wooo/awoooi
1
1
Fork 0
Code Issues 2 Pull Requests 1 Actions 6 Packages Projects Releases Wiki Activity
4,108 Commits 195 Branches 2 Tags
44ea892e4fb3e5847eaef30c8e9564d0acdafcea
Commit Graph

22 Commits

Author SHA1 Message Date
Your Name
35fe37c82a fix(api): route direct ollama callers through ordered fallback
All checks were successful
Code Review / ai-code-review (push) Successful in 23s
Details
CD Pipeline / tests (push) Successful in 5m51s
Details
CD Pipeline / build-and-deploy (push) Successful in 3m29s
Details
CD Pipeline / post-deploy-checks (push) Successful in 1m14s
Details
2026-05-19 12:56:13 +08:00
Your Name
e208798531 fix(ai): keep GCP Ollama lane on safe models
All checks were successful
CD Pipeline / tests (push) Successful in 54s
Details
Code Review / ai-code-review (push) Successful in 14s
Details
CD Pipeline / build-and-deploy (push) Successful in 3m25s
Details
CD Pipeline / post-deploy-checks (push) Successful in 1m50s
Details
2026-05-05 23:37:33 +08:00
OG T
7857c25677 feat: Ollama 本機 Tool Calling 取代 NVIDIA 雲端 (44s→~5s)
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
- nvidia_provider.py: 新增 OllamaToolProvider
  - 實作 INvidiaProvider protocol，打 Ollama /v1/chat/completions
  - 模型: llama3.1:8b (tool calling 最穩定的 8B)
  - 延遲: 44s → ~5s（本機 M1 Pro 192.168.0.111）
  - get_nvidia_provider() 根據 USE_OLLAMA_TOOL_CALLING 切換
- config.py: USE_OLLAMA_TOOL_CALLING=True (預設開啟), OLLAMA_TOOL_MODEL=llama3.1:8b
- 回退: USE_OLLAMA_TOOL_CALLING=False → 恢復 NvidiaProvider 雲端

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-09 14:55:04 +08:00
OG T
15aabd6ac5 fix(chat+nim): 修復首席架構師 Review I1-I4 + S3 四項重要問題
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 7m9s
Details 
I1: chat_manager._call_openclaw timeout=30.0 → 讀 settings.OPENCLAW_TIMEOUT
I2: nvidia_provider.py stale comment "45" → "55" 對齊 ConfigMap
I3: asyncio.shield 移除 — shield 超時後 task 繼續跑但無人等待 (silent leak)
I4: ChatManager.__init__ 移除 repo 實例 (leWOOOgo 禁 Service 持有 repository)
S3: _check_nemotron_health probe 10s → 25s + /v1/models 輕量端點

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-03 16:36:16 +08:00
OG T
1430b1283d fix(chat+nvidia): 還原 OpenClaw+Nemotron 架構 + 修 30s timeout 根因
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Details 
ChatManager 還原:
- OpenClaw (188:8088) 負責 RCA 仲裁，不改用 Gemini (未經批准)
- NemoClaw (NVIDIA NIM nemotron-mini-4b) 負責補充/評論
- 雙 AI 並行執行，OpenClaw 30s / NemoClaw 50s timeout
- 支援 @openclaw / @nemo 指定對象

nvidia_provider.py 修 timeout 根因:
- NVIDIA_TIMEOUT 從硬編碼 30.0 改為讀 NEMOTRON_TIMEOUT_SECONDS (45s)
- Memory 記載 NIM 免費 tier 延遲 11-45s，30s 硬編碼導致慢請求全超時

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-03 15:34:02 +08:00
OG T
9913f5dc6d feat(infra): 開發環境分離 + BuildKit cache 修復 + circuit breaker 優化
Some checks failed
CD Pipeline / build-and-deploy (push) Successful in 6m52s
Details
E2E Health Check / e2e-health (push) Successful in 17s
Details
CD Pipeline (Dev) / build-and-deploy-dev (push) Failing after 9s
Details 
1. k8s/awoooi-dev/: 新建 dev namespace (01-05 配置)
   - Namespace + ResourceQuota (cpu 2/4, mem 4Gi/8Gi)
   - ConfigMap: ENVIRONMENT=dev, LOG_LEVEL=DEBUG, SHADOW_MODE=false
   - Deployment: 1 replica, NodePort 32344, image dev-latest
   - RBAC: awoooi-executor-dev ServiceAccount

2. .gitea/workflows/cd-dev.yaml: dev branch CD pipeline
   - 觸發: dev branch push
   - Build: --no-cache (防 cache poisoning)
   - Tag: dev-{sha} / dev-latest
   - Deploy: awoooi-dev namespace, health check 32344
   - Telegram: [DEV] 前綴通知

3. apps/api/Dockerfile: ARG CACHE_BUST=none (防 BuildKit cache 毒化)
   - deps 層 (pip install) 仍可 cache
   - src/ 和 models.json 層每次重建

4. .gitea/workflows/cd.yaml: 正式環境 API build 加入 CACHE_BUST=git_sha
   - 確保 models.json 等配置變更正確進入 image

5. apps/api/src/services/nvidia_provider.py: timeout 不計入 circuit breaker
   - TimeoutException → 只 log，不 record_failure()
   - 只有硬性錯誤 (auth/rate limit/exception) 才斷路

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-01 16:22:21 +08:00
OG T
419dc2f8e0 fix(nvidia): timeout 60s→30s，NVIDIA 第一保免費，失敗轉 Gemini
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 5m46s
Details
E2E Health Check / e2e-health (push) Successful in 16s
Details 
- nvidia_provider.py: NVIDIA_TIMEOUT 60→30s
- models.json: timeout_seconds 60→30s
- configmap: NEMOTRON_TIMEOUT_SECONDS 45→30s, fallback 恢復 nvidia 第一
目標: Nemo 有足夠時間回應(free)，失敗快速轉 Gemini(備援)，整體機制可運作

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-01 16:05:19 +08:00
OG T
cc6b18e3bc fix(phase22): 修復 Telegram 對話三個 Bug (ADR-044)
All checks were successful
E2E Health Check / e2e-health (push) Successful in 18s
Details 
P0: security_interceptor.py 新增 intercept_telegram() 方法
- 修復 _handle_chat_message 的 AttributeError (致命 Bug)
- 白名單驗證，不需要 Nonce (對話訊息 vs 按鈕回調)

P1: nvidia_provider.py chat() 新增 use_json_mode 參數
- 對話場景預設 False (自然語言回應)
- RCA/分析場景傳入 True (結構化 JSON 輸出)
- openclaw.py RCA 呼叫加上 use_json_mode=True

P2: K8s ConfigMap 啟用 TELEGRAM_ENABLE_POLLING=true
- K8s AWOOOI API 接管 @tsenyangbot Long Polling
- OpenClaw (188) 停止 Telegram，改為純 REST 服務

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-31 21:53:09 +08:00
OG T
dffb535220 perf(nvidia): bump max_tokens to 2048 for full RCA responses
All checks were successful
E2E Health Check / e2e-health (push) Successful in 16s
Details
2026-03-31 15:07:51 +08:00
OG T
93a3173b5d fix(nvidia): super robust langfuse handling to prevent NoneType AttributeError
All checks were successful
E2E Health Check / e2e-health (push) Successful in 17s
Details
2026-03-31 15:01:15 +08:00
OG T
888cb78f0a fix(nvidia): avoid AttributeError when langfuse trace is None
All checks were successful
E2E Health Check / e2e-health (push) Successful in 19s
Details
2026-03-31 14:57:44 +08:00
OG T
46843c8e19 fix(nvidia): revert to nemotron-mini, truncate context for 4K limit, enforce precise confidence
All checks were successful
E2E Health Check / e2e-health (push) Successful in 17s
Details
2026-03-31 13:57:10 +08:00
OG T
22796c6aff fix(nvidia): upgrade to meta/llama-3.1-8b-instruct (128k context) to avoid 400 bad request on API
All checks were successful
E2E Health Check / e2e-health (push) Successful in 17s
Details
2026-03-31 13:49:49 +08:00
OG T
11627f25f0 fix(nvidia): lower default max_tokens to 1024 to fit nemotron-mini 4096 context length
All checks were successful
E2E Health Check / e2e-health (push) Successful in 16s
Details
2026-03-31 13:44:17 +08:00
OG T
4ce7999bd7 fix(nvidia): 記錄 HTTPStatusError 響應體以診斷 400 錯誤 
2026-03-31 ogt: 首席架構師審查要求增加錯誤診斷

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-31 11:38:09 +08:00
OG T
c80a69bd88 fix(lint): 修復 NVIDIA_LATENCY_HISTOGRAM 使用方式 
- 移除錯誤的 .labels() 調用 (Histogram 無 labels)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 20:53:55 +08:00
OG T
2a3e627c37 fix(api): 修正 NVIDIA_LATENCY_SECONDS → NVIDIA_LATENCY_HISTOGRAM 
2026-03-29 ogt: CI lint 修復 - 變數名稱錯誤

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 20:52:57 +08:00
OG T
04bfff9d19 refactor(ai): 模組化重構 - NVIDIA chat 移至 NvidiaProvider 
符合 feedback_lewooogo_modular_enforcement.md 規範:
- 移除 openclaw.py 中的 _call_nvidia() (重複邏輯)
- 新增 NvidiaProvider.chat() 方法
- 更新 INvidiaProvider Protocol
- openclaw.py 改用 get_nvidia_provider().chat()
- 測試移至 test_nvidia_chat.py

架構層次:
- Router → Service → Provider (正確)
- 禁止 Service 層重複實作已存在的 Provider 功能

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 20:49:23 +08:00
OG T
d89f0520f9 fix(api): 修復 34 個 Ruff lint 錯誤 
- 自動修復 import 排序、unused imports
- 手動修復 raise from、isinstance union、unused variable
- scripts/ 暫時保留 (非 CI 阻擋)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 15:27:49 +08:00
OG T
ae21ba2cc6 feat(ai): Phase 20 P3 優化 - Circuit Breaker + 指數退避 + Prometheus 
P3-1: Circuit Breaker 狀態機 (CLOSED/OPEN/HALF_OPEN)
- 連續 3 次失敗觸發斷路
- 60 秒後自動嘗試恢復
- 防止連鎖故障

P3-2: 指數退避重試
- 基礎延遲 1s，最大 30s
- 含 10% jitter 避免雷鳴

P3-3: Prometheus Metrics
- nvidia_tool_call_requests_total (status, tool_name)
- nvidia_tool_call_latency_seconds (histogram)
- nvidia_circuit_breaker_state_changes_total

測試: 25 → 34 PASSED

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 01:49:08 +08:00
OG T
4f7282a97a fix(ai): Phase 20 P2 修復 - Protocol + 邊界測試 + model_registry 
P2-1: 定義 INvidiaProvider Protocol (@runtime_checkable)
P2-2: 補充邊界測試 15 → 25 案例
P2-3: model_registry 新增 NVIDIA + tool_calling_fallback_order

首席架構師評分: 82 → 86 → 90/100

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-03-29 01:24:17 +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