test(model):增加打印信息

config/config.ini

@@ -70,6 +70,7 @@ ENGINE=glm-ocr
 # GLM-OCR 配置
 GLM_OCR_API_URL=http://183.220.37.46:25429/v1/chat/completions
 GLM_OCR_TIMEOUT=600
+GLM_OCR_API_KEY=2026_Unified_Secure_Key
 
 # MinerU 配置  
 MINERU_API_URL=http://183.220.37.46:25428/file_parse
@@ -147,8 +148,8 @@ LQ_QWEN3_8B_LQ_LORA_API_KEY=dummy
 MYSQL_HOST=192.168.92.61
 MYSQL_PORT=13306
 MYSQL_USER=root
-MYSQL_PASSWORD=lq@123
-MYSQL_DB=lq_db
+MYSQL_PASSWORD=Lq123456!
+MYSQL_DB=lq_db_dev
 MYSQL_MIN_SIZE=1
 MYSQL_MAX_SIZE=5
 MYSQL_AUTO_COMMIT=True

foundation/ai/agent/generate/model_generate.py

@@ -34,7 +34,7 @@ class GenerateModelClient:
         # 保存model_handler引用,用于动态获取模型
         self.model_handler = model_handler
 
-    async def _retry_with_backoff(self, func: Callable, *args, timeout: Optional[int] = None, **kwargs):
+    async def _retry_with_backoff(self, func: Callable, *args, timeout: Optional[int] = None, trace_id: Optional[str] = None, model_name: Optional[str] = None, **kwargs):
         """
         带指数退避的重试机制，每次重试都有独立的超时控制
 
@@ -42,6 +42,7 @@ class GenerateModelClient:
         避免在服务端过载时继续加重负载。
         """
         current_timeout = timeout or self.default_timeout
+        model_info = model_name or "default"
 
         def _is_server_unavailable_error(error: Exception) -> bool:
             """判断是否为服务端不可用错误（应立即失败）"""
@@ -57,28 +58,28 @@ class GenerateModelClient:
                     func(*args, **kwargs),
                     timeout=current_timeout
                 )
-            except asyncio.TimeoutError:
+            except asyncio.TimeoutError as e:
                 if attempt == self.max_retries:
-                    logger.error(f"[模型调用] 达到最大重试次数 {self.max_retries}，最终超时")
+                    logger.error(f"[模型调用] 达到最大重试次数 {self.max_retries}，最终超时 | trace_id: {trace_id}, model: {model_info}, timeout: {current_timeout}s, error_type: {type(e).__name__}, error_msg: {str(e)}")
                     raise TimeoutError(f"模型调用在 {self.max_retries} 次重试后均超时")
 
                 wait_time = self.backoff_factor * (2 ** attempt)
-                logger.warning(f"[模型调用] 第 {attempt + 1} 次超时, {wait_time}秒后重试...")
+                logger.warning(f"[模型调用] 第 {attempt + 1} 次超时, {wait_time}秒后重试... | trace_id: {trace_id}, model: {model_info}, timeout: {current_timeout}s, error_type: {type(e).__name__}, error_msg: {str(e)}")
                 await asyncio.sleep(wait_time)
             except Exception as e:
                 error_str = str(e)
 
                 # 服务端不可用错误（502/503/504）立即失败，不重试
                 if _is_server_unavailable_error(e):
-                    logger.error(f"[模型调用] 服务端不可用，立即失败: {error_str}")
+                    logger.error(f"[模型调用] 服务端不可用，立即失败: {error_str} | trace_id: {trace_id}, model: {model_info}")
                     raise
 
                 if attempt == self.max_retries:
-                    logger.error(f"[模型调用] 达到最大重试次数 {self.max_retries}，最终失败: {error_str}")
+                    logger.error(f"[模型调用] 达到最大重试次数 {self.max_retries}，最终失败: {error_str} | trace_id: {trace_id}, model: {model_info}")
                     raise
 
                 wait_time = self.backoff_factor * (2 ** attempt)
-                logger.warning(f"[模型调用] 第 {attempt + 1} 次尝试失败: {error_str}, {wait_time}秒后重试...")
+                logger.warning(f"[模型调用] 第 {attempt + 1} 次尝试失败: {error_str}, {wait_time}秒后重试... | trace_id: {trace_id}, model: {model_info}")
                 await asyncio.sleep(wait_time)
 
     async def get_model_generate_invoke(
@@ -159,7 +160,7 @@ class GenerateModelClient:
                 return await llm_to_use.ainvoke(final_messages)
 
             # 调用带重试机制
-            response = await self._retry_with_backoff(_invoke, timeout=current_timeout)
+            response = await self._retry_with_backoff(_invoke, timeout=current_timeout, trace_id=trace_id, model_name=model_name or "default")
 
             elapsed_time = time.time() - start_time
             logger.info(f"[模型调用] 成功 trace_id: {trace_id}, 耗时: {elapsed_time:.2f}s")