Update api_service.py

api_service.py

@@ -90,7 +90,7 @@ class ApiService:
                     
                     if stream:
                         # 流式响应
-                        chunk_response = self._create_stream_chunk(chunk_text, request_id)
+                        chunk_response = self._create_stream_chunk(chunk_text, request_id, model)
                         yield f"data: {json.dumps(chunk_response)}\n\n"
                     else:
                         # 非流式响应 - 等待完整内容
@@ -102,14 +102,14 @@ class ApiService:
             
             if stream:
                 # 发送结束标记
-                final_chunk = self._create_stream_end_chunk(request_id)
+                final_chunk = self._create_stream_end_chunk(request_id, model)
                 yield f"data: {json.dumps(final_chunk)}\n\n"
                 yield "data: [DONE]\n\n"
                 
                 logger.success(f"✅ 流式响应完成 [ID: {request_id[:8]}] [块数: {response_chunks}] [耗时: {duration:.2f}s]")
             else:
                 # 返回完整响应
-                response = self._create_complete_response(total_content, request_id)
+                response = self._create_complete_response(total_content, request_id, model)
                 yield response
                 
                 logger.success(f"✅ 完整响应完成 [ID: {request_id[:8]}] [长度: {len(total_content)}] [耗时: {duration:.2f}s]")
@@ -118,13 +118,13 @@ class ApiService:
             logger.error(f"❌ 聊天请求处理失败 [ID: {request_id[:8]}]: {e}")
             yield self._create_error_response(f"服务器内部错误: {str(e)}", request_id)
     
-    def _create_stream_chunk(self, content: str, request_id: str) -> Dict[str, Any]:
+    def _create_stream_chunk(self, content: str, request_id: str, model: str) -> Dict[str, Any]:
         """创建流式响应块"""
         return {
             "id": f"chatcmpl-{request_id}",
             "object": "chat.completion.chunk",
             "created": int(time.time()),
-            "model": "gemini-2.0-flash",
+            "model": model,
             "choices": [{
                 "index": 0,
                 "delta": {"content": content},
@@ -132,13 +132,13 @@ class ApiService:
             }]
         }
     
-    def _create_stream_end_chunk(self, request_id: str) -> Dict[str, Any]:
+    def _create_stream_end_chunk(self, request_id: str, model: str) -> Dict[str, Any]:
         """创建流式响应结束块"""
         return {
             "id": f"chatcmpl-{request_id}",
             "object": "chat.completion.chunk", 
             "created": int(time.time()),
-            "model": "gemini-2.0-flash",
+            "model": model,
             "choices": [{
                 "index": 0,
                 "delta": {},
@@ -146,13 +146,13 @@ class ApiService:
             }]
         }
     
-    def _create_complete_response(self, content: str, request_id: str) -> Dict[str, Any]:
+    def _create_complete_response(self, content: str, request_id: str, model: str) -> Dict[str, Any]:
         """创建完整响应"""
         return {
             "id": f"chatcmpl-{request_id}",
             "object": "chat.completion",
             "created": int(time.time()),
-            "model": "gemini-2.0-flash",
+            "model": model,
             "choices": [{
                 "index": 0,
                 "message": {