OG T
d148756b67
feat(api): LLM 整合 Expert System 診斷上下文
...
長期方案實作: Expert 診斷 + LLM 智能分析
變更:
1. decision_manager._dual_engine_analyze():
- 測試資源跳過 LLM (省錢)
- 傳遞 Expert 診斷上下文給 LLM
- LLM 失敗時根據診斷調整回應
2. openclaw.generate_incident_proposal():
- 新增 expert_context 參數
- Prompt 包含 Expert 診斷結果
- 引導 LLM 基於診斷做決策
流程:
Playbook → Expert診斷 → LLM(with context) → 智能建議
這是「先診斷根因，再決定行動」的正確實作
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-26 21:41:26 +08:00
OG T
2ef7daccde
feat(api): Expert System 智能診斷重構 - 根因優先
...
問題: 原本的 Expert System 只會建議「重啟」，不診斷根因
重構:
1. 分層診斷:
- 層 1: 測試資源過濾 (test/demo/tmp 自動忽略)
- 層 2: 規則匹配 (更精確的 pattern)
- 層 3: 診斷指令 (提供 kubectl 診斷命令)
2. 根因優先:
- OOM → 檢查記憶體用量，非重啟
- CrashLoop → 查看崩潰日誌，非重啟
- ImagePull → 檢查映像配置，非重啟
- Default → 人工診斷，非盲目重啟
3. 人工標記:
- 未知問題標記 human_review_required
- 降低 confidence (0.5)
這才是正確的自動化修復：先診斷根因，再決定行動
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-26 21:35:20 +08:00
OG T
35aa690bf1
fix(decision_manager): 修復 Telegram 重複發送問題
...
問題:
- Phase 6.5 (765ee39noreply@anthropic.com >
2026-03-26 19:21:36 +08:00
OG T
d1f0bbfbcd
refactor(api): Phase 17 P1 Tier 3 紅區服務 Protocol 定義
...
新增 5 個紅區核心服務的 Protocol 介面：
- IDecisionManager: 決策狀態機
- ITrustScoreManager: 信任評分引擎
- IIncidentEngine: 事件處理引擎
- IMultiSigRedisService: 分散式鎖服務
- ITelegramSecurityInterceptor: 安全攔截器
符合 leWOOOgo 積木化規範：
- 支援依賴注入 (DI)
- 便於測試時 Mock
- 型別約束確保實作一致性
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-26 12:49:30 +08:00
OG T
2e75a20150
feat(api): Phase 7.5-7.6 Playbook 整合決策與自動萃取
...
Phase 7.5: DecisionManager 三軌決策
- 新增 Playbook 優先匹配 (similarity >= 85%)
- 三軌決策順序: Playbook > LLM > Expert System
- 整合 PlaybookService 推薦引擎
Phase 7.6: 自動萃取機制
- approval_execution.py 成功執行後觸發萃取
- 條件: RESOLVED/CLOSED + effectiveness >= 4
- 滿分 (5) 自動核准 Playbook
測試:
- 13 個 Playbook 單元測試全部通過
- 修復 Incident 模型欄位對應 (reasoning_steps)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-26 11:09:25 +08:00
OG T
765ee39a90
feat(api): Phase 6.5 Statistics API + Y/n 按鈕修復
...
新增:
- /stats/incidents/summary - 事件總覽統計
- /stats/incidents/resolution - 解決時間 P50/P95
- /stats/ai-performance - AI 提案效能
- /stats/services/affected - 受影響服務排名
修復:
- Y/n 按鈕永久禁用問題 (decision.state=completed 但 incident 未解決)
- decision_manager.py: 只有當 incident 也已解決才返回已完成的 decision
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-24 09:50:03 +08:00
OG T
4f1c8ae473
fix(ci): Resolve Python and TypeScript lint errors
...
- Fix 35 Python ruff errors (B904, F841, E722, E741, B007, B008)
- Add eslint config for lewooogo-core package
- Update pyproject.toml to new ruff lint config format
- Relax frontend eslint rules to warnings for unused vars
- Allow console.* for debugging (TODO: unified logger)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-24 09:20:56 +08:00
OG T
6f049877fc
fix(lint): ruff auto-fix + lewooogo-core src 加入 git
...
- Python: ruff --fix 修復 280 個 lint 錯誤
- lewooogo-core: src/ 目錄未追蹤，導致 CI eslint 失敗
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-23 23:51:37 +08:00
OG T
eca3759fde
fix(telegram): 修復 Signal Worker 流程 Telegram 通知斷鏈
...
問題:
- Phase 6 Signal Worker 新架構沒有整合 Telegram 推送
- 決策就緒時 Telegram 完全沒收到通知
- 這是嚴重的監控盲點！
修復:
- 新增 _push_decision_to_telegram() 推送函數
- DecisionManager 決策 READY 時自動推送
- 非阻塞執行 (asyncio.create_task)
Telegram 通知內容:
- 告警來源 (LLM/Expert System)
- 受影響服務
- 建議動作
- 風險等級
- 信心分數
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-23 23:22:26 +08:00
OG T
7478dc0254
feat(phase6-9): Complete modular architecture and Agent Teams
...
Phase 6.4 - Modular Architecture:
- Add lewooogo-brain adapters for LLM providers
- Add lewooogo-data dual memory (Redis + PostgreSQL)
- Implement consensus engine for multi-agent decisions
- Add incident memory service for historical context
Phase 9 - Agent Teams (Claude Agent SDK):
- Add base agent class with Claude Sonnet 4 integration
- Implement action planner, blast radius, and security agents
- Add agent API endpoints and proposal workflow
- Integrate ADR-009 OpenClaw Agent Teams architecture
DevOps & CI/CD:
- Add GitHub Actions CI/CD workflows (ci.yaml, cd.yaml)
- Add pre-commit hooks and secrets baseline
- Add docker-compose for local development
- Update Kubernetes network policies
Frontend Improvements:
- Add auto-healing error boundary component
- Update i18n messages for agent features
- Enhance dual-state incident card with execution feedback
Documentation:
- Add 7 ADRs covering MCP, design system, architecture decisions
- Update ARCHITECTURE_MEMORY.md with modular design
- Add GLOBAL_RULES.md and SOUL.md for project identity
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-23 18:40:36 +08:00
OG T
0aaf6a276b
feat(api,web): Phase 6.5 DecisionManager with dual-engine fallback
...
Backend:
- Add DecisionManager with state machine (INIT→ANALYZING→READY→EXECUTING)
- Implement Expert System rules engine (100% local, never fails)
- Dual-engine: LLM (primary) + Expert System (fallback)
- Auto-generate decision_token for each incident
- 30-second timeout guarantee
Frontend:
- Use decision.state to unlock [Y/n] buttons
- Display AI action suggestion in card
- Show source indicator [AI] or [EXP]
- Generate proposal on-demand if needed
Fixes: UI locked with hourglass when LLM times out
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-03-23 13:19:55 +08:00
