943de8466c
Some checks failed
CD Pipeline / deploy (push) Has been cancelled
Operation Ollama-First v5.0 / Phase 7 Frontier 升級 services/anthropic_service.py (新檔, 226 行) - AnthropicService 包裝 + ClaudeResponse dataclass - Ephemeral prompt cache 5 分鐘 TTL（重複 system_prompt 省 90% 成本） - usage 解析 input/output/cache_creation/cache_read 四欄位 - ANTHROPIC_API_KEY 未設或 SDK 缺失時 is_available()=False 靜默退化 code_review_pipeline_service.py — _openclaw_assess 加 L1 Claude 分支 - CODE_REVIEW_USE_CLAUDE flag (預設 OFF，等 ANTHROPIC_API_KEY 設定後翻 ON) - 路由：Claude Opus 4.7 (Arena code Elo 1548) → Gemini → ElephantAlpha 三層 - request_id 串鏈不變 ai_call_logger.py COST_TABLE 補 3 個 Claude 模型： - claude-opus-4-7: $15/$75 per M tokens (程式碼 #1) - claude-sonnet-4-6: $3/$15 per M tokens (agentic 平衡) - claude-haiku-4-5: $0.8/$4 per M tokens (輕量快速) requirements.txt: 加 anthropic>=0.40.0 .env.example: 加 ANTHROPIC_API_KEY / CODE_REVIEW_USE_CLAUDE / CLAUDE_MODEL 52 unit tests 全綠（22 logger + 18 anthropic + 5 routing + 7 security） 啟用步驟（待統帥手動）： 1. .env 加 ANTHROPIC_API_KEY=sk-ant-... 2. CODE_REVIEW_USE_CLAUDE=true + restart momo-app 3. 觀察 ai_calls.cache_read_tokens > 0 確認 cache 生效 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
31 lines
858 B
Plaintext
31 lines
858 B
Plaintext
Flask>=2.3
|
||
Flask-WTF
|
||
gunicorn>=20.1
|
||
pandas>=1.5
|
||
pytz
|
||
openpyxl
|
||
SQLAlchemy>=1.4
|
||
psycopg2-binary>=2.9
|
||
schedule
|
||
pyngrok
|
||
selenium
|
||
requests
|
||
numpy
|
||
python-dotenv
|
||
google-auth
|
||
google-auth-oauthlib
|
||
google-auth-httplib2
|
||
google-api-python-client
|
||
google-generativeai
|
||
anthropic>=0.40.0 # Phase 7 Frontier 升級：Claude Opus 4.7 Code Review（feature flag CODE_REVIEW_USE_CLAUDE 預設 OFF）
|
||
feedparser
|
||
beautifulsoup4
|
||
lxml
|
||
prometheus-client
|
||
python-telegram-bot[job-queue]>=20.0
|
||
pgvector>=0.2
|
||
paramiko # ADR-013: AIOps SSH 跳板修復
|
||
python-pptx # ADR-014: PPT 簡報系統
|
||
matplotlib # 圖表生成（日報/週報/月報）
|
||
matplotlib-inline # Jupyter 相容層（可選）
|
||
psutil>=5.9 # ADR-019 Phase 2: ElephantAlpha system load 真實量測（production 必裝；缺失時 fallback 為 queue-based 估算） |