refactor(retry): 统一管理 API 最大重试次数配置

将 API 调用的最大重试次数 (`MAX_RETRIES`) 的配置移至 `app.config.config.settings`。

- 修改 `RetryHandler` 以直接从全局设置读取 `MAX_RETRIES`。
- 更新使用 `RetryHandler` 的路由装饰器，移除冗余的 `max_retries` 参数传递。

这使得重试次数的配置更加集中和易于管理。

app/handler/retry_handler.py

@@ -2,7 +2,7 @@
 from functools import wraps
 from typing import Callable, TypeVar
 
-from app.core.constants import MAX_RETRIES
+from app.config.config import settings
 from app.log.logger import get_retry_logger
 
 T = TypeVar("T")
@@ -12,8 +12,7 @@ logger = get_retry_logger()
 class RetryHandler:
     """重试处理装饰器"""
 
-    def __init__(self, max_retries: int = MAX_RETRIES, key_arg: str = "api_key"):
-        self.max_retries = max_retries
+    def __init__(self, key_arg: str = "api_key"):
         self.key_arg = key_arg
 
     def __call__(self, func: Callable[..., T]) -> Callable[..., T]:
@@ -21,14 +20,14 @@ class RetryHandler:
         async def wrapper(*args, **kwargs) -> T:
             last_exception = None
 
-            for attempt in range(self.max_retries):
+            for attempt in range(settings.MAX_RETRIES):
                 retries = attempt + 1
                 try:
                     return await func(*args, **kwargs)
                 except Exception as e:
                     last_exception = e
                     logger.warning(
-                        f"API call failed with error: {str(e)}. Attempt {retries} of {self.max_retries}"
+                        f"API call failed with error: {str(e)}. Attempt {retries} of {settings.MAX_RETRIES}"
                     )
 
                     # 从函数参数中获取 key_manager

app/router/gemini_routes.py

@@ -99,7 +99,7 @@ async def list_models(
 
 @router.post("/models/{model_name}:generateContent")
 @router_v1beta.post("/models/{model_name}:generateContent")
-@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
+@RetryHandler(key_arg="api_key")
 async def generate_content(
     model_name: str,
     request: GeminiRequest,
@@ -128,7 +128,7 @@ async def generate_content(
 
 @router.post("/models/{model_name}:streamGenerateContent")
 @router_v1beta.post("/models/{model_name}:streamGenerateContent")
-@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
+@RetryHandler(key_arg="api_key")
 async def stream_generate_content(
     model_name: str,
     request: GeminiRequest,
@@ -156,6 +156,7 @@ async def stream_generate_content(
         # 注意：流本身的错误需要在服务层或流迭代中处理，这里只返回流响应
         return StreamingResponse(response_stream, media_type="text/event-stream")
 
+
 @router.post("/reset-all-fail-counts")
 async def reset_all_key_fail_counts(key_type: str = None, key_manager: KeyManager = Depends(get_key_manager)):
     """批量重置Gemini API密钥的失败计数，可选择性地仅重置有效或无效密钥"""
@@ -250,7 +251,6 @@ async def reset_selected_key_fail_counts(
         return JSONResponse({"success": False, "message": f"批量重置处理失败: {str(e)}"}, status_code=500)
 
 
-
 @router.post("/reset-fail-count/{api_key}")
 async def reset_key_fail_count(api_key: str, key_manager: KeyManager = Depends(get_key_manager)):
     """重置指定Gemini API密钥的失败计数"""
@@ -266,6 +266,7 @@ async def reset_key_fail_count(api_key: str, key_manager: KeyManager = Depends(g
         logger.error(f"Failed to reset key failure count: {str(e)}")
         return JSONResponse({"success": False, "message": f"重置失败: {str(e)}"}, status_code=500)
 
+
 @router.post("/verify-key/{api_key}")
 async def verify_key(api_key: str, chat_service: GeminiChatService = Depends(get_chat_service), key_manager: KeyManager = Depends(get_key_manager)):
     """验证Gemini API密钥的有效性"""

app/router/openai_compatiable_routes.py

@@ -52,7 +52,7 @@ async def list_models(
 
 
 @router.post("/openai/v1/chat/completions")
-@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
+@RetryHandler(key_arg="api_key")
 async def chat_completion(
     request: ChatRequest,
     _=Depends(security_service.verify_authorization),

app/router/openai_routes.py

@@ -59,7 +59,7 @@ async def list_models(
 
 @router.post("/v1/chat/completions")
 @router.post("/hf/v1/chat/completions")
-@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
+@RetryHandler(key_arg="api_key")
 async def chat_completion(
     request: ChatRequest,
     _=Depends(security_service.verify_authorization),