fix:尝试修复炸飞问题

src/plugins/models/utils_model.py

@@ -198,6 +198,7 @@ class LLM_request:
                     headers["Accept"] = "text/event-stream"
 
                 async with aiohttp.ClientSession() as session:
+                    try:
                         async with session.post(api_url, headers=headers, json=payload) as response:
                             # 处理需要重试的状态码
                             if response.status in policy["retry_codes"]:
@@ -320,11 +321,36 @@ class LLM_request:
                                             except Exception as e:
                                                 logger.exception(f"解析流式输出错误: {str(e)}")
                                     except GeneratorExit:
-                                    logger.warning("流式输出被中断")
+                                        logger.warning("流式输出被中断，正在清理资源...")
-                                    break
+                                        # 确保资源被正确清理
+                                        await response.release()
+                                        # 返回已经累积的内容
+                                        result = {
+                                            "choices": [{"message": {"content": accumulated_content, "reasoning_content": reasoning_content}}],
+                                            "usage": usage,
+                                        }
+                                        return (
+                                            response_handler(result)
+                                            if response_handler
+                                            else self._default_response_handler(result, user_id, request_type, endpoint)
+                                        )
                                     except Exception as e:
                                         logger.error(f"处理流式输出时发生错误: {str(e)}")
-                                    break
+                                        # 确保在发生错误时也能正确清理资源
+                                        try:
+                                            await response.release()
+                                        except Exception as cleanup_error:
+                                            logger.error(f"清理资源时发生错误: {cleanup_error}")
+                                        # 返回已经累积的内容
+                                        result = {
+                                            "choices": [{"message": {"content": accumulated_content, "reasoning_content": reasoning_content}}],
+                                            "usage": usage,
+                                        }
+                                        return (
+                                            response_handler(result)
+                                            if response_handler
+                                            else self._default_response_handler(result, user_id, request_type, endpoint)
+                                        )
                                 content = accumulated_content
                                 think_match = re.search(r"<think>(.*?)</think>", content, re.DOTALL)
                                 if think_match:
@@ -349,6 +375,19 @@ class LLM_request:
                                     else self._default_response_handler(result, user_id, request_type, endpoint)
                                 )
 
+                    except (aiohttp.ClientError, asyncio.TimeoutError) as e:
+                        if retry < policy["max_retries"] - 1:
+                            wait_time = policy["base_wait"] * (2**retry)
+                            logger.error(f"网络错误，等待{wait_time}秒后重试... 错误: {str(e)}")
+                            await asyncio.sleep(wait_time)
+                            continue
+                        else:
+                            logger.critical(f"网络错误达到最大重试次数: {str(e)}")
+                            raise RuntimeError(f"网络请求失败: {str(e)}") from e
+                    except Exception as e:
+                        logger.critical(f"未预期的错误: {str(e)}")
+                        raise RuntimeError(f"请求过程中发生错误: {str(e)}") from e
+
             except aiohttp.ClientResponseError as e:
                 # 处理aiohttp抛出的响应错误
                 if retry < policy["max_retries"] - 1: