update

backend_service.py

@@ -481,28 +481,7 @@ async def list_models():
     return ModelsResponse(data=models)
 
         
-        # Clean up the response
-        response_text = response_text.strip() if response_text else "No response generated."
-        
-        # Create OpenAI-compatible response
-        response = ChatCompletionResponse(
-            id=f"chatcmpl-{int(time.time())}",
-            created=int(time.time()),
-            model=request.model,
-            choices=[
-                ChatCompletionChoice(
-                    index=0,
-                    message=ChatMessage(role="assistant", content=response_text),
-                    finish_reason="stop"
-                )
-            ]
-        )
-        
-        return response
-        
-    except Exception as e:
-        logger.error(f"Error in chat completion: {e}")
-        raise HTTPException(status_code=500, detail=f"Internal server error: {str(e)}")
+        # ...existing code...
 
 @app.post("/api/response")
 @app.post("/v1/chat/completions", response_model=ChatCompletionResponse)