feat: AI assistant phase 2 - configurable prompt, action operations, FAQ matching, NVIDIA provider

- Admin-configurable AI prompt/quick questions from system_configs DB
- GET /api/v1/ai/quick-questions endpoint for fetching quick questions
- Local FAQ matching for instant responses (avoid AI calls for common Qs)
- AI action extraction: "add customer" intent detected, structured data returned
- Frontend action confirmation card with editable fields, calls customer API on confirm
- NVIDIA provider (stepfun-ai/step-3.5-flash) for faster chat vs deepseek-v4-flash
- Fixed httpx client timeout preventing backend hangs
- Added log_usage calls for auth events (register/login/guest/wechat)
- Admin tabs (users/stats/logs/config) fully functional with real backend
- AiAssistant component added to all tabbar pages

backend/app/config.py

@@ -45,7 +45,11 @@ class Settings(BaseSettings):
 
     OPENCODE_GO_API_KEY: Optional[str] = None
     OPENCODE_GO_BASE_URL: str = "https://opencode.ai/zen/go/v1"
-    OPENCODE_GO_MODEL: str = "deepseek-v4-flash"
+    OPENCODE_GO_MODEL: str = "minimax-m2.7"
+
+    NVIDIA_API_KEY: Optional[str] = None
+    NVIDIA_BASE_URL: str = "https://integrate.api.nvidia.com/v1"
+    NVIDIA_MODEL: str = "stepfun-ai/step-3.5-flash"
 
     WHATSAPP_API_TOKEN: Optional[str] = None
     WHATSAPP_PHONE_NUMBER_ID: Optional[str] = None
@@ -72,6 +76,7 @@ class Settings(BaseSettings):
         "marketing": {"primary": "opencode_go", "fallback": ["sensenova", "openai", "local"]},
         "extract": {"primary": "opencode_go", "fallback": ["sensenova", "openai"]},
         "quotation": {"primary": "opencode_go", "fallback": ["sensenova", "openai"]},
+        "chat": {"primary": "nvidia", "fallback": ["opencode_go", "openai", "sensenova"]},
     }
 
     FREE_DAILY_TRANSLATE_CHARS: int = 5000