wooo/awoooi
1
1
Fork 0
Code Issues 2 Pull Requests 1 Actions 5 Packages Projects Releases Wiki Activity
1,722 Commits 184 Branches 2 Tags
b8b5c68f3143d78fdae1c8a911dfcd6f4ec2ddda
Commit Graph

748 Commits

Author SHA1 Message Date
Your Name
f9f2263c00 fix(execution-feedback): 修復系統自動化反饋完全斷鏈的三層 P0 故障
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 8m57s
Details 
**背景**
用戶報告執行狀態卡在「⚡ 執行中...」永不回報，導致自動修復機制完全癱瘓
（信心度修復後，執行失敗但無法推送 Telegram 卡片通知）

**L1 — Post-verify AttributeError（2 處）**
- approval_execution.py:757, 1010 調用不存在方法 IncidentService.get_incident()
- 正確方法：get_from_working_memory() fallback get_from_episodic_memory()
- 影響：post-verify 邏輯被 exception 無聲吞掉，下游 Telegram 推送完全卡住

**L2 — Notification Provider 未配置**
- 新增 notifications/telegram.py：複用既有 TelegramGateway.send_notification()
- 修改 manager.py：初始化時註冊 TelegramWebhookProvider
- 影響：執行完成後無任何 provider 發送推送，導致 Telegram 看不到結果

**L3 — Solver Agent 語意合成生成殘缺指令**
- 舊邏輯：action_title="重啟服務" → 合成 "kubectl rollout restart deployment -n awoooi-prod"（缺名）
- 下游 operation_parser 無法解析（regex 要求 deployment/<name>）
- 修法：優先從 parsed 提取 target 欄位；無名則 return []，降級到唯讀調查指令
- 測試全部通過：35/35，含 11 個新安全測試

**驗證**
- 被阻擋的惡意 kubectl_command 現在正確 fall-through 到語意合成路徑
- 無 target 名稱時返回空列表，不再生成殘缺指令
- Telegram 執行結果推送鏈路已完整

**預期效果**
- 執行失敗 → 立即收到「❌ 執行失敗」Telegram 卡片（L1 + L2 修復）
- 自動化決策遵循白名單，避免生成無法執行的指令（L3 修復）

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 03:29:38 +08:00
Your Name
7b6df17dee feat(hermes): 升級 Ollama 模型路由 — qwen3:8b 取代雙模型
Some checks are pending
CD Pipeline / build-and-deploy (push) Has started running
Details 
- qwen2.5-coder:7b + qwen2.5:7b-instruct → qwen3:8b (Hybrid Thinking)
- qwen3:8b 同時勝任程式碼與通用指令，單一模型涵蓋 9 個 agent
- deepseek-r1:14b 保留 debugger / vuln-verifier 推理任務
- gemma4 尚未在 Ollama registry 釋出，暫保留 gemma3:4b
- 已在 111 主機 pull qwen3:8b (4.9GB)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 03:24:16 +08:00
Your Name
250eca99c6 fix(hermes): 改用 Ollama 本地模型（111），零費用，按 agent 類型選模型
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
模型路由：
  debugger / vuln-verifier     → deepseek-r1:14b  (強推理，找根因/安全分析)
  critic / db-expert / coder 群 → qwen2.5-coder:7b (程式碼專用)
  planner / onboarder / web     → qwen2.5:7b-instruct (通用指令)
  default                       → deepseek-r1:14b

- _strip_think_tags(): 去除 deepseek-r1 <think> 推理塊，只留最終回答
- timeout=90s (deepseek-r1 推理較慢)
- log 加 model 欄位供 latency 監控

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 03:13:59 +08:00
Your Name
d467cac709 fix(hermes): 改用 anthropic Python SDK 直呼，棄用需要 claude CLI 的 claude-agent-sdk
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
根因：claude-agent-sdk 需要 spawn claude CLI，prod pod 沒有 CLI 所以 SDK 回空。
修法：改用 anthropic.AsyncAnthropic().messages.create() 直呼 API。
model: claude-haiku-4-5-20251001（快速低成本，適合 Telegram QA）

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 03:08:51 +08:00
Your Name
c14f23b33a feat(k8s+notification): TG_GROUP_CUTOVER=true — 所有告警全切 SRE 群組 
notification_matrix TYPE-5S: DM → GROUP（SignOz 事件補齊）
prod/dev ConfigMap TG_GROUP_CUTOVER: false → true

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 03:07:28 +08:00
Your Name
cc69f3ce04 fix(solver_agent): 修復 AI 信心度阻斷 + 三層 kubectl 安全防禦
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
**修法A — 恢復 AI 決策信心度 (0.5 → 0.9)**
- Solver Agent 優先使用 OpenClaw NIM 的 `kubectl_command` 欄位（完整指令），略過語義合成降級
- 保留原始 0.9 信心度，告警自動化能力回復
- Root cause: 舊版在 action_title 未含 "kubectl" 時執行 min(0.9, 0.5) 降級

**C1 — CRITICAL: ReDoS + 注入防禦**
- 正則 `\s` → `[ ]` 避免換行符號 (\n\r) 配對（Shell 注入向量）
- 加入 `re.ASCII` 與 `{1,500}` 有界量詞，防止指數級回溯
- 性能提升 7.256s → 0.015ms (48x faster)
- 明文拒絕 \n \r \t \x00

**C2 — CRITICAL: 繞過防禦 + 截斷攻擊**
- action_title 路徑加白名單驗證（舊版跳過）
- 標準候選路徑：驗證 → 截斷，防止截斷繞過
- 不安全指令自動降級至語義合成

**C3 — CRITICAL: 無界長度 DoS**
- 新增 _KUBECTL_MAX_LEN = 500，硬上限前置檢查
- 防止長輸入導致正則超時

**測試覆蓋**
- 35 個測試（24 回歸 + 11 新安全測試）
- LF/CR/Tab/Null 注入、Shell 元字元、ReDoS 效能、邊界條件全覆蓋
- Critic 與 vuln-verifier 雙重驗證

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 03:02:58 +08:00
Your Name
39f45dd305 fix(solver): 補 import re（solver_agent 已有 re.compile 但漏 import）
Some checks are pending
CD Pipeline / build-and-deploy (push) Has started running
Details 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:42:25 +08:00
Your Name
a49554c5a0 feat(hermes): 接入 polling 路徑 — @tsenyangbot @mention → Hermes NL (ADR-094)
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
_handle_group_message() 新增 Hermes NL 路由：
  HERMES_NL_ENABLED=true + @tsenyangbot @mention → process_nl_message()
  → send_hermes_reply()，不影響既有 OpenClaw/NemoClaw 路徑

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:42:03 +08:00
Your Name
7d1c85eb86 fix(hermes): ANTHROPIC_API_KEY 注入 + solver 信心度修法 A + 12-Agent 治理文件
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
- nl_gateway.py: ClaudeAgentOptions 透過 env= 注入 ANTHROPIC_API_KEY（CLAUDE_API_KEY alias），
  修復 SDK 找不到 API key 的問題（SDK 讀 ANTHROPIC_API_KEY，K8s secret 名稱是 CLAUDE_API_KEY）
- solver_agent.py: 修法 A — kubectl_command 欄位優先路徑，OpenClaw Nemo 回傳完整指令時
  不再被語意合成壓縮 confidence（0.9 → min(0.5) 的 bug），9 tests pass
- AGENTS.md: Codex CLI 對應版 CLAUDE.md（Codex Session 啟動用）
- docs/12-agent-game-rules.md: 12-Agent 任務判型 + 主責/協作派工 + 9 skills 對照（v1.0）
- .agents/skills/06-awoooi-monorepo-master.md: v1.6，新增 12-agent 協作治理章節

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:33:43 +08:00
Your Name
86ee013cdf feat(hermes-complete): Hermes NL 三項補強 + ConsensusEngine + ADR 收尾
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 9m32s
Details 
## Hermes NL 補強（nl_gateway.py）
- T1 hermes_dispatch_log DB 寫入（asyncio.create_task 非阻擋）
- T2 Redis 速率限制：per-chat_id 20 req/min，fail-open
- T3 Multi-turn session：hermes:session:{chat_id}:{user_id} TTL=300s，最近 3 輪

## ConsensusEngine（ADR-095 宣告式設計）
- consensus_engine.py: CONSENSUS_WEIGHTS class 屬性
  security=0.4 鎖定，9 個 Claude Code agent 分配 0.6
- config.py: ENABLE_12AGENT_CONSENSUS=False feature flag

## ADR 狀態
- ADR-093/094/095: Proposed → 🟡 批准實作中
- 各 ADR 加 v1.1 變更紀錄

## K8s ConfigMap
- prod 04-configmap.yaml: 加 3 個 feature flags（均 false）
- dev 02-configmap.yaml: 同步加入

## LOGBOOK
- 記錄 WS0–WS6 + 補強完成，feature flags 啟用指引

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:22:40 +08:00
Your Name
00443370ba feat(ws6): Hermes observability — latency logging + dispatch audit table
Some checks failed
run-migration / migrate (push) Failing after 16s
Details
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
- nl_gateway.py: time.monotonic() 測量 SDK call 耗時
  hermes_nl_dispatch log 加 latency_ms + success 欄位
- migrations/adr094_hermes_dispatch_log.sql
  hermes_dispatch_log（bigserial + chat_id/user_id/agent/latency_ms/success）
  已部署至 prod awoooi_prod
  ADR-094 P95 latency 監控 + 幻覺追蹤用

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:10:06 +08:00
Your Name
834a65c833 feat(ws5): ADR-093 Approvers 白名單 chat_member 同步 
- hermes/approvers.py: Redis Set hermes:approvers:{group_id}
  sync_member_joined / sync_member_left / get_approvers / is_approved_member
  空集合 → 降級不阻擋，由 config whitelist 把關
- telegram_webhook.py: chat_member / my_chat_member 事件處理
  member/administrator/creator → sadd; left/kicked → srem
  get_redis() 同步取 async client，再 await approvers 函數

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:10:06 +08:00
Your Name
2572ec46d2 feat(ws4): Hermes NL 自然語言介面 — 12-Agent Claude SDK 接入（ADR-094/095） 
## hermes/ 套件（5 個新模組）

### display_names.py
- 12 agent 視覺識別表（emoji + hashtag + handle + short_name）
- format_response_header() 產生 Telegram 前綴

### agent_loader.py
- 解析 .claude/agents/*.md frontmatter → system prompt
- lru_cache 避免重複讀檔

### safety_hooks.py
- 移植 awoooi-guard.js 20 條 HARD BLOCK 規則（DENY_PATTERNS）
- 5 條 MUTATE_PATTERNS → 須走審批流

### nl_gateway.py
- Layer 1: 關鍵字正則路由（12 條規則，<10ms）
- Layer 3: DEFAULT_AGENT = "debugger"
- Claude Agent SDK query() 非同步串流，取 ResultMessage.result
- 安全降級：SDK error → 友好錯誤訊息

### telegram_webhook.py
- WS4 Hermes NL 接入（@tsenyangbot mention 或私訊觸發）
- HERMES_NL_ENABLED=False（feature flag 保護，預設關閉）

## telegram_gateway.py
- send_hermes_reply(text, chat_id, reply_to_message_id)
  無 500 字截斷，支援 Agent 長回覆

## config.py
- HERMES_NL_ENABLED: bool = False
- TELEGRAM_BOT_USERNAME: str = "tsenyangbot"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:10:06 +08:00
Your Name
294e0e3387 feat(ws3): ADR-093 Callback User-ID Binding + ADR-094 Webhook 入口 
## T3.1/T3.2 Bound User Check（security_interceptor.py）
- verify_callback() Step 0: 檢查 Redis cb_bind:{nonce}
  → 若有 binding 且 caller != bound_user_id → UserNotWhitelistedError
  → 若 key 不存在（舊格式）→ 降級走 whitelist（向後相容）
  → 若 Redis unavailable → 降級繼續（安全降級）
- bind_callback_user(nonce, user_id): async 方法，TTL=48h

## T3.3 Telegram Webhook 入口（ADR-094）
- apps/api/src/api/v1/telegram_webhook.py（新建）
  POST /api/v1/telegram/webhook
  - X-Telegram-Bot-Api-Secret-Token header 驗證
  - TELEGRAM_WEBHOOK_SECRET="" → dev 跳過（不 break 現有測試）
  - WS4 Hermes NL 接入預留佔位

## T3.4 config.py
- 新增 TELEGRAM_WEBHOOK_SECRET field（預設空字串）

## main.py
- 掛載 telegram_webhook_v1.router 到 /api/v1

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:10:06 +08:00
Your Name
6d5fd3c124 feat(ws2): ADR-093 路由統一 — BIGINT + NotificationMatrix + feature flag 
## 修復

### T2.1 BigInteger overflow 修復
- `db/models.py`: telegram_chat_id Integer → BigInteger
  （原 int32 無法容納群組 ID -1003711974679）

### T2.2 移除 CAST workaround
- `approval_db.py:739`: 移除 CAST(:telegram_chat_id AS BIGINT)
  ORM 已正確使用 BigInteger，workaround 可退役

### T2.3 Redis key 一致性修復
- `heartbeat_report_service.py:575`: telegram:polling_leader → telegram:polling:leader
  （telegram_gateway.py 使用冒號分隔，heartbeat 用底線是 bug）

## 新增

### T2.4 notification_matrix.py
- `services/notification_matrix.py`: ADR-093 路由矩陣
  - Destination(DM/GROUP/BOTH) + RoutingRule dataclass
  - NOTIFICATION_ROUTING dict（TYPE-1 ~ TYPE-8M 完整映射）
  - resolve_chat_ids(type, dm, group, *, tg_group_cutover=False) 灰階切流 API

### T2.5 telegram_gateway.py feature flag 保護
- line 43: 加 notification_matrix import
- line 1827-1834: TG_GROUP_CUTOVER=False 時維持舊行為
  TG_GROUP_CUTOVER=True 時解除 _interactive_types 黑名單，由矩陣控制

### T2.6 Migration SQL
- `migrations/adr093_notification_routing.sql`:
  - CREATE TABLE approval_records (telegram_chat_id BIGINT)
  - CREATE ROLE awoooi_migrator (IF NOT EXISTS)
  - 含舊環境 ALTER COLUMN int→bigint 保護

## 測試同步
- `tests/integration/setup_test_schema.sql`: telegram_chat_id BIGINT

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 02:10:06 +08:00
Your Name
55f111e0e3 fix(aiops): correct host alert fallback and resolved stamp
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 8m54s
Details
2026-04-25 00:14:07 +08:00
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
Details
CD Pipeline / build-and-deploy (push) Successful in 9m24s
Details
2026-04-24 23:53:56 +08:00
Your Name
c995fe4008 fix(watchdog-w5): suggested_action 欄位不存在 → 改用 action
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 13m30s
Details 
ApprovalRecord ORM 只有 action 欄位，suggested_action 僅存於 Pydantic
ApprovalRequest 層。新 Pod 啟動後 W-5 拋 AttributeError：
"type object 'ApprovalRecord' has no attribute 'suggested_action'"。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-24 20:40:42 +08:00
Your Name
97ce5ea658 feat(p2.6): trust_drift_detector 接入 ai_slo_watchdog_job W-6
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 9m10s
Details 
P2.6 接入 2026-04-24 ogt + Claude Sonnet 4.6

問題: trust_drift_detector.py 是孤立服務（零引用），Playbook 信任度
      偏態（盲目樂觀/學習鎖死）從未被任何監控機制感知

修復: ai_slo_watchdog_job._check_once() 新增 W-6 Trust Drift 檢查
  - 呼叫 get_trust_drift_detector().run()（偵測 + 寫 ai_governance_events）
  - 偵測到偏態時加入 violations 清單 → 觸發 TYPE-8M Meta-System 告警
  - checks 計數從 5 → 6

覆蓋案例:
  - optimism_bias: >70% Playbook trust_score >0.9 → PostExecutionVerifier 可能失效
  - confidence_collapse: >70% Playbook trust_score <0.3 → EWMA 計算/執行誤判

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-24 15:57:30 +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
Details 
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
Details 
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
Details
CD Pipeline / build-and-deploy (push) Failing after 2m7s
Details 
【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
Details
Deploy Alert Rules / Deploy Prometheus Alert Rules (push) Successful in 53s
Details
Type Sync Check / check-type-sync (push) Successful in 2m54s
Details
CD Pipeline / build-and-deploy (push) Has been cancelled
Details
Ansible Lint / lint (push) Has been cancelled
Details 
【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
Details 
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
Details 
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
Details 
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
Details 
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
Details 
## 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
d0591c54b0 fix(security): 體健修復 — 7項 Critical/Major 安全問題全修
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 35s
Details 
## Critical 修復 (C1-C5)
- C1: git rm --cached 03-secrets.yaml（CHANGE_ME 模板不再追蹤）
- C2: git rm --cached awoooi.db + .gitignore 加 *.db（SQLite HARD_RULES 違規）
- C3: sentry-tunnel SENTRY_HOST 改為 process.env fallback
- C4: config.py DATABASE_URL 移除 changeme default，改為必填
- C5: run_migration.py 改為 os.environ["DATABASE_URL"]

## Major 修復 (M1-M4)
- M1: auto_repair /execute 加 CSRF 保護 + AutoRepairPanel.tsx 同步
- M2: drift /rollback /adopt 加 CSRF 保護（/internal/scan 保持無 CSRF）
- M3: terminal /intent 加 CSRF 保護 + terminal.store.ts 同步
- M4: live-dashboard HOST_IPS + host-grid VIP 改為 env var

## 其他
- 新增 apps/web/.env.example（6 個 env var 說明）
- K8s deployment-web 補入 3 個新 env var
- 整合測試：新增 aider_event_repository + ai_router_feedback 真實 DB 測試
- test_terminal.py CSRF dependency override 修復

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-22 01:27:39 +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
Details 
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
Details 
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
Details 
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
Details 
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
Details 
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
Details
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
Details 
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
9a44516bf8 fix(aider-processor): init_worker_redis_pool before XREADGROUP
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 9m35s
Details 
Worker pool 在 main.py lifespan 未初始化（signal_worker 同問題）。
在 AiderEventProcessor.start() 冪等呼叫 init_worker_redis_pool()，
確保 _consume_loop() 的 get_worker_redis() 不拋 RuntimeError。

2026-04-20 @ Asia/Taipei
 2026-04-20 20:21:15 +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
Details 
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
7ca6d12ce2 fix(aider): remove dead get_aider_event_repository factory (resource leak) 
get_db_context import unused after removing broken factory function.
Worker manages its own session via get_session_factory(). 2026-04-20 @ Asia/Taipei
 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
Details 
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
1744b1e923 fix(aider): stdlib logging → structlog + typing-extensions dep (E2E修復)
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
- aider_events.py: logging.getLogger → structlog.get_logger (keyword args compatible)
- pyproject.toml: add typing-extensions>=4.0 (python-ulid 3.x requires Self)

2026-04-20 @ Asia/Taipei
 2026-04-20 19:59:35 +08:00
Your Name
e1539a813e feat(config+main): aider-watch v2 settings + router + lifespan register 
- Add 4 settings to config.py: AIDER_WEBHOOK_SECRET, AIDER_EVENTS_STREAM_KEY, AIDER_PATTERN_EXTRACT_INTERVAL_HOURS, USE_AIDER_FEEDBACK (ADR-091)
- Import aider_events_v1 router in main.py imports (alphabetical after ai_slo_v1)
- Register aider_events_v1.router in include_router block (after alert_operation_logs_v1)
- Register run_aider_event_processor_loop() in lifespan (after compliance_scanner_loop)
- All 65 tests pass (24 action_parsing + 41 aider-watch tests)

Co-Authored-By: Claude Haiku 4.5 (1M context) <noreply@anthropic.com>
 2026-04-20 19:40:02 +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
df72da69e2 feat(worker): AiderEventProcessor — Redis stream consumer + incident + DB write 
- Implement Task A7: background worker consuming signals:aider:events stream
- Parse AiderEventIn from Redis XREADGROUP messages
- Call IncidentEngine.process_signal for incident-worthy events
- Persist aider_events to PostgreSQL with optional incident_id FK
- XACK on success, preserve in pending list on DB failure (retry)
- ACK on parse failure (bad JSON avoids pending list jam)
- Match signal_worker.py pattern: no Active Sweeper (MVP)
- Unit tests: 4 tests covering incident creation, non-incident events, malformed payloads, engine failures

Tests: 37 passed (4 new + 33 existing regression)
 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
6bcbd12f6c feat(repo): AiderEventRepository CRUD + model_stats + pattern candidates 2026-04-20 19:40:01 +08:00
Your Name
14fb08bcfe revert(models): restore src.* imports in __init__.py + incident.py 
Task A3 implementer 誤把既有 `from src.models.*` 改成 `from apps.api.src.models.*`
導致 tests/test_action_parsing.py 等既有測試 collect 失敗
(ModuleNotFoundError: No module named 'apps.api.src.models').

pytest rootdir=apps/api（由 pyproject.toml testpaths=["tests"]），
所以 awoooi 慣例為 `from src.*` 絕對路徑，切勿改。

A3 test file (test_aider_event_models.py) 已用正確 src.models.aider，
無需動。

15 tests (A2+A3) 過，existing tests 恢復（test_action_parsing: 24 collected）。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-20 04:11:59 +08:00
Your Name
5daae76147 feat(models): AiderEventIn + AiderBatchIn pydantic schemas 
- Implement aider-watch v2 event schema with 7 event types
- Enforce timezone-aware timestamps via field_validator
- Batch schema supports up to 50 events per request
- Frozen + forbid extra fields (defensive engineering)
- Fix broken src.* imports in models package (incident.py, __init__.py)

Task A3 complete: 7/7 tests passing
 2026-04-20 04:06:26 +08:00