wooo/awoooi
1
1
Fork 0
Code Issues 2 Pull Requests 1 Actions 2 Packages Projects Releases Wiki Activity
906 Commits 203 Branches 2 Tags
78a8d3dfa5368f9d3dfd08bf6b73f436ce5d8927
Commit Graph

18 Commits

Author SHA1 Message Date
OG T
73577f7c5d chore(ai-router): v4.3 版本號同步 (trigger CD push event)
Some checks failed
CD Pipeline / Deploy Prometheus Alert Rules (push) Has been cancelled
Details
CD Pipeline / build-and-deploy (push) Has been cancelled
Details
2026-04-05 12:03:15 +08:00
OG T
2243a21b96 fix(ai-router): v4.3 NIM 保護 — timeout 不計 CB 失敗，每次先跑 NIM 才切 Gemini
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 20s
Details 
需求: NIM 必須等到有回應才切換，不能因為慢就被 CB 封鎖走 Gemini

變更:
- Timeout exception 不累積 CB failure（只有真實連線錯誤才計）
- NIM CB: failure_threshold=10, recovery_timeout=30s（比預設寬鬆）
- 設計文件 v4.3: 更新方向二，移除錯誤假設

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 01:51:12 +08:00
OG T
5ad403b287 fix(p0): v4.3 — 實測確認 Ollama CPU-only 不可用，DIAGNOSE 統一走 NIM 
實測依據 (2026-04-05):
- Ollama llama3.2:3b CPU-only: 238s 回 {"ok":true}，生產不可用
- Nemotron NIM: 2.2s~27.3s，avg 10.6s，一直是主力（Phase 22 起）
- NIM 從未有隱私問題，Incident 資料一直送雲端 GPU

變更:
- ai_router.py: _local_fallback_chain 廢棄（空 list）
- ai_router.py: DIAGNOSE route/route_sync 改回 _full_fallback_chain
- config.py: 更新 timeout 說明反映實測結果
- test_p0_diagnose_routing.py: 更新 docstring

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 01:49:06 +08:00
OG T
96d5e18924 fix(p0): 實測修正 — timeout 依 benchmark 調整，_local_fallback_chain 移除雲端 Nemotron 
- config.py: NEMOTRON_DIAGNOSE_TIMEOUT_SECONDS=60s (NIM 實測 11-45s + 15s buffer)
- config.py: OLLAMA_DIAGNOSE_TIMEOUT_SECONDS=200s (Ollama 實測 ~173s + 27s buffer)
- ollama.py: 新增 per-task timeout (diagnose/force_local 用 200s)
- ai_router.py: _local_fallback_chain 移除 Nemotron (NIM=雲端，不可進 local chain)
- ai_router.py: v4.2 — Option C 分情境路由正式確立

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 00:29:09 +08:00
OG T
a562db4048 fix(phase25): 首席架構師 Review C1/C2/I1/I3 修正
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 57s
Details 
C1: NemotronProvider.privacy_level cloud→local
    NIM 部署在 192.168.0.188 內網，非官方雲端 API
    可納入 DIAGNOSE _local_fallback_chain 隱私邊界

C2: adopt() 端點暫停，返回 501
    API Pod 執行 git add -A 有安全風險
    ADR-057 起草後改用 Gitea PR API 實作

I1: timeout log 修正，記錄實際套用的 timeout 值
    原本永遠記錄 NEMOTRON_TIMEOUT_SECONDS=45
    現在記錄依 task_type 選擇的正確值

I3: route_sync() 補 DIAGNOSE 隱私邊界
    async route() 已有 _local_fallback_chain
    sync 版本遺漏，此次補齊

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-04 18:00:05 +08:00
OG T
c4eafd2a5b fix(ai-router): fallback_models 排除 selected_model 避免重複
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 6m58s
Details 
DIAGNOSE intent 路由至 Nemotron 後，fallback_chain 中的 OPENCLAW_NEMO
也使用相同 model string，導致 fallback_models 包含已選模型。

修正: 過濾掉與 selected_model 相同的 model string。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-04 17:43:44 +08:00
OG T
8056be5847 feat(ai-router): DIAGNOSE intent override 升級至 Nemotron (P0) 2026-04-04 17:41:45 +08:00
OG T
3455044457 feat(phase25): Nemotron 主動防禦三方向 P0+P1+P2 完整實作
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 38s
Details
Type Sync Check / check-type-sync (push) Failing after 35s
Details 
P0 - DIAGNOSE Privacy-First Routing:
- ai_router.py: _local_fallback_chain [NEMOTRON→OLLAMA→REJECT]
- DIAGNOSE 意圖 override 改為 NEMOTRON (原 OLLAMA)
- DIAGNOSE fallback 使用 local-only 鏈，不觸碰雲端
- 全部失敗時 REJECT + Telegram 通知
- config.py: NEMOTRON_DIAGNOSE_TIMEOUT_SECONDS=30, OLLAMA_DIAGNOSE_TIMEOUT_SECONDS=60
- nemotron.py: 根據 context[task_type] 選擇 timeout

P1 - Knowledge Auto-Harvesting:
- models/knowledge.py: EntryType.AUTO_RUNBOOK + ANTI_PATTERN + symptoms_hash
- EntryStatus.PUBLISHED (ANTI_PATTERN 直接發布，無需審核)
- models/playbook.py: SymptomPattern.compute_hash() (16字元確定性 hash)
- services/runbook_generator.py: NemotronRunbookGenerator (v1.1)
  - generate_runbook() → AUTO_RUNBOOK (DRAFT) + Telegram 審核 card
  - generate_anti_pattern() → ANTI_PATTERN (PUBLISHED) + Telegram 通知
  - 使用 nvidia.chat() (正確介面)，Nemotron 超時時 Minimal fallback
- knowledge_service.py: check_anti_pattern(symptoms_hash, days=7)
- db/models.py: symptoms_hash VARCHAR(16) + ix_knowledge_symptoms_hash
- repositories/knowledge_repository.py: create() 支援 symptoms_hash + status
- auto_repair_service.py: anti_pattern_gate 在 decide() + runbook hook 在 execute()
- migrations/phase8_symptoms_hash.sql: ALTER TABLE + partial index + PUBLISHED constraint

P2 - Config Drift Detection:
- models/drift.py: DriftItem/DriftReport/DriftLevel/DriftIntent/DriftStatus
- services/drift_detector.py: GitStateReader + K8sStateReader + DriftDetector
- services/drift_analyzer.py: 白名單過濾 + DriftLevel 分級
- services/drift_interpreter.py: NemotronDriftInterpreter（意圖分析，不生成修復指令）
- services/drift_remediator.py: rollback(kubectl apply) + adopt(git push gitea)
- api/v1/drift.py: POST /scan, GET /reports, POST /rollback, POST /adopt
- migrations/phase9_drift_reports.sql: drift_reports 表
- k8s/drift-cronjob.yaml: 每小時自動掃描 CronJob

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-04 12:35:05 +08:00
OG T
b225c23ad8 fix(ai_router): DIAGNOSE/ALERT_TRIAGE 改用 llama3.2:3b 避免 90秒 timeout
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 7m5s
Details 
qwen2.5:7b-instruct 在 prod 需要 >90s，導致 DIAGNOSE intent 全鏈路失敗。
llama3.2:3b (summary model) 實測 4s 回應，適合 triage 類快速判斷。

規則 3 新增特判: DIAGNOSE/ALERT_TRIAGE/QUERY → ollama summary model
不影響其他 intent 的 model 選擇邏輯。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-03 12:32:01 +08:00
OG T
97d86861ed fix(ai_router): C1 修復 — AIProviderEnum 對齊 Registry 實際 Provider 名稱
Some checks failed
CD Pipeline / build-and-deploy (push) Failing after 37s
Details 
問題: AIProviderEnum.NVIDIA = "nvidia" 在 Registry 無對應 Provider
      OpenClawNemoProvider.name = "openclaw_nemo"
      NemotronProvider.name = "nemotron"
      → 高複雜度/Tool Calling 路由永遠 skip，靜默 fallback 到 Gemini/Ollama

修復:
- 新增 OPENCLAW_NEMO = "openclaw_nemo" (一般推理, via .188 → NVIDIA NIM)
- 新增 NEMOTRON = "nemotron" (Tool Calling, direct NVIDIA NIM)
- 移除 NVIDIA = "nvidia" (Registry 無對應)
- 規則 4 (複雜度>=4/HIGH風險): NVIDIA → OPENCLAW_NEMO
- route_tool_calling: NVIDIA → NEMOTRON
- Rate Limiter check: "nvidia" → "openclaw_nemo"
- _full_fallback_chain: OPENCLAW_NEMO 首位
- _tool_calling_fallback_chain: NEMOTRON 首位

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-02 23:31:31 +08:00
OG T
5a8aae89c4 fix(phase24): 首席架構師 Review C1/C2/C3/I4 修復
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 7m12s
Details
E2E Health Check / e2e-health (push) Successful in 18s
Details 
C1 (P0): AIRouterExecutor.execute() 補 Langfuse Trace (D5)
  - 建立 langfuse_trace("ai_router_execute") 包住整個執行鏈
  - 成功時記錄 generation (model/input/output/tokens/cost)
  - prod 所有 AI 呼叫現在有 LLMOps 追蹤

C2 (P0): 絞殺者改為呼叫 AIRouter.route() 智慧路由
  - 先取得 RoutingDecision (意圖分類 + 複雜度評分)
  - provider_order 從 selected_provider + fallback_chain 動態生成
  - D1 意圖路由矩陣、D7 隱私保護 (DIAGNOSE 強制 local) 生效

C3 (P1): 型別標注 typo 修復
  - AIProviderEnumEnum → AIProviderEnum
  - AIProviderEnumProtocol → AIProviderProtocol

I4 (P1): interfaces.py AIProvider Protocol 補 close() 定義

S1: ai_router.py 模組版本標頭更新至 v4.0

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-02 21:47:06 +08:00
OG T
3ad7b60f68 fix(ai): Phase 24 R1+R2 首席架構師 Review 修復 (C1-C3 + I1-I5)
Some checks failed
E2E Health Check / e2e-health (push) Successful in 18s
Details
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
Critical 修復:
- C1: AIProvider Enum 改名為 AIProviderEnum (避免與 Protocol 同名衝突)
- C2: 共用 Circuit Breaker → per-provider _SimpleCircuitBreaker
  (避免 Gemini 掛掉時 Ollama 也被擋)
- C3: cache_key 移到 try 外面 (避免 UnboundLocalError)

Important 修復:
- I1: Claude hardcode model → 用 get_model_registry()
- I2: Claude 追蹤 tokens/cost (input_tokens + output_tokens)
- I3: Ollama 追蹤 tokens (eval_count + prompt_eval_count)
- I4: Gemini temperature → 用 model_registry
- I5: AIProviderRegistry.close_all() shutdown hook

2026-04-02 ogt: Phase 24 首席架構師審查通過後修復

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-02 13:40:58 +08:00
OG T
73e8f8ab77 feat(ai): Phase 24-A+B1 — AI Provider Registry + 絞殺者包裝 (ADR-052)
Some checks failed
E2E Health Check / e2e-health (push) Successful in 16s
Details
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
Brain Layer 雙軌 Registry 架構:
- 新建 src/services/ai_providers/ 目錄 (interfaces + 4 providers)
  - OllamaProvider (local, rca/chat/code_review)
  - GeminiProvider (cloud, rca/chat)
  - ClaudeProvider (cloud, rca/chat/code_review)
  - OpenClawNemoProvider (cloud, rca — 委派 188→NIM)
- 擴展 ai_router.py 加入:
  - AIProviderRegistry (動態註冊/啟停)
  - AIRouterExecutor (Cache + 閘門 CB/RL/Sem + 執行)
- openclaw.py 絞殺者包裝: USE_AI_ROUTER=true 走新路徑
- config.py + ConfigMap 加入 USE_AI_ROUTER=false (安全預設)
- ADR-052 正式文件 (14 項決策 D1-D14)
- HARD_RULES v1.7 加入 AI Router 規範

安全: USE_AI_ROUTER=false 預設不啟用，需手動開啟觀察
回滾: kubectl set env deployment/awoooi-api USE_AI_ROUTER=false

2026-04-02 ogt: Phase 24 首批實作

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-02 13:16:09 +08:00
OG T
1f9e94e78d refactor(ai-router): 新增 IAIRouter Protocol (P1 修復) 
首席架構師審查 P1 修復:
- 新增 IAIRouter Protocol 支援 DI 測試替換
- 參考 IModelRegistry, IComplexityScorer 實作模式
- 包含 route(), route_sync(), route_tool_calling() 方法簽名

審查評分: 78/100 → 85/100

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-31 21:23:07 +08:00
OG T
000533d32e feat(ai): promote Nvidia nemotron as default arbitrator for high complexity/risk incidents
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 4m35s
Details
E2E Health Check / e2e-health (push) Successful in 16s
Details
2026-03-30 00:26:53 +08:00
OG T
b77e151387 feat(ai): ADR-036 NVIDIA Nemotron Tool Calling 整合 
Phase 20 - 提升 Tool Calling 精準度 50% → 83.3%

新增:
- src/models/nvidia.py: Pydantic Schema
- src/services/nvidia_provider.py: NvidiaProvider 類別
- tests/test_nvidia_provider.py: 15 項單元測試 (全部通過)

修改:
- ai_router.py: AIProvider.NVIDIA + route_tool_calling()
- ai_rate_limiter.py: NVIDIA 限制 (5 RPM, 100/day)
- models.json: NVIDIA 配置
- cd.yaml: Secrets 注入 NVIDIA_API_KEY

路由策略:
- Tool Calling: Nemotron → Gemini → Claude
- 一般對話: Ollama → Gemini → Claude (不變)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 00:00:08 +08:00
OG T
579da38b8b feat(api): Phase 13 智能路由 + CI/CD 整合 (#74-88) 
Phase 13.1 CI/CD Integration:
- #76 workflow_run handler for CI failure diagnosis
- #77 SignOz log query (query_logs, error_logs_summary MCP)
- #78 CIAutoRepairService with risk-based execution decisions

Phase 13.3 Smart Routing:
- #85 Intent Classifier v2.0 (rule engine + LLM fallback)
- #86 Complexity Scorer (9-dimension scoring)
- #87 AI Router v3.0 (routing decision matrix)
- #88 Token Counter (OTEL + Langfuse integration)

New files:
- services/ci_auto_repair.py (risk stratification)
- services/model_registry.py (centralized model config)
- services/token_counter.py (677 lines)
- Skill 08: Model Router Expert
- Skill 09: Strangler Pattern Expert
- ADR-023: Smart Routing Architecture
- ADR-024: API Layer Architecture

Tests:
- phase11-conversational.spec.ts (E2E tests)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-26 15:32:52 +08:00
OG T
58b4004a18 feat(api): Phase 13.3 智能路由 (#85-87) 
- IntentClassifier: 意圖分類 (告警/部署/查詢/維運/審查)
- ComplexityScorer: 複雜度評分 (1-5 分)
- AIRouter: 動態模型選擇 (整合 Intent + Complexity)
- 測試: 完整單元測試覆蓋

Phase 13.3 設計: project_phase13_3_smart_router.md

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-26 10:01:04 +08:00