refactor: 重构Gemini和OpenAI聊天服务以支持工具和安全设置

- 将 `_build_payload`、`_build_tools`、`_get_safety_settings` 和 `_has_image_parts` 函数从 `OpenAIChatService` 和 `GeminiChatService` 类中提取为独立的函数。
- 将 `_handle_stream_response` 和 `_handle_normal_response` 函数从 `GeminiResponseHandler` 和 `OpenAIResponseHandler` 类中提取为独立的函数。
- 将 `_extract_text` 函数从 `OpenAIResponseHandler` 类中提取为独立的函数, 并在 `GeminiResponseHandler` 中复用。
- 将 `_convert_image` 函数从 `OpenAIMessageConverter` 类中提取为独立的函数。
- 优化 `OpenAIChatService` 和 `GeminiChatService` 中的代码结构, 使其更清晰。
- 优化 `app/api/openai_routes.py` 和 `app/api/gemini_routes.py` 中的路由函数, 移除不必要的参数。

app/api/gemini_routes.py

@@ -1,5 +1,4 @@
-from http.client import HTTPException
-from fastapi import APIRouter, Depends
+from fastapi import APIRouter, Depends, HTTPException
 from fastapi.responses import StreamingResponse
 
 from app.core.config import settings
@@ -10,6 +9,7 @@ from app.services.gemini_chat_service import GeminiChatService
 from app.services.key_manager import KeyManager
 from app.services.model_service import ModelService
 from app.services.chat.retry_handler import RetryHandler
+
 router = APIRouter(prefix="/gemini/v1beta")
 router_v1beta = APIRouter(prefix="/v1beta")
 logger = get_gemini_logger()
@@ -22,26 +22,29 @@ model_service = ModelService(settings.MODEL_SEARCH)
 
 @router.get("/models")
 @router_v1beta.get("/models")
-async def list_models(
-        key: str = None,
-        token: str = Depends(security_service.verify_key),
-):
+async def list_models(_=Depends(security_service.verify_key)):
     """获取可用的Gemini模型列表"""
     logger.info("-" * 50 + "list_gemini_models" + "-" * 50)
     logger.info("Handling Gemini models list request")
     api_key = await key_manager.get_next_working_key()
     logger.info(f"Using API key: {api_key}")
     models_json = model_service.get_gemini_models(api_key)
-    models_json["models"].append({"name": "models/gemini-2.0-flash-exp-search", "version": "2.0", "displayName": "Gemini 2.0 Flash Search Experimental", "description": "Gemini 2.0 Flash Search Experimental", "inputTokenLimit": 32767, "outputTokenLimit": 8192, "supportedGenerationMethods": ["generateContent", "countTokens"], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2})
+    models_json["models"].append({"name": "models/gemini-2.0-flash-exp-search", "version": "2.0",
+                                  "displayName": "Gemini 2.0 Flash Search Experimental",
+                                  "description": "Gemini 2.0 Flash Search Experimental", "inputTokenLimit": 32767,
+                                  "outputTokenLimit": 8192,
+                                  "supportedGenerationMethods": ["generateContent", "countTokens"], "temperature": 1,
+                                  "topP": 0.95, "topK": 64, "maxTemperature": 2})
     return models_json
 
+
 @router.post("/models/{model_name}:generateContent")
 @router_v1beta.post("/models/{model_name}:generateContent")
 @RetryHandler(max_retries=3, key_manager=key_manager, key_arg="api_key")
 async def generate_content(
         model_name: str,
         request: GeminiRequest,
-        x_goog_api_key: str = Depends(security_service.verify_goog_api_key),
+        _=Depends(security_service.verify_goog_api_key),
         api_key: str = Depends(key_manager.get_next_working_key),
 ):
     chat_service = GeminiChatService(settings.BASE_URL, key_manager)
@@ -70,7 +73,7 @@ async def generate_content(
 async def stream_generate_content(
         model_name: str,
         request: GeminiRequest,
-        x_goog_api_key: str = Depends(security_service.verify_goog_api_key),
+        _=Depends(security_service.verify_goog_api_key),
         api_key: str = Depends(key_manager.get_next_working_key),
 ):
     chat_service = GeminiChatService(settings.BASE_URL, key_manager)
@@ -81,7 +84,7 @@ async def stream_generate_content(
     logger.info(f"Using API key: {api_key}")
 
     try:
-        response_stream =chat_service.stream_generate_content(
+        response_stream = chat_service.stream_generate_content(
             model=model_name,
             request=request,
             api_key=api_key

app/api/openai_routes.py

@@ -1,16 +1,15 @@
-from http.client import HTTPException
-from fastapi import APIRouter, Depends, Header
+from fastapi import HTTPException, APIRouter, Depends
 from fastapi.responses import StreamingResponse
 
+from app.core.config import settings
+from app.core.logger import get_openai_logger
 from app.core.security import SecurityService
+from app.schemas.openai_models import ChatRequest, EmbeddingRequest
 from app.services.chat.retry_handler import RetryHandler
+from app.services.embedding_service import EmbeddingService
 from app.services.key_manager import KeyManager
 from app.services.model_service import ModelService
 from app.services.openai_chat_service import OpenAIChatService
-from app.services.embedding_service import EmbeddingService
-from app.schemas.openai_models import ChatRequest, EmbeddingRequest
-from app.core.config import settings
-from app.core.logger import get_openai_logger
 
 router = APIRouter()
 logger = get_openai_logger()
@@ -24,10 +23,7 @@ embedding_service = EmbeddingService(settings.BASE_URL)
 
 @router.get("/v1/models")
 @router.get("/hf/v1/models")
-async def list_models(
-    authorization: str = Header(None),
-    token: str = Depends(security_service.verify_authorization),
-):
+async def list_models(_=Depends(security_service.verify_authorization)):
     logger.info("-" * 50 + "list_models" + "-" * 50)
     logger.info("Handling models list request")
     api_key = await key_manager.get_next_working_key()
@@ -43,10 +39,9 @@ async def list_models(
 @router.post("/hf/v1/chat/completions")
 @RetryHandler(max_retries=3, key_manager=key_manager, key_arg="api_key")
 async def chat_completion(
-    request: ChatRequest,
-    authorization: str = Header(None),
-    token: str = Depends(security_service.verify_authorization),
-    api_key: str = Depends(key_manager.get_next_working_key),
+        request: ChatRequest,
+        _=Depends(security_service.verify_authorization),
+        api_key: str = Depends(key_manager.get_next_working_key),
 ):
     chat_service = OpenAIChatService(settings.BASE_URL, key_manager)
     logger.info("-" * 50 + "chat_completion" + "-" * 50)
@@ -67,15 +62,13 @@ async def chat_completion(
     except Exception as e:
         logger.error(f"Chat completion failed after retries: {str(e)}")
         raise HTTPException(status_code=500, detail="Chat completion failed") from e
-        
 
 
 @router.post("/v1/embeddings")
 @router.post("/hf/v1/embeddings")
 async def embedding(
-    request: EmbeddingRequest,
-    authorization: str = Header(None),
-    token: str = Depends(security_service.verify_authorization),
+        request: EmbeddingRequest,
+        _=Depends(security_service.verify_authorization),
 ):
     logger.info("-" * 50 + "embedding" + "-" * 50)
     logger.info(f"Handling embedding request for model: {request.model}")
@@ -95,8 +88,7 @@ async def embedding(
 @router.get("/v1/keys/list")
 @router.get("/hf/v1/keys/list")
 async def get_keys_list(
-    authorization: str = Header(None),
-    token: str = Depends(security_service.verify_auth_token),
+        _=Depends(security_service.verify_auth_token),
 ):
     """获取有效和无效的API key列表"""
     logger.info("-" * 50 + "get_keys_list" + "-" * 50)