feat: remove rate limit and message limit for /chat-dev endpoint

backend/api/chatbot_route.py

@@ -82,12 +82,9 @@ async def fashion_qa_chat(request: Request, req: QueryRequest, background_tasks:
 
 
 @router.post("/api/agent/chat-dev", summary="Fashion Q&A Chat (Dev - includes user_insight)")
-@rate_limit_service.limiter.limit("50/minute")
 async def fashion_qa_chat_dev(request: Request, req: QueryRequest, background_tasks: BackgroundTasks):
     """
-    Endpoint chat dành cho DEV - trả về đầy đủ user_insight.
-
-    Note: Rate limit đã được check trong middleware.
+    Endpoint chat dành cho DEV - không rate limit, không cache, không message limit.
     """
     user_id = getattr(request.state, "user_id", None)
     device_id = getattr(request.state, "device_id", "unknown")
@@ -105,30 +102,17 @@ async def fashion_qa_chat_dev(request: Request, req: QueryRequest, background_ta
             images=req.images,
             identity_key=str(identity_id),
             return_user_insight=False,
-            is_authenticated=is_authenticated,  # Pass auth status for Langfuse metadata
-            device_id=device_id,  # Luôn truyền device_id để lưu vào Langfuse metadata
-            skip_cache=True,  # Dev endpoint: luôn gọi LLM mới, không cache
-        )
-
-        usage_info = await message_limit_service.increment(
-            identity_key=identity_id,
             is_authenticated=is_authenticated,
+            device_id=device_id,
+            skip_cache=True,
         )
 
-        logger.warning(f"🔍 [DEBUG] usage_info = {usage_info}")
-
         return {
             "status": "success",
             "ai_response": result["ai_response"],
             "product_ids": result.get("product_ids", []),
             "insight_status": "success" if result.get("user_insight") else "pending",
             "user_insight": result.get("user_insight"),
-            "limit_info": {
-                "limit": usage_info["limit"],
-                "used": usage_info["used"],
-                "remaining": usage_info["remaining"],
-                "reset_seconds": usage_info.get("reset_seconds"),
-            },
         }
     except Exception as e:
         logger.error(f"Error in fashion_qa_chat_dev: {e}", exc_info=True)