Commit Graph

882 Commits

Author SHA1 Message Date
Your Name
0d81b28b1b fix(aiops): bound phase2 timeout and repair incident links
All checks were successful
E2E Health Check / e2e-health (push) Successful in 52s
CD Pipeline / build-and-deploy (push) Successful in 9m24s
2026-04-24 23:53:56 +08:00
Your Name
e75e4678a9 feat(p2.4): Telegram 中間態推播 — 分析中佔位卡 + 完成後自動刪除
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
P2.4 實作 2026-04-24 ogt + Claude Sonnet 4.6

問題: LLM 分析耗時 10-30s,期間 Telegram 無任何回應,使用者不知系統在處理

修復:
- telegram_gateway.py: 新增 send_analyzing_placeholder() — 發送「AI 正在分析中...」佔位卡
- telegram_gateway.py: 新增 delete_message() — 刪除佔位卡
- webhooks.py: LLM 分析前 3s 內送出佔位卡(超時不阻塞主流程)
- webhooks.py: _push_to_telegram_background 收到 placeholder_message_id → 完整卡發出後刪除佔位卡
- webhooks.py: import asyncio(補缺漏)

效果: 使用者在告警到達 <3s 內即看到「分析中...」訊息,完整卡出現後自動清除

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 15:56:26 +08:00
Your Name
bb5f16f8ef fix(aiops-p2): P2.1 LLM品質三修 — Evidence-First + consensus confidence + raw_evidence注入
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
根因:
- consensus_engine 四 ExpertAgent confidence=0.0 → 加權投票 total=0 → 永遠返回 NO_ACTION
- prompts.py 無 Evidence-First 指令 → LLM 靠記憶推理,無真實環境約束
- openclaw.py analyze_alert 建 prompt 未注入 MCP evidence (diagnosis_context)

修復:
- consensus_engine: SRE/Security/Cost/Performance 依訊號強度設 0.45~0.80 confidence
- consensus_engine: _normalize_action 加「重新啟動」別名 → RESTART
- consensus_engine: SecurityAgent 移除未使用的 _target 變數
- prompts.py: 加 Evidence-First Protocol + Skepticism Rules 區塊
- openclaw.py: analyze_alert 提取 diagnosis_context → <raw_evidence> 注入 full_prompt

驗證: consensus score 從 0.0 → 0.744(CrashLoop 測試案例)

P2.1 fix 2026-04-24 ogt + Claude Sonnet 4.6

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 15:52:25 +08:00
Your Name
04ff22563e fix(aiops-p1): Playbook 學習閉環 5斷點全修 + DB Migration(ADR-092 B4)
Some checks failed
run-migration / migrate (push) Failing after 14s
CD Pipeline / build-and-deploy (push) Failing after 2m7s
【P0.4 補丁】pre_decision_investigator Prometheus query 欄位缺失
- _build_tool_params() 補 "query" 欄位(prometheus_query tool 必要參數)
- 新增 _build_prometheus_query() — 依告警類型生成 PromQL(CPU/Memory/Crash/Disk/HTTP/Pod/fallback)
- 修復後 D3_METRICS 感官維度實際取得資料(原本 100% 回 missing_query_parameter)

【P1 Playbook 學習閉環 B1-B5 全修】
- B2 db/models.py: ApprovalRecord 新增 matched_playbook_id 欄位 + ix_approval_matched_playbook index
- B2 db/models.py: TimelineEvent 新增 incident_id 欄位(MCP 稽核用)+ index
- B3 approval_db.py: record→ApprovalRequest 補回 incident_id + matched_playbook_id
- B4 approval_repository.py: 同 B3(兩個轉換函式必須同步)
- B5 approval_db.py: approval_request_to_record_data 補 matched_playbook_id → DB 才能存值

【P1.5 KM 寫入】approval_execution.py: fire-and-forget → await wait_for(30s)
- 根因:asyncio.create_task 在 Pod recycle 時被殺,KM 寫入靜默遺失
- 修復:await asyncio.wait_for(..., timeout=30.0) + TimeoutError log

【Migration 文件】adr092_p1_learning_chain_fix.sql
- ALTER TABLE approval_records ADD COLUMN matched_playbook_id VARCHAR(36)
- ALTER TABLE timeline_events ADD COLUMN incident_id VARCHAR(64)
- 執行:psql $DATABASE_URL -f apps/api/migrations/adr092_p1_learning_chain_fix.sql

【附帶 Agent 改動】
- decision_manager: Phase 2 YAML NO_ACTION 優先門(主機層/外部服務跳過 Agent Debate)
- alert_rules.yaml: Sentry/ClickHouse + HostDiskUsageHigh/Critical 新規則
- solver_agent: action_title 語意合成兜底(取代靜默丟棄)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 15:41:35 +08:00
Your Name
7f4088bcd0 fix(aiops-p0): 六大病根 P0 全面修復(ADR-092 B4)
【P0.1】knowledge_extractor_service.py:210 — AttributeError 修復
- Signal.description 欄位不存在(100% 失敗,KM 每天+5 根因)
- 改用 alert_name + annotations.summary 拼接文字

【P0.2+P0.3】Gate 9+11 唯讀指令鬆綁
- blast_radius_calculator: kubectl get/top/describe/logs/version → score=1(非 50)
- operation_parser: 增加 INVESTIGATE 類型識別(唯讀 kubectl 不回 None)
- executor.py: OperationType 新增 INVESTIGATE enum
- approval_execution.py: INVESTIGATE 路徑直接呼叫 execute_kubectl_command

【P0.4】MCP SSH/K8s Provider 修復
- decision_manager: params= → parameters=(符合 MCPToolProvider.execute 簽名)
- decision_manager: MCPToolResult .get() → .success/.output(dataclass 用法)
- decision_manager + ssh_provider: 補入 hosts 120/121(原 default 缺失)
- auto_approve: phase2_agent_debate source bypass confidence 閾值

【P0.5】告警規則語義矛盾修復
- alert_rules.yaml: 8 條 kubectl 查詢規則 RESTART_DEPLOYMENT → NO_ACTION
  (CrashLoopBackOff/PostgreSQL 連線/慢查詢/MinIO 磁碟/K3s 節點/告警鏈路/SSL/CoreDNS 等)
- incident_service.py: cAdvisor/CoreDNS 從 general 拆出獨立分類

【P0.6】proactive_inspector 動態基線 PromQL 全修
- 5 個 MONITORED_METRICS PromQL 全部修正(cadvisor label/datname/blackbox)
- db_connection_pool: datname="awoooi" → "awoooi_prod"
- http_error_rate: 無效 http_requests_total → blackbox probe_success
- cpu/memory: namespace label → name=~"k8s_api_awoooi-api.*"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 15:32:23 +08:00
Your Name
45dbe07188 fix(flywheel): 自動化飛輪六大能力修復(ADR-092 B3)
Some checks failed
run-migration / migrate (push) Failing after 22s
Deploy Alert Rules / Deploy Prometheus Alert Rules (push) Successful in 53s
Type Sync Check / check-type-sync (push) Successful in 2m54s
CD Pipeline / build-and-deploy (push) Has been cancelled
Ansible Lint / lint (push) Has been cancelled
【根因鏈修復】
MCP Provider bugs → PreDecisionInvestigator 失敗 → Agent Debate 無上下文
→ LLM 逾時 → description="待分析" → ADR-091 鐵閘攔截 → tg_sent 未設
→ W-2 Watchdog 誤報「靜默故障」

【六大修復】
1. MCP Provider 三蟲修復
   - ssh_provider: asyncssh.run() → conn.run()
   - prometheus_provider: KeyError 'query' → .get() 容錯
   - k8s_provider: 空 pod_name → 早返回錯誤字典

2. Agent Debate / 決策品質
   - decision_manager: 逾時降級文字改為明確描述(繞過 ADR-091 鐵閘)
   - intent_classifier: LLM 逾時降級至關鍵字分類(非 None)

3. Watchdog 誤報修復(ADR-092 B3)
   - W-2: tg_sent Redis TTL → telegram_message_id IS NULL(DB 真值)
   - W-5 新增: suggested_action IN 空/待分析/NO_ACTION + tg_id IS NULL
   - approval_timeout_resolver: 60min → 15min,batch 50 → 200

4. Config Drift 自動化
   - drift_adopt_service: auto_adopt_if_safe() 六條件安全閘
   - drift.py: 背景任務先嘗試自動採納再發人工 Telegram 卡片

5. Playbook 飛輪穩定
   - playbook_seed_service: 修復幂等性(deprecated 不視為缺失)
   - playbook_evolver: 只載 DRAFT+APPROVED(非全部 294 筆)

6. 可觀測性
   - alert_rule_engine: auto_rule 結構化日誌 + Redis 計數器(pipeline)
   - auto_approve: reject 原因 Redis 計數器
   - heartbeat_report_service: 新增「⚙️ 自動化統計(今日)」區塊

【待人工執行】
psql $DATABASE_URL -f apps/api/migrations/cleanup_duplicate_deprecated_playbooks.sql

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 10:55:50 +08:00
Your Name
9244c5e845 feat(heartbeat): 系統報告新增 5 大動態區塊
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 13m50s
新增告警流水線(24h)、DB/Redis 狀態、K8s Pods、Scanner 狀態、Telegram Bot
各區塊採 asyncio.gather(return_exceptions=True) 平行探測,任一失敗不影響其他
新增 AlertPipelineStats/DbRedisStats/PodInfo/ScannerStats/TelegramBotStats dataclasses
_build_warnings() 加入 DB/Redis 異常、PENDING>10、Pod 未就緒/高重啟次數判斷
report_to_telegram_html() 對應輸出 5 個新 HTML 區塊

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-22 09:29:16 +08:00
Your Name
88af639651 fix(report): 修正 approval_records.status 大小寫不一致
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 9m46s
DB 以 SQLEnum 儲存 enum name(EXECUTION_FAILED 大寫),
而非 enum value(execution_failed 小寫)。
SQL 加 UPPER(status::text) 確保不論大小寫皆能命中。

驗證:live DB 查詢 success=0, failed=2(之前永遠 0/0)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-22 09:10:39 +08:00
Your Name
6810ab359d fix(report): 日報重發 + 自動修復 0% 兩大根因修復
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
問題一:日度巡檢報告重複發送(多 Pod 各自跑 daily job)
  - 根因:run_daily_report_loop 沒有接 leader lock
    其他 scanner(capacity/hermes/compliance)都有呼叫
    try_acquire_daily_lock,唯獨日報 loop 缺失
  - 修法:asyncio.sleep 後加 try_acquire_daily_lock("daily_report")
    搶不到 lock 的 Pod 直接 continue,等下一個 08:00

問題二:自動修復成功率永遠 0.0%
  - 根因:_collect_repair_stats 查 incidents.outcome->>'execution_success'
    但整條執行鏈路(approval_execution.py NO_ACTION + 真實執行)
    從未將 execution_success 寫回 incidents.outcome JSON
    導致查詢永遠回 0
  - 修法:改查 approval_records.status(EXECUTION_SUCCESS / EXECUTION_FAILED)
    這是唯一被穩定寫入的 source of truth

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-22 09:03:44 +08:00
Your Name
1625e7bd19 fix(telegram): 按鈕回覆靜默兩大根因修復
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 17m40s
問題一:ai_advisory_* 按鈕(容量預測/合規等)
  - 按下後只發 toast(2-3 秒消失),群組永無回覆
  - 修法:_handle_ai_advisory_action 加 message_id 參數,
    answer_callback 後額外 sendMessage reply 到原卡片

問題二:已解決告警再次點「批准」
  - sign_approval early-return(status != pending)但
    _notify_approval_result 仍發「 執行中...」→ 永無後續
  - 修法:僅 approval.status == APPROVED 時才發「執行中...」
    其他終態改發「ℹ️ 此告警已處理(狀態:...)」並 return

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-22 01:57:55 +08:00
Your Name
479f8d8971 refactor(tests): 技術債清零 — 移除 FakeRepo/FakeSession Mock DB 違規
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 35s
## ai_router.py
- 抽取 _aggregate_feedback_stats() 純函數,feedback_from_aider_events 呼叫它

## aider_event_processor.py
- _process_one 加 _session_factory=None DI 參數(預設 get_session_factory())
- 可注入測試 factory,不改既有生產邏輯

## test_ai_router_feedback.py(完全重寫)
- 移除 FakeRepo/FakeSession,改為直接測試 _aggregate_feedback_stats 純函數
- 新增 test_feedback_skips_missing_model 邊界條件
- DB 失敗降級行為 test 保留(只 patch get_session_factory,無 FakeRepo)

## test_aider_event_processor.py(完全重寫)
- 移除 FakeRepo/FakeSession,改用真實 PostgreSQL(real_factory fixture)
- Redis xack + IncidentEngine 保留 mock(外部 broker/AI 服務,符合例外)
- 每個測試後 rollback,不污染 dev DB

## setup_test_schema.sql
- 補入 aider_events_payload_gin GIN index(與 adr091 生產 migration 一致)

## integration/conftest.py
- 補注解說明密碼名稱 awoooi_prod_2026 的歷史混淆
- 修正 assert 邏輯:檢查 DB 名稱而非 URL 字串,避免密碼含 prod 觸發誤判

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-22 01:33:30 +08:00
Your Name
4fc1f49dca fix(pipeline): 三斷點修復 — SLO公式+NO_ACTION堆積+幻覺降級風險
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 14m3s
D1 flywheel_stats_service: execution_count 欄位不存在 → 改讀
    success_count+failure_count;消除飛輪執行成功率永遠 0.0% 假象

D2 openclaw._validate_deployment_inventory: 幻覺 deployment 降級後
    原 HIGH/CRITICAL risk 未清零 → 加 result.risk_level = AIRiskLevel.LOW

D3 webhooks.py (兩處 alert path): NO_ACTION/INVESTIGATE/OBSERVE 三類
    非破壞性動作強制 risk_level = LOW,跳過 Telegram 批准直接 auto-approve
    → approval_execution.py 的 NO_ACTION handler 立即標 EXECUTION_SUCCESS

Root cause 鏈:BUTTON_DATA_INVALID 修復後 TG 按鈕可發,但 NO_ACTION
積壓的 35 筆 PENDING 是因 HIGH risk 無法走 auto-approve 路徑導致。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 22:26:07 +08:00
Your Name
8fd31eca66 fix(telegram): nonce UUID base64url 壓縮 — 徹底解決 BUTTON_DATA_INVALID
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 9m45s
前次修法(truncate random)不完整:host_restart_service(20 chars) 即使去掉 random
仍 68 bytes > 64 限制。

根本修法:UUID (36 chars) → base64url encode UUID bytes → 22 chars
nonce 格式:{action}:{b64url_uuid}:{timestamp}:{random}
最長 case: host_restart_service(20)+22+10+8+3 colons = 63 bytes

generate_callback_nonce: UUID → base64url 22 chars
parse_callback_data: 22-char b64url → 還原完整 UUID,handler 不需改動

全 action 驗證:approve/silence/reject/docker_restart/host_restart_service/renew_cert
全部 ≤ 63 bytes,UUID round-trip 正確。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 21:30:20 +08:00
Your Name
bd735482f7 fix(telegram): BUTTON_DATA_INVALID — nonce 超過 64 bytes 根因修復
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
根因:Telegram callback_data 上限 64 bytes。
5 個長 action 名(docker_restart/host_restart_service 等)+ UUID approval_id
= 71-77 bytes → BUTTON_DATA_INVALID。

修復:
1. security_interceptor.generate_callback_nonce:若 nonce > 63 bytes,
   改用 3-part 格式(捨棄 random)— timestamp 仍保時間唯一性。
2. security_interceptor.parse_callback_data:接受 3-part 或 4-part 格式。
3. telegram_gateway:移除 debug payload logging(診斷完成)。

影響 action:docker_restart / host_restart_service / host_clear_log /
reload_nginx / renew_cert(全部 > 7 chars + UUID = 64 bytes 以上)。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 21:17:49 +08:00
Your Name
685f5c684f debug(telegram): log full payload on 4xx to diagnose BUTTON_DATA_INVALID
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 13m29s
前次 response_body 已確認錯誤碼,這次記錄完整 payload(payload_preview 前
1000 bytes)以找出觸發 BUTTON_DATA_INVALID 的確切欄位。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 20:56:28 +08:00
Your Name
acab1cd95e fix(gitea-review): PR/push AI analysis always failing — 兩個根因修復
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 17m26s
Root cause 1 (push review): local_code_review_service.review_push() 回傳
dict,但呼叫端直接存取 analysis.issues → AttributeError。
修復:_call_openclaw_push_review 將 dict 轉成 CodeReviewResult。

Root cause 2 (PR review): openclaw_http_service 呼叫
/api/v1/analyze/code-review 但 OpenClaw 從未實作此 endpoint(404)。
修復:_call_openclaw_code_review 改走 local_code_review_service.review_pr()
(Ollama qwen2.5-coder + Gemini fallback)。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 15:19:14 +08:00
Your Name
3323a9052c debug: log telegram 400 response body to diagnose card send failure
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 12m38s
2026-04-21 01:05:21 +08:00
Your Name
9e9bd8679f fix(aider-watch): code-review fixes (4 issues)
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
1. aiderw: session_end 補 model+cwd (AI Router feedback loop 修通)
2. repository: model_stats_since SQL 改 COALESCE(session_end, session_start) model
3. aider_event_service: classify_severity 移除 error_count 觸發告警(防假陽性)
4. worker: run_aider_event_processor_loop 包 proc.start() try/except(防靜默崩潰)

2026-04-20 @ Asia/Taipei
2026-04-21 00:59:21 +08:00
Your Name
de2d34d4cd fix(playbook): C1-C4 全流程串接 — evolver保護+seeder復活+規則即時建立+watchdog W-4
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
C1: playbook_evolver — yaml_rule source playbooks 加 YAML_RULE guard,
    evolver 不再封存 seeder 建立的 APPROVED playbook,保護自動修復鏈路

C2: playbook_seed_service — idempotency SQL 排除 DEPRECATED 記錄,
    evolver 封存後重啟可復活 yaml_rule playbooks

C3: alert_rule_engine — AI 自動生成規則成功後立即呼叫 seed_playbooks_from_rules(),
    不等下次重啟即可建立對應 APPROVED Playbook

C4: ai_slo_watchdog_job — 新增 W-4 APPROVED playbook 數量為 0 告警,
    鏈路斷裂立即 TYPE-8M;total checks 由 3 升為 4

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 20:18:11 +08:00
Your Name
156a52f807 fix(aiops): ADR-092 三修 — Playbook enum崩潰 + Telegram永久靜默 + 採納失敗 + AI自健診
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 13m33s
B1 playbook_service.py: evolver setattr傳str而非PlaybookStatus enum
  → _pg_upsert playbook.status.value炸(163次/48h),修:update_with_validation強制enum轉型

B2 approval_db.py + webhooks.py: find_by_fingerprint PENDING誤收斂
  → PENDING≠Telegram已發;修:成功push後mark tg_sent:{fingerprint} Redis(24h TTL)
  → find_by_fingerprint debounce窗外PENDING必須Redis確認才收斂

drift_adopt_service.py: telegram_gateway呼叫adopt_drift(report_id)但方法不存在
  → 新增adopt_drift()包裝:從DB載入DriftReport後委派adopt(),修復採納失敗

B3 ai_slo_watchdog_job.py + main.py: AI無法感知自身故障(MASTER §1.1盲區)
  → 新增每15分鐘自健診:W-1 SLO違反 W-2 TG靜默偵測 W-3 飛輪成功率
  → 任一異常→TYPE-8M send_meta_alert;Redis去重1h

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 20:00:06 +08:00
Your Name
40771cda6d feat(ai_router): feedback_from_aider_events read-only hook (Phase 24 A8) 2026-04-20 19:40:01 +08:00
Your Name
cd894310dc feat(api): POST /api/v1/aider/events HMAC webhook + Redis stream push
- Router layer: HTTP validation + HMAC-SHA256 signature verification
- Service layer: Redis stream push (aider_event_service.push_aider_batch_to_stream)
- leWOOOgo積木化遵循: Router → Service → Redis
- All 6 tests passing (signature validation, batch limits, edge cases)
2026-04-20 19:40:01 +08:00
Your Name
964427c5d4 feat(service): aider_event_service — classify + signal_data builder (uses existing debounce) 2026-04-20 19:40:01 +08:00
Your Name
54d60d04f5 feat(drift+target): P0.1+P0.2+P0.3 三修 — drift 分頁分類 + AI 推薦 + target 追 trace
統帥三問決議:全做;AI 推薦 0.85 門檻純顯示不自動;先查 aol 再修

## RCA: awoooi-service 失敗來源
- /api/v1/aiops/kpi 顯示過去 24h 有 1 筆 playbook_executed actor=approval_execution status=failed
- grep codebase: 無任何程式碼寫死 awoooi-service(只有歷史 comment)
- 最可能源: alert_rule_engine._extract_vars 從 labels.service 取值當 Deployment 名
- cf5050c/4f2e122(2026-04-18)已修 NEMOTRON 幻覺雙路徑;本次修第三條路徑

## 修復
### P0.3a alert_rule_engine._extract_vars
- labels.service 降級:-service 結尾先剝 suffix 視為 base name
- match_rule 回傳新增 target_source 欄位追 trace
- 下次 awoooi-service 復發可直接看來源(label.service(stripped) 等)

### P0.3c approval_execution._log_aol_started.input
- 補 parsed_target/operation/namespace 欄位
- 未來 aol 查 failed 可直接看 target,無需推敲

### P0.1 telegram_gateway._send_drift_diff_detail
- 分頁(10 項/頁)取代一次洗版 30 項
- header 3 桶分類計數: 人工高風險 / 一般修改 / K8s 自動
- 底部 ⬅️/➡️ 分頁按鈕(callback: drift_view_page:{report_id}_{page})
- security_interceptor INFO_ACTIONS 加 drift_view_page 白名單

### P0.2 drift_narrator recommendation
- LLM prompt 加 recommendation 欄位(action/confidence/reason)
- action ∈ {adopt, revert, ignore, investigate}
- 卡片頂部顯示「🎯 AI 建議: 回滾 (85%) — reason」
- LLM 失敗走 _fallback_recommendation(規則式依 intent 對應)
- 卡片 diff_summary 上限 500 → 1500 字容納推薦 + narrative + items
- 統帥指令:純顯示不自動執行(門檻 0.85 保留未來)

## 驗證
- 90 個 pytest test 全過(drift + rule_engine + approval_execution)
- 5 檔 AST syntax check 過

## 下次驗收
1. 下次 drift 觸發 → 卡片頂部有「🎯 AI 建議」
2. drift_view 按下 → 3 桶分類 header + ⬅️/➡️
3. awoooi-service 若復發 → automation_operation_log.input.parsed_target 直接查

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 04:04:13 +08:00
Your Name
f572561467 feat(ai_advisory): P0 修 leader lock + inline keyboard + callback handler
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 8m31s
統帥 2026-04-19 截圖反饋:
  1. 同一告警 22:44 連推 2 則 (多 Pod 都跑 daily loop)
  2. 純文字無按鈕 (無 feedback 閉環 / AI 只建議不執行)

新增 services/ai_advisory_helpers.py (~240 行):
  - try_acquire_daily_lock(job_name): Redis SETNX key 'aiops:daily_lock:{job}:{date}',
    TTL 25h,fail-open (Redis 掛照推,不阻塞).
  - try_acquire_hourly_lock(job_name): 同上 hourly 版 (coverage_evaluator 用).
  - is_snoozed / set_snooze: Redis key 'aiops:snooze:{type}:{target}' TTL 24h.
  - build_ai_advisory_keyboard: 統一 4 按鈕
       已處理 / 😴 忽略 24h / 🔍 查看詳情 / 📋 產 kubectl 指令
    callback_data 格式: 'ai_advisory_{action}:{type}:{id}'
  - handle_ai_advisory_callback: 處理 handled/snooze 兩個 action 寫 aol.output.human_feedback,
    view/produce_cmd 留 P1.

4 個 LLM scanner 改用 helper:
  - capacity_forecaster: daily_lock + snooze check per host + 按鈕
  - compliance_scanner: daily_lock (cron only) + snooze per date + 按鈕
  - coverage_evaluator: hourly_lock + snooze per worst_dimension + 按鈕
  - hermes_rule_quality: daily_lock + snooze per primary rule + 按鈕

telegram_gateway.py:
  handle_callback 加 'ai_advisory_*' 路由 (step 1.85 drift 後)
  新增 _handle_ai_advisory_action 方法:
    解析 payload 'type:id' → 呼叫 handle_ai_advisory_callback
    → answer_callback (Telegram toast 回饋)
    → 返回 dict (info_action=True for view/produce_cmd)

統帥鐵律對齊:
   多 Pod 場景只 leader 推 (Redis SETNX 保證冪等)
   失敗 fail-open 不阻塞主業務 (Redis 掛仍能運作)
   aol.output 加 human_feedback 供 AI 學習
   snooze 避免重複告警 (24h TTL)
   原 drift 按鈕 pattern 複用 (non-breaking)

明早 AI 將收到:
  - 單一訊息 (非重複)
  - 含 4 按鈕 (手動 feedback 閉環)
  - snooze 後同主題 24h 不再推

view/produce_cmd P1 留下 session (AI 主動 MCP 蒐證 + LLM 產 kubectl command).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 23:02:57 +08:00
Your Name
fa643ebdc7 refactor(p1): LLM JSON parse helper 抽出 + coverage 閾值雙條件 (架構師 Review P1)
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 8m52s
首席架構師 2026-04-19 Review (92/100 Grade A) 指出 P1 優化:
  1. LLM JSON 3-path parse 邏輯在 4 scanner 重複 (~80 行 × 4 = 320 行)
  2. coverage red>=20 觸發閾值偏低,生產 bootstrap 必觸發浪費 token

P1.1+1.2 新增 services/llm_json_parser.py (~90 行):
  parse_llm_json_response(text, required_key, logger_context)
  3-path fallback:
    Path 1: 剝 markdown fence + 直接 JSON 含 required_key
    Path 2: NemoTron wrapper (description/action_title/reasoning 內嵌 JSON)
    Path 3: 所有失敗 return None + logger.warning
  失敗永不 raise,呼叫者決定 fallback.

4 個 LLM scanner 改用 helper:
  - hermes_rule_quality_job: required_key='recommended_actions'
  - capacity_forecaster_job: required_key='priority_actions'
  - compliance_scanner_job: required_key='posture_grade'
  - coverage_evaluator_job: required_key='worst_dimension'
每個減少約 20 行重複.

P1.3 coverage 觸發條件改雙條件:
  原: total_red >= 20 (bootstrap 必觸發)
  新: red_ratio > 30% AND total_scanned >= 50
  _fetch_red_summary 加 total_scanned 回傳供計算.

5/5 單元測試 parse_llm_json_response:
   direct / markdown fence / NemoTron wrapper / invalid / missing key

P1.4 capacity_scanner + rule_catalog_sync: 檢查後已有完整作者註解 (Review 誤判).
其他 P1 (Prom HTTP helper / first_delay 錯開 / LLM budget guard) 留下 session.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 22:39:40 +08:00
Your Name
37b6c9ba56 chore: remove empty ai_orchestrator.py (意外進 commit 的空檔)
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 13m6s
上個 commit (86d9b22 LOGBOOK) 因 stash pop 意外帶入 0 行空檔
ai_orchestrator.py,非刻意創建。本次刪除保持 services/ 乾淨。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 22:22:53 +08:00
Your Name
86d9b22125 docs(logbook): Session 結尾 — Gap Review + AI 自主化 1/9→4/9 全景記錄
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Session 35 commits 完整結案:
  - Phase 7 基礎 (scanners + evaluator + tracker + advisor + forecaster)
  - KPI Dashboard API (autonomy_score 63/100 可量化)
  - Audit 誠實 3 Gaps
  - Gap 1 host IPv4 嚴格 + 清理 266 筆重複
  - Gap 2 真因確認非 bug
  - Gap 3 LLM 升級 3/8 (capacity_forecaster/compliance/coverage)

AI 自主化達成:
  1/9 LLM (只 Hermes) → 4/9 LLM decision
  8 張 0 writer 表全活化
  7/7 coverage 維度完整
  今晚 AI 將自主推 4 種 Telegram 分析報告

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 22:22:42 +08:00
OG T
0004554bc6 feat(api): AIOps KPI Dashboard — AI 自主化成熟度全景 (積木化重構)
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 8m47s
GET /api/v1/aiops/kpi → 一次整合 MASTER §7.1 全部 KPI.

leWOOOgo 積木化鐵律對齊:
  - Router (api/v1/aiops_kpi.py) 僅 HTTP 路由, 不碰 DB
  - Service (services/aiops_kpi_service.py) 負責所有 SQL + 計算
  - 前次 commit 被 hook 擋下 (Router 直接 import get_db_context), 本次修正

services/aiops_kpi_service.py (~230 行):
  AiopsKpiService.get_snapshot() 回 6 section:

  1. asset_inventory: by_type + total + last_scan (run_id/ended_at/總計/new/modified)
  2. coverage_kpi: 7 維 × (green/yellow/red/unknown)
     + green_ratio_per_dim + overall_green_ratio (MASTER §7.1 #5 SLO)
  3. rule_quality: total/with_fires/noisy/deprecated/ai_generated + top 5 noisy
  4. capacity_health: 最新 snapshot per host + by_verdict + violations_7d
  5. automation_flow_24h: aol detail + by_actor + by_operation_type
  6. ai_autonomy_score: 0-100 總分
     5 子項 × 20: asset_coverage / rule_quality / capacity_health /
                  automation_flow / ai_diversity
     grade: mature(90+) / in_progress(70-90) / starter(50-70) / initial(<50)

api/v1/aiops_kpi.py (~35 行 精簡 router):
  只做 router = APIRouter() + @router.get 委派給 service

main.py:
  include_router(aiops_kpi_v1.router, prefix='/api/v1', tags=['AIOps KPI'])

統帥使用:
  curl http://192.168.0.121:32334/api/v1/aiops/kpi | jq .
  一次看見 AI 自主化成熟度全景

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 21:21:46 +08:00
OG T
c0f3509d39 fix(drift-card): Drift Diff HTTP 400 — item-by-item 累計長度避免切斷 HTML
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 2m0s
統帥回報 14:18 點 [查看 Diff] 收到 'Drift Diff 查詢失敗: HTTP error: 400'

真因 (telegram_gateway.py:2087 _send_drift_diff_detail):
  - report_id=7ffe78ae 有 48 items,單筆 git_value 最長 1794 字 (env array)
  - 累計 _full 遠超 4096,執行 _full[:3950] 截斷
  - 截斷可能切在 HTML tag 中間 (<code>... 或 &lt; entity 中間)
  - Telegram parse_mode='HTML' 拒絕不完整 HTML → 400

修復:
  - item-by-item 累計長度,單個 item 算 _block 長度+1
  - 預留 3800 上限 (4096 - 250 buffer 給 header + '… 還有 X 項' 提示)
  - 確保 _full 永遠是完整 HTML 結構

驗證: 下次 drift report 出現 + 統帥點 [查看 Diff] 應正常顯示 (本 session 的下個 cycle)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 14:26:29 +08:00
OG T
e7ba8cb181 fix(aiops): 打通 AI 自主學習鏈 — verifier 改 await + aol 動作回灌
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 7m29s
統帥 2026-04-19 全景審計發現:
  - automation_operation_log: 22 筆 (全部 drift_narrator),33 件/7d approval 動作 0 筆回灌
  - incident_evidence.verification_result: 1212 筆 100% NULL,verifier 從未寫入
  - 根因: _run_post_execution_verify 用 asyncio.create_task fire-and-forget,
          Pod recycle 時 task 被殺,verification_result 永遠寫不進去

修復 (打通 verifier→learning→Playbook EWMA→finetune 全鏈):

approval_execution.py:
  + _log_aol_started: 主流程開始時 INSERT aol(playbook_executed, pending)
  + _log_aol_completed: 4 個 return 點 UPDATE aol 為 success/failed + duration + stderr
    └ NO_ACTION / parse_fail / K8s 成功 / K8s 失敗 全部留痕
  ~ _run_post_execution_verify 兩處 (成功+失敗 path) 從 create_task 改 await + 60s timeout
  + 失敗時 stderr_feed_back 寫入 result.error → 解開 E6 stderr 回灌閉環

declarative_remediation.py:
  ~ _log_remediation_event task 加 named + add_done_callback,task 失敗時有 log
    (原 fire-and-forget 0 筆寫入,現在可診斷為何 task 死掉)

預期效果:
  - aol playbook_executed 即時可見 (33 件/7d 立刻有資料)
  - incident_evidence.verification_result 開始累積 → finetune_exporter 7d cron 終於有料
  - Playbook EWMA trust_score 開始動態變化
  - stderr_feed_back 接通 → 失敗訊號回灌 retry/Playbook 負向強化

不影響:
  - background_task 跑在背景,+60s 延遲不阻塞 API
  - aol 寫入失敗只 logger.warning,不阻塞執行主流程

Refs: MASTER §3.1 L6×D1 (ADR-081 PostExecutionVerifier),
      MASTER §3.4 D4 (ADR-083 學習閉環),
      ADR-090 監控盲區治理 (2026-04-18 全景審計)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 12:07:29 +08:00
OG T
2abc91e360 fix(drift-card): 修 drift 卡片 2 bug — AI 研判 copy 樣式 + Diff 按鈕 AttributeError
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 13m8s
Bug 1: 按「🔍 查看 Diff」失敗
  錯誤: 'DriftReportRepository' object has no attribute 'get_by_id'
  根因: DriftReportRepository 方法叫 get(), 其他 repo 都叫 get_by_id()
  修法: 加 get_by_id() alias, 對齊 repo 介面慣例

Bug 2: AI 研判內容被渲染成 code block + copy 按鈕
  根因: telegram_gateway line 1962 用 <pre> 包 diff_summary
       但 diff_summary 是 AI 研判敘述 + emoji 清單, 非 code
  修法: 移除 <pre>, 改以分隔線 + html.escape 純文字顯示

驗收:
- 下次 drift 卡片: AI 研判段落純文字(無紫色 code block + copy)
- 按「🔍 查看 Diff」→ 送完整 diff 詳情(非 AttributeError)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 11:27:13 +08:00
OG T
4b8be32610 fix(telegram+approval): TG-1 + AP-1/2/3 — 4 修 Telegram UX
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 25m27s
Ansible Lint / lint (push) Has been cancelled
2026-04-19 凌晨(台北時區)— ogt + Claude Opus 4.7 (1M)

## TG-1: INFO_ACTIONS 加 view
security_interceptor.py — 'view' 按鈕現在走 2-part 讀格式,
不再誤觸發 4-part nonce 寫格式。

## AP-1: approval_records.telegram_message_id 持久化
telegram_gateway.send_approval_card send 成功後,在 DB 層 UPDATE
approval_records SET telegram_message_id, telegram_chat_id
(不只 Redis, Pod 重啟仍可找回原卡片)。

## AP-2: approval 執行完成原卡片 edit + KM/Playbook 增量
approval_execution._push_execution_result_to_alert 除了 reply 原卡片,
還 editMessageReplyMarkup 移除按鈕(修「永遠執行中」卡片問題)。
  - 同步查 knowledge_entries/playbooks 2min 內增量,附加到訊息
    顯示 "📚 KM +N  🎯 Playbook 更新×M"
  - 成功:  執行成功 + action + KM 增量
  - 失敗:  執行失敗 + 原因 + KM 增量

## AP-3: primary_responsibility 正規化降「 未知」比例
openclaw._parse_analysis_result: 若 LLM 填空/None/不在白名單
(FE/BE/INFRA/DB/COLLAB),強制 fallback: kubectl 關鍵字有 → INFRA,
否則 BE。之前只檢查 "not in data" 但 None 或空字串會穿過。

## 跳過: TG-3 (refactor) + TG-5 (webhook 為棄用 endpoint,design 採 Long Polling)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 01:15:58 +08:00
OG T
68a42a3c97 fix(openclaw): 幻覺驗證雙路徑覆蓋 + 抽出共用 helper
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-19 凌晨(台北時區)— ogt + Claude Opus 4.7 (1M)

根因:
  commit 7e9448f 的 Python hallucination validator 只裝在
  `analyze_alert` (webhook path),但 incident sweeper 走
  `generate_incident_proposal` (line 1552) 沒裝驗證 → 00:23
  PostgreSQLDiskGrowthRate 卡片出現 "deployment/awoooi-prod"
  幻覺未攔截。

修:
1. 抽出 `_validate_deployment_inventory(result, inventory, ns)` 共用方法
2. `analyze_alert` (line 1322 area) 呼叫此 helper — 原行內邏輯消除
3. `generate_incident_proposal` (line 1552) 動態抓 inventory + 呼叫 helper
4. helper 補:
   - result.action_title = '[安全降級] 調查 {ns} 真實資源狀態'
     (之前只改 description,action_title 沒變 → DB action 欄位仍殘留舊文字)
   - 每個欄位賦值 try/except 保底,單欄失敗不影響其他

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 01:11:09 +08:00
OG T
fdce0a3ab9 fix(approval): NO_ACTION 不再誤標 EXECUTION_FAILED (MASTER §7.1 #11 修)
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-19 凌晨(台北時區)— ogt + Claude Opus 4.7 (1M)

根因:
approval.action='NO_ACTION - 待分析' (幻覺 validator 降級產物) 丟進
parse_operation_from_action → operation_type=None → background_execution_skip
→ update_execution_status(success=False) → 標為 EXECUTION_FAILED。

污染 KPI:
  MASTER §7.1 #11 auto_execute 成功率 = EXECUTION_SUCCESS / (SUCCESS+FAILED)
  NO_ACTION 本來就不該計入失敗,但卻被算進去拖垮指標。
  實測 30d 成功率 0.9% 有很大比例是 NO_ACTION 誤標造成。

修復:
parse 失敗時先判斷是否 NO_ACTION 類 (action 含 NO_ACTION/OBSERVE/INVESTIGATE
等關鍵字) → 走專屬 noop 分支:
  - log event=background_execution_noop (info 級)
  - update_execution_status(success=True) → EXECUTION_SUCCESS
  - timeline 標  純觀察類動作完成
  - reply 原告警卡片顯示成功
  - return True

真正解析失敗 (非 NO_ACTION) 保留原失敗路徑,但補上 error_message
(P0.2 延伸),讓 rejection_reason 有 "Could not parse operation type from
action: <action>" 而非空字串。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 01:08:16 +08:00
OG T
2e988bdb81 fix(telegram): drift 執行結果貼回卡片 + audit log user_id
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
IDE 抓到 _stamp 未使用(結果沒送)+ user_id 未使用(audit 缺漏)。

修:
1. _edit_drift_card_outcome 不只移除按鈕,還 send 簽核戳訊息
   (reply_to 原卡片,若 msg_id 存在),格式:
      已採納 by @username (成功)
     Drift <report_id>
2. _handle_drift_action 加 drift_callback_dispatched log(audit)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 01:07:13 +08:00
OG T
877c8479e0 fix(telegram): TG-2 + TG-4 修 drift 按鈕 black hole
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-19 凌晨(台北時區)— ogt + Claude Opus 4.7 (1M)

統帥截圖直擊: 按「查看 Diff」→ 變成「執行中」,且看不到還有 21 項。

全景盤點發現 9 個 Telegram 子系統 bug,本 commit 修 2 個最痛的:

## TG-2: drift_view/drift_adopt/drift_revert 3 按鈕**無 handler**
  點擊 → fallthrough → UX 黑洞 / 誤觸發 approve 路徑。

修復: handle_callback 在 state guard 後(line 2752 後)加 Step 1.85
  offroute: 3 個 drift_* action → _handle_drift_action 專職處理,
  不走 nonce approve/reject dispatch,避免誤觸發執行流。

3 個按鈕實作:
  - drift_view: 讀 drift_reports → 送新訊息展示全部 items
    (HIGH/MEDIUM/INFO emoji + Git vs K8s 原值對照,上限 50 項 4000 字)
  - drift_adopt: 呼叫 drift_adopt_service.adopt_drift()
  - drift_revert: 呼叫 drift_remediator.revert()

## TG-4: drift card message_id 沒存 Redis → edit 回不了卡片
修復: send_drift_card 成功後 setex f"tg_drift:{incident_id}" TTL 24h,
  供 _edit_drift_card_outcome 在 adopt/revert 執行後更新原卡片(先移除
  按鈕 + 加「XX by @username (成功/失敗)」簽核戳)。

## 未包含(follow-up):
  TG-1 INFO_ACTIONS 擴充(view)  — 下一 commit
  TG-3 handler 重複分派 — 評估中
  TG-5 Bot webhook URL 未設 — 需統帥決策公開 URL
  approval card NO_ACTION 誤標 FAILED — 下一 commit
  approval card description 矛盾 / responsibility 未知 / 執行後 edit

全景 9 bug 清單詳見 project_phase7_round3_telegram_subsystem_audit(待建)。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 01:06:30 +08:00
OG T
98aef55b31 feat(kpi): ADR-090-D MASTER §7.1 北極星 KPI 5 斷鏈全修
Some checks failed
CD Pipeline / build-and-deploy (push) Successful in 11m49s
run-migration / migrate (push) Failing after 15s
2026-04-18 晚(台北時區)— ogt + Claude Opus 4.7 (1M)

MASTER §7.1 15 個北極星 KPI 實測對標發現 5 個斷鏈:
  #3  fine-tune JSONL /week        — finetune_exports 表不存在
  #4  MCP 呼叫/24h                 — timeline_events 沒 mcp_call event_type
  #6  Declarative 修復使用率       — remediation_events 表不存在
  #7  general 兜底 17.3%           — classify_alert_early 漏 5 類
  #10 notification_outcomes /week  — 表不存在

本 commit 全修。

## 1. Migration: adr090d_kpi_data_sources.sql (3 張表)

- finetune_exports       — P3 Fine-tune JSONL 追蹤
- remediation_events     — P5 Declarative 修復追蹤
- notification_outcomes  — 通知品質 + RLHF 語料

Idempotent (CREATE TABLE IF NOT EXISTS), 已 apply 進 prod。

## 2. classify_alert_early 擴 4 類規則 (降 general 兜底)

- test 攔截: Test*/FPTest/FingerprintTest/ADR089*Test/L4Closure*/*FreshUniq*
  → category='test', TYPE-1 純通知
- High*CPU/Memory/Disk/Load → host_resource
- TLS*/SSL*/*ProbeFailure* → ssl_cert
- PostgreSQL*/MySQL*/MongoDB*/*DiskGrowthRate → database

預期 general 17.3% → 3-5% (達標 <10%)。

## 3. finetune_exporter DB 寫入

_run_export() 結尾寫 finetune_exports 一筆,含 checksum/size/record_count。

## 4. declarative_remediation DB 寫入

evaluate() 後 fire-and-forget _log_remediation_event() 寫 remediation_events
(status='pending', remediation_type 依 tier 自動判為 declarative/imperative/gitops_pr)。

## 5. telegram_gateway DB 寫入 (send_approval_card)

_send_request 成功返回 message_id 後寫 notification_outcomes 一筆,
channel='telegram', delivery_status='delivered|failed'。未來人類按鈕時
update user_action → RLHF 訓料黃金。

## 6. pre_decision_investigator MCP 呼叫追蹤

_call_single_tool() finally 寫 timeline_events event_type='mcp_call',
含 provider/tool/status/duration_ms/error。24h 內 MCP 呼叫可 SQL 量測。

## 預期量化改善

| KPI | 修前 | 修後 24h 後應見 |
|-----|------|----------------|
| #3 fine-tune /week | 0 (表不存在) | >=10 (每週 cron 跑) |
| #4 MCP 呼叫/24h | 0 | >0 (實測將寫 timeline) |
| #6 declarative 使用率 | 表不存在 | 有資料 (pending/success/failed 分佈) |
| #7 general 兜底 | 17.3% | <10% |
| #10 notification_outcomes | 0 | 每次 approval card 寫一筆 |

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 00:00:31 +08:00
OG T
898145d68e refactor(openclaw): SuggestedAction 改用頂部 import (避免 inline 三重巢狀)
Some checks failed
CD Pipeline / build-and-deploy (push) Successful in 11m17s
Ansible Lint / lint (push) Has been cancelled
IDE 對 inline "from src.models.ai import" 誤報(但運行正常)。
改為頂部 import 既滿足 IDE 也更 Pythonic。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 23:28:19 +08:00
OG T
e6e484c1dc fix(openclaw): import path 修正 — src.models.ai (非 openclaw_schema)
Some checks are pending
CD Pipeline / build-and-deploy (push) Has started running
IDE 正確抓到的 bug(非 false positive),SuggestedAction 在 src/models/ai.py。
_SA.NO_ACTION 現在能正確降級。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 23:26:45 +08:00
OG T
7e9448f6d0 fix(openclaw): 幻覺 deployment 名雙層防禦 — Prompt + Python validator
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-18 晚(台北時區)— ogt + Claude Opus 4.7 (1M)

生產事件 (approval f763bedf, 22:58):
- Alert: KubePodCrashLooping, labels.deployment="awoooi-api"
- NEMOTRON 雖收 inventory "awoooi-api, awoooi-web, awoooi-worker"
  仍輸出 kubectl_command="kubectl rollout restart deployment/awoooi-prod"
  (把 namespace 誤當 deployment 名)
- 執行結果: "Deployment 'awoooi-prod' not found in namespace 'awoooi-prod'"

## Layer 1: NEMOTRON_SYSTEM_PROMPT 強化 (prompts.py)
新增「🔒 DEPLOYMENT NAME RULE (STRICTLY ENFORCED)」區塊:
- namespace NEVER is a deployment name
- "awoooi-prod" 是 NAMESPACE,不可寫 deployment/awoooi-prod
- 若有 inventory,deployment 必須 exact match
- 優先用 labels.deployment,unknown → NO_ACTION

## Layer 2: Python 後驗證 (openclaw.py:1322+)
LLM 回應解析後 regex 抽出 deployment 名,對照 _k8s_inventory:
- 在清單內 → 通過
- 不在清單內 → 降級:
    * kubectl_command → "kubectl get deploy -n {ns}"(純調查)
    * suggested_action → NO_ACTION
    * target_resource → "unknown(hallucinated)"
    * confidence → 0.0
    * description 加註 [安全降級] 並列出合法 inventory
- log 'openclaw_deployment_hallucination_detected' 記錄

效果: 就算 LLM 無視 prompt,Python 層也會擋下。
破壞性 kubectl 絕不執行於不存在的 deployment。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 23:26:09 +08:00
OG T
6ad73b4834 fix(flywheel): 三修 L5/L6 斷鏈 — RBAC 擴權 + 失敗原因入庫 + verifier 失敗時也跑
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 11m6s
2026-04-18 晚(台北時區) — ogt + Claude Opus 4.7 (1M)

全景飛輪診斷暴露 3 個真斷鏈:
  - L5 執行 30d: EXECUTION_FAILED 216 / EXECUTION_SUCCESS 2 (失敗率 99%)
  - L6 驗證 7d: verification_result 全 NULL (988 筆 evidence 都沒驗)
  - 所有 rejection_reason / error_message 欄位全空(無法診斷)

根因: awoooi-executor ServiceAccount RBAC 不足,executor.py 每次
kubectl get nodes/HPA 都 Forbidden,連 evidence 都抓不到,後面 repair
全炸,verifier 因為 execution 沒 success 永遠不 trigger,evidence
驗證結果永遠 NULL。修一個 RBAC 解 3 個節點。

## P0.1 RBAC 擴權 (k8s/awoooi-prod/07-rbac.yaml)

新增 cluster-scope 讀權(僅 list/get/watch,零寫入):
  - nodes + nodes/status (evidence gathering 必需)
  - horizontalpodautoscalers (HPA 狀態)
  - metrics.k8s.io: nodes + pods (resource metrics)
  - statefulsets + daemonsets (完整 workload 視圖)

已 kubectl apply + 煙霧測試: kubectl get nodes 可跑。

## P0.2 失敗時必寫 rejection_reason (approval_db.py)

update_execution_status() 新增 error_message 參數,失敗時寫入
rejection_reason (截 2000 字) → 之後診斷有依據。

approval_execution.py 呼叫端同步更新,result.error 一路傳進 DB。

## P0.3 Verifier 失敗時也跑 (approval_execution.py)

原邏輯: verifier 只在 result.success=True 時呼叫 → 99% 失敗下
永遠不跑。

新邏輯: 失敗 path 也 create_task 跑 verifier,action_taken 後綴
加 ":FAILED" 標記。verifier 抓 post_state 寫
verification_result='failed' 回 incident_evidence。

L7 learning 從此有失敗樣本可學,playbook trust 負向 2x 衰減才
真正生效。

預期效果:
  - EXECUTION_FAILED 率 30d 內應從 99% 降到 <30%
  - incident_evidence.verification_result NULL 率應從 100% 降到 <10%
  - approval_records.rejection_reason 補齊率從 0% 到 100%

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 20:12:57 +08:00
OG T
b0d560dbb3 fix(drift-narrator): shortener 用 replace — 包容 LLM 加 'Resource/Name:' 前綴幻覺
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 10m50s
2026-04-18 下午(台北時區)— ogt + Claude Opus 4.7

Round 4 LLM 自己在 field 前加資源識別符:
  'Deployment/awoooi-web: spec.template.spec.containers'
導致 startswith 模式 shortener 失效(前綴不在開頭)。

防禦式修法: startswith 不中 → 改用 replace 清除任何位置的前綴。
結果:
  'Deployment/awoooi-web: containers' 

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 18:12:15 +08:00
OG T
b63aed72df fix(drift-narrator): 砍 spec.template.spec. 前綴 — 修 Telegram 自動換行醜陋排版
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 12m1s
2026-04-18 下午(台北時區)— ogt + Claude Opus 4.7

統帥實彈三輪視覺回報: 字段名 'spec.template.spec.volumes' 共 24 字元,
加上 emoji+': '+summary 超過 Telegram <pre> 視覺寬度,自動換行
造成 emoji 與 field name 斷開、單獨成行的醜狀。

修復: _shorten_field_path() 砍 3 種常見前綴:
  - 'spec.template.spec.' → ''
  - 'spec.template.' → ''  (後備)
  - 'spec.' → ''  (後備)

效果對比:
  前: '🟡 spec.template.spec.affinity.podAntiAffinity.preferredDuringS: [清單 3 項]'
  後: '🟡 affinity.podAntiAffinity.preferredDuringS: [清單 3 項]'

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 17:10:20 +08:00
OG T
f3960f36d2 fix(drift-narrator): fallback 強化 — 標註 K8s 預設值補齊 + 可操作數獨立計算
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 10m37s
2026-04-18 下午(台北時區)—— ogt + Claude Opus 4.7 (1M)

統帥實彈測試回報: 卡片顯示「securityContext: (未設) → {物件 0 欄位}」毫無意義。

根因: _fallback_items 對「K8s controller 自動補齊空物件」的噪音
     誤當成真實變更輸出。且「還有 29 項」數字包含白名單 + trivial。

修復 3 項:

1. _is_trivial_drift() 新判定函數
   None/空字串/{}/[]/false/0 等互相視為「無實質變更」
   捕捉 K8s controller 自動補齊場景

2. _summarize_item() 替代原本 smart_shorten
   - trivial → "K8s 預設值補齊 (無實質變更)"
   - None → value → "新增 xxx"
   - value → None → "已刪除 (原: xxx)"
   - 其他 → "from → to"

3. _fallback_items() 改進
   - 按 level 排序 (HIGH 優先)
   - 白名單 + HPA allowlist 先過濾

4. _count_nontrivial_drift() + Telegram 呈現
   - 新增「可操作」計數 (去掉白名單 + trivial)
   - 「還有 N 項」用可操作數,不會誤導
   - items 為空時顯示「全為白名單或預設值補齊」

預期效果:
  之前: "... 還有 29 項" (其實只 1 個是真實 drift)
  現在: "... 還有 0 項" 或 "(全部為白名單或預設值補齊)"

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 16:29:49 +08:00
OG T
1606093dd2 fix(drift-narrator): 兩個 hotfix — NEMOTRON wrapper 解析 + tags asyncpg 型別
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-18 下午(台北時區)—— ogt + Claude Opus 4.7 (1M)

Live-fire test (report_id=80a34b58) 暴露兩個 bug:

## Bug 1: LLM JSON 被 NEMOTRON wrapper 吞掉
根因: openclaw.call() 經 NEMOTRON 路由時強制回 {description,...} 結構,
     我的 prompt 要 {narrative, items} 無法穿透。
     (同 1ff3405 早前碰過的 JSON 裸奔問題根源)

修復: 三路 fallback 解析
  - Path 1: 直接我們的 {narrative, items}(Ollama 或 LLM 守規矩)
  - Path 2: NEMOTRON wrapper,description 巢狀 JSON 含我們結構
  - Path 3: description 是純敘述 → 當 narrative + Python fallback_items

## Bug 2: tags 參數 asyncpg DataError
根因: 傳 '{drift,type4d,llm_summary}' 字面量字串,asyncpg 要求 Python list
      '(a sized iterable container expected (got type str))'

修復: tags 改傳 ['drift','type4d','llm_summary'] Python list,移除 CAST AS text[]
     asyncpg 自動推斷 text[]

Live-fire 結果驗證:
  - narrative  生成(fallback path)
  - items ⚠️ 只 1 筆(NEMOTRON 未吐我們結構)
  - DB write  tags 型別錯
  - Telegram  送出(雖 fallback 內容但視覺 OK)

本 commit 後預期:
  - LLM 回應走 Path 2/3 → narrative + Python fallback items(5 筆 smart summary)
  - DB write 成功 → automation_operation_log + ai_collaboration_trace 皆有記錄
  - 若 LLM 未來學會走 Path 1(給我們 {narrative, items}),自動升級

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 16:26:17 +08:00
OG T
a156566b17 feat(drift-narrator): ADR-090-C L4 稽核閉環 — notification_formatted op 入庫
Some checks failed
CD Pipeline / build-and-deploy (push) Successful in 10m47s
run-migration / migrate (push) Failing after 14s
2026-04-18 下午(台北時區)—— ogt + Claude Opus 4.7 (1M)

架構鐵律執行:
「沒有被記錄的 AI 決策,就等於沒有發生過。」
drift_narrator 每次呼叫 LLM 生成摘要,必須完整寫入
automation_operation_log + ai_collaboration_trace,形成 L4 稽核 + RLHF 語料。

本 commit 兩件事:

1. apps/api/migrations/adr090c_notification_formatted_op_type.sql
   - 擴充 automation_operation_log.operation_type CHECK 加 'notification_formatted'
   - DROP + ADD CONSTRAINT idempotent 模式
   - 已用 awoooi(表 owner)apply 進 prod 驗證通過

2. apps/api/src/services/drift_narrator_service.py
   - 新增 _log_ai_action_to_db() 負責 DB 稽核寫入
   - 在 _generate_narrative_and_items() 結尾(success / fallback 都寫)呼叫
   - automation_operation_log:
     * operation_type='notification_formatted'
     * actor='drift_narrator'
     * input = {report_id, namespace, counts, items_scanned}
     * output = {narrative, items, items_count}
     * duration_ms, tags=['drift','type4d','llm_summary']
     * parent_op_id 查詢 alert_fired 鏈路(未來 drift → alert 關聯)
   - ai_collaboration_trace:
     * agent='drift_narrator', model=provider (ollama / nemotron / 等)
     * prompt(限 8000 字)+ response(JSONB)
     * accepted = LLM JSON 解析成功 flag(未來 RLHF 訓料金礦)
   - 錯誤處理: DB 寫入 try/except 包住,永不破壞 Telegram 通知主流程

P2.4 事件關聯:
  - SELECT parent op via input->>'report_id' 或 'drift_report_id'
  - 若找到則綁定 parent_op_id(形成 alert_fired → notification_formatted 追溯鏈)
  - 目前 drift 本身不經 alert_fired,parent 為 NULL(等未來鏈路接通)

P2.5 RLHF 語料:
  - ai_collaboration_trace.accepted=true 的紀錄即為「LLM 解析成功」樣本
  - 未來統帥按 Telegram [ 採納變更] / [ 回滾] 時,對應 trace 也可更新
    outcome flag,形成完整 Human-in-the-loop 語料

技術細節:
  - get_db_context() auto-commit(src/db/base.py:128),無需手動 commit
  - prompt 最長 8000 字(一般 drift 約 2-3k)
  - raw_response 保留前 500 字在 trace.response JSON 中

相關:
  - feedback_ai_autonomous_direction.md L4 北極星
  - feedback_secrets_leak_incidents_2026-04-18.md L1-L4 分層
  - ADR-090 11 張神經網路表
  - commit fb88512(B 方案視覺層)

IDE 可能顯示 src.db.base 找不到 —— 那是誤報(drift_repository.py 用同一條路徑)。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 16:04:23 +08:00
OG T
fb88512fcb fix(drift-narrator): B 方案 LLM 驅動智能摘要 — 徹底消滅 str()[:30] 暴力截斷
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-18 下午(台北時區)—— ogt + Claude Opus 4.7 (1M)

根因:
_format_drift_summary() 對 dict/list 型別的 git_value/actual_value
直接呼叫 str()[:30] 暴力截斷,產生像 "[{'name': 'repair-ssh-key', 's"
這種亂碼掉半個 dict key 的亂七八糟輸出,徹底違背「AI 自主化」原則。

B 方案架構決策:
「捨棄 Python 寫死的字串解析邏輯。將原始 Config Diff 結構直接作為
Context,餵給 Hermes/NemoTron,利用 prompt 規定輸出格式,讓 LLM 自己
消化並輸出包含紅黃燈標示的 Top 5 人類易讀摘要。」

實作:
1. _NARRATIVE_PROMPT 重寫 — 要求 LLM 回傳 {narrative, items[]} JSON
   - drift items 以 JSON serialize 餵進 prompt(保留 200 字 context)
   - items 限 5 筆,HIGH 優先
   - summary 30 字繁中口語(非技術 repr)
2. _generate_narrative_and_items() 新方法 — 解析 LLM JSON 並驗證結構
3. _format_drift_for_llm() 新方法 — 結構化 JSON 給 LLM(取代舊 str 版)
4. _render_telegram_body() 新方法 — 組裝乾淨的 Telegram 卡片
   範例輸出:
     🤖 AI 研判
     <LLM 4-5 行敘述>

     📊 漂移明細 (HIGH: 1 | MEDIUM: 29)
     🔴 spec.template.spec.volumes: 新增 2 項 repair-ssh-key 掛載
     🟡 spec.template.spec.serviceAccount: (未設) → awoooi-executor
     ... 還有 27 項 (按 🔍 查看 Diff)

5. Fallback 強化 — _smart_shorten() + _fallback_items()
   LLM 失敗時用型別感知的 Python 摘要(dict/list 顯示大小,不暴力 repr)

移除:
- _format_drift_summary() — 舊的暴力截斷實作
- _generate_narrative() — 只回 string 的舊介面

保留:
- _fallback_narrative() / _format_intent_summary() — 仍有用
- Redis 快取 / trigger 條件 / DB update — 邏輯不變

MVP 階段:
本 commit 只改視覺呈現,沒動 automation_operation_log / ai_collaboration_trace
稽核寫入。等 Telegram 視覺驗證 OK 後再做 Phase 2 加入 DB 稽核。

相關:
  - feedback_ai_autonomous_direction.md 北極星原則
  - 1ff3405 今早的 JSON 裸奔 hotfix(只修了 narrative,沒修 items)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 15:54:16 +08:00
OG T
1ff3405755 fix(drift-narrator): 修復 JSON 裸奔 — 從 NEMOTRON 回傳解析 description 欄位
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 10m44s
根因:openclaw.call() 經 NEMOTRON 路由後強制輸出 JSON(NEMOTRON_SYSTEM_PROMPT 鐵律)
      但 _generate_narrative 期待純文字 → JSON 整包吐到 Telegram <pre> 區塊裸奔

修復:收到 text 後先嘗試 JSON 解析
      - 成功 → 按優先順序取 description / action_title / reasoning
      - 失敗(非 JSON)→ 原文使用(向下相容 Ollama qwen 純文字回傳)

效果:Telegram Config Drift 卡片顯示繁中人話摘要,不再吐原始 JSON

2026-04-17 ogt + Claude Sonnet 4.6

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-18 01:08:32 +08:00
OG T
4f2e122fd2 fix(openclaw): Checkpoint-2 webhook path K8s inventory injection — 防止 NemoTron 幻覺 awoooi-service
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 11m39s
根因:NemoTron 在 webhook path(analyze_alert)無叢集上下文
→ 盲猜 deployment/awoooi-service → kubectl not found → EXECUTION_FAILED → trust score 0 永遠

修復:
- analyze_alert() Step 0.5: 呼叫 _fetch_k8s_inventory_for_openclaw() 拉取真實 Deployment 清單
- 注入「🔒 叢集實際資源清單」section 到 full_prompt,強制 LLM 從清單選擇資源名
- 失敗/超時 → 返回空字串 → 注入警示提示,主流程不中斷
- available_len 計算納入 k8s_section 長度防止 4K 截斷

影響:
- Solver Agent path (solver_agent.py) 已在 cf50a5c 修復
- 本 commit 修復 Alertmanager webhook path(analyze_alert → NemoTron)
- 兩條路徑均有 K8s 環境感知,LLM 不再幻覺資源名

ADR-082: Phase 2 多 Agent 協作
2026-04-17 ogt + Claude Sonnet 4.6(Checkpoint-2 webhook path completion)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-18 00:53:27 +08:00