feat: Dockerfile 中添加 VERSION 文件复制

将 VERSION 文件复制到 Docker 镜像中，以便在运行时可以访问版本信息。

.env.example

@@ -8,6 +8,8 @@ API_KEYS=["AIzaSyxxxxxxxxxxxxxxxxxxx","AIzaSyxxxxxxxxxxxxxxxxxxx"]
 ALLOWED_TOKENS=["sk-123456"]
 # AUTH_TOKEN=sk-123456
 TEST_MODEL=gemini-1.5-flash
+THINKING_MODELS=["gemini-2.5-flash-preview-04-17"]
+THINKING_BUDGET_MAP={"gemini-2.5-flash-preview-04-17": 4000}
 IMAGE_MODELS=["gemini-2.0-flash-exp"]
 SEARCH_MODELS=["gemini-2.0-flash-exp","gemini-2.0-pro-exp"]
 FILTERED_MODELS=["gemini-1.0-pro-vision-latest", "gemini-pro-vision", "chat-bison-001", "text-bison-001", "embedding-gecko-001"]

Dockerfile

@@ -4,6 +4,7 @@ WORKDIR /app
 
 # 复制所需文件到容器中
 COPY ./requirements.txt /app
+COPY ./VERSION /app
 
 RUN pip install --no-cache-dir -r requirements.txt
 COPY ./app /app/app

README.md

@@ -156,6 +156,8 @@ app/
 | `TOOLS_CODE_EXECUTION_ENABLED` | 可选，是否启用代码执行工具                                     | `false`                                               |
 | `SHOW_SEARCH_LINK`           | 可选，是否在响应中显示搜索结果链接                             | `true`                                                |
 | `SHOW_THINKING_PROCESS`      | 可选，是否显示模型思考过程                                     | `true`                                                |
+| `THINKING_MODELS`            | 可选，支持思考功能的模型列表                                   | `[]`                                                  |
+| `THINKING_BUDGET_MAP`        | 可选，思考功能预算映射 (模型名:预算值)                         | `{}`                                                  |
 | `BASE_URL`                   | 可选，Gemini API 基础 URL，默认无需修改                        | `https://generativelanguage.googleapis.com/v1beta`    |
 | `MAX_FAILURES`               | 可选，允许单个key失败的次数                                    | `3`                                                   |
 | `MAX_RETRIES`                | 可选，API 请求失败时的最大重试次数                             | `3`                                                   |

VERSION

@@ -0,0 +1 @@
+2.0.9

app/config/config.py

@@ -21,7 +21,6 @@ from app.log.logger import Logger
 
 
 class Settings(BaseSettings):
-    """应用程序配置"""
     # 数据库配置
     MYSQL_HOST: str
     MYSQL_PORT: int
@@ -46,6 +45,8 @@ class Settings(BaseSettings):
     TOOLS_CODE_EXECUTION_ENABLED: bool = False
     SHOW_SEARCH_LINK: bool = True
     SHOW_THINKING_PROCESS: bool = True
+    THINKING_MODELS: List[str] = [] # 新增：用于思考过程的模型列表
+    THINKING_BUDGET_MAP: Dict[str, float] = {} # 新增：模型对应的预算映射
     
     # 图像生成相关配置
     PAID_KEY: str = ""
@@ -67,6 +68,10 @@ class Settings(BaseSettings):
     # 调度器配置
     CHECK_INTERVAL_HOURS: int = 1 # 默认检查间隔为1小时
     TIMEZONE: str = "Asia/Shanghai" # 默认时区
+    
+    # github 
+    GITHUB_REPO_OWNER: str = "snailyp"
+    GITHUB_REPO_NAME: str = "gemini-balance"
 
     # 日志配置
     LOG_LEVEL: str = "INFO" # 默认日志级别
@@ -85,25 +90,54 @@ def _parse_db_value(key: str, db_value: str, target_type: Type) -> Any:
     from app.log.logger import get_config_logger # 函数内导入
     logger = get_config_logger() # 函数内初始化
     try:
+        # 处理 List[str]
         if target_type == List[str]:
-            # 尝试解析 JSON 列表，如果失败则按逗号分割
             try:
                 parsed = json.loads(db_value)
                 if isinstance(parsed, list):
                     return [str(item) for item in parsed]
             except json.JSONDecodeError:
-                # 回退到逗号分割，去除空格
                 return [item.strip() for item in db_value.split(',') if item.strip()]
-            # 如果解析后不是列表或解析失败，返回空列表或进行其他处理
             logger.warning(f"Could not parse '{db_value}' as List[str] for key '{key}', falling back to comma split or empty list.")
-            return [item.strip() for item in db_value.split(',') if item.strip()] # Fallback
+            return [item.strip() for item in db_value.split(',') if item.strip()]
+        # 处理 Dict[str, float]
+        elif target_type == Dict[str, float]:
+            parsed_dict = {}
+            try:
+                # First attempt: standard JSON parsing
+                parsed = json.loads(db_value)
+                if isinstance(parsed, dict):
+                    parsed_dict = {str(k): float(v) for k, v in parsed.items()}
+                else:
+                     logger.warning(f"Parsed DB value for key '{key}' is not a dictionary type. Value: {db_value}")
+            except (json.JSONDecodeError, ValueError, TypeError) as e1:
+                # Second attempt: try replacing single quotes if JSONDecodeError occurred
+                if isinstance(e1, json.JSONDecodeError) and "'" in db_value:
+                    logger.warning(f"Failed initial JSON parse for key '{key}'. Attempting to replace single quotes. Error: {e1}")
+                    try:
+                        corrected_db_value = db_value.replace("'", '"')
+                        parsed = json.loads(corrected_db_value)
+                        if isinstance(parsed, dict):
+                             parsed_dict = {str(k): float(v) for k, v in parsed.items()}
+                        else:
+                            logger.warning(f"Parsed DB value (after quote replacement) for key '{key}' is not a dictionary type. Value: {corrected_db_value}")
+                    except (json.JSONDecodeError, ValueError, TypeError) as e2:
+                         logger.error(f"Could not parse '{db_value}' as Dict[str, float] for key '{key}' even after replacing quotes: {e2}. Returning empty dict.")
+                else:
+                    # Log other errors (ValueError, TypeError) or JSON errors without single quotes
+                    logger.error(f"Could not parse '{db_value}' as Dict[str, float] for key '{key}': {e1}. Returning empty dict.")
+            return parsed_dict # Return the parsed dict or an empty one if all attempts fail
+        # 处理 bool
         elif target_type == bool:
             return db_value.lower() in ('true', '1', 'yes', 'on')
+        # 处理 int
         elif target_type == int:
             return int(db_value)
+        # 处理 float
         elif target_type == float:
             return float(db_value)
-        else: # 默认为 str 或其他 pydantic 能处理的类型
+        # 默认为 str 或其他 pydantic 能直接处理的类型
+        else:
             return db_value
     except (ValueError, TypeError, json.JSONDecodeError) as e:
         logger.warning(f"Failed to parse db_value '{db_value}' for key '{key}' as type {target_type}: {e}. Using original string value.")
@@ -161,20 +195,18 @@ async def sync_initial_settings():
                         # 比较解析后的值和内存中的值
                         # 注意：对于列表等复杂类型，直接比较可能不够健壮，但这里简化处理
                         if parsed_db_value != memory_value:
-                             # 检查类型是否匹配，以防解析函数返回了不兼容的类型
-                            # 优先处理 List[str] 类型，避免直接对泛型使用 isinstance
-                            if target_type == List[str]:
-                                if isinstance(parsed_db_value, list):
-                                    # 可以选择性地添加对列表元素的检查，但这里保持简化
-                                    setattr(settings, key, parsed_db_value)
-                                    logger.info(f"Updated setting '{key}' in memory from database value (List[str]).")
-                                    updated_in_memory = True
-                                else:
-                                     logger.warning(f"Parsed DB value type mismatch for key '{key}'. Expected List[str], got {type(parsed_db_value)}. Skipping update.")
-                            # 对于其他非泛型类型，使用常规的 isinstance 检查
-                            elif isinstance(parsed_db_value, target_type):
+                            # 检查类型是否匹配，以防解析函数返回了不兼容的类型
+                            type_match = False
+                            if target_type == List[str] and isinstance(parsed_db_value, list):
+                                type_match = True
+                            elif target_type == Dict[str, float] and isinstance(parsed_db_value, dict):
+                                type_match = True
+                            elif target_type not in (List[str], Dict[str, float]) and isinstance(parsed_db_value, target_type):
+                                type_match = True
+
+                            if type_match:
                                 setattr(settings, key, parsed_db_value)
-                                logger.info(f"Updated setting '{key}' in memory from database value.")
+                                logger.info(f"Updated setting '{key}' in memory from database value ({target_type}).")
                                 updated_in_memory = True
                             else:
                                 logger.warning(f"Parsed DB value type mismatch for key '{key}'. Expected {target_type}, got {type(parsed_db_value)}. Skipping update.")
@@ -205,10 +237,12 @@ async def sync_initial_settings():
 
         for key, value in final_memory_settings.items():
             # 序列化值为字符串或 JSON 字符串
-            if isinstance(value, list):
-                db_value = json.dumps(value)
+            if isinstance(value, (list, dict)): # 处理列表和字典
+                db_value = json.dumps(value, ensure_ascii=False) # 使用 ensure_ascii=False 以支持非 ASCII 字符
             elif isinstance(value, bool):
                 db_value = str(value).lower()
+            elif value is None: # 处理 None 值
+                db_value = "" # 或者根据需要设为 NULL 或其他标记
             else:
                 db_value = str(value)
 

app/core/application.py

@@ -4,6 +4,7 @@
 from contextlib import asynccontextmanager
 from fastapi import FastAPI
 from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
 
 from app.config.config import settings, sync_initial_settings
 from app.log.logger import get_application_logger
@@ -15,9 +16,41 @@ from app.core.initialization import initialize_app
 from app.database.connection import connect_to_db, disconnect_from_db
 from app.database.initialization import initialize_database
 from app.scheduler.key_checker import start_scheduler, stop_scheduler # 导入调度器函数
+from app.service.update.update_service import check_for_updates # 导入更新检查服务
 
 logger = get_application_logger()
 
+VERSION_FILE_PATH = "VERSION" # Path relative to project root
+
+def _get_current_version(default_version: str = "0.0.0") -> str:
+    """Reads the current version from the VERSION file."""
+    try:
+        # Assuming execution from project root d:/develop/pythonProjects/gemini-balance
+        with open(VERSION_FILE_PATH, 'r', encoding='utf-8') as f:
+            version = f.read().strip()
+        if not version:
+            logger.warning(f"VERSION file ('{VERSION_FILE_PATH}') is empty. Using default version '{default_version}'.")
+            return default_version
+        return version
+    except FileNotFoundError:
+        logger.warning(f"VERSION file not found at '{VERSION_FILE_PATH}'. Using default version '{default_version}'.")
+        return default_version
+    except IOError as e:
+        logger.error(f"Error reading VERSION file ('{VERSION_FILE_PATH}'): {e}. Using default version '{default_version}'.")
+        return default_version
+
+# 初始化模板引擎，并添加全局变量
+templates = Jinja2Templates(directory="app/templates")
+
+# 定义一个函数来更新模板全局变量
+def update_template_globals(app: FastAPI, update_info: dict):
+    # Jinja2Templates 实例没有直接更新全局变量的方法
+    # 我们需要在请求上下文中传递这些变量，或者修改 Jinja 环境
+    # 更简单的方法是将其存储在 app.state 中，并在渲染时传递
+    app.state.update_info = update_info
+    logger.info(f"Update info stored in app.state: {update_info}")
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """
@@ -44,11 +77,29 @@ async def lifespan(app: FastAPI):
         logger.info("KeyManager initialized successfully")
     except Exception as e:
         logger.error(f"Failed to initialize application: {str(e)}")
-        raise
+        # 不重新抛出，允许应用继续运行，但记录错误
+        # raise # 取消注释以在初始化失败时停止应用
+
+    # 检查更新 (在核心初始化之后)
+    update_available, latest_version, error_message = await check_for_updates()
+    update_info = {
+        "update_available": update_available,
+        "latest_version": latest_version,
+        "error_message": error_message,
+        "current_version": _get_current_version() # Read from VERSION file
+    }
+    # 将更新信息存储在 app.state 中
+    app.state.update_info = update_info
+    logger.info(f"Update check completed. Info: {update_info}")
+
+
+    # 启动调度器 (如果初始化成功)
+    try:
+        start_scheduler()
+        logger.info("Scheduler started successfully.")
+    except Exception as e:
+         logger.error(f"Failed to start scheduler: {e}")
 
-    # 启动调度器
-    start_scheduler()
-    logger.info("Scheduler started successfully.")
 
     yield  # 应用程序运行期间
     
@@ -79,7 +130,15 @@ def create_app() -> FastAPI:
         version="1.0.0",
         lifespan=lifespan
     )
-    
+
+    # 初始化 app.state (如果尚未存在)
+    if not hasattr(app, "state"):
+        from starlette.datastructures import State
+        app.state = State()
+    # 确保 update_info 即使在 lifespan 之前访问也不会出错
+    app.state.update_info = {"update_available": False, "latest_version": None, "error_message": "Checking...", "current_version": _get_current_version()} # Read from VERSION file for initial state
+
+
     # 配置静态文件
     app.mount("/static", StaticFiles(directory="app/static"), name="static")
     

app/handler/retry_handler.py

@@ -23,21 +23,26 @@ class RetryHandler:
             last_exception = None
 
             for attempt in range(self.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 {attempt + 1} of {self.max_retries}"
+                        f"API call failed with error: {str(e)}. Attempt {retries} of {self.max_retries}"
                     )
 
                     # 从函数参数中获取 key_manager
                     key_manager = kwargs.get("key_manager")
                     if key_manager:
                         old_key = kwargs.get(self.key_arg)
-                        new_key = await key_manager.handle_api_failure(old_key, attempt)
-                        kwargs[self.key_arg] = new_key
-                        logger.info(f"Switched to new API key: {new_key}")
+                        new_key = await key_manager.handle_api_failure(old_key, retries)
+                        if new_key:
+                            kwargs[self.key_arg] = new_key
+                            logger.info(f"Switched to new API key: {new_key}")
+                        else:
+                            logger.error(f"No valid API key available after {retries} retries.")
+                            break
 
             logger.error(
                 f"All retry attempts failed, raising final exception: {str(last_exception)}"

app/log/logger.py

@@ -199,4 +199,12 @@ def get_log_routes_logger():
 
 
 def get_stats_logger():
-    return Logger.setup_logger("stats")
+    return Logger.setup_logger("stats")
+
+
+def get_update_logger():
+    return Logger.setup_logger("update_service")
+
+
+def get_scheduler_routes():
+    return Logger.setup_logger("scheduler_routes")

app/middleware/request_logging_middleware.py

@@ -26,7 +26,7 @@ class RequestLoggingMiddleware(BaseHTTPMiddleware):
                         f"Formatted request body:\n{json.dumps(formatted_body, indent=2, ensure_ascii=False)}"
                     )
                 except json.JSONDecodeError:
-                    logger.info("Request body is not valid JSON.")
+                    logger.error("Request body is not valid JSON.")
         except Exception as e:
             logger.error(f"Error reading request body: {str(e)}")
 

app/router/gemini_routes.py

@@ -83,6 +83,21 @@ async def list_models(
             
             models_json["models"].append(item)
             
+    # 添加思考模型的非思考版本
+    if settings.THINKING_MODELS:
+        for name in settings.THINKING_MODELS:
+            model = model_mapping.get(name)
+            if not model:
+                continue
+                
+            item = deepcopy(model)
+            item["name"] = f"models/{name}-non-thinking"
+            display_name = f'{item.get("displayName")} Non Thinking'
+            item["displayName"] = display_name
+            item["description"] = display_name
+            
+            models_json["models"].append(item)
+            
     return models_json
 
 
@@ -94,6 +109,7 @@ async def generate_content(
     request: GeminiRequest,
     _=Depends(security_service.verify_key_or_goog_api_key),
     api_key: str = Depends(get_next_working_key),
+    key_manager: KeyManager = Depends(get_key_manager),
     chat_service: GeminiChatService = Depends(get_chat_service)
 ):
     """非流式生成内容"""
@@ -125,6 +141,7 @@ async def stream_generate_content(
     request: GeminiRequest,
     _=Depends(security_service.verify_key_or_goog_api_key),
     api_key: str = Depends(get_next_working_key),
+    key_manager: KeyManager = Depends(get_key_manager),
     chat_service: GeminiChatService = Depends(get_chat_service)
 ):
     """流式生成内容"""

app/router/openai_routes.py

@@ -86,7 +86,7 @@ async def chat_completion(
     try:
         # 如果model是imagen3,使用paid_key
         if request.model == f"{settings.CREATE_IMAGE_MODEL}-chat":
-            response = await chat_service.create_image_chat_completion(request=request)
+            response = await chat_service.create_image_chat_completion(request, api_key)
         else:
             response = await chat_service.create_chat_completion(request, api_key)
         # 处理流式响应

app/router/routes.py

@@ -8,9 +8,9 @@ from fastapi.templating import Jinja2Templates
 
 from app.core.security import verify_auth_token
 from app.log.logger import get_routes_logger
-from app.router import gemini_routes, openai_routes, config_routes, log_routes, scheduler_routes # 新增导入
+from app.router import gemini_routes, openai_routes, config_routes, log_routes, scheduler_routes, stats_routes # 新增导入 stats_routes
 from app.service.key.key_manager import get_key_manager_instance
-from app.service.stats_service import get_api_usage_stats, get_api_call_details # <-- Import stats service and details function
+from app.service.stats_service import StatsService
 
 logger = get_routes_logger()
 
@@ -32,6 +32,7 @@ def setup_routers(app: FastAPI) -> None:
     app.include_router(config_routes.router)
     app.include_router(log_routes.router)
     app.include_router(scheduler_routes.router) # 新增包含 scheduler 路由
+    app.include_router(stats_routes.router) # 包含 stats API 路由
 
     # 添加页面路由
     setup_page_routes(app)
@@ -92,8 +93,8 @@ def setup_page_routes(app: FastAPI) -> None:
             valid_key_count = len(keys_status["valid_keys"])
             invalid_key_count = len(keys_status["invalid_keys"])
 
-            # Get API usage stats
-            api_stats = await get_api_usage_stats()
+            stats_service = StatsService()
+            api_stats = await stats_service.get_api_usage_stats()
             logger.info(f"API stats retrieved: {api_stats}")
 
             logger.info(f"Keys status retrieved successfully. Total keys: {total_keys}")
@@ -180,7 +181,9 @@ def setup_api_stats_routes(app: FastAPI) -> None:
                 return {"error": "Unauthorized"}, 401
 
             logger.info(f"Fetching API call details for period: {period}")
-            details = await get_api_call_details(period)
+            # Use the service instance here as well
+            stats_service = StatsService() # Create an instance
+            details = await stats_service.get_api_call_details(period)
             return details
         except ValueError as e:
             logger.warning(f"Invalid period requested for API stats details: {period} - {str(e)}")

app/router/scheduler_routes.py

@@ -7,9 +7,9 @@ from fastapi.responses import JSONResponse
 
 from app.core.security import verify_auth_token # 导入 verify_auth_token
 from app.scheduler.key_checker import start_scheduler, stop_scheduler
-from app.log.logger import get_routes_logger # 使用路由日志记录器
+from app.log.logger import get_scheduler_routes # 使用路由日志记录器
 
-logger = get_routes_logger()
+logger = get_scheduler_routes()
 
 router = APIRouter(
     prefix="/api/scheduler",

app/router/stats_routes.py

@@ -0,0 +1,60 @@
+from fastapi import APIRouter, Depends, HTTPException, Request
+from starlette import status
+from app.core.security import verify_auth_token
+from app.service.stats_service import StatsService
+from app.log.logger import get_stats_logger # 使用路由日志记录器
+
+logger = get_stats_logger()
+
+
+# 认证检查的辅助函数
+async def verify_token(request: Request):
+    auth_token = request.cookies.get("auth_token")
+    if not auth_token or not verify_auth_token(auth_token):
+        logger.warning("Unauthorized access attempt to scheduler API")
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail="Not authenticated",
+            headers={"WWW-Authenticate": "Bearer"},
+        )
+
+router = APIRouter(
+    prefix="/api",
+    tags=["stats"],
+    dependencies=[Depends(verify_token)] # Assuming API routes need authentication
+)
+
+stats_service = StatsService()
+
+@router.get("/key-usage-details/{key}",
+            summary="获取指定密钥最近24小时的模型调用次数",
+            description="根据提供的 API 密钥，返回过去24小时内每个模型被调用的次数统计。")
+async def get_key_usage_details(key: str):
+    """
+    Retrieves the model usage count for a specific API key within the last 24 hours.
+
+    Args:
+        key: The API key to get usage details for.
+
+    Returns:
+        A dictionary with model names as keys and their call counts as values.
+        Example: {"gemini-pro": 10, "gemini-1.5-pro-latest": 5}
+
+    Raises:
+        HTTPException: If an error occurs during data retrieval.
+    """
+    try:
+        usage_details = await stats_service.get_key_usage_details_last_24h(key)
+        if usage_details is None:
+            # Handle case where key might be valid but has no recent usage,
+            # or if the service layer explicitly returns None for other reasons.
+            # Returning an empty dict is usually fine for the frontend.
+            return {}
+        return usage_details
+    except Exception as e:
+        # Log the exception details here if needed
+        print(f"Error fetching key usage details for key {key[:4]}...: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"获取密钥使用详情时出错: {e}"
+        )

app/service/chat/gemini_chat_service.py

@@ -108,6 +108,12 @@ def _build_payload(model: str, request: GeminiRequest) -> Dict[str, Any]:
     if model.endswith("-image") or model.endswith("-image-generation"):
         payload.pop("systemInstruction")
         payload["generationConfig"]["responseModalities"] = ["Text", "Image"]
+        
+    if model.endswith("-non-thinking"):
+        payload["generationConfig"]["thinkingConfig"] = {"thinkingBudget": 0} 
+    if model in settings.THINKING_BUDGET_MAP:
+        payload["generationConfig"]["thinkingConfig"] = {"thinkingBudget": settings.THINKING_BUDGET_MAP.get(model,1000)}
+
     return payload
 
 
@@ -156,10 +162,6 @@ class GeminiChatService:
 
         try:
             response = await self.api_client.generate_content(payload, model, api_key)
-            # Assuming success if no exception is raised and response is received
-            # The actual status code might be within the response structure or headers,
-            # but api_client doesn't seem to expose it directly here.
-            # We'll assume 200 for success if no exception.
             is_success = True
             status_code = 200 # Assume 200 on success
             return self.response_handler.handle_response(response, model, stream=False)
@@ -178,7 +180,7 @@ class GeminiChatService:
             await add_error_log(
                 gemini_key=api_key,
                 model_name=model,
-                error_type="gemini_chat_service",
+                error_type="gemini-chat-non-stream",
                 error_log=error_log_msg,
                 error_code=status_code,
                 request_msg=payload
@@ -204,96 +206,90 @@ class GeminiChatService:
         retries = 0
         max_retries = settings.MAX_RETRIES
         payload = _build_payload(model, request)
-        start_time = time.perf_counter() # Record start time before loop
-        request_datetime = datetime.datetime.now()
         is_success = False
         status_code = None
-        final_api_key = api_key # Store the initial key
+        final_api_key = api_key
 
-        try:
-            while retries < max_retries:
-                current_attempt_key = api_key # Key used for this attempt
-                final_api_key = current_attempt_key # Update final key used
-                try:
-                    async for line in self.api_client.stream_generate_content(
-                        payload, model, current_attempt_key
-                    ):
-                        # print(line)
-                        if line.startswith("data:"):
-                            line = line[6:]
-                            response_data = self.response_handler.handle_response(
-                                json.loads(line), model, stream=True
-                            )
-                            text = self._extract_text_from_response(response_data)
-                            # 如果有文本内容，且开启了流式输出优化器，则使用流式输出优化器处理
-                            if text and settings.STREAM_OPTIMIZER_ENABLED:
-                                # 使用流式输出优化器处理文本输出
-                                async for (
-                                    optimized_chunk
-                                ) in gemini_optimizer.optimize_stream_output(
-                                    text,
-                                    lambda t: self._create_char_response(response_data, t),
-                                    lambda c: "data: " + json.dumps(c) + "\n\n",
-                                ):
-                                    yield optimized_chunk
-                            else:
-                                # 如果没有文本内容（如工具调用等），整块输出
-                                yield "data: " + json.dumps(response_data) + "\n\n"
-                    logger.info("Streaming completed successfully")
-                    is_success = True
-                    status_code = 200 # Assume 200 on success
-                    break # Exit loop on success
-                except Exception as e:
-                    retries += 1
-                    is_success = False # Mark as failed for this attempt
-                    error_log_msg = str(e)
-                    logger.warning(
-                        f"Streaming API call failed with error: {error_log_msg}. Attempt {retries} of {max_retries}"
-                    )
-                    # Parse error code for logging
-                    match = re.search(r"status code (\d+)", error_log_msg)
-                    if match:
-                        status_code = int(match.group(1))
-                    else:
-                        status_code = 500 # Default if parsing fails
-
-                    # Log error to error log table
-                    await add_error_log(
-                        gemini_key=current_attempt_key, # Log key used for this failed attempt
-                        model_name=model,
-                        error_log=error_log_msg,
-                        error_code=status_code,
-                        request_msg=payload
-                    )
-
-                    # Attempt to switch API Key
-                    api_key = await self.key_manager.handle_api_failure(current_attempt_key, retries)
-                    if api_key:
-                        logger.info(f"Switched to new API key: {api_key}")
-                    else: # No more keys or retries exceeded by handle_api_failure logic
-                         logger.error(f"No valid API key available after {retries} retries.")
-                         break # Exit loop if no key available
-
-                    if retries >= max_retries:
-                        logger.error(
-                            f"Max retries ({max_retries}) reached for streaming."
+        while retries < max_retries:
+            request_datetime = datetime.datetime.now()
+            start_time = time.perf_counter()
+            current_attempt_key = api_key
+            final_api_key = current_attempt_key # Update final key used
+            try:
+                async for line in self.api_client.stream_generate_content(
+                    payload, model, current_attempt_key
+                ):
+                    # print(line)
+                    if line.startswith("data:"):
+                        line = line[6:]
+                        response_data = self.response_handler.handle_response(
+                            json.loads(line), model, stream=True
                         )
-                        break # Exit loop after max retries
-        finally:
-            # Log the final outcome of the streaming request
-            end_time = time.perf_counter()
-            latency_ms = int((end_time - start_time) * 1000)
-            await add_request_log(
-                model_name=model,
-                api_key=final_api_key, # Log the last key used
-                is_success=is_success, # Log the final success status
-                status_code=status_code, # Log the last known status code
-                latency_ms=latency_ms, # Log total time including retries
-                request_time=request_datetime
-            )
-            # If the loop finished due to failure, ensure an exception is raised if not already handled
-            if not is_success and retries >= max_retries:
-                 # We need to raise an exception here if the loop exited due to max retries failure
-                 # However, the original code structure doesn't explicitly raise here after the loop.
-                 # For now, we just log. Consider raising HTTPException if needed.
-                 pass
+                        text = self._extract_text_from_response(response_data)
+                        # 如果有文本内容，且开启了流式输出优化器，则使用流式输出优化器处理
+                        if text and settings.STREAM_OPTIMIZER_ENABLED:
+                            # 使用流式输出优化器处理文本输出
+                            async for (
+                                optimized_chunk
+                            ) in gemini_optimizer.optimize_stream_output(
+                                text,
+                                lambda t: self._create_char_response(response_data, t),
+                                lambda c: "data: " + json.dumps(c) + "\n\n",
+                            ):
+                                yield optimized_chunk
+                        else:
+                            # 如果没有文本内容（如工具调用等），整块输出
+                            yield "data: " + json.dumps(response_data) + "\n\n"
+                logger.info("Streaming completed successfully")
+                is_success = True
+                status_code = 200
+                break
+            except Exception as e:
+                retries += 1
+                is_success = False
+                error_log_msg = str(e)
+                logger.warning(
+                    f"Streaming API call failed with error: {error_log_msg}. Attempt {retries} of {max_retries}"
+                )
+                # Parse error code for logging
+                match = re.search(r"status code (\d+)", error_log_msg)
+                if match:
+                    status_code = int(match.group(1))
+                else:
+                    status_code = 500
+
+                # Log error to error log table
+                await add_error_log(
+                    gemini_key=current_attempt_key, # Log key used for this failed attempt
+                    model_name=model,
+                    error_type="gemini-chat-stream",
+                    error_log=error_log_msg,
+                    error_code=status_code,
+                    request_msg=payload
+                )
+
+                # Attempt to switch API Key
+                api_key = await self.key_manager.handle_api_failure(current_attempt_key, retries)
+                if api_key:
+                    logger.info(f"Switched to new API key: {api_key}")
+                else: # No more keys or retries exceeded by handle_api_failure logic
+                        logger.error(f"No valid API key available after {retries} retries.")
+                        break # Exit loop if no key available
+
+                if retries >= max_retries:
+                    logger.error(
+                        f"Max retries ({max_retries}) reached for streaming."
+                    )
+                    break # Exit loop after max retries
+            finally:
+                # Log the final outcome of the streaming request
+                end_time = time.perf_counter()
+                latency_ms = int((end_time - start_time) * 1000)
+                await add_request_log(
+                    model_name=model,
+                    api_key=final_api_key, # Log the last key used
+                    is_success=is_success, # Log the final success status
+                    status_code=status_code, # Log the last known status code
+                    latency_ms=latency_ms, # Log total time including retries
+                    request_time=request_datetime
+                )

app/service/chat/openai_chat_service.py

@@ -130,6 +130,10 @@ def _build_payload(
         payload["generationConfig"]["maxOutputTokens"] = request.max_tokens
     if request.model.endswith("-image") or request.model.endswith("-image-generation"):
         payload["generationConfig"]["responseModalities"] = ["Text", "Image"]
+    if request.model.endswith("-non-thinking"):
+        payload["generationConfig"]["thinkingConfig"] = {"thinkingBudget": 0} 
+    if request.model in settings.THINKING_BUDGET_MAP:
+        payload["generationConfig"]["thinkingConfig"] = {"thinkingBudget": settings.THINKING_BUDGET_MAP.get(request.model,1000)}
 
     if (
         instruction
@@ -219,7 +223,7 @@ class OpenAIChatService:
             await add_error_log(
                 gemini_key=api_key, # Note: Parameter name is gemini_key in add_error_log
                 model_name=model,
-                error_type="openai_chat_service", # Indicate service type
+                error_type="openai-chat-non-stream",
                 error_log=error_log_msg,
                 error_code=status_code,
                 request_msg=payload
@@ -243,118 +247,117 @@ class OpenAIChatService:
         """处理流式聊天完成，添加重试逻辑"""
         retries = 0
         max_retries = settings.MAX_RETRIES
-        start_time = time.perf_counter() # Record start time before loop
-        request_datetime = datetime.datetime.now()
         is_success = False
         status_code = None
-        final_api_key = api_key # Store the initial key
+        final_api_key = api_key
 
-        try:
-            while retries < max_retries:
-                current_attempt_key = api_key # Key used for this attempt
-                final_api_key = current_attempt_key # Update final key used
-                try:
-                    tool_call_flag = False
-                    async for line in self.api_client.stream_generate_content(
-                        payload, model, current_attempt_key
-                    ):
-                        # print(line)
-                        if line.startswith("data:"):
-                            chunk = json.loads(line[6:])
-                            openai_chunk = self.response_handler.handle_response(
-                                chunk, model, stream=True, finish_reason=None
-                            )
-                            if openai_chunk:
-                                # 提取文本内容
-                                text = self._extract_text_from_openai_chunk(openai_chunk)
-                                if text and settings.STREAM_OPTIMIZER_ENABLED:
-                                    # 使用流式输出优化器处理文本输出
-                                    async for (
-                                        optimized_chunk
-                                    ) in openai_optimizer.optimize_stream_output(
-                                        text,
-                                        lambda t: self._create_char_openai_chunk(
-                                            openai_chunk, t
-                                        ),
-                                        lambda c: f"data: {json.dumps(c)}\n\n",
-                                    ):
-                                        yield optimized_chunk
-                                else:
-                                    # 如果没有文本内容（如工具调用等），整块输出
-                                    if "tool_calls" in json.dumps(openai_chunk):
-                                        tool_call_flag = True
-                                    yield f"data: {json.dumps(openai_chunk)}\n\n"
-                    if tool_call_flag:
-                        yield f"data: {json.dumps(self.response_handler.handle_response({}, model, stream=True, finish_reason='tool_calls'))}\n\n"
-                    else:
-                        yield f"data: {json.dumps(self.response_handler.handle_response({}, model, stream=True, finish_reason='stop'))}\n\n"
-                    yield "data: [DONE]\n\n"
-                    logger.info("Streaming completed successfully")
-                    is_success = True
-                    status_code = 200 # Assume 200 on success
-                    break  # 成功后退出循环
-                except Exception as e:
-                    retries += 1
-                    is_success = False # Mark as failed for this attempt
-                    error_log_msg = str(e)
-                    logger.warning(
-                        f"Streaming API call failed with error: {error_log_msg}. Attempt {retries} of {max_retries}"
-                    )
-                    # Parse error code for logging
-                    match = re.search(r"status code (\d+)", error_log_msg)
-                    if match:
-                        status_code = int(match.group(1))
-                    else:
-                        status_code = 500 # Default if parsing fails
-
-                    # Log error to error log table
-                    await add_error_log(
-                        gemini_key=current_attempt_key, # Note: Parameter name is gemini_key
-                        model_name=model,
-                        error_type="openai_chat_service", # Indicate service type
-                        error_log=error_log_msg,
-                        error_code=status_code,
-                        request_msg=payload
-                    )
-
-                    # Attempt to switch API Key
-                    # Ensure key_manager is available (might need adjustment if not always passed)
-                    if self.key_manager:
-                        api_key = await self.key_manager.handle_api_failure(current_attempt_key, retries)
-                        if api_key:
-                            logger.info(f"Switched to new API key: {api_key}")
-                        else:
-                            logger.error(f"No valid API key available after {retries} retries.")
-                            break # Exit loop if no key available
-                    else:
-                         logger.error("KeyManager not available for retry logic.")
-                         break # Exit loop if key manager is missing
-
-                    if retries >= max_retries:
-                        logger.error(
-                            f"Max retries ({max_retries}) reached for streaming."
+        while retries < max_retries:
+            start_time = time.perf_counter()
+            request_datetime = datetime.datetime.now()
+            current_attempt_key = api_key
+            final_api_key = current_attempt_key
+            try:
+                tool_call_flag = False
+                async for line in self.api_client.stream_generate_content(
+                    payload, model, current_attempt_key
+                ):
+                    if line.startswith("data:"):
+                        chunk = json.loads(line[6:])
+                        openai_chunk = self.response_handler.handle_response(
+                            chunk, model, stream=True, finish_reason=None
                         )
-                        break # Exit loop after max retries
-        finally:
-            # Log the final outcome of the streaming request
-            end_time = time.perf_counter()
-            latency_ms = int((end_time - start_time) * 1000)
-            await add_request_log(
-                model_name=model,
-                api_key=final_api_key, # Log the last key used
-                is_success=is_success, # Log the final success status
-                status_code=status_code, # Log the last known status code
-                latency_ms=latency_ms, # Log total time including retries
-                request_time=request_datetime
-            )
-            # If the loop finished due to failure, yield error and DONE
-            if not is_success and retries >= max_retries:
-                 yield f"data: {json.dumps({'error': 'Streaming failed after retries'})}\n\n"
-                 yield "data: [DONE]\n\n"
+                        if openai_chunk:
+                            # 提取文本内容
+                            text = self._extract_text_from_openai_chunk(openai_chunk)
+                            if text and settings.STREAM_OPTIMIZER_ENABLED:
+                                # 使用流式输出优化器处理文本输出
+                                async for (
+                                    optimized_chunk
+                                ) in openai_optimizer.optimize_stream_output(
+                                    text,
+                                    lambda t: self._create_char_openai_chunk(
+                                        openai_chunk, t
+                                    ),
+                                    lambda c: f"data: {json.dumps(c)}\n\n",
+                                ):
+                                    yield optimized_chunk
+                            else:
+                                # 如果没有文本内容（如工具调用等），整块输出
+                                if "tool_calls" in json.dumps(openai_chunk):
+                                    tool_call_flag = True
+                                yield f"data: {json.dumps(openai_chunk)}\n\n"
+                if tool_call_flag:
+                    yield f"data: {json.dumps(self.response_handler.handle_response({}, model, stream=True, finish_reason='tool_calls'))}\n\n"
+                else:
+                    yield f"data: {json.dumps(self.response_handler.handle_response({}, model, stream=True, finish_reason='stop'))}\n\n"
+                yield "data: [DONE]\n\n"
+                logger.info("Streaming completed successfully")
+                is_success = True
+                status_code = 200 # Assume 200 on success
+                break  # 成功后退出循环
+            except Exception as e:
+                retries += 1
+                is_success = False
+                error_log_msg = str(e)
+                logger.warning(
+                    f"Streaming API call failed with error: {error_log_msg}. Attempt {retries} of {max_retries}"
+                )
+                # Parse error code for logging
+                match = re.search(r"status code (\d+)", error_log_msg)
+                if match:
+                    status_code = int(match.group(1))
+                else:
+                    status_code = 500 # Default if parsing fails
+
+                # Log error to error log table
+                await add_error_log(
+                    gemini_key=current_attempt_key,
+                    model_name=model,
+                    error_type="openai-chat-stream",
+                    error_log=error_log_msg,
+                    error_code=status_code,
+                    request_msg=payload
+                )
+
+                # Attempt to switch API Key
+                # Ensure key_manager is available (might need adjustment if not always passed)
+                if self.key_manager:
+                    api_key = await self.key_manager.handle_api_failure(current_attempt_key, retries)
+                    if api_key:
+                        logger.info(f"Switched to new API key: {api_key}")
+                    else:
+                        logger.error(f"No valid API key available after {retries} retries.")
+                        break # Exit loop if no key available
+                else:
+                        logger.error("KeyManager not available for retry logic.")
+                        break # Exit loop if key manager is missing
+
+                if retries >= max_retries:
+                    logger.error(
+                        f"Max retries ({max_retries}) reached for streaming."
+                    )
+                    break # Exit loop after max retries
+            finally:
+                # Log the final outcome of the streaming request
+                end_time = time.perf_counter()
+                latency_ms = int((end_time - start_time) * 1000)
+                await add_request_log(
+                    model_name=model,
+                    api_key=final_api_key, # Log the last key used
+                    is_success=is_success, # Log the final success status
+                    status_code=status_code, # Log the last known status code
+                    latency_ms=latency_ms, # Log total time including retries
+                    request_time=request_datetime
+                )
+                # If the loop finished due to failure, yield error and DONE
+                if not is_success and retries >= max_retries:
+                    yield f"data: {json.dumps({'error': 'Streaming failed after retries'})}\n\n"
+                    yield "data: [DONE]\n\n"
 
     async def create_image_chat_completion(
         self,
         request: ChatRequest,
+        api_key: str
     ) -> Union[Dict[str, Any], AsyncGenerator[str, None]]:
 
         image_generate_request = ImageGenerationRequest()
@@ -364,41 +367,120 @@ class OpenAIChatService:
         )
 
         if request.stream:
-            return self._handle_stream_image_completion(request.model, image_res)
+            return self._handle_stream_image_completion(request.model, image_res, api_key)
         else:
-            return self._handle_normal_image_completion(request.model, image_res)
+            return await self._handle_normal_image_completion(request.model, image_res, api_key)
 
     async def _handle_stream_image_completion(
-        self, model: str, image_data: str
+        self, model: str, image_data: str, api_key:str
     ) -> AsyncGenerator[str, None]:
-        if image_data:
-            openai_chunk = self.response_handler.handle_image_chat_response(
-                image_data, model, stream=True, finish_reason=None
+        logger.info(f"Starting stream image completion for model: {model}")
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now() # Although not used for DB log here
+        is_success = False
+        status_code = None # Although not used for DB log here
+
+        try:
+            if image_data:
+                openai_chunk = self.response_handler.handle_image_chat_response(
+                    image_data, model, stream=True, finish_reason=None
+                )
+                if openai_chunk:
+                    # 提取文本内容
+                    text = self._extract_text_from_openai_chunk(openai_chunk)
+                    if text:
+                        # 使用流式输出优化器处理文本输出
+                        async for (
+                            optimized_chunk
+                        ) in openai_optimizer.optimize_stream_output(
+                            text,
+                            lambda t: self._create_char_openai_chunk(openai_chunk, t),
+                            lambda c: f"data: {json.dumps(c)}\n\n",
+                        ):
+                            yield optimized_chunk
+                    else:
+                        # 如果没有文本内容（如图片URL等），整块输出
+                        yield f"data: {json.dumps(openai_chunk)}\n\n"
+            yield f"data: {json.dumps(self.response_handler.handle_response({}, model, stream=True, finish_reason='stop'))}\n\n"
+            logger.info(f"Stream image completion finished successfully for model: {model}")
+            is_success = True
+            status_code = 200
+            yield "data: [DONE]\n\n"
+        except Exception as e:
+            is_success = False
+            error_log_msg = f"Stream image completion failed for model {model}: {e}"
+            logger.error(error_log_msg)
+            status_code = 500 # Default error code
+            # Call add_error_log using the passed api_key
+            await add_error_log(
+                gemini_key=api_key,
+                model_name=model,
+                error_type="openai-image-stream", # Specific error type
+                error_log=error_log_msg,
+                error_code=status_code,
+                request_msg={"image_data_truncated": image_data[:1000]} # Log truncated data
+            )
+            yield f"data: {json.dumps({'error': error_log_msg})}\n\n" # Send error to client
+            yield "data: [DONE]\n\n" # Still need DONE message
+            # Re-raising might break the stream, decide if needed
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            logger.info(f"Stream image completion for model {model} took {latency_ms} ms. Success: {is_success}")
+            # Call add_request_log using the passed api_key
+            await add_request_log(
+                model_name=model,
+                api_key=api_key,
+                is_success=is_success,
+                status_code=status_code,
+                latency_ms=latency_ms,
+                request_time=request_datetime
             )
-            if openai_chunk:
-                # 提取文本内容
-                text = self._extract_text_from_openai_chunk(openai_chunk)
-                if text:
-                    # 使用流式输出优化器处理文本输出
-                    async for (
-                        optimized_chunk
-                    ) in openai_optimizer.optimize_stream_output(
-                        text,
-                        lambda t: self._create_char_openai_chunk(openai_chunk, t),
-                        lambda c: f"data: {json.dumps(c)}\n\n",
-                    ):
-                        yield optimized_chunk
-                else:
-                    # 如果没有文本内容（如图片URL等），整块输出
-                    yield f"data: {json.dumps(openai_chunk)}\n\n"
-        yield f"data: {json.dumps(self.response_handler.handle_response({}, model, stream=True, finish_reason='stop'))}\n\n"
-        yield "data: [DONE]\n\n"
-        logger.info("Image chat streaming completed successfully")
 
-    def _handle_normal_image_completion(
-        self, model: str, image_data: str
+    async def _handle_normal_image_completion(
+        self, model: str, image_data: str, api_key: str # Add api_key parameter
     ) -> Dict[str, Any]:
+        logger.info(f"Starting normal image completion for model: {model}")
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now() # Although not used for DB log here
+        is_success = False
+        status_code = None # Although not used for DB log here
+        result = None
 
-        return self.response_handler.handle_image_chat_response(
-            image_data, model, stream=False, finish_reason="stop"
-        )
+        try:
+            result = self.response_handler.handle_image_chat_response(
+                image_data, model, stream=False, finish_reason="stop"
+            )
+            logger.info(f"Normal image completion finished successfully for model: {model}")
+            is_success = True
+            status_code = 200
+            return result
+        except Exception as e:
+            is_success = False
+            error_log_msg = f"Normal image completion failed for model {model}: {e}"
+            logger.error(error_log_msg)
+            status_code = 500 # Default error code
+            # Call add_error_log using the passed api_key
+            await add_error_log(
+                gemini_key=api_key,
+                model_name=model,
+                error_type="openai-image-non-stream", # Specific error type
+                error_log=error_log_msg,
+                error_code=status_code,
+                request_msg={"image_data_truncated": image_data[:1000]} # Log truncated data
+            )
+            # Re-raise the exception so the caller knows about the failure
+            raise e
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            logger.info(f"Normal image completion for model {model} took {latency_ms} ms. Success: {is_success}")
+            # Call add_request_log using the passed api_key
+            await add_request_log(
+                model_name=model,
+                api_key=api_key,
+                is_success=is_success,
+                status_code=status_code,
+                latency_ms=latency_ms,
+                request_time=request_datetime
+            )

app/service/client/api_client.py

@@ -31,7 +31,10 @@ class GeminiApiClient(ApiClient):
             model = model[:-7]
         if model.endswith("-image"):
             model = model[:-6]
-
+        if model.endswith("-non-thinking"):
+            model = model[:-13]
+        if "-search" in model and "-non-thinking" in model:
+            model = model[:-20]
         return model
 
     async def generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:

app/service/config/config_service.py

@@ -47,6 +47,8 @@ class ConfigService:
             # 处理不同类型的值
             if isinstance(value, list):
                 db_value = json.dumps(value)
+            elif isinstance(value, dict): # 新增对 dict 类型的处理
+                db_value = json.dumps(value)
             elif isinstance(value, bool):
                 db_value = str(value).lower()
             else:

app/service/embedding/embedding_service.py

@@ -1,9 +1,15 @@
+import datetime
+import time
+import re # For potential status code parsing from generic errors
 from typing import List, Union
 
 import openai
+from openai import APIStatusError # Import specific error type
 from openai.types import CreateEmbeddingResponse
+
 from app.config.config import settings
 from app.log.logger import get_embeddings_logger
+from app.database.services import add_error_log, add_request_log # Import DB logging functions
 
 logger = get_embeddings_logger()
 
@@ -13,11 +19,64 @@ class EmbeddingService:
     async def create_embedding(
         self, input_text: Union[str, List[str]], model: str, api_key: str
     ) -> CreateEmbeddingResponse:
-        """Create embeddings using OpenAI API"""
+        """Create embeddings using OpenAI API with database logging"""
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now()
+        is_success = False
+        status_code = None
+        response = None
+        error_log_msg = ""
+        # Prepare request message for logging (truncate if list or long string)
+        if isinstance(input_text, list):
+            request_msg_log = {"input_truncated": [str(item)[:100] + "..." if len(str(item)) > 100 else str(item) for item in input_text[:5]]}
+            if len(input_text) > 5:
+                 request_msg_log["input_truncated"].append("...")
+        else:
+            request_msg_log = {"input_truncated": input_text[:1000] + "..." if len(input_text) > 1000 else input_text}
+
+
         try:
             client = openai.OpenAI(api_key=api_key, base_url=settings.BASE_URL)
             response = client.embeddings.create(input=input_text, model=model)
+            is_success = True
+            status_code = 200 # Assume 200 OK on success
             return response
+        except APIStatusError as e:
+            is_success = False
+            status_code = e.status_code
+            error_log_msg = f"OpenAI API error: {e}"
+            logger.error(f"Error creating embedding (APIStatusError): {error_log_msg}")
+            raise e # Re-raise the specific error
         except Exception as e:
-            logger.error(f"Error creating embedding: {str(e)}")
-            raise
+            is_success = False
+            error_log_msg = f"Generic error: {e}"
+            logger.error(f"Error creating embedding (Exception): {error_log_msg}")
+            # Try to parse status code from generic error (less reliable)
+            match = re.search(r"status code (\d+)", str(e))
+            if match:
+                status_code = int(match.group(1))
+            else:
+                status_code = 500 # Default if parsing fails
+            raise e # Re-raise the generic error
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            if not is_success:
+                 # Log error to database if it failed
+                 await add_error_log(
+                     gemini_key=api_key, # Using gemini_key parameter name for consistency
+                     model_name=model,
+                     error_type="openai-embedding",
+                     error_log=error_log_msg,
+                     error_code=status_code,
+                     request_msg=request_msg_log
+                 )
+            # Log request outcome to database regardless of success/failure
+            await add_request_log(
+                model_name=model,
+                api_key=api_key,
+                is_success=is_success,
+                status_code=status_code,
+                latency_ms=latency_ms,
+                request_time=request_datetime
+            )

app/service/image/image_create_service.py

@@ -17,7 +17,6 @@ logger = get_image_create_logger()
 class ImageCreateService:
     def __init__(self, aspect_ratio="1:1"):
         self.image_model = settings.CREATE_IMAGE_MODEL
-        self.paid_key = settings.PAID_KEY
         self.aspect_ratio = aspect_ratio
 
     def parse_prompt_parameters(self, prompt: str) -> tuple:
@@ -53,7 +52,7 @@ class ImageCreateService:
         return prompt, n, aspect_ratio
 
     def generate_images(self, request: ImageGenerationRequest):
-        client = genai.Client(api_key=self.paid_key)
+        client = genai.Client(api_key=settings.PAID_KEY)
 
         if request.size == "1024x1024":
             self.aspect_ratio = "1:1"

app/service/model/model_service.py

@@ -24,7 +24,7 @@ class ModelService:
                     if model_id not in settings.FILTERED_MODELS:
                         filtered_models_list.append(model)
                     else:
-                        logger.info(f"Filtered out model: {model_id}")
+                        logger.debug(f"Filtered out model: {model_id}")
 
                 gemini_models["models"] = filtered_models_list
                 return gemini_models
@@ -70,6 +70,10 @@ class ModelService:
                 image_model = openai_model.copy()
                 image_model["id"] = f"{model_id}-image"
                 openai_format["data"].append(image_model)
+            if model_id in settings.THINKING_MODELS:
+                non_thinking_model = openai_model.copy()
+                non_thinking_model["id"] = f"{model_id}-non-thinking"
+                openai_format["data"].append(non_thinking_model)
 
         if settings.CREATE_IMAGE_MODEL:
             image_model = openai_model.copy()

app/service/stats_service.py

@@ -9,115 +9,166 @@ from app.log.logger import get_stats_logger
 
 logger = get_stats_logger()
 
-async def get_calls_in_last_seconds(seconds: int) -> int:
-    """获取过去 N 秒内的调用次数 (包括成功和失败)"""
-    try:
-        cutoff_time = datetime.datetime.now() - datetime.timedelta(seconds=seconds)
-        query = select(func.count(RequestLog.id)).where(
-            RequestLog.request_time >= cutoff_time
-        )
-        count_result = await database.fetch_one(query)
-        return count_result[0] if count_result else 0
-    except Exception as e:
-        logger.error(f"Failed to get calls in last {seconds} seconds: {e}")
-        return 0 # Return 0 on error
 
-async def get_calls_in_last_minutes(minutes: int) -> int:
-    """获取过去 N 分钟内的调用次数 (包括成功和失败)"""
-    return await get_calls_in_last_seconds(minutes * 60)
+class StatsService:
+    """Service class for handling statistics related operations."""
 
-async def get_calls_in_last_hours(hours: int) -> int:
-    """获取过去 N 小时内的调用次数 (包括成功和失败)"""
-    return await get_calls_in_last_seconds(hours * 3600)
+    async def get_calls_in_last_seconds(self, seconds: int) -> int:
+        """获取过去 N 秒内的调用次数 (包括成功和失败)"""
+        try:
+            cutoff_time = datetime.datetime.now() - datetime.timedelta(seconds=seconds)
+            query = select(func.count(RequestLog.id)).where(
+                RequestLog.request_time >= cutoff_time
+            )
+            count_result = await database.fetch_one(query)
+            return count_result[0] if count_result else 0
+        except Exception as e:
+            logger.error(f"Failed to get calls in last {seconds} seconds: {e}")
+            return 0 # Return 0 on error
 
-async def get_calls_in_current_month() -> int:
-    """获取当前自然月内的调用次数 (包括成功和失败)"""
-    try:
+    async def get_calls_in_last_minutes(self, minutes: int) -> int:
+        """获取过去 N 分钟内的调用次数 (包括成功和失败)"""
+        return await self.get_calls_in_last_seconds(minutes * 60)
+
+    async def get_calls_in_last_hours(self, hours: int) -> int:
+        """获取过去 N 小时内的调用次数 (包括成功和失败)"""
+        return await self.get_calls_in_last_seconds(hours * 3600)
+
+    async def get_calls_in_current_month(self) -> int:
+        """获取当前自然月内的调用次数 (包括成功和失败)"""
+        try:
+            now = datetime.datetime.now()
+            start_of_month = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
+            query = select(func.count(RequestLog.id)).where(
+                RequestLog.request_time >= start_of_month
+            )
+            count_result = await database.fetch_one(query)
+            return count_result[0] if count_result else 0
+        except Exception as e:
+            logger.error(f"Failed to get calls in current month: {e}")
+            return 0 # Return 0 on error
+
+    async def get_api_usage_stats(self) -> dict:
+        """获取所有需要的 API 使用统计数据"""
+        try:
+            calls_1m = await self.get_calls_in_last_minutes(1)
+            calls_1h = await self.get_calls_in_last_hours(1)
+            calls_24h = await self.get_calls_in_last_hours(24)
+            calls_month = await self.get_calls_in_current_month()
+
+            return {
+                "calls_1m": calls_1m,
+                "calls_1h": calls_1h,
+                "calls_24h": calls_24h,
+                "calls_month": calls_month,
+            }
+        except Exception as e:
+            logger.error(f"Failed to get API usage stats: {e}")
+            # Return default values on error
+            return {
+                "calls_1m": 0,
+                "calls_1h": 0,
+                "calls_24h": 0,
+                "calls_month": 0,
+            }
+
+
+    async def get_api_call_details(self, period: str) -> list[dict]:
+        """
+        获取指定时间段内的 API 调用详情
+
+        Args:
+            period: 时间段标识 ('1m', '1h', '24h')
+
+        Returns:
+            包含调用详情的字典列表，每个字典包含 timestamp, key, model, status
+
+        Raises:
+            ValueError: 如果 period 无效
+        """
         now = datetime.datetime.now()
-        start_of_month = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
-        query = select(func.count(RequestLog.id)).where(
-            RequestLog.request_time >= start_of_month
-        )
-        count_result = await database.fetch_one(query)
-        return count_result[0] if count_result else 0
-    except Exception as e:
-        logger.error(f"Failed to get calls in current month: {e}")
-        return 0 # Return 0 on error
+        if period == '1m':
+            start_time = now - datetime.timedelta(minutes=1)
+        elif period == '1h':
+            start_time = now - datetime.timedelta(hours=1)
+        elif period == '24h':
+            start_time = now - datetime.timedelta(hours=24)
+        else:
+            raise ValueError(f"无效的时间段标识: {period}")
 
-async def get_api_usage_stats() -> dict:
-    """获取所有需要的 API 使用统计数据"""
-    try:
-        calls_1m = await get_calls_in_last_minutes(1)
-        calls_1h = await get_calls_in_last_hours(1)
-        calls_24h = await get_calls_in_last_hours(24)
-        calls_month = await get_calls_in_current_month()
+        try:
+            query = select(
+                RequestLog.request_time.label("timestamp"),
+                RequestLog.api_key.label("key"),
+                RequestLog.model_name.label("model"),
+                RequestLog.status_code # We might need to map this to 'success'/'failure' later
+            ).where(
+                RequestLog.request_time >= start_time
+            ).order_by(RequestLog.request_time.desc()) # Order by most recent first
 
-        return {
-            "calls_1m": calls_1m,
-            "calls_1h": calls_1h,
-            "calls_24h": calls_24h,
-            "calls_month": calls_month,
-        }
-    except Exception as e:
-        logger.error(f"Failed to get API usage stats: {e}")
-        # Return default values on error
-        return {
-            "calls_1m": 0,
-            "calls_1h": 0,
-            "calls_24h": 0,
-            "calls_month": 0,
-        }
+            results = await database.fetch_all(query)
 
+            # Convert results to list of dicts and map status_code
+            details = []
+            for row in results:
+                status = 'failure' # 默认状态为 failure，如果 status_code 有效且在 200-299 范围内则更新为 success
+                if row['status_code'] is not None: # 检查 status_code 是否为空
+                    status = 'success' if 200 <= row['status_code'] < 300 else 'failure'
+                details.append({
+                    "timestamp": row['timestamp'].isoformat(), # Use ISO format for JS compatibility
+                    "key": row['key'],
+                    "model": row['model'],
+                    "status": status
+                })
+            logger.info(f"Retrieved {len(details)} API call details for period '{period}'")
+            return details
 
-async def get_api_call_details(period: str) -> list[dict]:
-    """
-    获取指定时间段内的 API 调用详情
+        except Exception as e:
+            logger.error(f"Failed to get API call details for period '{period}': {e}")
+            # Re-raise the exception to be handled by the route
+            raise
 
-    Args:
-        period: 时间段标识 ('1m', '1h', '24h')
+    async def get_key_usage_details_last_24h(self, key: str) -> dict | None:
+        """
+        获取指定 API 密钥在过去 24 小时内按模型统计的调用次数。
 
-    Returns:
-        包含调用详情的字典列表，每个字典包含 timestamp, key, model, status
+        Args:
+            key: 要查询的 API 密钥。
 
-    Raises:
-        ValueError: 如果 period 无效
-    """
-    now = datetime.datetime.now()
-    if period == '1m':
-        start_time = now - datetime.timedelta(minutes=1)
-    elif period == '1h':
-        start_time = now - datetime.timedelta(hours=1)
-    elif period == '24h':
-        start_time = now - datetime.timedelta(hours=24)
-    else:
-        raise ValueError(f"无效的时间段标识: {period}")
+        Returns:
+            一个字典，其中键是模型名称，值是调用次数。
+            如果查询出错或没有找到记录，可能返回 None 或空字典。
+            Example: {"gemini-pro": 10, "gemini-1.5-pro-latest": 5}
+        """
+        logger.info(f"Fetching usage details for key ending in ...{key[-4:]} for the last 24h.")
+        cutoff_time = datetime.datetime.now() - datetime.timedelta(hours=24)
 
-    try:
-        query = select(
-            RequestLog.request_time.label("timestamp"),
-            RequestLog.api_key.label("key"),
-            RequestLog.model_name.label("model"),
-            RequestLog.status_code # We might need to map this to 'success'/'failure' later
-        ).where(
-            RequestLog.request_time >= start_time
-        ).order_by(RequestLog.request_time.desc()) # Order by most recent first
+        try:
+            query = select(
+                RequestLog.model_name,
+                func.count(RequestLog.id).label("call_count")
+            ).where(
+                RequestLog.api_key == key,
+                RequestLog.request_time >= cutoff_time,
+                RequestLog.model_name.isnot(None) # Ensure model_name is not null
+            ).group_by(
+                RequestLog.model_name
+            ).order_by(
+                func.count(RequestLog.id).desc() # Order by count descending
+            )
 
-        results = await database.fetch_all(query)
+            results = await database.fetch_all(query)
 
-        # Convert results to list of dicts and map status_code
-        details = []
-        for row in results:
-            status = 'success' if 200 <= row['status_code'] < 300 else 'failure'
-            details.append({
-                "timestamp": row['timestamp'].isoformat(), # Use ISO format for JS compatibility
-                "key": row['key'],
-                "model": row['model'],
-                "status": status
-            })
-        logger.info(f"Retrieved {len(details)} API call details for period '{period}'")
-        return details
+            if not results:
+                logger.info(f"No usage details found for key ending in ...{key[-4:]} in the last 24h.")
+                return {} # Return empty dict if no records found
 
-    except Exception as e:
-        logger.error(f"Failed to get API call details for period '{period}': {e}")
-        # Re-raise the exception to be handled by the route
-        raise
+            usage_details = {row['model_name']: row['call_count'] for row in results}
+            logger.info(f"Successfully fetched usage details for key ending in ...{key[-4:]}: {usage_details}")
+            return usage_details
+
+        except Exception as e:
+            logger.error(f"Failed to get key usage details for key ending in ...{key[-4:]}: {e}", exc_info=True)
+            # Depending on requirements, you might return None or raise the exception
+            # Raising allows the route handler to return a 500 error.
+            raise # Re-raise the exception

app/service/update/update_service.py

@@ -0,0 +1,108 @@
+import httpx
+from packaging import version
+from typing import Optional, Tuple
+
+from app.config.config import settings
+from app.log.logger import get_update_logger
+
+logger = get_update_logger()
+
+# GitHub repository details are read from settings (defined in app/config/config.py or environment variables)
+
+# GITHUB_API_URL will be constructed inside the function to ensure settings are loaded
+
+VERSION_FILE_PATH = "VERSION" # Path relative to project root
+
+async def check_for_updates() -> Tuple[bool, Optional[str], Optional[str]]:
+    """
+    通过比较当前版本与最新的 GitHub release 来检查应用程序更新。
+
+    Returns:
+        Tuple[bool, Optional[str], Optional[str]]: 一个元组，包含：
+            - bool: 如果有可用更新则为 True，否则为 False。
+            - Optional[str]: 如果有可用更新，则为最新的版本字符串，否则为 None。
+            - Optional[str]: 如果检查失败，则为错误消息，否则为 None。
+    """
+    try:
+        # Read current version from VERSION file
+        # Ensure the path is correct relative to the execution context or use absolute path if needed
+        # Assuming execution from project root d:/develop/pythonProjects/gemini-balance
+        with open(VERSION_FILE_PATH, 'r', encoding='utf-8') as f:
+            current_v = f.read().strip()
+        if not current_v:
+            logger.error(f"VERSION file ('{VERSION_FILE_PATH}') is empty.")
+            return False, None, f"VERSION file ('{VERSION_FILE_PATH}') is empty."
+    except FileNotFoundError:
+        logger.error(f"VERSION file not found at '{VERSION_FILE_PATH}'. Make sure it exists in the project root.")
+        return False, None, f"VERSION file not found at '{VERSION_FILE_PATH}'."
+    except IOError as e:
+        logger.error(f"Error reading VERSION file ('{VERSION_FILE_PATH}'): {e}")
+        return False, None, f"Error reading VERSION file ('{VERSION_FILE_PATH}')."
+
+    logger.info(f"当前应用程序版本 (from {VERSION_FILE_PATH}): {current_v}")
+
+    # Check if repository details are configured in settings
+    if not settings.GITHUB_REPO_OWNER or not settings.GITHUB_REPO_NAME or \
+       settings.GITHUB_REPO_OWNER == "your_owner" or settings.GITHUB_REPO_NAME == "your_repo":
+        logger.warning("GitHub repository owner/name not configured in settings. Skipping update check.")
+        return False, None, "Update check skipped: Repository not configured in settings."
+
+    # Construct the API URL inside the function to ensure settings are loaded
+    github_api_url = f"https://api.github.com/repos/{settings.GITHUB_REPO_OWNER}/{settings.GITHUB_REPO_NAME}/releases/latest"
+    logger.debug(f"Checking for updates at URL: {github_api_url}") # Log the URL for debugging
+
+    try:
+        async with httpx.AsyncClient(timeout=10.0) as client:
+            # 添加 User-Agent 头，GitHub API 可能需要
+            headers = {
+                "Accept": "application/vnd.github.v3+json",
+                "User-Agent": f"{settings.GITHUB_REPO_NAME}-UpdateChecker/1.0" # Use repo name from settings for User-Agent
+            }
+            response = await client.get(github_api_url, headers=headers) # Use the locally constructed URL
+            response.raise_for_status() # 对错误的 HTTP 状态码（4xx 或 5xx）抛出异常
+
+            latest_release = response.json()
+            latest_v_str = latest_release.get("tag_name")
+
+            if not latest_v_str:
+                logger.warning("在最新的 GitHub release 响应中找不到 'tag_name'。")
+                return False, None, "无法从 GitHub 解析最新版本。"
+
+            # 移除 tag 名称中可能存在的 'v' 前缀
+            if latest_v_str.startswith('v'):
+                latest_v_str = latest_v_str[1:]
+
+            logger.info(f"在 GitHub 上找到的最新版本: {latest_v_str}")
+
+            # 比较版本
+            current_version = version.parse(current_v)
+            latest_version = version.parse(latest_v_str)
+
+            if latest_version > current_version:
+                logger.info(f"有可用更新: {current_v} -> {latest_v_str}")
+                return True, latest_v_str, None
+            else:
+                logger.info("应用程序已是最新版本。")
+                return False, None, None
+
+    except httpx.HTTPStatusError as e:
+        logger.error(f"检查更新时发生 HTTP 错误: {e.response.status_code} - {e.response.text}")
+        # 避免向用户显示详细的错误文本
+        error_msg = f"获取更新信息失败 (HTTP {e.response.status_code})。"
+        if e.response.status_code == 404:
+            error_msg += " 请检查仓库名称是否正确或仓库是否有发布版本。"
+        elif e.response.status_code == 403:
+             error_msg += " API 速率限制或权限问题。"
+        return False, None, error_msg
+    except httpx.RequestError as e:
+        logger.error(f"检查更新时发生网络错误: {e}")
+        return False, None, "更新检查期间发生网络错误。"
+    except version.InvalidVersion:
+        # Note: latest_v_str might not be defined if the error occurs before fetching it.
+        # Consider adding a check or default value for logging.
+        latest_v_str_for_log = latest_v_str if 'latest_v_str' in locals() else 'N/A'
+        logger.error(f"发现无效的版本格式。当前 (from {VERSION_FILE_PATH}): '{current_v}', 最新: '{latest_v_str_for_log}'")
+        return False, None, "遇到无效的版本格式。"
+    except Exception as e:
+        logger.error(f"更新检查期间发生意外错误: {e}", exc_info=True)
+        return False, None, "发生意外错误。"

app/static/js/config_editor.js

@@ -1,7 +1,7 @@
 document.addEventListener('DOMContentLoaded', function() {
     // 初始化配置
     initConfig();
-    
+
     // 标签切换
     const tabButtons = document.querySelectorAll('.tab-btn');
     tabButtons.forEach(button => {
@@ -12,7 +12,7 @@ document.addEventListener('DOMContentLoaded', function() {
             switchTab(tabId);
         });
     });
-    
+
     // 上传提供商切换
     const uploadProviderSelect = document.getElementById('UPLOAD_PROVIDER');
     if (uploadProviderSelect) {
@@ -20,7 +20,7 @@ document.addEventListener('DOMContentLoaded', function() {
             toggleProviderConfig(this.value);
         });
     }
-    
+
     // 切换按钮事件
     const toggleSwitches = document.querySelectorAll('.toggle-switch');
     toggleSwitches.forEach(toggleSwitch => {
@@ -33,19 +33,19 @@ document.addEventListener('DOMContentLoaded', function() {
             }
         });
     });
-    
+
     // 保存按钮
     const saveBtn = document.getElementById('saveBtn');
     if (saveBtn) {
         saveBtn.addEventListener('click', saveConfig);
     }
-    
+
     // 重置按钮
     const resetBtn = document.getElementById('resetBtn');
     if (resetBtn) {
         resetBtn.addEventListener('click', resetConfig);
     }
-    
+
     // 滚动按钮
     window.addEventListener('scroll', toggleScrollButtons);
 
@@ -197,55 +197,97 @@ document.addEventListener('DOMContentLoaded', function() {
             showNotification('已生成新认证令牌', 'success');
         });
     }
+
+    // --- 修改：思考模型预算映射不再需要手动添加按钮 ---
+    // const addBudgetMapItemBtn = document.getElementById('addBudgetMapItemBtn');
+    // if (addBudgetMapItemBtn) {
+    //     addBudgetMapItemBtn.addEventListener('click', addBudgetMapItem);
+    // }
+    // --- 结束：思考模型预算映射相关 ---
+
+    // 添加事件委托，处理动态添加的 THINKING_MODELS 输入框的 input 事件
+    const thinkingModelsContainer = document.getElementById('THINKING_MODELS_container');
+    if (thinkingModelsContainer) {
+        thinkingModelsContainer.addEventListener('input', function(event) {
+            if (event.target && event.target.classList.contains('array-input') && event.target.closest('.array-item[data-model-id]')) {
+                const modelInput = event.target;
+                const modelId = modelInput.closest('.array-item').getAttribute('data-model-id');
+                const budgetKeyInput = document.querySelector(`.map-key-input[data-model-id="${modelId}"]`);
+                if (budgetKeyInput) {
+                    budgetKeyInput.value = modelInput.value;
+                }
+            }
+        });
+    }
+
+
 }); // <-- DOMContentLoaded 结束括号
 
+// --- 新增：生成唯一ID ---
+function generateUUID() {
+    return 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'.replace(/[xy]/g, function(c) {
+        var r = Math.random() * 16 | 0, v = c == 'x' ? r : (r & 0x3 | 0x8);
+        return v.toString(16);
+    });
+}
+// --- 结束：生成唯一ID ---
+
+
 // 初始化配置
 async function initConfig() {
     try {
         showNotification('正在加载配置...', 'info');
         const response = await fetch('/api/config');
-        
+
         if (!response.ok) {
             throw new Error(`HTTP error! status: ${response.status}`);
         }
-        
+
         const config = await response.json();
-        
+
         // 确保数组字段有默认值
         if (!config.API_KEYS || !Array.isArray(config.API_KEYS) || config.API_KEYS.length === 0) {
             config.API_KEYS = ['请在此处输入 API 密钥'];
         }
-        
+
         if (!config.ALLOWED_TOKENS || !Array.isArray(config.ALLOWED_TOKENS) || config.ALLOWED_TOKENS.length === 0) {
             config.ALLOWED_TOKENS = [''];
         }
-        
+
         if (!config.IMAGE_MODELS || !Array.isArray(config.IMAGE_MODELS) || config.IMAGE_MODELS.length === 0) {
             config.IMAGE_MODELS = ['gemini-1.5-pro-latest'];
         }
-        
+
         if (!config.SEARCH_MODELS || !Array.isArray(config.SEARCH_MODELS) || config.SEARCH_MODELS.length === 0) {
             config.SEARCH_MODELS = ['gemini-1.5-flash-latest'];
         }
-        
+
         if (!config.FILTERED_MODELS || !Array.isArray(config.FILTERED_MODELS) || config.FILTERED_MODELS.length === 0) {
             config.FILTERED_MODELS = ['gemini-1.0-pro-latest'];
         }
-        
+        // --- 新增：处理新字段的默认值 ---
+        if (!config.THINKING_MODELS || !Array.isArray(config.THINKING_MODELS)) {
+            config.THINKING_MODELS = []; // 默认为空数组
+        }
+        if (!config.THINKING_BUDGET_MAP || typeof config.THINKING_BUDGET_MAP !== 'object' || config.THINKING_BUDGET_MAP === null) {
+            config.THINKING_BUDGET_MAP = {}; // 默认为空对象
+        }
+        // --- 结束：处理新字段的默认值 ---
+
         populateForm(config);
-        
+
         // 确保上传提供商有默认值
         const uploadProvider = document.getElementById('UPLOAD_PROVIDER');
         if (uploadProvider && !uploadProvider.value) {
             uploadProvider.value = 'smms'; // 设置默认值为 smms
             toggleProviderConfig('smms');
         }
-        
+
         showNotification('配置加载成功', 'success');
     } catch (error) {
         console.error('加载配置失败:', error);
         showNotification('加载配置失败: ' + error.message, 'error');
-        
+
         // 加载失败时，使用默认配置
         const defaultConfig = {
             API_KEYS: [''],
@@ -253,9 +295,11 @@ async function initConfig() {
             IMAGE_MODELS: ['gemini-1.5-pro-latest'],
             SEARCH_MODELS: ['gemini-1.5-flash-latest'],
             FILTERED_MODELS: ['gemini-1.0-pro-latest'],
-            UPLOAD_PROVIDER: 'smms'
+            UPLOAD_PROVIDER: 'smms',
+            THINKING_MODELS: [],
+            THINKING_BUDGET_MAP: {}
         };
-        
+
         populateForm(defaultConfig);
         toggleProviderConfig('smms');
     }
@@ -263,45 +307,105 @@ async function initConfig() {
 
 // 填充表单
 function populateForm(config) {
+    const modelIdMap = {}; // modelName -> modelId
+
+    // 1. Clear existing dynamic content first
+    const arrayContainers = document.querySelectorAll('.array-container');
+    arrayContainers.forEach(container => {
+        container.innerHTML = ''; // Clear all array containers
+    });
+    const budgetMapContainer = document.getElementById('THINKING_BUDGET_MAP_container');
+    if (budgetMapContainer) {
+        budgetMapContainer.innerHTML = ''; // Clear budget map container
+    } else {
+        console.error("Critical: THINKING_BUDGET_MAP_container not found!");
+        return; // Cannot proceed
+    }
+
+    // 2. Populate THINKING_MODELS and build the map
+    if (Array.isArray(config.THINKING_MODELS)) {
+        const container = document.getElementById('THINKING_MODELS_container');
+        if (container) {
+            config.THINKING_MODELS.forEach(modelName => {
+                if (modelName && typeof modelName === 'string' && modelName.trim()) {
+                    const trimmedModelName = modelName.trim();
+                    // Call addArrayItemWithValue to add the model DOM element and get its ID
+                    const modelId = addArrayItemWithValue('THINKING_MODELS', trimmedModelName);
+                    if (modelId) {
+                        modelIdMap[trimmedModelName] = modelId;
+                    } else {
+                         console.warn(`Failed to get modelId for THINKING_MODEL: '${trimmedModelName}'`);
+                    }
+                } else {
+                     console.warn(`Invalid THINKING_MODEL entry found:`, modelName);
+                }
+            });
+        } else {
+             console.error("Critical: THINKING_MODELS_container not found!");
+        }
+    }
+
+    // 3. Populate THINKING_BUDGET_MAP using the map
+    let budgetItemsAdded = false;
+    if (config.THINKING_BUDGET_MAP && typeof config.THINKING_BUDGET_MAP === 'object') {
+        for (const [modelName, budgetValue] of Object.entries(config.THINKING_BUDGET_MAP)) {
+             if (modelName && typeof modelName === 'string') {
+                const trimmedModelName = modelName.trim();
+                const modelId = modelIdMap[trimmedModelName]; // Look up the ID
+                if (modelId) {
+                    // Call the function specifically designed to add ONLY the budget map DOM element
+                    createAndAppendBudgetMapItem(trimmedModelName, budgetValue, modelId);
+                    budgetItemsAdded = true;
+                } else {
+                    // Log if a budget entry exists but its corresponding model wasn't found/added
+                    console.warn(`Budget map: Could not find model ID for '${trimmedModelName}'. Skipping budget item.`);
+                }
+            } else {
+                 console.warn(`Invalid key found in THINKING_BUDGET_MAP:`, modelName);
+            }
+        }
+    }
+    // Add placeholder only if no budget items were successfully added
+    if (!budgetItemsAdded && budgetMapContainer) {
+         budgetMapContainer.innerHTML = '<div class="text-gray-500 text-sm italic">请在上方添加思考模型，预算将自动关联。</div>';
+    }
+
+    // 4. Populate other array fields (excluding THINKING_MODELS)
     for (const [key, value] of Object.entries(config)) {
-        // 首先检查是否是数组类型
-        if (Array.isArray(value)) {
+        if (Array.isArray(value) && key !== 'THINKING_MODELS') {
             const container = document.getElementById(`${key}_container`);
             if (container) {
-                // 清除现有项
-                const existingItems = container.querySelectorAll('.array-item');
-                existingItems.forEach(item => item.remove());
-                // 添加数组项
-                value.forEach(item => {
-                    // 确保只添加非空字符串项（如果需要）
-                    // if (item && typeof item === 'string' && item.trim() !== '') {
-                 addArrayItemWithValue(key, item);
-            // }
+                // Container already cleared, just add items
+                value.forEach(itemValue => {
+                    if (typeof itemValue === 'string') {
+                         addArrayItemWithValue(key, itemValue); // This adds non-thinking model array items
+                    } else {
+                         console.warn(`Invalid item found in array '${key}':`, itemValue);
+                    }
                 });
             }
-            // 处理完数组后，跳过本次循环的剩余部分
-            continue;
         }
+    }
 
-        // 如果不是数组，再尝试查找对应的单个元素
-        const element = document.getElementById(key);
-        if (element) {
-            if (typeof value === 'boolean') {
-                element.checked = value;
-            } else {
-                // 处理其他类型 (确保 value 不是 null 或 undefined)
-                // 特别处理 LOG_LEVEL，确保大小写匹配 option 的 value
-                if (key === 'LOG_LEVEL' && typeof value === 'string') {
-                    element.value = value.toUpperCase();
-                } else {
-                    element.value = value ?? ''; // 使用空字符串作为默认值
+    // 5. Populate non-array/non-budget fields
+     for (const [key, value] of Object.entries(config)) {
+        if (!Array.isArray(value) && !(typeof value === 'object' && value !== null && key === 'THINKING_BUDGET_MAP')) {
+            const element = document.getElementById(key);
+            if (element) {
+                if (element.type === 'checkbox' && typeof value === 'boolean') {
+                    element.checked = value;
+                } else if (element.type !== 'checkbox') {
+                    if (key === 'LOG_LEVEL' && typeof value === 'string') {
+                        element.value = value.toUpperCase();
+                    } else {
+                        element.value = (value !== null && value !== undefined) ? value : '';
+                    }
                 }
             }
         }
-        // 如果既不是数组，也找不到对应 ID 的元素，则忽略该配置项
     }
 
-    // 初始化上传提供商配置 (保持不变)
+    // 6. Initialize upload provider
     const uploadProvider = document.getElementById('UPLOAD_PROVIDER');
     if (uploadProvider) {
         toggleProviderConfig(uploadProvider.value);
@@ -432,7 +536,7 @@ function switchTab(tabId) {
             button.classList.add('bg-white', 'bg-opacity-50', 'text-gray-700', 'hover:bg-opacity-70');
         }
     });
-    
+
     // 更新内容区域
     const sections = document.querySelectorAll('.config-section');
     sections.forEach(section => {
@@ -461,18 +565,31 @@ function toggleProviderConfig(provider) {
 function addArrayItem(key) {
     const container = document.getElementById(`${key}_container`);
     if (!container) return;
-    
-    addArrayItemWithValue(key, '');
+
+    const newItemValue = ''; // Start with an empty value for new items
+    const modelId = addArrayItemWithValue(key, newItemValue); // Add the DOM element
+
+    // If it's a thinking model, also add the corresponding budget map item
+    if (key === 'THINKING_MODELS' && modelId) {
+        createAndAppendBudgetMapItem(newItemValue, 0, modelId); // Default budget 0
+    }
 }
 
-// 添加带值的数组项
+// 添加带值的数组项 (Adds array item DOM, returns modelId if it's a thinking model)
 function addArrayItemWithValue(key, value) {
     const container = document.getElementById(`${key}_container`);
-    if (!container) return;
-    
+    if (!container) return null;
+
+    const isThinkingModel = key === 'THINKING_MODELS';
+    const modelId = isThinkingModel ? generateUUID() : null;
+
     const arrayItem = document.createElement('div');
     // 主容器使用 Flexbox
     arrayItem.className = 'array-item flex items-center mb-2 gap-2'; // 添加 gap-2 来分隔元素
+    if (isThinkingModel) {
+        arrayItem.setAttribute('data-model-id', modelId); // 添加ID属性
+    }
+
 
     // 创建一个包装器 div 来包含输入框和生成按钮
     const inputWrapper = document.createElement('div');
@@ -485,6 +602,11 @@ function addArrayItemWithValue(key, value) {
     input.value = value;
     // 输入框占据包装器内的主要空间，移除边框和圆角，因为包装器已有
     input.className = 'array-input flex-grow px-3 py-2 border-none rounded-l-md focus:outline-none'; // 移除右侧圆角
+    if (isThinkingModel) {
+         input.setAttribute('data-model-id', modelId); // 添加ID属性
+         input.placeholder = '思考模型名称'; // 添加占位符
+    }
+
 
     inputWrapper.appendChild(input); // 将输入框添加到包装器
 
@@ -514,7 +636,21 @@ function addArrayItemWithValue(key, value) {
     removeBtn.innerHTML = '<i class="fas fa-trash-alt"></i>';
     removeBtn.title = '删除';
     removeBtn.addEventListener('click', function() {
-        arrayItem.remove();
+        const currentArrayItem = this.closest('.array-item');
+        if (isThinkingModel) {
+            const currentModelId = currentArrayItem.getAttribute('data-model-id');
+            // 查找并删除对应的预算映射项
+            const budgetMapItem = document.querySelector(`.map-item[data-model-id="${currentModelId}"]`);
+            if (budgetMapItem) {
+                budgetMapItem.remove();
+                 // 检查预算映射容器是否为空，如果是，则添加回占位符
+                const budgetContainer = document.getElementById('THINKING_BUDGET_MAP_container');
+                if (budgetContainer && budgetContainer.children.length === 0) {
+                    budgetContainer.innerHTML = '<div class="text-gray-500 text-sm italic">请在上方添加思考模型，预算将自动关联。</div>';
+                }
+            }
+        }
+        currentArrayItem.remove(); // 删除模型项本身
     });
 
     // 将包装器（包含输入框和可能的生成按钮）和删除按钮添加到主容器
@@ -523,12 +659,83 @@ function addArrayItemWithValue(key, value) {
 
     // 插入到容器末尾
     container.appendChild(arrayItem);
+
+    // 返回生成的 ID (如果是思考模型) 或 null
+    return isThinkingModel ? modelId : null;
+    // Note: This function no longer automatically calls createAndAppendBudgetMapItem
 }
 
+
+// --- 新增：专门用于创建和添加预算映射 DOM 元素 ---
+function createAndAppendBudgetMapItem(mapKey, mapValue, modelId) {
+   const container = document.getElementById('THINKING_BUDGET_MAP_container');
+   if (!container) {
+       console.error("Cannot add budget item: THINKING_BUDGET_MAP_container not found!");
+       return;
+   }
+
+   // If container currently only has the placeholder, clear it
+   const placeholder = container.querySelector('.text-gray-500.italic');
+   // Check if the only child is the placeholder before clearing
+   if (placeholder && container.children.length === 1 && container.firstChild === placeholder) {
+       container.innerHTML = '';
+   }
+
+   const mapItem = document.createElement('div');
+   mapItem.className = 'map-item flex items-center mb-2 gap-2';
+   mapItem.setAttribute('data-model-id', modelId); // Add ID attribute
+
+   // Key Input (Model Name) - Read-only
+   const keyInput = document.createElement('input');
+   keyInput.type = 'text';
+   keyInput.value = mapKey;
+   keyInput.placeholder = '模型名称 (自动关联)';
+   keyInput.readOnly = true;
+   keyInput.className = 'map-key-input flex-grow px-3 py-2 border border-gray-300 rounded-md focus:outline-none bg-gray-100 text-gray-500';
+   keyInput.setAttribute('data-model-id', modelId);
+
+   // Value Input (Budget) - Integer
+   const valueInput = document.createElement('input');
+   valueInput.type = 'number';
+   // Ensure mapValue is treated as integer, default to 0 if invalid
+   const intValue = parseInt(mapValue, 10);
+   valueInput.value = isNaN(intValue) ? 0 : intValue;
+   valueInput.placeholder = '预算 (整数)';
+   valueInput.className = 'map-value-input w-24 px-3 py-2 border border-gray-300 rounded-md focus:outline-none focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50';
+   valueInput.min = 0; // 添加最小值
+   valueInput.max = 24576; // 添加最大值
+   valueInput.addEventListener('input', function() {
+        // 限制输入为0到24576之间的整数
+        let value = this.value.replace(/[^0-9]/g, '');
+        if (value !== '') {
+            value = parseInt(value, 10);
+            if (value < 0) value = 0;
+            if (value > 24576) value = 24576;
+        }
+        this.value = value;
+   });
+
+   // Remove Button - Removed for budget map items
+   // const removeBtn = document.createElement('button');
+   // removeBtn.type = 'button';
+   // removeBtn.className = 'remove-btn text-gray-300 cursor-not-allowed focus:outline-none'; // Kept original class for reference
+   // removeBtn.innerHTML = '<i class="fas fa-trash-alt"></i>';
+   // removeBtn.title = '请从上方模型列表删除';
+   // removeBtn.disabled = true;
+
+   mapItem.appendChild(keyInput);
+   mapItem.appendChild(valueInput);
+   // mapItem.appendChild(removeBtn); // Do not append the remove button
+
+   container.appendChild(mapItem);
+}
+// --- 结束：专门的预算映射项创建函数 ---
+
+
 // 收集表单数据
 function collectFormData() {
     const formData = {};
-    
+
     // 处理普通输入
     const inputs = document.querySelectorAll('input[type="text"], input[type="number"], select');
     inputs.forEach(input => {
@@ -541,13 +748,13 @@ function collectFormData() {
             }
         }
     });
-    
+
     // 处理复选框
     const checkboxes = document.querySelectorAll('input[type="checkbox"]');
     checkboxes.forEach(checkbox => {
         formData[checkbox.name] = checkbox.checked;
     });
-    
+
     // 处理数组
     const arrayContainers = document.querySelectorAll('.array-container');
     arrayContainers.forEach(container => {
@@ -555,7 +762,25 @@ function collectFormData() {
         const arrayInputs = container.querySelectorAll('.array-input');
         formData[key] = Array.from(arrayInputs).map(input => input.value).filter(value => value.trim() !== '');
     });
-    
+
+    // --- 新增：处理 THINKING_BUDGET_MAP ---
+    const budgetMapContainer = document.getElementById('THINKING_BUDGET_MAP_container');
+    if (budgetMapContainer) {
+        formData['THINKING_BUDGET_MAP'] = {};
+        const mapItems = budgetMapContainer.querySelectorAll('.map-item');
+        mapItems.forEach(item => {
+            const keyInput = item.querySelector('.map-key-input');
+            const valueInput = item.querySelector('.map-value-input');
+            if (keyInput && valueInput && keyInput.value.trim() !== '') {
+                // 将预算值解析为整数
+                const budgetValue = parseInt(valueInput.value, 10); // 使用基数10
+                // 检查是否为有效数字，如果不是则默认为 0
+                formData['THINKING_BUDGET_MAP'][keyInput.value.trim()] = isNaN(budgetValue) ? 0 : budgetValue;
+            }
+        });
+    }
+    // --- 结束：处理 THINKING_BUDGET_MAP ---
+
     return formData;
 }
 
@@ -596,7 +821,7 @@ async function saveConfig() {
 
         // 1. 停止定时任务
         await stopScheduler();
-        
+
         const response = await fetch('/api/config', {
             method: 'PUT',
             headers: {
@@ -604,16 +829,16 @@ async function saveConfig() {
             },
             body: JSON.stringify(formData)
         });
-        
+
         if (!response.ok) {
             const errorData = await response.json();
             throw new Error(errorData.detail || `HTTP error! status: ${response.status}`);
         }
-        
+
         const result = await response.json();
-        
+
         // 移除居中的 saveStatus 提示
-        
+
         showNotification('配置保存成功', 'success');
 
         // 3. 启动新的定时任务
@@ -624,21 +849,21 @@ async function saveConfig() {
         // 保存失败时，也尝试重启定时任务，以防万一
         await startScheduler();
         // 移除居中的 saveStatus 提示
-        
+
         showNotification('保存配置失败: ' + error.message, 'error');
     }
 }
 
 // 重置配置 (现在只负责打开模态框)
-function resetConfig(event) { 
+function resetConfig(event) {
     // 阻止事件冒泡和默认行为
     if (event) {
         event.preventDefault();
         event.stopPropagation();
     }
-    
+
     console.log('resetConfig called. Event target:', event ? event.target.id : 'No event');
-    
+
     // 确保只有当事件来自重置按钮时才显示模态框
     if (!event || event.target.id === 'resetBtn' || event.currentTarget.id === 'resetBtn') {
         const resetConfirmModal = document.getElementById('resetConfirmModal');
@@ -729,7 +954,7 @@ function scrollToBottom() {
 // 切换滚动按钮显示
 function toggleScrollButtons() {
     const scrollButtons = document.querySelector('.scroll-buttons');
-    
+
     if (window.scrollY > 200) {
         scrollButtons.style.display = 'flex';
     } else {
@@ -749,3 +974,17 @@ function generateRandomToken() {
     return result;
 }
 // --- 结束：生成随机令牌函数 ---
+
+// --- 修改：添加思考模型预算映射项 (现在由添加思考模型触发) ---
+// function addBudgetMapItem() {
+//    // 不再需要手动添加
+// }
+
+// Deprecated: This function is now effectively replaced by createAndAppendBudgetMapItem
+// for the initial population logic. It delegates to the new function if called.
+function addBudgetMapItemWithValue(mapKey, mapValue, modelId) {
+    // console.warn("Deprecated call to addBudgetMapItemWithValue, use createAndAppendBudgetMapItem instead for population.");
+    // Delegate to the new function which handles DOM creation
+    createAndAppendBudgetMapItem(mapKey, mapValue, modelId);
+}
+/* --- 结束：(addBudgetMapItemWithValue 已弃用) --- */

app/static/js/keys_status.js

@@ -914,3 +914,109 @@ function renderApiCallDetails(data, container) {
 
     container.innerHTML = tableHtml;
 }
+
+// --- 密钥使用详情模态框逻辑 ---
+
+// 显示密钥使用详情模态框
+window.showKeyUsageDetails = async function(key) {
+    const modal = document.getElementById('keyUsageDetailsModal');
+    const contentArea = document.getElementById('keyUsageDetailsContent');
+    const titleElement = document.getElementById('keyUsageDetailsModalTitle');
+    const keyDisplay = key.substring(0, 4) + '...' + key.substring(key.length - 4);
+
+    if (!modal || !contentArea || !titleElement) {
+        console.error('无法找到密钥使用详情模态框元素');
+        showNotification('无法显示详情，页面元素缺失', 'error');
+        return;
+    }
+
+    // 设置标题
+    titleElement.textContent = `密钥 ${keyDisplay} - 最近24小时请求详情`;
+
+    // 显示模态框并设置加载状态
+    modal.classList.remove('hidden');
+    contentArea.innerHTML = `
+        <div class="text-center py-10">
+             <i class="fas fa-spinner fa-spin text-primary-600 text-3xl"></i>
+             <p class="text-gray-500 mt-2">加载中...</p>
+        </div>`;
+
+    try {
+        // 调用新的后端 API 获取数据
+        // 注意：后端需要实现 /api/key-usage-details/{key} 端点
+        const response = await fetch(`/api/key-usage-details/${key}`);
+        if (!response.ok) {
+            let errorMsg = `服务器错误: ${response.status}`;
+            try {
+                const errorData = await response.json();
+                errorMsg = errorData.detail || errorMsg; // 假设后端错误信息在 detail 字段
+            } catch (e) { /* 忽略解析错误 */ }
+            throw new Error(errorMsg);
+        }
+        const data = await response.json();
+
+        // 渲染数据
+        renderKeyUsageDetails(data, contentArea);
+
+    } catch (error) {
+        console.error('获取密钥使用详情失败:', error);
+        contentArea.innerHTML = `
+            <div class="text-center py-10 text-danger-500">
+                <i class="fas fa-exclamation-triangle text-3xl"></i>
+                <p class="mt-2">加载失败: ${error.message}</p>
+            </div>`;
+    }
+}
+
+// 关闭密钥使用详情模态框
+window.closeKeyUsageDetailsModal = function() {
+    const modal = document.getElementById('keyUsageDetailsModal');
+    if (modal) {
+        modal.classList.add('hidden');
+    }
+}
+
+// 渲染密钥使用详情到模态框 (这个函数主要由 showKeyUsageDetails 调用，不一定需要全局，但保持一致性)
+window.renderKeyUsageDetails = function(data, container) {
+    // data 预期格式: { "model_name1": count1, "model_name2": count2, ... }
+    if (!data || Object.keys(data).length === 0) {
+        container.innerHTML = `
+            <div class="text-center py-10 text-gray-500">
+                <i class="fas fa-info-circle text-3xl"></i>
+                <p class="mt-2">该密钥在最近24小时内没有调用记录。</p>
+            </div>`;
+        return;
+    }
+
+    // 创建表格
+    let tableHtml = `
+        <table class="min-w-full divide-y divide-gray-200">
+            <thead class="bg-gray-50">
+                <tr>
+                    <th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider">模型名称</th>
+                    <th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider">调用次数 (24h)</th>
+                </tr>
+            </thead>
+            <tbody class="bg-white divide-y divide-gray-200">
+    `;
+
+    // 排序模型（可选，按调用次数降序）
+    const sortedModels = Object.entries(data).sort(([, countA], [, countB]) => countB - countA);
+
+    // 填充表格行
+    sortedModels.forEach(([model, count]) => {
+        tableHtml += `
+            <tr>
+                <td class="px-6 py-4 whitespace-nowrap text-sm font-medium text-gray-900">${model}</td>
+                <td class="px-6 py-4 whitespace-nowrap text-sm text-gray-500">${count}</td>
+            </tr>
+        `;
+    });
+
+    tableHtml += `
+            </tbody>
+        </table>
+    `;
+
+    container.innerHTML = tableHtml;
+}

app/templates/base.html

@@ -196,6 +196,20 @@
         <a href="https://github.com/snailyp/gemini-balance" target="_blank" class="text-primary-600 hover:text-primary-800 transition duration-300">
             <i class="fab fa-github"></i> GitHub
         </a>
+        {% if request and request.app.state.update_info %}
+            {% set update_info = request.app.state.update_info %}
+            <span class="mx-1">|</span>
+            <span class="text-xs text-gray-500">v{{ update_info.current_version }}</span>
+            {% if update_info.update_available %}
+                <span class="mx-1">|</span>
+                <a href="https://github.com/snailyp/gemini-balance/releases/latest" target="_blank" class="text-yellow-600 hover:text-yellow-800 transition duration-300 animate-pulse">
+                    <i class="fas fa-arrow-up"></i> 新版本: v{{ update_info.latest_version }}
+                </a>
+            {% elif update_info.error_message and update_info.error_message != 'Checking...' %}
+                 <span class="mx-1">|</span>
+                 <span class="text-xs text-red-500" title="{{ update_info.error_message }}">更新检查失败</span>
+            {% endif %}
+        {% endif %}
     </div>
 
     <!-- 通用JS -->

app/templates/config_editor.html

@@ -265,8 +265,38 @@
                             <label for="SHOW_THINKING_PROCESS" class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"></label>
                         </div>
                     </div>
+
+                    <!-- 思考模型列表 -->
+                    <div class="mb-6">
+                        <label for="THINKING_MODELS" class="block font-semibold mb-2 text-gray-700">思考模型列表</label>
+                        <div class="array-container bg-white rounded-lg border border-gray-200 p-4 mb-2" id="THINKING_MODELS_container">
+                            <!-- 数组项将在这里动态添加 -->
+                        </div>
+                        <div class="flex justify-end">
+                            <button type="button" class="bg-primary-600 hover:bg-primary-700 text-white px-4 py-2 rounded-lg font-medium transition-all duration-200 flex items-center gap-2" onclick="addArrayItem('THINKING_MODELS')">
+                                <i class="fas fa-plus"></i> 添加模型
+                            </button>
+                        </div>
+                        <small class="text-gray-500 mt-1 block">用于“思考过程”的模型列表</small>
+                    </div>
+
+                    <!-- 思考模型预算映射 -->
+                    <div class="mb-6">
+                        <label for="THINKING_BUDGET_MAP" class="block font-semibold mb-2 text-gray-700">思考模型预算映射</label>
+                        <div class="bg-white rounded-lg border border-gray-200 p-4 mb-2 space-y-3" id="THINKING_BUDGET_MAP_container">
+                            <!-- 键值对将在这里动态添加 -->
+                            <div class="text-gray-500 text-sm italic">请先在上方添加思考模型，然后在此处配置预算。</div>
+                        </div>
+                        <!-- 移除添加预算映射按钮 -->
+                        <!-- <div class="flex justify-end">
+                            <button type="button" class="bg-primary-600 hover:bg-primary-700 text-white px-4 py-2 rounded-lg font-medium transition-all duration-200 flex items-center gap-2" id="addBudgetMapItemBtn">
+                                <i class="fas fa-plus"></i> 添加预算映射
+                            </button>
+                        </div> -->
+                        <small class="text-gray-500 mt-1 block">为每个思考模型设置预算（整数，最大值 24576），此项与上方模型列表自动关联。</small>
+                    </div>
                 </div>
-                
+
                 <!-- 图像生成相关配置 -->
                 <div class="config-section bg-white bg-opacity-70 rounded-xl p-6 mb-6 shadow-lg" id="image-section">
                     <h2 class="text-xl font-bold mb-6 pb-3 border-b border-gray-200 flex items-center gap-2">

app/templates/keys_status.html

@@ -374,6 +374,10 @@
                                         <i class="fas fa-copy"></i>
                                         复制
                                     </button>
+                                    <button class="flex items-center gap-1 bg-purple-500 hover:bg-purple-600 text-white px-3 py-1.5 rounded-lg text-sm font-medium transition-all duration-200" onclick="showKeyUsageDetails('{{ key }}')">
+                                        <i class="fas fa-chart-pie"></i>
+                                        详情
+                                    </button>
                                 </div>
                             </div>
                         </li>
@@ -443,6 +447,10 @@
                                         <i class="fas fa-copy"></i>
                                         复制
                                     </button>
+                                    <button class="flex items-center gap-1 bg-purple-500 hover:bg-purple-600 text-white px-3 py-1.5 rounded-lg text-sm font-medium transition-all duration-200" onclick="showKeyUsageDetails('{{ key }}')">
+                                        <i class="fas fa-chart-pie"></i>
+                                        详情
+                                    </button>
                                 </div>
                             </div>
                         </li>
@@ -564,6 +572,30 @@
             </div>
         </div>
     </div>
+
+   <!-- 密钥使用详情模态框 -->
+   <div id="keyUsageDetailsModal" class="fixed inset-0 bg-black bg-opacity-50 flex items-center justify-center z-50 hidden">
+       <div class="bg-white rounded-lg p-6 shadow-xl max-w-lg w-full animate-fade-in"> <!-- Adjusted max-width -->
+           <div class="flex items-center justify-between mb-4 border-b pb-3">
+               <h3 class="text-xl font-semibold text-gray-800" id="keyUsageDetailsModalTitle">密钥请求详情</h3>
+               <button onclick="closeKeyUsageDetailsModal()" class="text-gray-500 hover:text-gray-700 focus:outline-none text-xl">
+                   <i class="fas fa-times"></i>
+               </button>
+           </div>
+           <div id="keyUsageDetailsContent" class="mb-6 max-h-[50vh] overflow-y-auto pr-2"> <!-- Adjusted max-height -->
+               <!-- 详细数据将加载到这里 -->
+               <div class="text-center py-10">
+                    <i class="fas fa-spinner fa-spin text-primary-600 text-3xl"></i>
+                    <p class="text-gray-500 mt-2">加载中...</p>
+               </div>
+           </div>
+           <div class="flex justify-end pt-4 border-t">
+               <button onclick="closeKeyUsageDetailsModal()" class="px-5 py-2 bg-gray-200 hover:bg-gray-300 text-gray-800 rounded-lg transition-colors text-sm font-medium">
+                   关闭
+               </button>
+           </div>
+       </div>
+   </div>
     
     <!-- Footer is now in base.html -->
     

requirements.txt

@@ -17,3 +17,5 @@ aiomysql
 databases
 python-dotenv
 apscheduler # 添加定时任务库
+
+packaging