推送行為 |
|------|---------|
| 健康(無 warnings)| 6h 內最多 1 次「我活著」訊號 |
| 有 warnings 跟上次同 hash | 跳過 |
| 有 warnings 跟上次不同 | 立即推送(新狀況不漏)|
| 健康 ↔ 有事 切換 | 自動清掉相反 marker |
Redis keys:
- `heartbeat:silent_last_sent` — 健康狀態 silent marker, TTL=6h
- `heartbeat:warnings_hash` — 上次 warnings 的 md5[:12], TTL=24h
效果:統帥每天從 48 條 heartbeat → ~4 條(健康狀態 4×6h),有事立即推。
Tests: 6 passed (test_heartbeat_dedup_p0_4.py)
- healthy_first_send_goes_through
- healthy_second_send_within_6h_skipped
- warnings_unchanged_skipped
- warnings_changed_pushes
- warnings_to_healthy_clears_warnings_hash
- healthy_to_warnings_clears_silent_marker
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 01:48:57 +08:00
Your Name
2ce722bda9
feat(heartbeat): full K8s pod lifecycle state machine + regression tests
...
Code Review / ai-code-review (push) Successful in 51s
CD Pipeline / tests (push) Successful in 2m59s
CD Pipeline / build-and-deploy (push) Has started running
CD Pipeline / post-deploy-checks (push) Has been cancelled
P0 #3 (徹底長期修系列) — 把 daily report 的 pod 健康判斷從「ready=False 一律告警」
升級到完整 K8s pod lifecycle state machine:
| Phase | 行為 |
|-------|------|
| Succeeded / Completed | 跳過(CronJob/Job 跑完正常) |
| Failed | 必告警 |
| Unknown | 必告警 |
| Pending <5min | 跳過(剛 schedule 合理) |
| Pending >=5min | 告警「image pull / scheduling 卡住」|
| Running ready=True | 健康,跳過 |
| Running ready=False <2min | 跳過(剛起來 probe 還沒過)|
| Running ready=False >=2min | 告警「readiness probe fail / 啟動異常」|
| restarts >=3 | 必告警(無論 phase)|
實作:
- PodInfo 加 start_time: Optional[str](從 .status.startTime)
- _get_pod_status kubectl custom-columns 加 STARTTIME
- _build_warnings 完整 state machine + 閾值常數
regression test (test_heartbeat_pod_state_machine.py 13 個) 覆蓋每個 phase
+ 邊界條件,含 2026-05-02 統帥截圖鐵證重現(3 個 drift-scanner Succeeded
pod 不該觸發「需關注 3 項」假警報)。
Tests: 13 passed (新增 test_heartbeat_pod_state_machine.py)
接續 a38d9112(單純 Succeeded skip),這次徹底處理 Pending/Failed/Unknown
+ 時間閾值 + 沒 start_time 的保守告警。
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 01:44:58 +08:00
Your Name
f1362fcc8d
fix(governance): 修治理告警 4 個 silent failure + Prom sentinel 連鎖
...
Code Review / ai-code-review (push) Successful in 49s
CD Pipeline / tests (push) Successful in 2m9s
CD Pipeline / build-and-deploy (push) Failing after 31m11s
CD Pipeline / post-deploy-checks (push) Has been skipped
【全景檢測:12-agent 並行掃描定位 4 大 bug 與 1 個 P0 連鎖回歸】
Bug 1(P0 silent failure)— governance_agent.check_trust_drift
原 `await db.commit()` 縮排錯在 async with 區塊外(8 空格 vs 12),
session 已 auto-commit 關閉,二次 commit 拋 InvalidRequestError 被吞,
governance_trust_drift_auto_deprecated log 從不出現。修:commit/log 移回 with 內。
附 AST regression guard test 擋退化。
Bug 2 — flywheel_stats_service / W-3 fresh deploy 假告警
Redis 空時 total_exec=0 → rate=0.0 → watchdog `< 0.30` 立即觸發
「飛輪成功率 0%」假告警。修:total_exec < FLYWHEEL_MIN_SAMPLE(10) 回 None,
watchdog 判 None 跳過 W-3。Prometheus sentinel 用 NaN(非 -1.0)
避免觸發 ops/monitoring/alerts.yml:775 等 3 份 prom rule 的 `< 0.1`
條件造成 2h 後假告警連鎖。前端 type 同步 number | null。
Bug 3 — failover_alerter dedup key
原 key 只看 event_type 不看 payload,trust_drift 4→25 IDs 變動全被
1h dedup 吞掉。修:dedup key 加 sha256(impact subdict)[:8],event_type
sanitize 防特殊字元污染 Redis key。
Bug 4 — ai_slo_watchdog_job W-4 evolver 全封存初始化誤報
原邏輯 approved==0 即告警,未排除「playbooks 表初始化中」場景。
修:_count_approved_playbooks 回 (approved, total),total==0 → skip。
【執行結果】
- 39 個相關 unit test 全過(test_failover_alerter / test_governance_agent /
test_trust_drift_watchdog / test_check_trust_drift_commit_outside_context_poc)
- 6 個關鍵路徑實測:NaN sentinel / float 渲染 / hash 區分性 / dedup 同 impact
相同 hash / datetime 容錯 / 4 檔 py_compile 全過
【調度教訓 — 留作未來改進】
- 12-agent 並行調度時,vuln-verifier 與 fullstack-engineer 競態
導致 vuln-verifier 讀到已修代碼誤判 NOT REPRODUCIBLE。
未來:vuln-verifier 應在 fullstack 之前執行,或用 git show HEAD~1 對比修復前。
- fullstack-engineer 引入 P0 regression(f-string 內嵌 ternary 非法 format spec),
critic 抓到 + Prom sentinel 連鎖 — 證明 critic 審查必要不可省。
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-03 00:18:57 +08:00
Your Name
b710f3f38f
feat(governance): normalize AI治理告警輸出與元告警解析度
CD Pipeline / tests (push) Failing after 25s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
Code Review / ai-code-review (push) Successful in 46s
2026-05-02 23:49:59 +08:00
Your Name
a38d911213
fix(heartbeat): exclude Succeeded/Completed CronJob pods from warnings
...
Code Review / ai-code-review (push) Successful in 50s
CD Pipeline / tests (push) Failing after 1m22s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
統帥 23:30 截圖鐵證:每日系統報告永遠列「需關注 3 項:
Pod drift-scanner-* 未就緒 (Succeeded)」,讓人誤以為告警重複。
實際上 Succeeded/Completed 是 CronJob/Job 跑完的成功狀態,
ready=False 是設計(容器已退出)— 不該算 warning。
修法:heartbeat_report_service.py:704 加判斷跳過 Succeeded/Completed pods。
預期效果:今天 23:30 的「需關注 3 項」明天起會降為 0 項,daily report
header 從「需關注 N 項」變回「全系統正常」。
Tests: 50 passed (heartbeat 相關)
注意:working tree 還有 statq Codex 未 commit 的 7 個檔案改動
(approval_execution.py 有 indentation error 半成品),本 commit 只動
heartbeat_report_service.py 單檔,不誤碰其他。
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-02 23:48:31 +08:00
Your Name
dedb12085b
chore(governance,watchdog): enrich alerts and enable prometheus multiproc
CD Pipeline / tests (push) Failing after 1m22s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
Code Review / ai-code-review (push) Successful in 43s
Deploy Alert Rules / Deploy Prometheus Alert Rules (push) Successful in 57s
2026-05-02 23:44:12 +08:00
Your Name
b371edb70c
fix host alert auto-repair routing and backup false positives
2026-05-02 23:44:12 +08:00
Your Name
da772a1605
fix(decision): block kubectl actions on bare_metal host alerts
...
Code Review / ai-code-review (push) Successful in 54s
CD Pipeline / tests (push) Successful in 3m47s
CD Pipeline / build-and-deploy (push) Successful in 13m26s
CD Pipeline / post-deploy-checks (push) Successful in 5m45s
When HostHighCpuLoad / HostOutOfMemory fire on a bare-metal host
(192.168.0.110 et al, where Sentry / ClickHouse / Snuba are eating
CPU), the LLM kept proposing "kubectl rollout restart awoooi-api",
which is a wrong-domain action — restarting awoooi cannot fix a
third-party process's CPU usage on the host. Auto-execute would then
either run the no-op kubectl restart (wasted) or escalate after
ssh_diagnose because no safe action was found, producing the
"AI 自動修復失敗" Telegram noise the user just complained about.
Adds a guard at the top of DecisionManager._auto_execute: if the
incident's primary signal carries host_type=bare_metal AND the
proposed action starts with "kubectl", refuse to execute. The
incident is marked READY with a clear blocked_reason so human
operators see why automation declined, and emergency_escalation
records the event in AOL for audit.
Also patches /home/wooo/monitoring/alerts.yml on 110 (and the new
ops/monitoring/alerts.yml in repo) to add an explicit
auto_repair_action annotation on HostHighCpuLoad / HostOutOfMemory
that hints LLM toward `ssh ... ps aux` rather than kubectl restart.
Prometheus reload returned 200.
Tests: tests/test_decision_manager_bare_metal_kubectl_guard.py
covers (1) bare_metal+kubectl blocked, (2) kubectl get also blocked,
(3) bare_metal+ssh NOT blocked, (4) k8s host_type+kubectl NOT
blocked, (5) missing host_type label NOT blocked.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-02 17:41:28 +08:00
Your Name
47342dfb34
fix(escalation): dedup escalation card by fingerprint + 24h TTL
...
Code Review / ai-code-review (push) Successful in 55s
CD Pipeline / build-and-deploy (push) Has been cancelled
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / tests (push) Has been cancelled
接續 b3a0f0d7(decision card dedup)—— 統帥 17:35 鐵證:4 條 ESCALATION P0
連發(HostOutOfDiskSpace + 3×HostDiskUsageHigh,全 target=node-exporter-110,
全不同 INC ID C9CD6E/FB7944/559B54/C1BBF3)。
decision card 修了但 escalation card 走另一條路徑,根因相同:
- emergency_escalation_service.py:31 dedup key 綁 incident_id (uuid4 隨機)
- TTL 900s 比 sweeper 重觸週期 1h 短
修法:
- escalate_auto_repair_unavailable() 改用 alertname+target fingerprint dedup
- TTL 900s → 86400s,與 decision_manager.py:574 對齊
drift_auto_adopt 路徑暫不動(TTL 已 3600s + report_id 非隨機,非當前問題)。
Tests: 7 passed (escalation/emergency 相關用例)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-02 17:38:54 +08:00
Your Name
b3a0f0d766
fix(telegram): dedup by fingerprint + 24h TTL to stop repeat alerts
...
CD Pipeline / tests (push) Successful in 2m22s
Code Review / ai-code-review (push) Successful in 57s
CD Pipeline / build-and-deploy (push) Successful in 21m3s
CD Pipeline / post-deploy-checks (push) Successful in 5m2s
Telegram 重複發告警鐵證(4 個 agent 真實數據):
- INC-6FE3BD (HostBackupFailed) 24h 內被推 15 次
- INC-FD6E21 (HostHighCpuLoad) 24h 內被推 6 次
- 06:44:18 同秒兩送 = pod 並發 race
根因:
1. `telegram_sent:{incident_id}` dedup key 綁 uuid4 隨機 INC ID,
同 fingerprint 換新 INC 完全不去重
2. dedup TTL=600s 比 incident_analysis_sweeper 重觸週期 1h、
alertmanager repeat_interval 4h 都短 → 每輪都過期通過
3. pod restart 走 _resend_unconfirmed_ready_tokens 用同一 incident_id key
→ 重啟必炸一波
修法(不消音、是「AI 認得這是同一事故」):
- decision_manager.py:207-225 dedup key 改 alertname+target fingerprint
- decision_manager.py:573-578 TTL 600s → 86400s (蓋住 sweeper 1h × alertmanager 4h)
- decision_manager.py:3189-3208 pod restart resend 路徑同步改 fingerprint
- incident_analysis_sweeper.py:37-42 sweeper_done TTL 3600s → 86400s
預期:同症狀 24h 內最多發 1 張 decision card;resolved 後 line 220-226
status check 會 early return,不影響復發偵測。
Tests: 35 passed (test_telegram_adr050 + test_decision_manager_docker_prune_routing)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-02 16:25:48 +08:00
Your Name
84ba3216ee
feat(notifications): tag autonomous repair actions with [AUTO] prefix
...
Code Review / ai-code-review (push) Successful in 57s
CD Pipeline / tests (push) Successful in 2m36s
CD Pipeline / build-and-deploy (push) Failing after 31m11s
CD Pipeline / post-deploy-checks (push) Has been skipped
Per user request: every AI-driven repair must surface a Telegram trace
even when it succeeds, so nobody can later deny what the autonomy did.
Adds 🤖 [AUTO] markers and an explicit `Actor: leWOOOgo (autonomous)`
line to both success and failure status messages emitted by
_push_auto_repair_result, making them clearly distinguishable from
human-clicked approval cards.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-02 12:49:43 +08:00
Your Name
3059897318
feat(governance): auto-deprecate low-trust unused playbooks (>30d)
...
Code Review / ai-code-review (push) Successful in 41s
CD Pipeline / tests (push) Successful in 3m29s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
trust_drift previously fired alerts forever for playbooks stuck below
the 0.2 threshold. With user authorization for governance-class
auto-fixes, check_trust_drift now retires playbooks that have been
unused for 30+ days (or never used and created 30+ days ago) by
flipping status to 'deprecated' before alerting.
Alerts now report drifted_count, auto_deprecated_count, and the kept
playbook_ids that still need human review (those in their 30d trial
window). Existing alert noise from the four currently-drifted
playbooks should drop to whatever fraction is genuinely in trial.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-02 12:31:37 +08:00
Your Name
607358c4dd
fix(approval): route SSH actions through SSHProvider on manual approve
...
parse_operation_from_action only knew kubectl and Chinese restart phrases,
so any "ssh host '...'" action approved via Telegram fell through to
"Could not parse operation type" and reported a fake failure even though
the LLM had proposed a valid host repair.
Adds OperationType.SSH_HOST, makes the parser detect ssh prefixes (with
optional flags / user@host) before kubectl patterns, and routes the
SSH_HOST branch in approval_execution.execute_in_background through
SSHProvider with the same tool keywords decision_manager uses
(ssh_docker_prune / ssh_docker_restart / ssh_systemctl_restart /
ssh_diagnose). Unroutable SSH actions now fail loudly with a descriptive
error instead of silently breaking.
Trigger: 2026-05-02 incidents INC-20260502-D6D0B7 / E12EE4 / 557055
were approved by the user but executor reported "Could not parse" and
left the alerts pending.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-02 12:31:37 +08:00
Your Name
3156ff1c69
feat(aiops): add ssh_docker_prune to auto-repair flywheel for disk-full alerts
...
Adds Group B SSH MCP tool ssh_docker_prune (image+volume+builder prune
with ≥75% disk usage gate) and routes "docker prune" actions through it.
Flips HostDiskUsageHigh from auto_repair=false to true with mcp_provider
routing labels so the flywheel can self-heal next disk-full event without
hitting the emergency_channel Telegram path.
Trigger: 2026-05-01 → 05-02 Telegram alert storm (peak 53/hr) caused by
empty ssh-mcp-key/known_hosts secret rejecting all SSH and forcing every
disk-full alert through "Host key is not trusted → escalate" loop.
known_hosts patched live; this commit closes the playbook gap so the
next occurrence resolves without manual intervention.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-02 12:31:37 +08:00
Your Name
7795f027d2
fix(aiops): persist emergency intervention traces
CD Pipeline / tests (push) Successful in 2m56s
Code Review / ai-code-review (push) Failing after 39s
CD Pipeline / build-and-deploy (push) Successful in 12m54s
CD Pipeline / post-deploy-checks (push) Successful in 4m40s
2026-05-01 20:34:33 +08:00
Your Name
433f7b068e
fix(aiops): close ssh and telegram remediation gaps
CD Pipeline / tests (push) Successful in 2m7s
Code Review / ai-code-review (push) Successful in 42s
CD Pipeline / build-and-deploy (push) Successful in 13m14s
CD Pipeline / post-deploy-checks (push) Successful in 4m29s
2026-05-01 16:53:02 +08:00
Your Name
b0da6da1e9
feat(aiops): structure agent loop shadow output
CD Pipeline / tests (push) Successful in 2m50s
Code Review / ai-code-review (push) Successful in 33s
CD Pipeline / build-and-deploy (push) Failing after 25m48s
CD Pipeline / post-deploy-checks (push) Has been cancelled
2026-05-01 15:09:57 +08:00
Your Name
f8e44971c1
feat(aiops): enable read-only agent loop canary
CD Pipeline / tests (push) Successful in 1m43s
Code Review / ai-code-review (push) Successful in 31s
CD Pipeline / build-and-deploy (push) Successful in 10m22s
CD Pipeline / post-deploy-checks (push) Successful in 4m3s
2026-05-01 14:20:16 +08:00
Your Name
b6cf616707
fix(aiops): harden agent tool permission names
CD Pipeline / tests (push) Successful in 1m32s
Code Review / ai-code-review (push) Successful in 27s
CD Pipeline / build-and-deploy (push) Successful in 8m26s
CD Pipeline / post-deploy-checks (push) Successful in 3m37s
2026-05-01 13:52:33 +08:00
Your Name
7e4d995e4b
feat(aiops): add mcp agent loop foundation
CD Pipeline / tests (push) Successful in 1m59s
Code Review / ai-code-review (push) Successful in 28s
run-migration / migrate (push) Failing after 24s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-05-01 13:21:19 +08:00
Your Name
9db87f177e
fix(aiops): suppress repeated llm alert loops
CD Pipeline / tests (push) Successful in 1m37s
Code Review / ai-code-review (push) Successful in 28s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-05-01 13:02:07 +08:00
Your Name
11673d80ea
fix(aiops): route backup decisions through ssh
CD Pipeline / tests (push) Successful in 1m35s
Code Review / ai-code-review (push) Successful in 34s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-05-01 12:50:01 +08:00
Your Name
2c12bce135
fix(aiops): use existing escalation event type
CD Pipeline / tests (push) Successful in 1m54s
Code Review / ai-code-review (push) Successful in 29s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-05-01 10:56:59 +08:00
Your Name
97be5dedd7
fix(aiops): escalate failed host verification
CD Pipeline / tests (push) Successful in 1m27s
Code Review / ai-code-review (push) Successful in 29s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-05-01 10:47:42 +08:00
Your Name
e4aef6ac4e
fix(aiops): block k8s playbooks for host repair
CD Pipeline / tests (push) Successful in 1m27s
Code Review / ai-code-review (push) Successful in 26s
CD Pipeline / build-and-deploy (push) Successful in 8m6s
CD Pipeline / post-deploy-checks (push) Successful in 3m31s
2026-05-01 10:33:52 +08:00
Your Name
f154ac022e
feat(playbook): version generated playbooks
CD Pipeline / tests (push) Successful in 1m34s
Code Review / ai-code-review (push) Successful in 28s
Type Sync Check / check-type-sync (push) Successful in 1m10s
CD Pipeline / build-and-deploy (push) Successful in 10m19s
CD Pipeline / post-deploy-checks (push) Successful in 3m1s
2026-04-30 23:59:39 +08:00
Your Name
f0d14ab6c4
fix(aiops): escalate blocked auto repair
CD Pipeline / tests (push) Successful in 1m33s
Code Review / ai-code-review (push) Successful in 28s
Deploy Alert Rules / Deploy Prometheus Alert Rules (push) Successful in 40s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-30 23:49:17 +08:00
Your Name
6e04fe9c8a
feat(playbook): generate drafts with local llm
CD Pipeline / tests (push) Successful in 1m28s
Code Review / ai-code-review (push) Successful in 29s
Type Sync Check / check-type-sync (push) Failing after 2m41s
CD Pipeline / build-and-deploy (push) Successful in 8m40s
CD Pipeline / post-deploy-checks (push) Successful in 3m10s
2026-04-30 23:04:58 +08:00
Your Name
95110971f3
fix(telegram): close remaining DM alert routes
CD Pipeline / tests (push) Successful in 1m27s
Code Review / ai-code-review (push) Successful in 29s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-30 23:02:17 +08:00
Your Name
61f5a6a419
fix(telegram): route alerts to SRE war room
CD Pipeline / tests (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
CD Pipeline / post-deploy-checks (push) Has been cancelled
Code Review / ai-code-review (push) Has been cancelled
2026-04-30 15:01:23 +08:00
Your Name
80defbed7c
fix(aiops): fallback and escalate automation blockers
CD Pipeline / tests (push) Successful in 2m41s
Code Review / ai-code-review (push) Successful in 24s
CD Pipeline / build-and-deploy (push) Successful in 7m51s
CD Pipeline / post-deploy-checks (push) Failing after 2m15s
2026-04-30 14:13:57 +08:00
Your Name
ed2a4838f2
fix(auto): use action parser for repair gates
CD Pipeline / tests (push) Failing after 1m2s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
Code Review / ai-code-review (push) Successful in 24s
2026-04-30 14:06:09 +08:00
Your Name
639bb64788
feat(flywheel): surface ai automation and code review
Code Review / ai-code-review (push) Successful in 31s
CD Pipeline / build-and-deploy (push) Failing after 5m23s
2026-04-30 00:09:25 +08:00
Your Name
4a57c2d04f
feat(flywheel): expose incident processing timeline
CD Pipeline / build-and-deploy (push) Successful in 10m56s
2026-04-29 23:38:30 +08:00
Your Name
d845d53257
fix(security): keep Gemini key out of request URLs
CD Pipeline / build-and-deploy (push) Successful in 15m5s
2026-04-29 22:56:12 +08:00
Your Name
fe2b8f4571
fix(flywheel): fallback on OpenClaw degraded responses
CD Pipeline / build-and-deploy (push) Successful in 9m56s
2026-04-29 22:38:57 +08:00
Your Name
dccdcdbaf5
fix(flywheel): unblock action safety and Claude fallback
CD Pipeline / build-and-deploy (push) Successful in 9m45s
2026-04-29 21:51:18 +08:00
Your Name
7b471e7ae2
fix(secret-leak): Gemini API key 從 prod log 清除(P0 SECRET LEAK)
...
CD Pipeline / build-and-deploy (push) Failing after 2m6s
## 問題(2026-04-29 11:50 prod log 證據)
prod log 出現完整 Gemini API key 明碼:
```
"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=AIzaSyCqv7TY2iTGi2wa91d2irwH08VYXjT9YUk "
event: gemini_provider_failed
```
違反鐵律:
- feedback_secret_debug_output_ban.md: debug 含 secret 字串禁 echo/log 原值
- feedback_secrets_leak_incidents_2026-04-18.md: 已有 2 起 secret leak 事故
## 根因
`gemini.py:118` `logger.warning("gemini_provider_failed", error=str(e), ...)`
httpx HTTPStatusError str() 會包含完整 URL(含 ?key=... query string):
- Google Gemini API 設計用 query string 傳 API key(不像 Claude/NVIDIA 用 header)
- httpx 拋例外時把 URL 寫進 error message
- str(e) 直接 log → key 進 K8s pod log → audit log → Sentry → 任何下游 log 接收方
## 修法
新增 `_sanitize_error()` 函式:
- regex `([?&])key=[^&\s'"]+` → `\1key=<redacted>`
- 在 `gemini_provider_failed` log 出口呼叫
- AIResult.error 也用 sanitize 過的(不污染下游)
只修 Gemini(其他 provider 用 header / 內網無 key):
- Claude: API key 在 `x-api-key` header → 不在 URL → 安全
- OpenClaw: 內網 188:8088 → 無 API key → 安全
- Ollama: 內網 111:11434 → 無 API key → 安全
- NVIDIA: API key 在 `Authorization: Bearer` header → 安全
## 驗證
- 1635 unit tests 全綠(修法不破壞任何既有行為)
- 直接執行 sanitize 函式確認 `AIzaSy*` key 被替換成 `<redacted>`
## 已知債
- 此 commit 只防新 leak,**舊 log 中的 key 仍存在**(K8s pod log / Sentry / structlog backend)
- Gemini API key 仍應**輪換**(已洩漏的 key 不可信)
- 統帥需手動:
1. 去 https://aistudio.google.com/apikey 新增 key
2. 在 K8s secret 換 GEMINI_API_KEY
3. 撤銷舊 key
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-29 19:49:09 +08:00
Your Name
3668d49f2f
feat(flywheel): W2 三件 + KMWriter critic 修法(1635 tests 全綠)
...
CD Pipeline / build-and-deploy (push) Failing after 1m38s
W2 (onboarder 4 週飛輪 80→90 路徑第二週) + critic PR review 5 個 critical/major
全部修完,default flag=false 安全無爆炸風險。
## W2 三件 PR
### PR-R2 — AOL → catalog confidence EWMA 回灌(修飛輪斷鏈 C2)
- 新檔 `apps/api/src/jobs/aol_to_catalog_writeback_job.py`
- 邏輯:每小時掃 AOL 計算 EWMA confidence (alpha=0.3) 回灌 alert_rule_catalog
- 失敗閾值 N=5 連續低成功率 → review_status='draft'
- Hermes _fetch_noisy_rules SQL 加 OR review_status='draft'
- ENABLE_AOL_WRITEBACK_JOB=false (default)
- 8 個測試(mock path 修正:lazy import → patch src.db.base.get_db_context)
### PR-V1 — self_healing_validator 串接 (修飛輪斷鏈 C6)
- 新檔 `apps/api/src/services/self_healing_validator.py`(純函數 assess_self_healing)
- post_execution_verifier.py step 5 串接(feature flag gate)
- evidence_snapshot.py 加 self_healing_score / self_healing_detail 欄位
- db/models.py + base.py ALTER IF NOT EXISTS
- score < 0.5 → 觸發 rollback 提案 Telegram alert(不自動執行)
- ENABLE_SELF_HEALING_VALIDATOR=false (default)
- 7 個測試
### PR-L1 — KM ↔ Playbook 雙向回路 (修飛輪斷鏈 C3+C4)
- learning_service.py 三條新邏輯:
1. _write_playbook_evolution_km:promote/demote 寫 KM 演化條目
2. _check_and_mark_playbook_review:N=5 累積觸發 review_required
3. _demote_alert_rule_catalog_confidence:DEPRECATED → confidence×=0.5
- PlaybookRecord 加 review_required 欄位(schema migration via base.py)
- ENABLE_KM_PLAYBOOK_FEEDBACK_LOOP=false (default)
- KM_PLAYBOOK_REVIEW_THRESHOLD=5 可調
- 6 個測試
## KMWriter Critic 5 個 Critical/Major 修復(之前 critic PR review 發現)
之前 push commit c5753e1c 已修,本 commit 補回 stash 中的對應檔案:
- C1 km_writer.py:194 backfill 自打臉(已修:同步 await + DLQ)
- C2 km_writer.py:391 KM_WRITE_AWAIT=false 路徑收緊
- M1 decision_manager.py:2178/2203 移除 _fire_and_forget
- M2 incident_service.py:1099 自製 path 加 retry+DLQ
- M3 km_writer.py:166 冪等聲明對齊(UPSERT + partial unique index)
## 驗證
- 1635 unit tests 全綠(+27 from 1608)
- 與 fb0c72db (推翻 A2 Ollama primary) 共存無衝突
- 所有新 Job/Service default flag=false(不爆炸)
## 期望影響
飛輪斷鏈 C2 + C3 + C4 + C6 全修
飛輪自主化評分:65 → 85 預估(W2 完成後)
啟用順序(待 prod fb0c72db 驗證 OLLAMA primary 跑得起來後):
1. ENABLE_AOL_WRITEBACK_JOB=true
2. ENABLE_KM_PLAYBOOK_FEEDBACK_LOOP=true
3. ENABLE_SELF_HEALING_VALIDATOR=true
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-29 19:44:04 +08:00
Your Name
fb0c72db42
feat(ai-router): 推翻 A2 鐵律 — DIAGNOSE primary 改 Ollama 本地優先
...
CD Pipeline / build-and-deploy (push) Failing after 2m26s
統帥鐵律 2026-04-29:「主要優先用 111 主機的 Ollama」
+ feedback_ai_autonomous_direction.md:以本地免費 LLM 為主
+ feedback_ollama_111_only.md:Ollama 唯一主機 = 111
## 推翻 A2 (2026-04-27 INC-20260425) 的事實基礎
**舊事實**:Ollama = CPU-only deepseek-r1:14b @ 238s(不可用)
**新事實**:prod Ollama 111 = M1 Pro Apple Silicon GPU + qwen2.5:7b-instruct
VRAM 8.2GB 全載入,ctx 32k,實測 hi prompt 0.54s
**雲端全死**(2026-04-29 prod log 證據):
- OpenClaw 188:8088 → 500 Internal Server Error
- Gemini → 429 Too Many Requests(配額爆)
- Claude → 404 Not Found(model claude-3-haiku-20240307 過期)
**不推翻 A2 → 100% incident llm_failed → AI 自動修復永遠不啟動**
## 修改範圍(最小、安全、可驗證)
### ai_router.py
- `_diagnose_fallback_chain`: OLLAMA 第一順位(取代「永久排除」舊註解)
順序:[OLLAMA, OPENCLAW_NEMO, GEMINI, CLAUDE]
- `_intent_provider_overrides[DIAGNOSE]`: OPENCLAW_NEMO → OLLAMA
- 不動 _full_fallback_chain(避免影響 RESTART/SCALE/CONFIG/DELETE)
- 不動 _tool_calling_fallback_chain
- 不動 complexity_map(critic M2 留待後續)
### openclaw.py
- 注入 task_type="diagnose" 到 alert_context(critic C2 真根因)
- 修復 ai_providers/ollama.py:77 timeout 對齊問題:
- 有 task_type → OLLAMA_DIAGNOSE_TIMEOUT_SECONDS=200s
- 沒有 → OPENCLAW_TIMEOUT=30s(不夠 qwen2.5:7b 推理)
- prod log 看到 latency_ms=120014 的根因
- 用 dict(alert_context) 複製,不污染原 context
## Regression Test 同步更新(5 個)
A2 鐵律守門 test 全部反映新鐵律:
- test_p0_diagnose_routing.py::test_diagnose_override_is_ollama
(原 test_diagnose_override_is_openclaw_nemo)
- test_ai_router_diagnose_fallback.py::test_diagnose_fallback_chain_ollama_primary
(原 test_diagnose_fallback_chain_no_ollama)
- test_ai_router_diagnose_fallback.py::test_diagnose_route_primary_is_ollama
(原 test_diagnose_route_fallback_chain_excludes_ollama)
- test_ai_router_diagnose_fallback.py::test_diagnose_route_sync_primary_is_ollama
(原 test_diagnose_route_sync_fallback_chain_excludes_ollama)
- test_ai_router_diagnose_fallback.py::test_build_fallback_chain_for_intent_diagnose_with_ollama_primary
(原 test_build_fallback_chain_for_intent_diagnose_no_ollama)
- test_ai_router_failover_integration.py::test_router_uses_failover_for_diagnose_ollama_primary
(原 test_router_does_not_use_failover_for_openclaw_nemo)
每個 test docstring 都記載歷史脈絡 + 推翻原因。
## 驗證
- 1608 unit tests 全綠
- LLM 路徑 16 個 test 全綠(含 6 個 A2 守門 test 更新版)
- complexity_scorer / failover_manager / intent_classifier 不受影響
## 期望 prod 行為(部署後驗證)
incident 進入 → DIAGNOSE intent → primary OLLAMA (qwen2.5:7b on M1 Pro GPU)
失敗才 fallback → OpenClaw 188 → Gemini → Claude
Ollama 用 200s timeout(之前 30s 不夠)
→ AI 自動修復終於可以啟動,不再 100% llm_failed
## 已知債(後續處理)
- models.json:21 ollama.default 仍是 deepseek-r1:14b(critic C1,但 prod 已自動 route 到實載 model)
- complexity 4/5 仍寫死 gemini/claude(critic M2)
- Gemini API key 在 prod log 明文(需輪換 + sanitize)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-29 11:39:36 +08:00
Your Name
8d24f15183
fix(critic-review): PR-R1 4 Major 修 — wildcard 過濾 + 二次確認 + unverified 旗標
...
CD Pipeline / build-and-deploy (push) Failing after 1m34s
critic PR review 681b5ac9 揭示 4 Major 問題(無 Critical),全部修復。
## Major #1 — generic_fallback wildcard 污染 RAG 語料
位置:rule_to_playbook_migrator.py:128 `_build_symptom_pattern`
問題:generic_fallback 規則的 `alert_names=["*"]` 會原樣寫入 PlaybookRecord,
進 playbook_rag 向量化文字「告警: *」變成普通 token,每筆查詢都會跟它算相似度
→ RAG top-k 可能回 fallback DRAFT 誤導推薦。
修法:在 `_build_symptom_pattern` 過濾 `["*"]`(與 keywords 一致對待)。
## Major #2 — CLI --commit 無二次確認
位置:scripts/migrate_rules_to_playbooks.py
問題:`--commit` 直接寫 prod DB 25 筆 DRAFT,誤跑無法回頭。
修法:
- 加 `--yes` flag(CI / 自動化用)
- 沒帶 `--yes` 時 stdin prompt: "Type 'yes' to confirm"
## Major #3 — yaml_rule kubectl_command 未過 SPF-2 action_parser
位置:rule_to_playbook_migrator.py:153 `_build_repair_steps`
問題:DRAFT 不會自動 promote(門檻 0.9),但人工 review 路徑無安全攔截器。
若有人 UI 一鍵 promote → 含 {target} placeholder 的危險指令直接到 prod。
修法:在 step dict 加 metadata:
- unverified_command: True
- needs_action_parser_review: True
- source: "yaml_rule_migration"
(promote 流程須強制走 action_parser,由 SPF-2 落地時實作)
## Minor 修
- 刪除 dead import `import re`(未使用)
- `enumerate([:3], start=2)` 取代 `if idx >= 4: break`(邊界寫法易誤讀)
## 驗證
- 23 個 PR-R1 測試全綠(修法不破壞既有行為)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-29 10:56:32 +08:00
Your Name
681b5ac949
feat(flywheel): W1 PR-R1 規則→Playbook 遷移 + PR-K1 timeline 防禦 ALTER
...
run-migration / migrate (push) Failing after 12s
Type Sync Check / check-type-sync (push) Successful in 1m25s
CD Pipeline / build-and-deploy (push) Failing after 1m48s
W1 第二波:onboarder 飛輪 80→90 路徑剩餘兩件 PR。
## PR-R1 — 25 條 yaml 規則 → DRAFT Playbook 遷移
斷鏈背景(onboarder C2):alert_rules.yaml 25 條規則 68% 寫死 RESTART,
沒有對應 Playbook → RAG 永遠 generic_fallback → 規則命中率沒回饋給 catalog。
修法:
- 新建 services/rule_to_playbook_migrator.py
- 自動從 alert_rules.yaml 解析每條 rule
- 產生 PlaybookRecord(status=DRAFT, ai_confidence=0.3, source=YAML_RULE)
- 誠實標示信心 0.3(非假 1.0,違反 feedback_confidence_truthfulness)
- INSERT ON CONFLICT 冪等(name LIKE 'AutoMigrated: %' 去重,不擾動 seed)
- 新建 scripts/migrate_rules_to_playbooks.py(CLI: --dry-run/--commit/--disable-flag)
- ENABLE_RULE_MIGRATION_DRAFT=true(rollback flag)
- 23 測試覆蓋(parse / build_dict / idempotent / dry_run / action_type /
severity_map / feature_flag / wildcard_filter / partial_existing 等)
## PR-K1 — timeline_events 防禦性 ALTER(db-expert finding)
任務原前提錯誤:onboarder 報告的 C7 斷鏈(incident_id 欄位)在
2026-04-24 P1.6 已修復 ORM。但生產環境若在 P1.6 前已建表,create_all 跳過
已存在的表 → ORM 寫入 SELECT 仍可能找不到 column。
修法:
- db/base.py:init_db() 補防禦性 ALTER:
ALTER TABLE timeline_events ADD COLUMN IF NOT EXISTS incident_id VARCHAR(64);
CREATE INDEX IF NOT EXISTS ix_timeline_incident_id ON timeline_events(incident_id);
- IF NOT EXISTS 為 no-op 安全(已有 column 不做事)
- stage 欄位是任務描述的幻覺(codebase 0 writer),不新增
未做:
- alembic migration(專案不用 alembic,遵循既有 init_db ALTER pattern)
- onboarder C7 在 ORM 層已修,本 commit 確保 prod schema 對齊
## 驗證
- 1608 unit tests 全綠(+23 from 1585)
- PR-R1 23 個測試獨立通過
## 期望影響
- 飛輪 RAG 終於有 25 條 DRAFT Playbook 可查 → +5 分
- prod schema 對齊保險 → 防 ORM SELECT 失敗
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-29 10:49:25 +08:00