Add deployment tuning and chat load test

ai_knowledge_base_v2/apps/backend/app/api/chat.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import asyncio
 import json
+import logging
 from collections.abc import AsyncIterator
 
 from fastapi import APIRouter, Depends, HTTPException, Query
@@ -31,6 +32,7 @@ from app.services.chat_queue_service import load_chat_queue_config
 from app.services.chat_stream_service import ChatStreamService
 
 router = APIRouter()
+logger = logging.getLogger(__name__)
 
 
 @router.post("/session")
@@ -155,6 +157,7 @@ async def _chat_stream(payload: ChatCompletionRequest, db: Session, current_user
     except asyncio.CancelledError:
         raise
     except Exception:
+        logger.exception("Chat stream failed")
         yield _sse_event("error", message="AI 回复生成失败，请稍后再试。")
     finally:
         if acquired: