fix: 修复 error_logs.html 中的脚本路径错误

- 删除了不再使用的 `app/static/js/auth.js` 文件。
- 修正了 `app/templates/error_logs.html` 中 `error_logs.js` 的脚本引用路径，移除了 `url_for` 函数调用，直接使用静态路径。

.env.example

@@ -1,15 +1,40 @@
+# MySQL数据库配置
+MYSQL_HOST=
+MYSQL_PORT=
+MYSQL_USER=
+MYSQL_PASSWORD=
+MYSQL_DATABASE=default_db
 API_KEYS=["AIzaSyxxxxxxxxxxxxxxxxxxx","AIzaSyxxxxxxxxxxxxxxxxxxx"]
 ALLOWED_TOKENS=["sk-123456"]
 # AUTH_TOKEN=sk-123456
-MODEL_SEARCH=["gemini-2.0-flash-exp","gemini-2.0-pro-exp"]
-TOOLS_CODE_EXECUTION_ENABLED=true
+TEST_MODEL=gemini-1.5-flash
+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"]
+TOOLS_CODE_EXECUTION_ENABLED=false
 SHOW_SEARCH_LINK=true
 SHOW_THINKING_PROCESS=true
 BASE_URL=https://generativelanguage.googleapis.com/v1beta
 MAX_FAILURES=10
+MAX_RETRIES=3
+CHECK_INTERVAL_HOURS=1
+TIMEZONE=Asia/Shanghai
+# 请求超时时间（秒）
+TIME_OUT=300
 #########################image_generate 相关配置###########################
 PAID_KEY=AIzaSyxxxxxxxxxxxxxxxxxxx
 CREATE_IMAGE_MODEL=imagen-3.0-generate-002
 UPLOAD_PROVIDER=smms
 SMMS_SECRET_TOKEN=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
+PICGO_API_KEY=xxxx
+CLOUDFLARE_IMGBED_URL=https://xxxxxxx.pages.dev/upload
+CLOUDFLARE_IMGBED_AUTH_CODE=xxxxxxxxx
+##########################################################################
+#########################stream_optimizer 相关配置########################
+STREAM_OPTIMIZER_ENABLED=false
+STREAM_MIN_DELAY=0.016
+STREAM_MAX_DELAY=0.024
+STREAM_SHORT_TEXT_THRESHOLD=10
+STREAM_LONG_TEXT_THRESHOLD=50
+STREAM_CHUNK_SIZE=5
 ##########################################################################

.github/workflows/docker-publish.yml

@@ -2,8 +2,6 @@ name: Docker Image CI
 
 on:
   push:
-    # branches: [ "main" ]
-    tags: [ 'v*.*.*' ]
   pull_request:
     branches: [ "main" ]
 
@@ -43,20 +41,30 @@ jobs:
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           tags: |
-            type=raw,value=latest,enable={{is_default_branch}}
+            # https://github.com/docker/metadata-action/tree/v5/?tab=readme-ov-file#semver
+            # Event: push,     Ref: refs/head/main,       Tags: main
+            # Event: push tag, Ref: refs/tags/v1.2.3,     Tags: 1.2.3, 1.2, 1, latest
+            # Event: push tag, Ref: refs/tags/v2.0.8-rc1, Tags: 2.0.8-rc1
+            type=ref,event=branch
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
-            type=sha,format=long
+            type=semver,pattern={{major}}
           labels: |
             org.opencontainers.image.description=OpenAI API Compatible Server
             org.opencontainers.image.source=${{ github.event.repository.html_url }}
 
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v5
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Build and push
+        uses: docker/build-push-action@v6
         with:
+          file: Dockerfile
           context: .
+          platforms: linux/amd64,linux/arm64
           push: ${{ github.event_name != 'pull_request' }}
+          load: false
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          cache-from: type=gha,scope=${{ github.workflow }}
+          cache-to: type=gha,scope=${{ github.workflow }}

.github/workflows/release.yml

@@ -6,9 +6,10 @@ on:
       - 'v*' # 当推送以 "v" 开头的标签时触发（如 v1.0.0, v2.1.0）
 
 jobs:
-  release:
+  update-release-draft:
     permissions:
-      contents: write    # 添加写入权限
+      contents: write
+      pull-requests: write
     runs-on: ubuntu-latest
     steps:
       # Step 1: 检出代码库

Dockerfile

@@ -3,15 +3,16 @@ FROM python:3.10-slim
 WORKDIR /app
 
 # 复制所需文件到容器中
-COPY ./app /app/app
 COPY ./requirements.txt /app
 
 RUN pip install --no-cache-dir -r requirements.txt
+COPY ./app /app/app
 ENV API_KEYS='["your_api_key_1"]'
 ENV ALLOWED_TOKENS='["your_token_1"]'
 ENV BASE_URL=https://generativelanguage.googleapis.com/v1beta
-ENV TOOLS_CODE_EXECUTION_ENABLED=true
-ENV MODEL_SEARCH='["gemini-2.0-flash-exp"]'
+ENV TOOLS_CODE_EXECUTION_ENABLED=false
+ENV IMAGE_MODELS='["gemini-2.0-flash-exp"]'
+ENV SEARCH_MODELS='["gemini-2.0-flash-exp","gemini-2.0-pro-exp"]'
 
 # Expose port
 EXPOSE 8000

README.md

@@ -1,144 +1,74 @@
-# 🚀 FastAPI OpenAI (Gemini) 代理服务
+# Gemini Balance - Gemini API 代理和负载均衡器
 
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python](https://img.shields.io/badge/Python-3.9%2B-blue.svg)](https://www.python.org/)
+[![FastAPI](https://img.shields.io/badge/FastAPI-0.100%2B-green.svg)](https://fastapi.tiangolo.com/)
+[![Uvicorn](https://img.shields.io/badge/Uvicorn-running-purple.svg)](https://www.uvicorn.org/)
 
-## 📝 项目简介
+## 项目简介
 
-本项目是一个基于 FastAPI 框架开发的高性能、易于部署的Gemini OpenAI兼容 和 Gemini API 代理服务。它不仅兼容 OpenAI 的 API 接口，还支持 Google 的 Gemini 原生接口。该代理服务内置了多 API Key 轮询、负载均衡、自动重试、访问控制（Bearer Token 认证）、流式响应等功能，旨在简化 AI 应用的开发和部署流程。
+Gemini Balance 是一个基于 Python FastAPI 构建的应用程序，旨在提供 Google Gemini API 的代理和负载均衡功能。它允许您管理多个 Gemini API Key，并通过简单的配置实现 Key 的轮询、认证、模型过滤和状态监控。此外，项目还集成了图像生成和多种图床上传功能，并支持 OpenAI API 格式的代理。
 
-**核心功能与优势:**
+**项目结构:**
 
-- **多协议支持**: 无缝切换 OpenAI兼容 和 Gemini 协议。
-- **智能 API Key 管理**: 自动轮询多个 API Key，实现负载均衡和故障转移。
-- **安全访问控制**: 使用 Bearer Token 进行身份验证，保护 API 访问。
-- **流式响应支持**: 提供实时的流式数据传输，提升用户体验。
-- **内置工具支持**: 支持代码执行和 Google 搜索等工具, 丰富模型功能 (可选)。
-- **灵活配置**: 通过环境变量或 `.env` 文件轻松配置。
-- **易于部署**: 提供 Docker 一键部署，也支持手动部署。
-- **健康检查**: 提供健康检查接口，方便监控服务状态。
-- **图片生成支持**: 支持使用OpenAI的DALL-E模型生成图片
+```plaintext
+app/
+├── config/       # 配置管理
+├── core/         # 核心应用逻辑 (FastAPI 实例创建, 中间件等)
+├── database/     # 数据库模型和连接
+├── domain/       # 业务领域对象 (可选)
+├── exception/    # 自定义异常
+├── handler/      # 请求处理器 (可选, 或在 router 中处理)
+├── log/          # 日志配置
+├── main.py       # 应用入口
+├── middleware/   # FastAPI 中间件
+├── router/       # API 路由 (Gemini, OpenAI, 状态页等)
+├── scheduler/    # 定时任务 (如 Key 状态检查)
+├── service/      # 业务逻辑服务 (聊天, Key 管理, 统计等)
+├── static/       # 静态文件 (CSS, JS)
+├── templates/    # HTML 模板 (如 Key 状态页)
+├── utils/        # 工具函数
+```
 
-## 🛠️ 技术栈
+## ✨ 功能亮点
 
-- **FastAPI**: 高性能 Web 框架。
-- **Python 3.9+**: 编程语言。
-- **Pydantic**: 数据验证和设置管理。
-- **httpx**: 异步 HTTP 客户端。
-- **uvicorn**: ASGI 服务器。
-- **Docker**: 容器化部署 (可选)。
+* **多 Key 负载均衡**: 支持配置多个 Gemini API Key (`API_KEYS`)，自动按顺序轮询使用，提高可用性和并发能力。
+* **可视化配置即时生效**: 通过管理后台修改配置后，无需重启服务即可生效，切记要点击保存才会生效。
+![配置面板](files/image4.png)
+* **双协议API 兼容**: 同时支持 Gemini 和 OpenAI 格式的 CHAT API 请求转发。
+
+    ```palintext
+    openai baseurl `http://localhost:8000(/hf)/v1`
+    gemini baseurl `http://localhost:8000(/gemini)/v1beta`
+    ```
+
+* **支持图文对话和修改图片**: `IMAGE_MODELS`配置哪个模型可以图文对话和修图的功能，实际调用的时候，用 `配置模型-image`这个模型名对话使用该功能。
+![对话生图](files/image6.png)
+![修改图片](files/image7.png)
+* **支持联网搜索**: 支持联网搜索，`SEARCH_MODELS`配置哪些模型可以联网搜索，实际调用的时候，用 `配置模型-search`这个模型名对话使用该功能
+![联网搜索](files/image8.png)
+* **Key 状态监控**: 提供 `/keys_status` 页面（需要认证），实时查看各 Key 的状态和使用情况。
+![监控面板](files/image.png)
+* **详细的日志记录**: 提供详细的错误日志，方便排查。
+![调用详情](files/image1.png)
+![日志列表](files/image2.png)
+![日志详情](files/image3.png)
+* **支持自定义gemini代理**: 支持自定义gemini代理，比如自行在deno或者cloudflare上搭建gemini代理
+* **openai画图接口兼容**: 将`imagen-3.0-generate-002`模型接口改造成openai画图接口，支持客户端调用。
+* **灵活的添加密钥方式**: 灵活的添加密钥方式，采用正则匹配`gemini_key`,密钥去重
+![添加密钥](files/image5.png)
+* **兼容openai格式embeddings接口**：完美适配openai格式的`embeddings`接口，可用于本地文档向量化。
+* **流式响应优化**: 可选的流式输出优化器 (`STREAM_OPTIMIZER_ENABLED`)，改善长文本流式响应的体验。
+* **失败重试与 Key 管理**: 自动处理 API 请求失败，进行重试 (`MAX_RETRIES`)，并在 Key 失效次数过多时自动禁用 (`MAX_FAILURES`)，定时检查恢复 (`CHECK_INTERVAL_HOURS`)。
+* **Docker 支持**: 支持AMD，ARM架构的docker部署，也可自行构建docker镜像。
+    >镜像地址: docker pull ghcr.io/snailyp/gemini-balance:latest
+* **模型列表自动维护**: 支持openai和gemini模型列表获取，与newapi自动获取模型列表完美兼容，无需手动填写。
+* **支持移除不使用的模型**: 默认提供的模型太多，很多用不上，可以通过`FILTERED_MODELS`过滤掉。
 
 ## 🚀 快速开始
 
-### 环境要求
+### 自行构建 Docker (推荐)
 
-- Python 3.9 或更高版本
-- Docker (可选，推荐用于生产环境)
-
-### 📦 安装与配置
-
-1. **克隆项目**:
-
-    ```bash
-    git clone https://github.com/snailyp/gemini-balance.git
-    cd gemini-balance
-    ```
-
-2. **安装依赖**:
-
-    ```bash
-    pip install -r requirements.txt
-    ```
-
-3. **配置**:
-
-    创建 `.env` 文件，并按以下分类配置环境变量：
-
-    ```env
-    # 基础配置
-    BASE_URL="https://generativelanguage.googleapis.com/v1beta"  # Gemini API 基础 URL，默认无需修改
-    MAX_FAILURES=3  # 允许单个key失败的次数，默认3次
-
-    # 认证与安全配置
-    API_KEYS=["your-gemini-api-key-1", "your-gemini-api-key-2"]  # Gemini API 密钥列表，用于负载均衡
-    ALLOWED_TOKENS=["your-access-token-1", "your-access-token-2"]  # 允许访问的 Token 列表
-    AUTH_TOKEN=""  # 超级管理员token，具有所有权限，默认使用 ALLOWED_TOKENS 的第一个
-
-    # 模型功能配置
-    MODEL_SEARCH=["gemini-2.0-flash-exp"]  # 支持搜索功能的模型列表
-    TOOLS_CODE_EXECUTION_ENABLED=false  # 是否启用代码执行工具，默认false
-    SHOW_SEARCH_LINK=true  # 是否在响应中显示搜索结果链接，默认true
-    SHOW_THINKING_PROCESS=true  # 是否显示模型思考过程，默认true
-
-    # 图片生成配置
-    PAID_KEY="your-paid-api-key"  # 付费版API Key，用于图片生成等高级功能
-    CREATE_IMAGE_MODEL="imagen-3.0-generate-002"  # 图片生成模型，默认使用imagen-3.0
-    
-    # 图片上传配置
-    UPLOAD_PROVIDER="smms"  # 图片上传提供商，目前支持smms
-    SMMS_SECRET_TOKEN="your-smms-token"  # SM.MS图床的API Token
-    ```
-
-   ### 配置说明
-
-   #### 基础配置
-
-    - `BASE_URL`: Gemini API 的基础 URL
-      - 默认值: `https://generativelanguage.googleapis.com/v1beta`
-      - 说明: 通常无需修改，除非 API 地址发生变化
-    - `MAX_FAILURES`: API Key 允许的最大失败次数
-      - 默认值: `3`
-      - 说明: 超过此次数后，Key 将被暂时标记为无效
-
-   #### 认证与安全配置
-
-    - `API_KEYS`: Gemini API 密钥列表
-      - 格式: JSON 数组字符串
-      - 用途: 支持多个 Key 轮询，实现负载均衡
-      - 建议: 至少配置 2 个 Key 以保证服务可用性
-    - `ALLOWED_TOKENS`: 访问令牌列表
-      - 格式: JSON 数组字符串
-      - 用途: 用于客户端认证
-      - 安全提示: 请使用足够复杂的令牌
-    - `AUTH_TOKEN`: 超级管理员令牌
-      - 可选配置，留空则使用 ALLOWED_TOKENS 的第一个
-      - 具有查看 API Key 状态等特权操作权限
-
-   #### 模型功能配置
-
-    - `MODEL_SEARCH`: 搜索功能支持的模型
-      - 默认值: `["gemini-2.0-flash-exp"]`
-      - 说明: 仅列表中的模型可使用搜索功能
-    - `TOOLS_CODE_EXECUTION_ENABLED`: 代码执行功能
-      - 默认值: `false`
-      - 安全提示: 生产环境建议禁用
-    - `SHOW_SEARCH_LINK`: 搜索结果链接显示
-      - 默认值: `true`
-      - 用途: 控制搜索结果中是否包含原始链接
-    - `SHOW_THINKING_PROCESS`: 思考过程显示
-      - 默认值: `true`
-      - 用途: 显示模型的推理过程，便于调试
-
-   #### 图片生成配置
-
-    - `PAID_KEY`: 付费版 API Key
-      - 用途: 用于图片生成等高级功能
-      - 说明: 需要单独申请的付费版 Key
-    - `CREATE_IMAGE_MODEL`: 图片生成模型
-      - 默认值: `imagen-3.0-generate-002`
-      - 说明: 当前支持的最新图片生成模型
-
-   #### 图片上传配置
-
-    - `UPLOAD_PROVIDER`: 图片上传服务提供商
-      - 默认值: `smms`
-      - 说明: 目前支持 SM.MS 图床
-    - `SMMS_SECRET_TOKEN`: SM.MS API Token
-      - 用途: 用于图片上传到 SM.MS 图床
-      - 获取方式: 需要在 SM.MS 官网注册并获取
-
-### ▶️ 运行
-
-#### 使用 Docker (推荐)
+#### a) dockerfile构建
 
 1. **构建镜像**:
 
@@ -152,265 +82,132 @@
     docker run -d -p 8000:8000 --env-file .env gemini-balance
     ```
 
-    - `-d`: 后台运行。
-    - `-p 8000:8000`: 将容器的 8000 端口映射到主机的 8000 端口。
-    - `--env-file .env`: 使用 `.env` 文件设置环境变量。
+    * `-d`: 后台运行。
+    * `-p 8000:8000`: 将容器的 8000 端口映射到主机的 8000 端口。
+    * `--env-file .env`: 使用 `.env` 文件设置环境变量。
 
-#### 手动运行
+#### b) 用现有的docker镜像部署
 
-```bash
-uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
-```
+1. **拉取镜像**:
 
-- `--reload`: 开启热重载，方便开发调试 (生产环境不建议开启)。
+   ```bash
+   docker pull ghcr.io/snailyp/gemini-balance:latest
+   ```
 
-## 🔌 API 接口
+2. **运行容器**:
 
-### 认证
+   ```bash
+   docker run -d -p 8000:8000 --env-file .env ghcr.io/snailyp/gemini-balance:latest
+   ```
 
-所有 API 请求都需要在 Header 中添加 `Authorization` 字段，值为 `Bearer <your-token>`，其中 `<your-token>` 需要替换为你在 `.env` 文件中配置的 `ALLOWED_TOKENS` 中的一个或者 `AUTH_TOKEN`。
+   * `-d`: 后台运行。
+   * `-p 8000:8000`: 将容器的 8000 端口映射到主机的 8000 端口 (根据需要调整)。
+   * `--env-file .env`: 使用 `.env` 文件设置环境变量 (确保 `.env` 文件存在于执行命令的目录)。
 
-### API 路由
+### 本地运行 (适用于开发和测试)
 
-本服务提供两种API路由：
+如果您想在本地直接运行源代码进行开发或测试，请按照以下步骤操作：
 
-1. **OpenAI 兼容路由** (推荐)
-   - 基础路径: `/v1`
-   - 完全兼容OpenAI API格式
-   - 支持所有Gemini模型
+1. **确保已完成准备工作**:
+    * 克隆仓库到本地。
+    * 安装 Python 3.9 或更高版本。
+    * 在项目根目录下创建并配置好 `.env` 文件 (参考前面的“配置环境变量”部分)。
+    * 安装项目依赖：
 
-2. **Gemini 原生路由**
-   - 基础路径: `/gemini/v1beta` 或 `/v1beta`
-   - 遵循Google原生API格式
-   - 适用于需要直接使用Gemini API的场景
+        ```bash
+        pip install -r requirements.txt
+        ```
 
-### OpenAI兼容路由
+2. **启动应用**:
+    在项目根目录下运行以下命令：
 
-#### 获取模型列表
-
-- **URL**: `/v1/models`
-- **Method**: `GET`
-- **Header**: `Authorization: Bearer <your-token>`
-- **Response**: 返回支持的所有模型列表，包括最新的`gemini-2.0-flash-exp-search`等模型
-
-#### 聊天补全 (Chat Completions)
-
-- **URL**: `/v1/chat/completions`
-- **Method**: `POST`
-- **Header**: `Authorization: Bearer <your-token>`
-- **Body** (JSON):
-
-    ```json
-    {
-        "messages": [
-            {
-                "role": "user",
-                "content": "你好"
-            }
-        ],
-        "model": "gemini-1.5-flash-002",
-        "temperature": 0.7,
-        "stream": false,
-        "tools": [],
-        "max_tokens": 8192,
-        "stop": [],
-        "top_p": 0.9,
-        "top_k": 40
-    }
+    ```bash
+    uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
     ```
 
-  - `messages`: 消息列表，格式与 OpenAI API 相同
-  - `model`: 模型名称，支持所有Gemini模型，包括:
-    - `gemini-1.5-flash-002`: 快速响应模型
-    - `gemini-2.0-flash-exp`: 实验性快速响应模型
-    - `gemini-2.0-flash-exp-search`: 支持搜索功能的实验性模型
-  - `stream`: 是否开启流式响应，`true` 或 `false`
-  - `tools`: 使用的工具列表
-  - 其他参数：与 OpenAI API 兼容的参数，如 `temperature`, `max_tokens` 等
+    * `app.main:app`: 指定 FastAPI 应用实例的位置 (`app` 模块中的 `main.py` 文件里的 `app` 对象)。
+    * `--host 0.0.0.0`: 使应用可以从本地网络中的任何 IP 地址访问。
+    * `--port 8000`: 指定应用监听的端口号 (您可以根据需要修改)。
+    * `--reload`: 启用自动重载功能。当您修改代码时，服务会自动重启，非常适合开发环境 (生产环境请移除此选项)。
 
-### Gemini原生路由
+3. **访问应用**:
+    应用启动后，您可以通过浏览器或 API 工具访问 `http://localhost:8000` (或您指定的主机和端口)。
 
-#### 获取模型列表
+### 完整配置项列表
 
-- **URL**: `/gemini/v1beta/models` 或 `/v1beta/models`
-- **Method**: `GET`
-- **Header**: `Authorization: Bearer <your-token>`
+| 配置项                       | 说明                                                     | 默认值                             |
+| :--------------------------- | :------------------------------------------------------- | :---------------------------------------------------- |
+| **数据库配置**               |                                                          |                                                       |
+| `MYSQL_HOST`                 | 必填，MySQL 数据库主机地址                               | `localhost`                                           |
+| `MYSQL_PORT`                 | 必填，MySQL 数据库端口                                   | `3306`                                                |
+| `MYSQL_USER`                 | 必填，MySQL 数据库用户名                                 | `your_db_user`                                        |
+| `MYSQL_PASSWORD`             | 必填，MySQL 数据库密码                                   | `your_db_password`                                    |
+| `MYSQL_DATABASE`             | 必填，MySQL 数据库名称                                   | `defaultdb`                                   |
+| **API 相关配置**             |                                                          |                                                       |
+| `API_KEYS`                   | 必填，Gemini API 密钥列表，用于负载均衡                        | `["your-gemini-api-key-1", "your-gemini-api-key-2"]`  |
+| `ALLOWED_TOKENS`             | 必填，允许访问的 Token 列表                                    | `["your-access-token-1", "your-access-token-2"]`      |
+| `AUTH_TOKEN`                 | 可选，超级管理员token，具有所有权限，不填默认使用 ALLOWED_TOKENS 的第一个 | `""`                                                  |
+| `TEST_MODEL`                 | 可选，用于测试密钥是否可用的模型名                             | `gemini-1.5-flash`                                    |
+| `IMAGE_MODELS`               | 可选，支持绘图功能的模型列表                                   | `["gemini-2.0-flash-exp"]`                            |
+| `SEARCH_MODELS`              | 可选，支持搜索功能的模型列表                                   | `["gemini-2.0-flash-exp"]`                            |
+| `FILTERED_MODELS`            | 可选，被禁用的模型列表                                         | `["gemini-1.0-pro-vision-latest", ...]`               |
+| `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`                                                |
+| `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`                                                   |
+| `CHECK_INTERVAL_HOURS`       | 可选，检查禁用 Key 是否恢复的时间间隔 (小时)                   | `1`                                                   |
+| `TIMEZONE`                   | 可选，应用程序使用的时区                                       | `Asia/Shanghai`                                       |
+| `TIME_OUT`                   | 可选，请求超时时间 (秒)                                        | `300`                                                 |
+| **图像生成相关**             |                                                          |                                                       |
+| `PAID_KEY`                   | 可选，付费版API Key，用于图片生成等高级功能                    | `your-paid-api-key`                                   |
+| `CREATE_IMAGE_MODEL`         | 可选，图片生成模型                                             | `imagen-3.0-generate-002`                             |
+| `UPLOAD_PROVIDER`            | 可选，图片上传提供商: `smms`, `picgo`, `cloudflare_imgbed`     | `smms`                                                |
+| `SMMS_SECRET_TOKEN`          | 可选，SM.MS图床的API Token                                     | `your-smms-token`                                     |
+| `PICGO_API_KEY`              | 可选，PicoGo图床的API Key                                      | `your-picogo-apikey`                                  |
+| `CLOUDFLARE_IMGBED_URL`      | 可选，CloudFlare 图床上传地址                                  | `https://xxxxxxx.pages.dev/upload`                    |
+| `CLOUDFLARE_IMGBED_AUTH_CODE`| 可选，CloudFlare图床的鉴权key                                  | `your-cloudflare-imgber-auth-code`                    |
+| **流式优化器相关**           |                                                          |                                                       |
+| `STREAM_OPTIMIZER_ENABLED`   | 可选，是否启用流式输出优化                                     | `false`                                               |
+| `STREAM_MIN_DELAY`           | 可选，流式输出最小延迟                                         | `0.016`                                               |
+| `STREAM_MAX_DELAY`           | 可选，流式输出最大延迟                                         | `0.024`                                               |
+| `STREAM_SHORT_TEXT_THRESHOLD`| 可选，短文本阈值                                               | `10`                                                  |
+| `STREAM_LONG_TEXT_THRESHOLD` | 可选，长文本阈值                                               | `50`                                                  |
+| `STREAM_CHUNK_SIZE`          | 可选，流式输出块大小                                           | `5`                                                   |
 
-#### 生成内容
+## ⚙️ API 端点
 
-- **URL**: `/gemini/v1beta/models/{model_name}:generateContent`
-- **Method**: `POST`
-- **Header**: `Authorization: Bearer <your-token>`
+以下是服务提供的主要 API 端点：
 
-#### 流式生成内容
+### Gemini API 相关 (`(/gemini)/v1beta`)
 
-- **URL**: `/gemini/v1beta/models/{model_name}:streamGenerateContent`
-- **Method**: `POST`
-- **Header**: `Authorization: Bearer <your-token>`
+* `GET /models`: 列出可用的 Gemini 模型。
+* `POST /models/{model_name}:generateContent`: 使用指定的 Gemini 模型生成内容。
+* `POST /models/{model_name}:streamGenerateContent`: 使用指定的 Gemini 模型流式生成内容。
 
-### 获取词向量 (Embeddings)
+### OpenAI API 相关 (`(/hf)/v1`)
 
-- **URL**: `/v1/embeddings`
-- **Method**: `POST`
-- **Header**: `Authorization: Bearer <your-token>`
-- **Body** (JSON):
-
-    ```json
-    {
-        "input": "你的文本",
-        "model": "text-embedding-004"
-    }
-    ```
-
-  - `input`: 输入文本。
-  - `model`: 模型名称。
-
-### 健康检查
-
-- **URL**: `/health`
-- **Method**: `GET`
-
-### Web界面功能
-
-#### 验证页面
-
-- **URL**: `/auth`
-- **说明**: 提供了一个简洁的Web界面用于验证访问令牌
-- **功能**:
-  - 美观的用户界面，支持响应式设计
-  - 安全的令牌验证机制
-  - 错误提示功能
-  - 支持移动端访问
-
-#### API密钥状态管理
-
-- **URL**: `/v1/keys/list`
-- **Method**: `GET`
-- **Header**: `Authorization: Bearer <your-auth-token>`
-- **说明**:
-  - 只有使用 `AUTH_TOKEN` 才能访问此接口
-  - 提供了可视化的Web界面展示API密钥状态
-  - 支持查看有效和无效的API密钥列表
-  - 显示每个密钥的失败次数统计
-  - 提供一键复制功能（支持复制单个密钥或批量复制）
-  - 实时显示密钥总数统计
-
-### 图片生成 (Image Generation)
-
-- **URL**: `/v1/images/generations`
-- **Method**: `POST`
-- **Header**: `Authorization: Bearer <your-auth-token>`
-- **说明**: Body示例和参数说明
-
-    ```json
-    {
-    "model": "dall-e-3",
-    "prompt": "{n:2} {ratio:16:9} 汉服美女",
-    "n": 1,
-    "size": "1024x1024"
-    }
-    ```
-
-    **Prompt参数说明:**
-
-    prompt支持通过特殊标记来控制生成参数：
-
-    1. 图片数量控制:
-       - 格式: `{n:数量}`
-       - 示例: `{n:2} 一只可爱的猫` - 生成2张图片
-       - 取值范围: 1-4
-       - 说明: 如果在prompt中指定了n，将覆盖请求body中的n参数
-
-    2. 图片比例控制:
-       - 格式: `{ratio:宽:高}`
-       - 示例: `{ratio:16:9} 一片森林` - 生成16:9比例的图片
-       - 支持的比例: "1:1"、"3:4"、"4:3"、"9:16"、"16:9"
-       - 说明: 如果指定了size参数，将优先使用size对应的比例
-
-    3. 参数组合:
-       - 示例: `{n:2} {ratio:16:9} 一片美丽的森林` - 生成2张16:9比例的图片
-       - 说明: 这些参数标记会自动从prompt中移除，不会影响实际的图片生成提示词
-
-    > 注意：n的取值范围[1,4], ratio取值范围"1:1"、"3:4"、"4:3"、"9:16" 和 "16:9"
-
-## 📚 代码结构
-
-```plaintext
-.
-├── app/
-│   ├── api/                # API 路由
-│   │   ├── gemini_routes.py   # Gemini 模型路由
-│   │   └── openai_routes.py   # OpenAI 兼容路由
-│   ├── core/               # 核心组件
-│   │   ├── config.py         # 配置管理
-│   │   ├── logger.py         # 日志配置
-│   │   └── security.py       # 安全认证
-│   ├── middleware/         # 中间件
-│   │   └── request_logging_middleware.py  # 请求日志中间件
-│   ├── schemas/            # 数据模型
-│   │   ├── gemini_models.py  # Gemini 原始请求/响应模型
-│   │   └── openai_models.py  # OpenAI 兼容请求/响应模型
-│   ├── services/           # 服务层
-│   │   ├── chat/           # 聊天相关服务
-│   │   │   ├── api_client.py # API 客户端
-│   │   │   ├── message_converter.py # 消息转换器
-│   │   │   ├── response_handler.py # 响应处理器
-│   │   │   └── retry_handler.py #重试处理器
-│   │   ├── gemini_chat_service.py   # Gemini 原始聊天服务
-│   │   ├── openai_chat_service.py   # OpenAI 兼容聊天服务
-│   │   ├── embedding_service.py # 向量服务
-│   │   ├── key_manager.py    # API Key 管理
-│   │   └── model_service.py  # 模型服务
-│   └── main.py              # 主程序入口
-├── Dockerfile              # Dockerfile
-├── requirements.txt       # 项目依赖
-└── README.md               # 项目说明
-```
-
-## 🔒 安全性
-
-- **API Key 轮询**: 自动轮换 API Key，提高可用性和负载均衡。
-- **Bearer Token 认证**: 保护 API 端点，防止未经授权的访问。
-- **请求日志记录**: 记录详细的请求信息，便于调试和审计 (可选，通过取消 `app.add_middleware(RequestLoggingMiddleware)` 的注释来启用)。
-- **自动重试**: 在 API 请求失败时自动重试，提高服务的稳定性。
+* `GET /v1/models`: 列出可用的 OpenAI 模型。
+* `POST /v1/chat/completions`: 通过 OpenAI API 进行聊天补全。
+* `POST /v1/images/generations`: 通过 OpenAI API 生成图像。
+* `POST /v1/embeddings`: 通过 OpenAI API 创建文本嵌入。
 
 ## 🤝 贡献
 
-欢迎任何形式的贡献！如果你发现 bug、有新功能建议或者想改进代码，请随时提交 Issue 或 Pull Request。
+欢迎提交 Pull Request 或 Issue。
 
-1. Fork 本项目。
-2. 创建你的特性分支 (`git checkout -b feature/AmazingFeature`)。
-3. 提交你的改动 (`git commit -m 'Add some AmazingFeature'`)。
-4. 推送到你的分支 (`git push origin feature/AmazingFeature`)。
-5. 创建一个新的 Pull Request。
+## 🙏 感谢贡献者
 
-## ❓ 常见问题解答 (FAQ)
+感谢所有为本项目做出贡献的开发者！
 
-**Q: 如何获取 Gemini API Key？**
-
-A: 请参考 Gemini API 的官方文档，申请 API Key。
-
-**Q: 如何配置多个 API Key？**
-
-A: 在 `.env` 文件的 `API_KEYS` 变量中，用列表的形式添加多个 Key，例如：`API_KEYS=["key1", "key2", "key3"]`。
-
-**Q: 为什么我的 API Key 总是失败？**
-
-A: 请检查以下几点：
-
-- API Key 是否正确。
-- API Key 是否已过期或被禁用。
-- 是否超出了 API Key 的速率限制或配额。
-- 网络连接是否正常。
-
-**Q: 如何启用流式响应？**
-
-A: 在请求的 Body 中，将 `stream` 参数设置为 `true` 即可。
-
-**Q: 如何启用代码执行工具？**
-
-A: 在 `.env` 文件的 `TOOLS_CODE_EXECUTION_ENABLED` 变量中, 设置为 `true` 即可。
+<a href="https://github.com/toddyoe" title="toddyoe"><img src="https://avatars.githubusercontent.com/u/167494546?s=64&v=4" width="64" height="64"></a>
+<a href="https://github.com/yangtb2024" title="yangtb2024"><img src="https://avatars.githubusercontent.com/u/164613316?s=64&v=4" width="64" height="64"></a>
+<a href="https://github.com/cr-zhichen" title="cr-zhichen"><img src="https://avatars.githubusercontent.com/u/57337795?s=64&v=4" width="64" height="64"></a>
+<a href="https://github.com/BetterAndBetterII" title="BetterAndBetterII"><img src="https://avatars.githubusercontent.com/u/141388234?s=96&v=4" width="64" height="64"></a>
+<a href="https://github.com/yanhao98" title="yanhao98"><img src="https://avatars.githubusercontent.com/u/37316281?s=64&v=4" width="64" height="64"></a>
+<a href="https://github.com/Haoyu99" title="Haoyu99"><img src="https://avatars.githubusercontent.com/u/93185981?s=60&v=4" width="64" height="64"></a>
 
 ## 📄 许可证
 
-本项目采用 MIT 许可证。有关详细信息，请参阅 [LICENSE](LICENSE) 文件 (你需要创建一个 LICENSE 文件)。
+本项目采用 MIT 许可证。

app/api/gemini_routes.py

@@ -1,104 +0,0 @@
-from fastapi import APIRouter, Depends, HTTPException
-from fastapi.responses import StreamingResponse
-
-from app.core.config import settings
-from app.core.logger import get_gemini_logger
-from app.core.security import SecurityService
-from app.schemas.gemini_models import GeminiRequest
-from app.services.gemini_chat_service import GeminiChatService
-from app.services.key_manager import KeyManager, get_key_manager_instance
-from app.services.model_service import ModelService
-from app.services.chat.retry_handler import RetryHandler
-
-router = APIRouter(prefix="/gemini/v1beta")
-router_v1beta = APIRouter(prefix="/v1beta")
-logger = get_gemini_logger()
-
-# 初始化服务
-security_service = SecurityService(settings.ALLOWED_TOKENS, settings.AUTH_TOKEN)
-
-async def get_key_manager():
-    return await get_key_manager_instance()
-
-async def get_next_working_key_wrapper(key_manager: KeyManager = Depends(get_key_manager)):
-    return await key_manager.get_next_working_key()
-
-model_service = ModelService(settings.MODEL_SEARCH)
-
-
-@router.get("/models")
-@router_v1beta.get("/models")
-async def list_models(_=Depends(security_service.verify_key),
-    key_manager: KeyManager = Depends(get_key_manager)):
-    """获取可用的Gemini模型列表"""
-    logger.info("-" * 50 + "list_gemini_models" + "-" * 50)
-    logger.info("Handling Gemini models list request")
-    api_key = await key_manager.get_next_working_key()
-    logger.info(f"Using API key: {api_key}")
-    models_json = model_service.get_gemini_models(api_key)
-    models_json["models"].append({"name": "models/gemini-2.0-flash-exp-search", "version": "2.0",
-                                  "displayName": "Gemini 2.0 Flash Search Experimental",
-                                  "description": "Gemini 2.0 Flash Search Experimental", "inputTokenLimit": 32767,
-                                  "outputTokenLimit": 8192,
-                                  "supportedGenerationMethods": ["generateContent", "countTokens"], "temperature": 1,
-                                  "topP": 0.95, "topK": 64, "maxTemperature": 2})
-    return models_json
-
-
-@router.post("/models/{model_name}:generateContent")
-@router_v1beta.post("/models/{model_name}:generateContent")
-@RetryHandler(max_retries=3, key_manager=Depends(get_key_manager), key_arg="api_key")
-async def generate_content(
-        model_name: str,
-        request: GeminiRequest,
-        _=Depends(security_service.verify_goog_api_key),
-        api_key: str = Depends(get_next_working_key_wrapper),
-        key_manager: KeyManager = Depends(get_key_manager)
-):
-    chat_service = GeminiChatService(settings.BASE_URL, key_manager)
-    """非流式生成内容"""
-    logger.info("-" * 50 + "gemini_generate_content" + "-" * 50)
-    logger.info(f"Handling Gemini content generation request for model: {model_name}")
-    logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
-    logger.info(f"Using API key: {api_key}")
-
-    try:
-        response = chat_service.generate_content(
-            model=model_name,
-            request=request,
-            api_key=api_key
-        )
-        return response
-
-    except Exception as e:
-        logger.error(f"Chat completion failed after retries: {str(e)}")
-        raise HTTPException(status_code=500, detail="Chat completion failed") from e
-
-
-@router.post("/models/{model_name}:streamGenerateContent")
-@router_v1beta.post("/models/{model_name}:streamGenerateContent")
-@RetryHandler(max_retries=3, key_manager=Depends(get_key_manager), key_arg="api_key")
-async def stream_generate_content(
-        model_name: str,
-        request: GeminiRequest,
-        _=Depends(security_service.verify_goog_api_key),
-        api_key: str = Depends(get_next_working_key_wrapper),
-        key_manager: KeyManager = Depends(get_key_manager)
-):
-    chat_service = GeminiChatService(settings.BASE_URL, key_manager)
-    """流式生成内容"""
-    logger.info("-" * 50 + "gemini_stream_generate_content" + "-" * 50)
-    logger.info(f"Handling Gemini streaming content generation for model: {model_name}")
-    logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
-    logger.info(f"Using API key: {api_key}")
-
-    try:
-        response_stream = chat_service.stream_generate_content(
-            model=model_name,
-            request=request,
-            api_key=api_key
-        )
-        return StreamingResponse(response_stream, media_type="text/event-stream")
-
-    except Exception as e:
-        logger.error(f"Streaming request failed: {str(e)}")

app/config/config.py

@@ -0,0 +1,273 @@
+"""
+应用程序配置模块
+"""
+import datetime
+import json
+from typing import List, Any, Dict, Type
+
+from pydantic import ValidationError
+from pydantic_settings import BaseSettings
+from sqlalchemy import insert, update, select
+
+from app.core.constants import API_VERSION, DEFAULT_CREATE_IMAGE_MODEL, DEFAULT_FILTER_MODELS, DEFAULT_MODEL, DEFAULT_STREAM_CHUNK_SIZE, DEFAULT_STREAM_LONG_TEXT_THRESHOLD, DEFAULT_STREAM_MAX_DELAY, DEFAULT_STREAM_MIN_DELAY, DEFAULT_STREAM_SHORT_TEXT_THRESHOLD, DEFAULT_TIMEOUT, MAX_RETRIES
+from app.log.logger import get_config_logger
+# 延迟导入以避免循环依赖，仅在 sync_initial_settings 中使用
+# from app.database.connection import database
+# from app.database.models import Settings as SettingsModel
+# from app.database.services import get_all_settings # get_all_settings 可能不适合启动时调用，直接查询
+
+logger = get_config_logger()
+
+
+class Settings(BaseSettings):
+    """应用程序配置"""
+    # 数据库配置
+    MYSQL_HOST: str
+    MYSQL_PORT: int
+    MYSQL_USER: str
+    MYSQL_PASSWORD: str
+    MYSQL_DATABASE: str
+    
+    # API相关配置
+    API_KEYS: List[str]
+    ALLOWED_TOKENS: List[str]
+    BASE_URL: str = f"https://generativelanguage.googleapis.com/{API_VERSION}"
+    AUTH_TOKEN: str = ""
+    MAX_FAILURES: int = 3
+    TEST_MODEL: str = DEFAULT_MODEL
+    TIME_OUT: int = DEFAULT_TIMEOUT
+    MAX_RETRIES: int = MAX_RETRIES
+    
+    # 模型相关配置
+    SEARCH_MODELS: List[str] = ["gemini-2.0-flash-exp"]
+    IMAGE_MODELS: List[str] = ["gemini-2.0-flash-exp"]
+    FILTERED_MODELS: List[str] = DEFAULT_FILTER_MODELS
+    TOOLS_CODE_EXECUTION_ENABLED: bool = False
+    SHOW_SEARCH_LINK: bool = True
+    SHOW_THINKING_PROCESS: bool = True
+    
+    # 图像生成相关配置
+    PAID_KEY: str = ""
+    CREATE_IMAGE_MODEL: str = DEFAULT_CREATE_IMAGE_MODEL
+    UPLOAD_PROVIDER: str = "smms"
+    SMMS_SECRET_TOKEN: str = ""
+    PICGO_API_KEY: str = ""
+    CLOUDFLARE_IMGBED_URL: str = ""
+    CLOUDFLARE_IMGBED_AUTH_CODE: str = ""
+    
+    # 流式输出优化器配置
+    STREAM_OPTIMIZER_ENABLED: bool = False
+    STREAM_MIN_DELAY: float = DEFAULT_STREAM_MIN_DELAY
+    STREAM_MAX_DELAY: float = DEFAULT_STREAM_MAX_DELAY
+    STREAM_SHORT_TEXT_THRESHOLD: int = DEFAULT_STREAM_SHORT_TEXT_THRESHOLD
+    STREAM_LONG_TEXT_THRESHOLD: int = DEFAULT_STREAM_LONG_TEXT_THRESHOLD
+    STREAM_CHUNK_SIZE: int = DEFAULT_STREAM_CHUNK_SIZE
+
+    # 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
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        # 设置默认AUTH_TOKEN（如果未提供）
+        if not self.AUTH_TOKEN and self.ALLOWED_TOKENS:
+            self.AUTH_TOKEN = self.ALLOWED_TOKENS[0]
+
+# 创建全局配置实例
+settings = Settings()
+
+def _parse_db_value(key: str, db_value: str, target_type: Type) -> Any:
+    """尝试将数据库字符串值解析为目标 Python 类型"""
+    try:
+        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
+        elif target_type == bool:
+            return db_value.lower() in ('true', '1', 'yes', 'on')
+        elif target_type == int:
+            return int(db_value)
+        elif target_type == float:
+            return float(db_value)
+        else: # 默认为 str 或其他 pydantic 能处理的类型
+            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.")
+        return db_value # 解析失败则返回原始字符串
+
+async def sync_initial_settings():
+    """
+    应用启动时同步配置：
+    1. 从数据库加载设置。
+    2. 将数据库设置合并到内存 settings (数据库优先)。
+    3. 将最终的内存 settings 同步回数据库。
+    """
+    # 延迟导入以避免循环依赖和确保数据库连接已初始化
+    from app.database.connection import database
+    from app.database.models import Settings as SettingsModel
+
+    global settings
+    logger.info("Starting initial settings synchronization...")
+
+    if not database.is_connected:
+        try:
+            await database.connect()
+            logger.info("Database connection established for initial sync.")
+        except Exception as e:
+            logger.error(f"Failed to connect to database for initial settings sync: {e}. Skipping sync.")
+            return
+
+    try:
+        # 1. 从数据库加载设置
+        db_settings_raw: List[Dict[str, Any]] = []
+        try:
+            query = select(SettingsModel.key, SettingsModel.value)
+            results = await database.fetch_all(query)
+            db_settings_raw = [{"key": row["key"], "value": row["value"]} for row in results]
+            logger.info(f"Fetched {len(db_settings_raw)} settings from database.")
+        except Exception as e:
+            logger.error(f"Failed to fetch settings from database: {e}. Proceeding with environment/dotenv settings.")
+            # 即使数据库读取失败，也要继续执行，确保基于 env/dotenv 的配置能同步到数据库
+
+        db_settings_map: Dict[str, str] = {s['key']: s['value'] for s in db_settings_raw}
+
+        # 2. 将数据库设置合并到内存 settings (数据库优先)
+        updated_in_memory = False
+
+        for key, db_value in db_settings_map.items():
+            if hasattr(settings, key):
+                target_type = Settings.__annotations__.get(key)
+                if target_type:
+                    try:
+                        parsed_db_value = _parse_db_value(key, db_value, target_type)
+                        memory_value = getattr(settings, key)
+
+                        # 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):
+                                setattr(settings, key, parsed_db_value)
+                                logger.info(f"Updated setting '{key}' in memory from database value.")
+                                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.")
+
+                    except Exception as e:
+                        logger.error(f"Error processing database setting for key '{key}': {e}")
+            else:
+                 logger.warning(f"Database setting '{key}' not found in Settings model definition. Ignoring.")
+
+
+        # 如果内存中有更新，重新验证 Pydantic 模型（可选但推荐）
+        if updated_in_memory:
+            try:
+                # 重新加载以确保类型转换和验证
+                settings = Settings(**settings.model_dump())
+                logger.info("Settings object re-validated after merging database values.")
+            except ValidationError as e:
+                 logger.error(f"Validation error after merging database settings: {e}. Settings might be inconsistent.")
+
+
+        # 3. 将最终的内存 settings 同步回数据库
+        final_memory_settings = settings.model_dump()
+        settings_to_update: List[Dict[str, Any]] = []
+        settings_to_insert: List[Dict[str, Any]] = []
+        now = datetime.datetime.now(datetime.timezone.utc)
+
+        existing_db_keys = set(db_settings_map.keys())
+
+        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)
+            elif isinstance(value, bool):
+                db_value = str(value).lower()
+            else:
+                db_value = str(value)
+
+            data = {
+                'key': key,
+                'value': db_value,
+                'description': f"{key} configuration setting", # 默认描述
+                'updated_at': now
+            }
+
+            if key in existing_db_keys:
+                # 仅当值与数据库中的不同时才更新
+                if db_settings_map[key] != db_value:
+                    settings_to_update.append(data)
+            else:
+                # 如果键不在数据库中，则插入
+                data['created_at'] = now
+                settings_to_insert.append(data)
+
+        # 在事务中执行批量插入和更新
+        if settings_to_insert or settings_to_update:
+            try:
+                async with database.transaction():
+                    if settings_to_insert:
+                        # 获取现有描述以避免覆盖
+                        query_existing = select(SettingsModel.key, SettingsModel.description).where(SettingsModel.key.in_([s['key'] for s in settings_to_insert]))
+                        existing_desc = {row['key']: row['description'] for row in await database.fetch_all(query_existing)}
+                        for item in settings_to_insert:
+                            item['description'] = existing_desc.get(item['key'], item['description'])
+
+                        query_insert = insert(SettingsModel).values(settings_to_insert)
+                        await database.execute(query=query_insert)
+                        logger.info(f"Synced (inserted) {len(settings_to_insert)} settings to database.")
+
+                    if settings_to_update:
+                        # 获取现有描述以避免覆盖
+                        query_existing = select(SettingsModel.key, SettingsModel.description).where(SettingsModel.key.in_([s['key'] for s in settings_to_update]))
+                        existing_desc = {row['key']: row['description'] for row in await database.fetch_all(query_existing)}
+
+                        for setting_data in settings_to_update:
+                            setting_data['description'] = existing_desc.get(setting_data['key'], setting_data['description'])
+                            query_update = (
+                                update(SettingsModel)
+                                .where(SettingsModel.key == setting_data['key'])
+                                .values(
+                                    value=setting_data['value'],
+                                    description=setting_data['description'],
+                                    updated_at=setting_data['updated_at']
+                                )
+                            )
+                            await database.execute(query=query_update)
+                        logger.info(f"Synced (updated) {len(settings_to_update)} settings to database.")
+            except Exception as e:
+                logger.error(f"Failed to sync settings to database during startup: {str(e)}")
+        else:
+            logger.info("No setting changes detected between memory and database during initial sync.")
+
+    except Exception as e:
+        logger.error(f"An unexpected error occurred during initial settings sync: {e}")
+    finally:
+        if database.is_connected:
+             try:
+                 # Don't disconnect if it's managed elsewhere (e.g., FastAPI lifespan)
+                 # await database.disconnect()
+                 # logger.info("Database connection closed after initial sync.")
+                 pass # Assume connection lifecycle is managed by the application lifespan
+             except Exception as e:
+                 logger.error(f"Error disconnecting database after initial sync: {e}")
+
+    logger.info("Initial settings synchronization finished.")

app/core/application.py

@@ -0,0 +1,95 @@
+"""
+应用程序工厂模块，负责创建和配置FastAPI应用程序实例
+"""
+from contextlib import asynccontextmanager
+from fastapi import FastAPI
+from fastapi.staticfiles import StaticFiles
+
+from app.config.config import settings, sync_initial_settings
+from app.log.logger import get_application_logger
+from app.middleware.middleware import setup_middlewares
+from app.exception.exceptions import setup_exception_handlers
+from app.router.routes import setup_routers
+from app.service.key.key_manager import get_key_manager_instance
+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
+
+logger = get_application_logger()
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """
+    应用程序生命周期管理器
+    
+    Args:
+        app: FastAPI应用实例
+    """
+    # 启动事件
+    logger.info("Application starting up...")
+    try:
+        # 初始化数据库
+        initialize_database()
+        logger.info("Database initialized successfully")
+        
+        # 连接到数据库
+        await connect_to_db()
+        
+        # 同步初始配置（DB优先，然后同步回DB）
+        await sync_initial_settings()
+
+        # 初始化KeyManager (使用可能已从DB更新的settings)
+        await get_key_manager_instance(settings.API_KEYS)
+        logger.info("KeyManager initialized successfully")
+    except Exception as e:
+        logger.error(f"Failed to initialize application: {str(e)}")
+        raise
+
+    # 启动调度器
+    start_scheduler()
+    logger.info("Scheduler started successfully.")
+
+    yield  # 应用程序运行期间
+    
+    # 关闭事件
+    logger.info("Application shutting down...")
+    
+    # 停止调度器
+    stop_scheduler()
+    logger.info("Scheduler stopped.")
+
+    # 断开数据库连接
+    await disconnect_from_db()
+
+def create_app() -> FastAPI:
+    """
+    创建并配置FastAPI应用程序实例
+    
+    Returns:
+        FastAPI: 配置好的FastAPI应用程序实例
+    """
+    # 初始化应用程序
+    initialize_app()
+    
+    # 创建FastAPI应用
+    app = FastAPI(
+        title="Gemini Balance API",
+        description="Gemini API代理服务，支持负载均衡和密钥管理",
+        version="1.0.0",
+        lifespan=lifespan
+    )
+    
+    # 配置静态文件
+    app.mount("/static", StaticFiles(directory="app/static"), name="static")
+    
+    # 配置中间件
+    setup_middlewares(app)
+    
+    # 配置异常处理器
+    setup_exception_handlers(app)
+    
+    # 配置路由
+    setup_routers(app)
+    
+    return app

app/core/config.py

@@ -1,29 +0,0 @@
-from pydantic_settings import BaseSettings
-from typing import List
-
-
-class Settings(BaseSettings):
-    API_KEYS: List[str]
-    ALLOWED_TOKENS: List[str]
-    BASE_URL: str = "https://generativelanguage.googleapis.com/v1beta"
-    MODEL_SEARCH: List[str] = ["gemini-2.0-flash-exp"]
-    TOOLS_CODE_EXECUTION_ENABLED: bool = False
-    SHOW_SEARCH_LINK: bool = True
-    SHOW_THINKING_PROCESS: bool = True
-    AUTH_TOKEN: str = ""
-    MAX_FAILURES: int = 3
-    PAID_KEY: str = ""
-    CREATE_IMAGE_MODEL: str = "imagen-3.0-generate-002"
-    UPLOAD_PROVIDER: str = "smms"
-    SMMS_SECRET_TOKEN: str = ""
-
-    def __init__(self):
-        super().__init__()
-        if not self.AUTH_TOKEN:
-            self.AUTH_TOKEN = self.ALLOWED_TOKENS[0] if self.ALLOWED_TOKENS else ""
-
-    class Config:
-        env_file = ".env"
-
-
-settings = Settings()

app/core/constants.py

@@ -0,0 +1,42 @@
+"""
+常量定义模块
+"""
+
+# API相关常量
+API_VERSION = "v1beta"
+DEFAULT_TIMEOUT = 300  # 秒
+MAX_RETRIES = 3  # 最大重试次数
+
+# 模型相关常量
+SUPPORTED_ROLES = ["user", "model", "system"]
+DEFAULT_MODEL = "gemini-1.5-flash"
+DEFAULT_TEMPERATURE = 0.7
+DEFAULT_MAX_TOKENS = 8192
+DEFAULT_TOP_P = 0.9
+DEFAULT_TOP_K = 40
+DEFAULT_FILTER_MODELS = [
+        "gemini-1.0-pro-vision-latest", 
+        "gemini-pro-vision", 
+        "chat-bison-001", 
+        "text-bison-001", 
+        "embedding-gecko-001"
+    ]
+DEFAULT_CREATE_IMAGE_MODEL = "imagen-3.0-generate-002"
+
+# 图像生成相关常量
+VALID_IMAGE_RATIOS = ["1:1", "3:4", "4:3", "9:16", "16:9"]
+
+# 上传提供商
+UPLOAD_PROVIDERS = ["smms", "picgo", "cloudflare_imgbed"]
+DEFAULT_UPLOAD_PROVIDER = "smms"
+
+# 流式输出相关常量
+DEFAULT_STREAM_MIN_DELAY = 0.016
+DEFAULT_STREAM_MAX_DELAY = 0.024
+DEFAULT_STREAM_SHORT_TEXT_THRESHOLD = 10
+DEFAULT_STREAM_LONG_TEXT_THRESHOLD = 50
+DEFAULT_STREAM_CHUNK_SIZE = 5
+
+# 正则表达式模式
+IMAGE_URL_PATTERN = r'!\[(.*?)\]\((.*?)\)'
+DATA_URL_PATTERN = r'data:([^;]+);base64,(.+)'

app/core/initialization.py

@@ -0,0 +1,40 @@
+"""
+应用程序初始化模块
+"""
+from pathlib import Path
+from typing import List
+
+from app.log.logger import get_initialization_logger
+
+logger = get_initialization_logger()
+
+
+def ensure_directories_exist(directories: List[str]) -> None:
+    """
+    确保指定的目录存在，如果不存在则创建
+    
+    Args:
+        directories: 要确保存在的目录列表
+    """
+    for directory in directories:
+        try:
+            Path(directory).mkdir(parents=True, exist_ok=True)
+            logger.info(f"Ensured directory exists: {directory}")
+        except Exception as e:
+            logger.error(f"Failed to create directory {directory}: {str(e)}")
+
+
+def initialize_app() -> None:
+    """
+    初始化应用程序，确保所需的目录和文件都存在
+    """
+    # 确保必要的目录存在
+    required_directories = [
+        "app/static/css",
+        "app/static/js",
+        "app/static/icons",
+        "app/templates",
+    ]
+    
+    ensure_directories_exist(required_directories)
+    logger.info("core initialization completed")

app/core/security.py

@@ -1,26 +1,27 @@
-from fastapi import HTTPException, Header
 from typing import Optional
-from app.core.logger import get_security_logger
-from app.core.config import settings
+
+from fastapi import Header, HTTPException
+
+from app.config.config import settings
+from app.log.logger import get_security_logger
 
 logger = get_security_logger()
 
+
 def verify_auth_token(token: str) -> bool:
     return token == settings.AUTH_TOKEN
 
+
 class SecurityService:
-    def __init__(self, allowed_tokens: list, auth_token: str):
-        self.allowed_tokens = allowed_tokens
-        self.auth_token = auth_token
 
     async def verify_key(self, key: str):
-        if key not in self.allowed_tokens and key != self.auth_token:
+        if key not in settings.ALLOWED_TOKENS and key != settings.AUTH_TOKEN:
             logger.error("Invalid key")
             raise HTTPException(status_code=401, detail="Invalid key")
         return key
 
     async def verify_authorization(
-            self, authorization: Optional[str] = Header(None)
+        self, authorization: Optional[str] = Header(None)
     ) -> str:
         if not authorization:
             logger.error("Missing Authorization header")
@@ -33,31 +34,57 @@ class SecurityService:
             )
 
         token = authorization.replace("Bearer ", "")
-        if token not in self.allowed_tokens and token != self.auth_token:
+        if token not in settings.ALLOWED_TOKENS and token != settings.AUTH_TOKEN:
             logger.error("Invalid token")
             raise HTTPException(status_code=401, detail="Invalid token")
 
         return token
 
-    async def verify_goog_api_key(self, x_goog_api_key: Optional[str] = Header(None)) -> str:
+    async def verify_goog_api_key(
+        self, x_goog_api_key: Optional[str] = Header(None)
+    ) -> str:
         """验证Google API Key"""
         if not x_goog_api_key:
             logger.error("Missing x-goog-api-key header")
             raise HTTPException(status_code=401, detail="Missing x-goog-api-key header")
 
-        if x_goog_api_key not in self.allowed_tokens and x_goog_api_key != self.auth_token:
+        if (
+            x_goog_api_key not in settings.ALLOWED_TOKENS
+            and x_goog_api_key != settings.AUTH_TOKEN
+        ):
             logger.error("Invalid x-goog-api-key")
             raise HTTPException(status_code=401, detail="Invalid x-goog-api-key")
 
         return x_goog_api_key
 
-    async def verify_auth_token(self, authorization: Optional[str] = Header(None)) -> str:
+    async def verify_auth_token(
+        self, authorization: Optional[str] = Header(None)
+    ) -> str:
         if not authorization:
             logger.error("Missing auth_token header")
             raise HTTPException(status_code=401, detail="Missing auth_token header")
         token = authorization.replace("Bearer ", "")
-        if token != self.auth_token:
+        if token != settings.AUTH_TOKEN:
             logger.error("Invalid auth_token")
             raise HTTPException(status_code=401, detail="Invalid auth_token")
 
         return token
+
+    async def verify_key_or_goog_api_key(
+        self, key: Optional[str] = None , x_goog_api_key: Optional[str] = Header(None)
+    ) -> str:
+        """验证URL中的key或请求头中的x-goog-api-key"""
+        # 如果URL中的key有效，直接返回
+        if key in settings.ALLOWED_TOKENS or key == settings.AUTH_TOKEN:
+            return key
+        
+        # 否则检查请求头中的x-goog-api-key
+        if not x_goog_api_key:
+            logger.error("Invalid key and missing x-goog-api-key header")
+            raise HTTPException(status_code=401, detail="Invalid key and missing x-goog-api-key header")
+        
+        if x_goog_api_key not in settings.ALLOWED_TOKENS and x_goog_api_key != settings.AUTH_TOKEN:
+            logger.error("Invalid key and invalid x-goog-api-key")
+            raise HTTPException(status_code=401, detail="Invalid key and invalid x-goog-api-key")
+        
+        return x_goog_api_key

app/core/uploader.py

@@ -1,163 +0,0 @@
-import requests
-from app.schemas.image_models import ImageMetadata, ImageUploader, UploadResponse
-from enum import Enum
-from typing import Optional, Any
-
-class UploadErrorType(Enum):
-    """上传错误类型枚举"""
-    NETWORK_ERROR = "network_error"  # 网络请求错误
-    AUTH_ERROR = "auth_error"        # 认证错误
-    INVALID_FILE = "invalid_file"    # 无效文件
-    SERVER_ERROR = "server_error"    # 服务器错误
-    PARSE_ERROR = "parse_error"      # 响应解析错误
-    UNKNOWN = "unknown"              # 未知错误
-
-
-class UploadError(Exception):
-    """图片上传错误异常类"""
-    
-    def __init__(
-        self,
-        message: str,
-        error_type: UploadErrorType = UploadErrorType.UNKNOWN,
-        status_code: Optional[int] = None,
-        details: Optional[dict] = None,
-        original_error: Optional[Exception] = None
-    ):
-        """
-        初始化上传错误异常
-        
-        Args:
-            message: 错误消息
-            error_type: 错误类型
-            status_code: HTTP状态码
-            details: 详细错误信息
-            original_error: 原始异常
-        """
-        self.message = message
-        self.error_type = error_type
-        self.status_code = status_code
-        self.details = details or {}
-        self.original_error = original_error
-        
-        # 构建完整错误信息
-        full_message = f"[{error_type.value}] {message}"
-        if status_code:
-            full_message = f"{full_message} (Status: {status_code})"
-        if details:
-            full_message = f"{full_message} - Details: {details}"
-            
-        super().__init__(full_message)
-    
-    @classmethod
-    def from_response(cls, response: Any, message: Optional[str] = None) -> "UploadError":
-        """
-        从HTTP响应创建错误实例
-        
-        Args:
-            response: HTTP响应对象
-            message: 自定义错误消息
-        """
-        try:
-            error_data = response.json()
-            details = error_data.get("data", {})
-            return cls(
-                message=message or error_data.get("message", "Unknown error"),
-                error_type=UploadErrorType.SERVER_ERROR,
-                status_code=response.status_code,
-                details=details
-            )
-        except Exception:
-            return cls(
-                message=message or "Failed to parse error response",
-                error_type=UploadErrorType.PARSE_ERROR,
-                status_code=response.status_code
-            )
-
-
-class SmMsUploader(ImageUploader):
-    API_URL = "https://sm.ms/api/v2/upload"
-    
-    def __init__(self, api_key: str):
-        self.api_key = api_key
-        
-    def upload(self, file: bytes, filename: str) -> UploadResponse:
-        try:
-            # 准备请求头
-            headers = {
-                "Authorization": f"Basic {self.api_key}"
-            }
-            
-            # 准备文件数据
-            files = {
-                "smfile": (filename, file, "image/png")
-            }
-            
-            # 发送请求
-            response = requests.post(
-                self.API_URL,
-                headers=headers,
-                files=files
-            )
-            
-            # 检查响应状态
-            response.raise_for_status()
-            
-            # 解析响应
-            result = response.json()
-            
-            # 验证上传是否成功
-            if not result.get("success"):
-                raise UploadError(result.get("message", "Upload failed"))
-                
-            # 转换为统一格式
-            data = result["data"]
-            image_metadata = ImageMetadata(
-                width=data["width"],
-                height=data["height"],
-                filename=data["filename"],
-                size=data["size"],
-                url=data["url"],
-                delete_url=data["delete"]
-            )
-            
-            return UploadResponse(
-                success=True,
-                code="success",
-                message="Upload success",
-                data=image_metadata
-            )
-            
-        except requests.RequestException as e:
-            # 处理网络请求相关错误
-            raise UploadError(f"Upload request failed: {str(e)}")
-        except (KeyError, ValueError) as e:
-            # 处理响应解析错误
-            raise UploadError(f"Invalid response format: {str(e)}")
-        except Exception as e:
-            # 处理其他未预期的错误
-            raise UploadError(f"Upload failed: {str(e)}")
-    
-    
-class QiniuUploader(ImageUploader):
-    def __init__(self, access_key: str, secret_key: str):
-        self.access_key = access_key
-        self.secret_key = secret_key
-        
-    def upload(self, file: bytes, filename: str) -> UploadResponse:
-        # 实现七牛云的具体上传逻辑
-        pass
-    
-    
-class ImageUploaderFactory:
-    @staticmethod
-    def create(provider: str, **credentials) -> ImageUploader:
-        if provider == "smms":
-            return SmMsUploader(credentials["api_key"])
-        elif provider == "qiniu":
-            return QiniuUploader(
-                credentials["access_key"], 
-                credentials["secret_key"]
-            )
-        raise ValueError(f"Unknown provider: {provider}")
-    

app/database/__init__.py

@@ -0,0 +1,3 @@
+"""
+数据库模块
+"""

app/database/connection.py

@@ -0,0 +1,55 @@
+"""
+数据库连接池模块
+"""
+from databases import Database
+from sqlalchemy import create_engine, MetaData
+from sqlalchemy.ext.declarative import declarative_base
+
+from app.config.config import settings
+from app.log.logger import get_database_logger
+
+logger = get_database_logger()
+
+# 数据库URL
+DATABASE_URL = f"mysql+pymysql://{settings.MYSQL_USER}:{settings.MYSQL_PASSWORD}@{settings.MYSQL_HOST}:{settings.MYSQL_PORT}/{settings.MYSQL_DATABASE}"
+
+# 创建数据库引擎
+# pool_pre_ping=True: 在从连接池获取连接前执行简单的 "ping" 测试，确保连接有效
+engine = create_engine(DATABASE_URL, pool_pre_ping=True)
+
+# 创建元数据对象
+metadata = MetaData()
+
+# 创建基类
+Base = declarative_base(metadata=metadata)
+
+# 创建数据库连接池，并配置连接池参数
+# min_size/max_size: 连接池的最小/最大连接数
+# pool_recycle=3600: 连接在池中允许存在的最大秒数（生命周期）。
+#                    设置为 3600 秒（1小时），确保在 MySQL 默认的 wait_timeout (通常8小时) 或其他网络超时之前回收连接。
+#                    如果遇到连接失效问题，可以尝试调低此值，使其小于实际的 wait_timeout 或网络超时时间。
+# databases 库会自动处理连接失效后的重连尝试。
+database = Database(DATABASE_URL, min_size=5, max_size=20, pool_recycle=1800) # Reduced recycle time to 30 mins
+
+
+async def connect_to_db():
+    """
+    连接到数据库
+    """
+    try:
+        await database.connect()
+        logger.info("Connected to database")
+    except Exception as e:
+        logger.error(f"Failed to connect to database: {str(e)}")
+        raise
+
+
+async def disconnect_from_db():
+    """
+    断开数据库连接
+    """
+    try:
+        await database.disconnect()
+        logger.info("Disconnected from database")
+    except Exception as e:
+        logger.error(f"Failed to disconnect from database: {str(e)}")

app/database/initialization.py

@@ -0,0 +1,77 @@
+"""
+数据库初始化模块
+"""
+from dotenv import dotenv_values
+
+from sqlalchemy import inspect
+from sqlalchemy.orm import Session
+
+from app.database.connection import engine, Base
+from app.database.models import Settings
+from app.log.logger import get_database_logger
+
+logger = get_database_logger()
+
+
+def create_tables():
+    """
+    创建数据库表
+    """
+    try:
+        # 创建所有表
+        Base.metadata.create_all(engine)
+        logger.info("Database tables created successfully")
+    except Exception as e:
+        logger.error(f"Failed to create database tables: {str(e)}")
+        raise
+
+
+def import_env_to_settings():
+    """
+    将.env文件中的配置项导入到t_settings表中
+    """
+    try:
+        # 获取.env文件中的所有配置项
+        env_values = dotenv_values(".env")
+        
+        # 获取检查器
+        inspector = inspect(engine)
+        
+         # 检查t_settings表是否存在
+        if "t_settings" in inspector.get_table_names():
+            # 使用Session进行数据库操作
+            with Session(engine) as session:
+                # 获取所有现有的配置项
+                current_settings = {setting.key: setting for setting in session.query(Settings).all()}
+                
+                # 遍历所有配置项
+                for key, value in env_values.items():
+                    # 检查配置项是否已存在
+                    if key not in current_settings:
+                        # 插入配置项
+                        new_setting = Settings(key=key, value=value)
+                        session.add(new_setting)
+                        logger.info(f"Inserted setting: {key}")
+                
+                # 提交事务
+                session.commit()
+                
+        logger.info("Environment variables imported to settings table successfully")
+    except Exception as e:
+        logger.error(f"Failed to import environment variables to settings table: {str(e)}")
+        raise
+
+
+def initialize_database():
+    """
+    初始化数据库
+    """
+    try:
+        # 创建表
+        create_tables()
+        
+        # 导入环境变量
+        import_env_to_settings()
+    except Exception as e:
+        logger.error(f"Failed to initialize database: {str(e)}")
+        raise

app/database/models.py

@@ -0,0 +1,61 @@
+"""
+数据库模型模块
+"""
+import datetime
+from sqlalchemy import Column, Integer, String, Text, DateTime, JSON, Boolean # 添加 Boolean
+
+from app.database.connection import Base
+
+
+class Settings(Base):
+    """
+    设置表，对应.env中的配置项
+    """
+    __tablename__ = "t_settings"
+    
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    key = Column(String(100), nullable=False, unique=True, comment="配置项键名")
+    value = Column(Text, nullable=True, comment="配置项值")
+    description = Column(String(255), nullable=True, comment="配置项描述")
+    created_at = Column(DateTime, default=datetime.datetime.now, comment="创建时间")
+    updated_at = Column(DateTime, default=datetime.datetime.now, onupdate=datetime.datetime.now, comment="更新时间")
+    
+    def __repr__(self):
+        return f"<Settings(key='{self.key}', value='{self.value}')>"
+
+
+class ErrorLog(Base):
+    """
+    错误日志表
+    """
+    __tablename__ = "t_error_logs"
+    
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    gemini_key = Column(String(100), nullable=True, comment="Gemini API密钥")
+    model_name = Column(String(100), nullable=True, comment="模型名称")
+    error_type = Column(String(50), nullable=True, comment="错误类型")
+    error_log = Column(Text, nullable=True, comment="错误日志")
+    error_code = Column(Integer, nullable=True, comment="错误代码")
+    request_msg = Column(JSON, nullable=True, comment="请求消息")
+    request_time = Column(DateTime, default=datetime.datetime.now, comment="请求时间")
+    
+    def __repr__(self):
+        return f"<ErrorLog(id='{self.id}', gemini_key='{self.gemini_key}')>"
+
+# 新增 RequestLog 模型
+class RequestLog(Base):
+    """
+    API 请求日志表
+    """
+    __tablename__ = "t_request_log"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    request_time = Column(DateTime, default=datetime.datetime.now, comment="请求时间")
+    model_name = Column(String(100), nullable=True, comment="模型名称")
+    api_key = Column(String(100), nullable=True, comment="使用的API密钥") # 考虑安全性，后续可优化
+    is_success = Column(Boolean, nullable=False, comment="请求是否成功")
+    status_code = Column(Integer, nullable=True, comment="API响应状态码")
+    latency_ms = Column(Integer, nullable=True, comment="请求耗时(毫秒)")
+
+    def __repr__(self):
+        return f"<RequestLog(id='{self.id}', key='{self.api_key[:4]}...', success='{self.is_success}')>"

app/database/services.py

@@ -0,0 +1,284 @@
+"""
+数据库服务模块
+"""
+import json
+from typing import Dict, List, Optional, Any, Union
+from datetime import datetime # Keep this import
+
+from sqlalchemy import select, insert, update, func
+
+from app.database.connection import database
+from app.database.models import Settings, ErrorLog, RequestLog # Import RequestLog
+from app.log.logger import get_database_logger
+
+logger = get_database_logger()
+
+
+async def get_all_settings() -> List[Dict[str, Any]]:
+    """
+    获取所有设置
+    
+    Returns:
+        List[Dict[str, Any]]: 设置列表
+    """
+    try:
+        query = select(Settings)
+        result = await database.fetch_all(query)
+        return [dict(row) for row in result]
+    except Exception as e:
+        logger.error(f"Failed to get all settings: {str(e)}")
+        raise
+
+
+async def get_setting(key: str) -> Optional[Dict[str, Any]]:
+    """
+    获取指定键的设置
+    
+    Args:
+        key: 设置键名
+    
+    Returns:
+        Optional[Dict[str, Any]]: 设置信息，如果不存在则返回None
+    """
+    try:
+        query = select(Settings).where(Settings.key == key)
+        result = await database.fetch_one(query)
+        return dict(result) if result else None
+    except Exception as e:
+        logger.error(f"Failed to get setting {key}: {str(e)}")
+        raise
+
+
+async def update_setting(key: str, value: str, description: Optional[str] = None) -> bool:
+    """
+    更新设置
+    
+    Args:
+        key: 设置键名
+        value: 设置值
+        description: 设置描述
+    
+    Returns:
+        bool: 是否更新成功
+    """
+    try:
+        # 检查设置是否存在
+        setting = await get_setting(key)
+        
+        if setting:
+            # 更新设置
+            query = (
+                update(Settings)
+                .where(Settings.key == key)
+                .values(
+                    value=value,
+                    description=description if description else setting["description"],
+                    updated_at=datetime.now() # Use datetime.now()
+                )
+            )
+            await database.execute(query)
+            logger.info(f"Updated setting: {key}")
+            return True
+        else:
+            # 插入设置
+            query = (
+                insert(Settings)
+                .values(
+                    key=key,
+                    value=value,
+                    description=description,
+                    created_at=datetime.now(), # Use datetime.now()
+                    updated_at=datetime.now() # Use datetime.now()
+                )
+            )
+            await database.execute(query)
+            logger.info(f"Inserted setting: {key}")
+            return True
+    except Exception as e:
+        logger.error(f"Failed to update setting {key}: {str(e)}")
+        return False
+
+
+async def add_error_log(
+    gemini_key: Optional[str] = None,
+    model_name: Optional[str] = None,
+    error_type: Optional[str] = None,
+    error_log: Optional[str] = None,
+    error_code: Optional[int] = None,
+    request_msg: Optional[Union[Dict[str, Any], str]] = None
+) -> bool:
+    """
+    添加错误日志
+    
+    Args:
+        gemini_key: Gemini API密钥
+        error_log: 错误日志
+        error_code: 错误代码 (例如 HTTP 状态码)
+        request_msg: 请求消息
+    
+    Returns:
+        bool: 是否添加成功
+    """
+    try:
+        # 如果request_msg是字典，则转换为JSON字符串
+        if isinstance(request_msg, dict):
+            request_msg_json = request_msg
+        elif isinstance(request_msg, str):
+            try:
+                request_msg_json = json.loads(request_msg)
+            except json.JSONDecodeError:
+                request_msg_json = {"message": request_msg}
+        else:
+            request_msg_json = None
+        
+        # 插入错误日志
+        query = (
+            insert(ErrorLog)
+            .values(
+                gemini_key=gemini_key,
+                error_type=error_type,
+                error_log=error_log,
+                model_name=model_name,
+                error_code=error_code,
+                request_msg=request_msg_json,
+                request_time=datetime.now()
+            )
+        )
+        await database.execute(query)
+        logger.info(f"Added error log for key: {gemini_key}")
+        return True
+    except Exception as e:
+        logger.error(f"Failed to add error log: {str(e)}")
+        return False
+
+
+async def get_error_logs(
+    limit: int = 20,
+    offset: int = 0,
+    key_search: Optional[str] = None,
+    error_search: Optional[str] = None,
+    start_date: Optional[datetime] = None,
+    end_date: Optional[datetime] = None
+) -> List[Dict[str, Any]]:
+    """
+    获取错误日志，支持搜索和日期过滤
+
+    Args:
+        limit (int): 限制数量
+        offset (int): 偏移量
+        key_search (Optional[str]): Gemini密钥搜索词 (模糊匹配)
+        error_search (Optional[str]): 错误类型或日志内容搜索词 (模糊匹配)
+        start_date (Optional[datetime]): 开始日期时间
+        end_date (Optional[datetime]): 结束日期时间
+
+    Returns:
+        List[Dict[str, Any]]: 错误日志列表
+    """
+    try:
+        query = select(ErrorLog)
+        
+        # Apply filters
+        if key_search:
+            query = query.where(ErrorLog.gemini_key.ilike(f"%{key_search}%"))
+        if error_search:
+            query = query.where(
+                (ErrorLog.error_type.ilike(f"%{error_search}%")) |
+                (ErrorLog.error_log.ilike(f"%{error_search}%"))
+            )
+        if start_date:
+            query = query.where(ErrorLog.request_time >= start_date)
+        if end_date:
+            # Use the datetime object directly for comparison
+            query = query.where(ErrorLog.request_time < end_date)
+
+        # Apply ordering, limit, and offset
+        query = query.order_by(ErrorLog.request_time.desc()).limit(limit).offset(offset)
+        
+        result = await database.fetch_all(query)
+        return [dict(row) for row in result]
+    except Exception as e:
+        logger.exception(f"Failed to get error logs with filters: {str(e)}") # Use exception for stack trace
+        raise
+
+
+async def get_error_logs_count(
+    key_search: Optional[str] = None,
+    error_search: Optional[str] = None,
+    start_date: Optional[datetime] = None,
+    end_date: Optional[datetime] = None
+) -> int:
+    """
+    获取符合条件的错误日志总数
+
+    Args:
+        key_search (Optional[str]): Gemini密钥搜索词 (模糊匹配)
+        error_search (Optional[str]): 错误类型或日志内容搜索词 (模糊匹配)
+        start_date (Optional[datetime]): 开始日期时间
+        end_date (Optional[datetime]): 结束日期时间
+
+    Returns:
+        int: 日志总数
+    """
+    try:
+        query = select(func.count()).select_from(ErrorLog)
+
+        # Apply the same filters as get_error_logs
+        if key_search:
+            query = query.where(ErrorLog.gemini_key.ilike(f"%{key_search}%"))
+        if error_search:
+            query = query.where(
+                (ErrorLog.error_type.ilike(f"%{error_search}%")) |
+                (ErrorLog.error_log.ilike(f"%{error_search}%"))
+            )
+        if start_date:
+            query = query.where(ErrorLog.request_time >= start_date)
+        if end_date:
+            # Use the datetime object directly for comparison
+            query = query.where(ErrorLog.request_time < end_date)
+
+        count_result = await database.fetch_one(query)
+        return count_result[0] if count_result else 0
+    except Exception as e:
+        logger.exception(f"Failed to count error logs with filters: {str(e)}") # Use exception for stack trace
+        raise
+
+# 新增函数：添加请求日志
+async def add_request_log(
+    model_name: Optional[str],
+    api_key: Optional[str],
+    is_success: bool,
+    status_code: Optional[int] = None,
+    latency_ms: Optional[int] = None,
+    request_time: Optional[datetime] = None
+) -> bool:
+    """
+    添加 API 请求日志
+
+    Args:
+        model_name: 模型名称
+        api_key: 使用的 API 密钥
+        is_success: 请求是否成功
+        status_code: API 响应状态码
+        latency_ms: 请求耗时(毫秒)
+        request_time: 请求发生时间 (如果为 None, 则使用当前时间)
+
+    Returns:
+        bool: 是否添加成功
+    """
+    try:
+        log_time = request_time if request_time else datetime.now()
+
+        query = insert(RequestLog).values(
+            request_time=log_time,
+            model_name=model_name,
+            api_key=api_key,
+            is_success=is_success,
+            status_code=status_code,
+            latency_ms=latency_ms
+        )
+        await database.execute(query)
+        # logger.debug(f"Added request log: key={api_key[:4]}..., success={is_success}, model={model_name}") # Use debug level
+        return True
+    except Exception as e:
+        logger.error(f"Failed to add request log: {str(e)}")
+        return False

app/domain/gemini_models.py

@@ -1,6 +1,8 @@
-from typing import List, Optional, Dict, Any, Literal
+from typing import List, Optional, Dict, Any, Literal, Union
 from pydantic import BaseModel
 
+from app.core.constants import DEFAULT_TEMPERATURE, DEFAULT_TOP_K, DEFAULT_TOP_P
+
 
 class SafetySetting(BaseModel):
     category: Optional[Literal["HARM_CATEGORY_HATE_SPEECH", "HARM_CATEGORY_DANGEROUS_CONTENT", "HARM_CATEGORY_HARASSMENT", "HARM_CATEGORY_SEXUALLY_EXPLICIT", "HARM_CATEGORY_CIVIC_INTEGRITY"]] = None
@@ -13,9 +15,9 @@ class GenerationConfig(BaseModel):
     responseSchema: Optional[Dict[str, Any]] = None
     candidateCount: Optional[int] = 1
     maxOutputTokens: Optional[int] = None
-    temperature: Optional[float] = None
-    topP: Optional[float] = None
-    topK: Optional[int] = None
+    temperature: Optional[float] = DEFAULT_TEMPERATURE
+    topP: Optional[float] = DEFAULT_TOP_P
+    topK: Optional[int] = DEFAULT_TOP_K
     presencePenalty: Optional[float] = None
     frequencyPenalty: Optional[float] = None
     responseLogprobs: Optional[bool] = None
@@ -33,8 +35,8 @@ class GeminiContent(BaseModel):
 
 
 class GeminiRequest(BaseModel):
-    contents: List[GeminiContent]
-    tools: Optional[List[Dict[str, Any]]] = []
+    contents: List[GeminiContent] = []
+    tools: Optional[Union[List[Dict[str, Any]], Dict[str, Any]]] = []
     safetySettings: Optional[List[SafetySetting]] = None
     generationConfig: Optional[GenerationConfig] = None
     systemInstruction: Optional[SystemInstruction] = None

app/domain/openai_models.py

@@ -1,17 +1,19 @@
 from pydantic import BaseModel
 from typing import List, Optional, Union
 
+from app.core.constants import DEFAULT_MODEL, DEFAULT_TEMPERATURE, DEFAULT_TOP_K, DEFAULT_TOP_P
+
 
 class ChatRequest(BaseModel):
     messages: List[dict]
-    model: str = "gemini-1.5-flash-002"
-    temperature: Optional[float] = 0.7
+    model: str = DEFAULT_MODEL
+    temperature: Optional[float] = DEFAULT_TEMPERATURE
     stream: Optional[bool] = False
     tools: Optional[List[dict]] = []
-    max_tokens: Optional[int] = 8192
+    max_tokens: Optional[int] = None
+    top_p: Optional[float] = DEFAULT_TOP_P
+    top_k: Optional[int] = DEFAULT_TOP_K
     stop: Optional[List[str]] = []
-    top_p: Optional[float] = 0.9
-    top_k: Optional[int] = 40
 
 
 class EmbeddingRequest(BaseModel):

app/exception/exceptions.py

@@ -0,0 +1,140 @@
+"""
+异常处理模块，定义应用程序中使用的自定义异常和异常处理器
+"""
+
+from fastapi import FastAPI, Request
+from fastapi.exceptions import RequestValidationError
+from fastapi.responses import JSONResponse
+from starlette.exceptions import HTTPException as StarletteHTTPException
+
+from app.log.logger import get_exceptions_logger
+
+logger = get_exceptions_logger()
+
+
+class APIError(Exception):
+    """API错误基类"""
+
+    def __init__(self, status_code: int, detail: str, error_code: str = None):
+        self.status_code = status_code
+        self.detail = detail
+        self.error_code = error_code or "api_error"
+        super().__init__(self.detail)
+
+
+class AuthenticationError(APIError):
+    """认证错误"""
+
+    def __init__(self, detail: str = "Authentication failed"):
+        super().__init__(
+            status_code=401, detail=detail, error_code="authentication_error"
+        )
+
+
+class AuthorizationError(APIError):
+    """授权错误"""
+
+    def __init__(self, detail: str = "Not authorized to access this resource"):
+        super().__init__(
+            status_code=403, detail=detail, error_code="authorization_error"
+        )
+
+
+class ResourceNotFoundError(APIError):
+    """资源未找到错误"""
+
+    def __init__(self, detail: str = "Resource not found"):
+        super().__init__(
+            status_code=404, detail=detail, error_code="resource_not_found"
+        )
+
+
+class ModelNotSupportedError(APIError):
+    """模型不支持错误"""
+
+    def __init__(self, model: str):
+        super().__init__(
+            status_code=400,
+            detail=f"Model {model} is not supported",
+            error_code="model_not_supported",
+        )
+
+
+class APIKeyError(APIError):
+    """API密钥错误"""
+
+    def __init__(self, detail: str = "Invalid or expired API key"):
+        super().__init__(status_code=401, detail=detail, error_code="api_key_error")
+
+
+class ServiceUnavailableError(APIError):
+    """服务不可用错误"""
+
+    def __init__(self, detail: str = "Service temporarily unavailable"):
+        super().__init__(
+            status_code=503, detail=detail, error_code="service_unavailable"
+        )
+
+
+def setup_exception_handlers(app: FastAPI) -> None:
+    """
+    设置应用程序的异常处理器
+
+    Args:
+        app: FastAPI应用程序实例
+    """
+
+    @app.exception_handler(APIError)
+    async def api_error_handler(request: Request, exc: APIError):
+        """处理API错误"""
+        logger.error(f"API Error: {exc.detail} (Code: {exc.error_code})")
+        return JSONResponse(
+            status_code=exc.status_code,
+            content={"error": {"code": exc.error_code, "message": exc.detail}},
+        )
+
+    @app.exception_handler(StarletteHTTPException)
+    async def http_exception_handler(request: Request, exc: StarletteHTTPException):
+        """处理HTTP异常"""
+        logger.error(f"HTTP Exception: {exc.detail} (Status: {exc.status_code})")
+        return JSONResponse(
+            status_code=exc.status_code,
+            content={"error": {"code": "http_error", "message": exc.detail}},
+        )
+
+    @app.exception_handler(RequestValidationError)
+    async def validation_exception_handler(
+        request: Request, exc: RequestValidationError
+    ):
+        """处理请求验证错误"""
+        error_details = []
+        for error in exc.errors():
+            error_details.append(
+                {"loc": error["loc"], "msg": error["msg"], "type": error["type"]}
+            )
+
+        logger.error(f"Validation Error: {error_details}")
+        return JSONResponse(
+            status_code=422,
+            content={
+                "error": {
+                    "code": "validation_error",
+                    "message": "Request validation failed",
+                    "details": error_details,
+                }
+            },
+        )
+
+    @app.exception_handler(Exception)
+    async def general_exception_handler(request: Request, exc: Exception):
+        """处理通用异常"""
+        logger.exception(f"Unhandled Exception: {str(exc)}")
+        return JSONResponse(
+            status_code=500,
+            content={
+                "error": {
+                    "code": "internal_server_error",
+                    "message": "An unexpected error occurred",
+                }
+            },
+        )

app/handler/message_converter.py

@@ -0,0 +1,174 @@
+# app/services/chat/message_converter.py
+
+from abc import ABC, abstractmethod
+import json
+import re
+from typing import Any, Dict, List, Optional
+import requests
+import base64
+
+from app.core.constants import DATA_URL_PATTERN, IMAGE_URL_PATTERN, SUPPORTED_ROLES
+
+
+class MessageConverter(ABC):
+    """消息转换器基类"""
+
+    @abstractmethod
+    def convert(self, messages: List[Dict[str, Any]]) -> tuple[List[Dict[str, Any]], Optional[Dict[str, Any]]]:
+        pass
+
+def _get_mime_type_and_data(base64_string):
+    """
+    从 base64 字符串中提取 MIME 类型和数据。
+    
+    参数:
+        base64_string (str): 可能包含 MIME 类型信息的 base64 字符串
+        
+    返回:
+        tuple: (mime_type, encoded_data)
+    """
+    # 检查字符串是否以 "data:" 格式开始
+    if base64_string.startswith('data:'):
+        # 提取 MIME 类型和数据
+        pattern = DATA_URL_PATTERN
+        match = re.match(pattern, base64_string)
+        if match:
+            mime_type = "image/jpeg" if match.group(1) == "image/jpg" else match.group(1)
+            encoded_data = match.group(2)
+            return mime_type, encoded_data
+    
+    # 如果不是预期格式，假定它只是数据部分
+    return None, base64_string
+
+def _convert_image(image_url: str) -> Dict[str, Any]:
+    if image_url.startswith("data:image"):
+        mime_type, encoded_data = _get_mime_type_and_data(image_url)
+        return {
+            "inline_data": {
+                "mime_type": mime_type,
+                "data": encoded_data
+            }
+        }
+    else:
+        encoded_data = _convert_image_to_base64(image_url)
+        return {
+            "inline_data": {
+                "mime_type": "image/png",
+                "data": encoded_data
+            }
+        }
+
+
+def _convert_image_to_base64(url: str) -> str:
+    """
+    将图片URL转换为base64编码
+    Args:
+        url: 图片URL
+    Returns:
+        str: base64编码的图片数据
+    """
+    response = requests.get(url)
+    if response.status_code == 200:
+        # 将图片内容转换为base64
+        img_data = base64.b64encode(response.content).decode('utf-8')
+        return img_data
+    else:
+        raise Exception(f"Failed to fetch image: {response.status_code}")
+
+
+def _process_text_with_image(text: str) -> List[Dict[str, Any]]:
+    """
+    处理可能包含图片URL的文本，提取图片并转换为base64
+
+    Args:
+        text: 可能包含图片URL的文本
+
+    Returns:
+        List[Dict[str, Any]]: 包含文本和图片的部分列表
+    """
+    parts = []
+    img_url_match = re.search(IMAGE_URL_PATTERN, text)
+    if img_url_match:
+        # 提取URL
+        img_url = img_url_match.group(2)
+        # 将URL对应的图片转换为base64
+        try:
+            base64_data = _convert_image_to_base64(img_url)
+            parts.append({
+                "inlineData": {
+                    "mimeType": "image/png",
+                    "data": base64_data
+                }
+            })
+        except Exception:
+            # 如果转换失败，回退到文本模式
+            parts.append({"text": text})
+    else:
+        # 没有图片URL，作为纯文本处理
+        parts.append({"text": text})
+    return parts
+
+
+class OpenAIMessageConverter(MessageConverter):
+    """OpenAI消息格式转换器"""
+
+    def convert(self, messages: List[Dict[str, Any]]) -> tuple[List[Dict[str, Any]], Optional[Dict[str, Any]]]:
+        converted_messages = []
+        system_instruction_parts = []
+
+        for idx, msg in enumerate(messages):
+            role = msg.get("role", "")
+            
+            parts = []
+            # 特别处理最后一个assistant的消息，按\n\n分割
+            if "content" in msg and isinstance(msg["content"], str) and msg["content"] and role == "assistant" and idx == len(messages) - 2:
+                # 按\n\n分割消息
+                content_parts = msg["content"].split("\n\n")
+                for part in content_parts:
+                    if not part.strip():  # 跳过空内容
+                        continue
+                    # 处理可能包含图片的文本
+                    parts.extend(_process_text_with_image(part))
+            elif "content" in msg and isinstance(msg["content"], str) and msg["content"]:
+                # 请求 gemini 接口时如果包含 content 字段但内容为空时会返回 400 错误，所以需要判断是否为空并移除
+                parts.extend(_process_text_with_image(msg["content"]))
+            elif "content" in msg and isinstance(msg["content"], list):
+                for content in msg["content"]:
+                    if isinstance(content, str) and content:
+                        parts.append({"text": content})
+                    elif isinstance(content, dict):
+                        if content["type"] == "text" and content["text"]:
+                            parts.append({"text": content["text"]})
+                        elif content["type"] == "image_url":
+                            parts.append(_convert_image(content["image_url"]["url"]))
+            elif "tool_calls" in msg and isinstance(msg["tool_calls"], list):
+                for tool_call in msg["tool_calls"]:
+                    function_call = tool_call.get("function",{})
+                    function_call["args"] = json.loads(function_call.get("arguments","{}"))
+                    del function_call["arguments"]
+                    parts.append({"functionCall": function_call})
+            
+            if role not in SUPPORTED_ROLES:
+                if role == "tool":
+                    role = "user"
+                else:
+                    # 如果是最后一条消息，则认为是用户消息
+                    if idx == len(messages) - 1:
+                        role = "user"
+                    else:
+                        role = "model"
+            if parts:
+                if role == "system":
+                    system_instruction_parts.extend(parts)
+                else:
+                    converted_messages.append({"role": role, "parts": parts})
+
+        system_instruction = (
+            None
+            if not system_instruction_parts
+            else {
+                "role": "system",
+                "parts": system_instruction_parts,
+            }
+        )
+        return converted_messages, system_instruction

app/handler/response_handler.py

@@ -1,10 +1,15 @@
 # app/services/chat/response_handler.py
 
+import base64
+import json
+import random
+import string
 from abc import ABC, abstractmethod
-from typing import Dict, Any, Optional
+from typing import Dict, Any, List, Optional
 import time
 import uuid
-from app.core.config import settings
+from app.config.config import settings
+from app.utils.uploader import ImageUploaderFactory
 
 
 class ResponseHandler(ABC):
@@ -29,40 +34,38 @@ class GeminiResponseHandler(ResponseHandler):
 
 
 def _handle_openai_stream_response(response: Dict[str, Any], model: str, finish_reason: str) -> Dict[str, Any]:
-    text = _extract_text(response, model, stream=True)
+    text, tool_calls = _extract_result(response, model, stream=True, gemini_format=False)
+    if not text and not tool_calls:
+        delta = {}
+    else:
+        delta = {"content": text, "role": "assistant"}
+        if tool_calls:
+            delta["tool_calls"] = tool_calls
+
     return {
         "id": f"chatcmpl-{uuid.uuid4()}",
         "object": "chat.completion.chunk",
         "created": int(time.time()),
         "model": model,
-        "choices": [{
-            "index": 0,
-            "delta": {"content": text} if text else {},
-            "finish_reason": finish_reason
-        }]
+        "choices": [{"index": 0, "delta": delta, "finish_reason": finish_reason}],
     }
 
 
 def _handle_openai_normal_response(response: Dict[str, Any], model: str, finish_reason: str) -> Dict[str, Any]:
-    text = _extract_text(response, model, stream=False)
+    text, tool_calls = _extract_result(response, model, stream=False, gemini_format=False)
     return {
         "id": f"chatcmpl-{uuid.uuid4()}",
         "object": "chat.completion",
         "created": int(time.time()),
         "model": model,
-        "choices": [{
-            "index": 0,
-            "message": {
-                "role": "assistant",
-                "content": text
-            },
-            "finish_reason": finish_reason
-        }],
-        "usage": {
-            "prompt_tokens": 0,
-            "completion_tokens": 0,
-            "total_tokens": 0
-        }
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": text, "tool_calls": tool_calls},
+                "finish_reason": finish_reason,
+            }
+        ],
+        "usage": {"prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0},
     }
 
 
@@ -127,74 +130,15 @@ def _handle_openai_normal_image_response(image_str: str,model: str,finish_reason
     }
 
 
-def _extract_text(response: Dict[str, Any], model: str, stream: bool = False) -> str:
-    text = ""
+def _extract_result(response: Dict[str, Any], model: str, stream: bool = False, gemini_format: bool = False) -> tuple[str, List[Dict[str, Any]]]:
+    text, tool_calls = "", []
     if stream:
         if response.get("candidates"):
             candidate = response["candidates"][0]
             content = candidate.get("content", {})
             parts = content.get("parts", [])
-            # if "thinking" in model:
-            #     if settings.SHOW_THINKING_PROCESS:
-            #         if len(parts) == 1:
-            #             if self.thinking_first:
-            #                 self.thinking_first = False
-            #                 self.thinking_status = True
-            #                 text = "> thinking\n\n" + parts[0].get("text")
-            #             else:
-            #                 text = parts[0].get("text")
-
-            #         if len(parts) == 2:
-            #             self.thinking_status = False
-            #             if self.thinking_first:
-            #                 self.thinking_first = False
-            #                 text = (
-            #                     "> thinking\n\n"
-            #                     + parts[0].get("text")
-            #                     + "\n\n---\n> output\n\n"
-            #                     + parts[1].get("text")
-            #                 )
-            #             else:
-            #                 text = (
-            #                     parts[0].get("text")
-            #                     + "\n\n---\n> output\n\n"
-            #                     + parts[1].get("text")
-            #                 )
-            #     else:
-            #         if len(parts) == 1:
-            #             if self.thinking_first:
-            #                 self.thinking_first = False
-            #                 self.thinking_status = True
-            #                 text = ""
-            #             elif self.thinking_status:
-            #                 text = ""
-            #             else:
-            #                 text = parts[0].get("text")
-
-            #         if len(parts) == 2:
-            #             self.thinking_status = False
-            #             if self.thinking_first:
-            #                 self.thinking_first = False
-            #                 text = parts[1].get("text")
-            #             else:
-            #                 text = parts[1].get("text")
-            # else:
-            #     if "text" in parts[0]:
-            #         text = parts[0].get("text")
-            #     elif "executableCode" in parts[0]:
-            #         text = _format_code_block(parts[0]["executableCode"])
-            #     elif "codeExecution" in parts[0]:
-            #         text = _format_code_block(parts[0]["codeExecution"])
-            #     elif "executableCodeResult" in parts[0]:
-            #         text = _format_execution_result(
-            #             parts[0]["executableCodeResult"]
-            #         )
-            #     elif "codeExecutionResult" in parts[0]:
-            #         text = _format_execution_result(
-            #             parts[0]["codeExecutionResult"]
-            #         )
-            #     else:
-            #         text = ""
+            if not parts:
+                return "", []
             if "text" in parts[0]:
                 text = parts[0].get("text")
             elif "executableCode" in parts[0]:
@@ -209,9 +153,12 @@ def _extract_text(response: Dict[str, Any], model: str, stream: bool = False) ->
                 text = _format_execution_result(
                     parts[0]["codeExecutionResult"]
                 )
+            elif "inlineData" in parts[0]:
+                text = _extract_image_data(parts[0])
             else:
                 text = ""
             text = _add_search_link_text(model, candidate, text)
+            tool_calls = _extract_tool_calls(parts, gemini_format)
     else:
         if response.get("candidates"):
             candidate = response["candidates"][0]
@@ -232,23 +179,93 @@ def _extract_text(response: Dict[str, Any], model: str, stream: bool = False) ->
                     else:
                         text = candidate["content"]["parts"][0]["text"]
             else:
-                text = candidate["content"]["parts"][0]["text"]
+                text = ""
+                if "parts" in candidate["content"]:
+                    for part in candidate["content"]["parts"]:
+                        if "text" in part:
+                            text += part["text"]
+                        elif "inlineData" in part:
+                            text += _extract_image_data(part)
+
+
             text = _add_search_link_text(model, candidate, text)
+            tool_calls = _extract_tool_calls(candidate["content"]["parts"], gemini_format)
         else:
             text = "暂无返回"
+    return text, tool_calls
+
+def _extract_image_data(part: dict) -> str:
+    image_uploader = None
+    if settings.UPLOAD_PROVIDER == "smms":
+        image_uploader = ImageUploaderFactory.create(provider=settings.UPLOAD_PROVIDER,api_key=settings.SMMS_SECRET_TOKEN)
+    elif settings.UPLOAD_PROVIDER == "picgo":
+        image_uploader = ImageUploaderFactory.create(provider=settings.UPLOAD_PROVIDER,api_key=settings.PICGO_API_KEY)
+    elif settings.UPLOAD_PROVIDER == "cloudflare_imgbed":
+        image_uploader = ImageUploaderFactory.create(provider=settings.UPLOAD_PROVIDER,base_url=settings.CLOUDFLARE_IMGBED_URL,auth_code=settings.CLOUDFLARE_IMGBED_AUTH_CODE)
+    current_date = time.strftime("%Y/%m/%d")
+    filename = f"{current_date}/{uuid.uuid4().hex[:8]}.png"
+    base64_data = part["inlineData"]["data"]
+    #将base64_data转成bytes数组
+    bytes_data = base64.b64decode(base64_data)
+    upload_response = image_uploader.upload(bytes_data,filename)
+    if upload_response.success:
+        text = f"\n\n![image]({upload_response.data.url})\n\n"
+    else:
+        text = ""
     return text
+    
+def _extract_tool_calls(parts: List[Dict[str, Any]], gemini_format: bool) -> List[Dict[str, Any]]:
+    """提取工具调用信息"""
+    if not parts or not isinstance(parts, list):
+        return []
+
+    letters = string.ascii_lowercase + string.digits
+
+    tool_calls = list()
+    for i in range(len(parts)):
+        part = parts[i]
+        if not part or not isinstance(part, dict):
+            continue
+
+        item = part.get("functionCall", {})
+        if not item or not isinstance(item, dict):
+            continue
+
+        if gemini_format:
+            tool_calls.append(part)
+        else:
+            id = f"call_{''.join(random.sample(letters, 32))}"
+            name = item.get("name", "")
+            arguments = json.dumps(item.get("args", None) or {})
+
+            tool_calls.append(
+                {
+                    "index": i,
+                    "id": id,
+                    "type": "function",
+                    "function": {"name": name, "arguments": arguments},
+                }
+            )
+
+    return tool_calls
 
 
 def _handle_gemini_stream_response(response: Dict[str, Any], model: str, stream: bool) -> Dict[str, Any]:
-    text = _extract_text(response, model, stream=stream)
-    content = {"parts": [{"text": text}], "role": "model"}
+    text, tool_calls = _extract_result(response, model, stream=stream, gemini_format=True)
+    if tool_calls:
+        content = {"parts": tool_calls, "role": "model"}
+    else:
+        content = {"parts": [{"text": text}], "role": "model"}
     response["candidates"][0]["content"] = content
     return response
 
 
 def _handle_gemini_normal_response(response: Dict[str, Any], model: str, stream: bool) -> Dict[str, Any]:
-    text = _extract_text(response, model, stream=stream)
-    content = {"parts": [{"text": text}], "role": "model"}
+    text, tool_calls = _extract_result(response, model, stream=stream, gemini_format=True)
+    if tool_calls:
+        content = {"parts": tool_calls, "role": "model"}
+    else:
+        content = {"parts": [{"text": text}], "role": "model"}
     response["candidates"][0]["content"] = content
     return response
 

app/handler/retry_handler.py

@@ -1,20 +1,20 @@
 # app/services/chat/retry_handler.py
 
-from typing import TypeVar, Callable
 from functools import wraps
-from app.core.logger import get_retry_logger
-from app.services.key_manager import KeyManager
+from typing import Callable, TypeVar
 
-T = TypeVar('T')
+from app.core.constants import MAX_RETRIES
+from app.log.logger import get_retry_logger
+
+T = TypeVar("T")
 logger = get_retry_logger()
 
 
 class RetryHandler:
     """重试处理装饰器"""
 
-    def __init__(self, max_retries: int = 3, key_manager: KeyManager = None, key_arg: str = "api_key"):
+    def __init__(self, max_retries: int = MAX_RETRIES, key_arg: str = "api_key"):
         self.max_retries = max_retries
-        self.key_manager = key_manager
         self.key_arg = key_arg
 
     def __call__(self, func: Callable[..., T]) -> Callable[..., T]:
@@ -27,15 +27,21 @@ class RetryHandler:
                     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}")
+                    logger.warning(
+                        f"API call failed with error: {str(e)}. Attempt {attempt + 1} of {self.max_retries}"
+                    )
 
-                    if self.key_manager:
+                    # 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 self.key_manager.handle_api_failure(old_key)
+                        new_key = await key_manager.handle_api_failure(old_key)
                         kwargs[self.key_arg] = new_key
                         logger.info(f"Switched to new API key: {new_key}")
 
-            logger.error(f"All retry attempts failed, raising final exception: {str(last_exception)}")
+            logger.error(
+                f"All retry attempts failed, raising final exception: {str(last_exception)}"
+            )
             raise last_exception
 
         return wrapper

app/handler/stream_optimizer.py

@@ -0,0 +1,148 @@
+# app/services/chat/stream_optimizer.py
+
+import asyncio
+import math
+from typing import Any, AsyncGenerator, Callable, List
+
+from app.config.config import settings
+from app.core.constants import (
+    DEFAULT_STREAM_CHUNK_SIZE,
+    DEFAULT_STREAM_LONG_TEXT_THRESHOLD,
+    DEFAULT_STREAM_MAX_DELAY,
+    DEFAULT_STREAM_MIN_DELAY,
+    DEFAULT_STREAM_SHORT_TEXT_THRESHOLD,
+)
+from app.log.logger import get_gemini_logger, get_openai_logger
+
+logger_openai = get_openai_logger()
+logger_gemini = get_gemini_logger()
+
+
+class StreamOptimizer:
+    """流式输出优化器
+
+    提供流式输出优化功能，包括智能延迟调整和长文本分块输出。
+    """
+
+    def __init__(
+        self,
+        logger=None,
+        min_delay: float = DEFAULT_STREAM_MIN_DELAY,
+        max_delay: float = DEFAULT_STREAM_MAX_DELAY,
+        short_text_threshold: int = DEFAULT_STREAM_SHORT_TEXT_THRESHOLD,
+        long_text_threshold: int = DEFAULT_STREAM_LONG_TEXT_THRESHOLD,
+        chunk_size: int = DEFAULT_STREAM_CHUNK_SIZE,
+    ):
+        """初始化流式输出优化器
+
+        参数:
+            logger: 日志记录器
+            min_delay: 最小延迟时间（秒）
+            max_delay: 最大延迟时间（秒）
+            short_text_threshold: 短文本阈值（字符数）
+            long_text_threshold: 长文本阈值（字符数）
+            chunk_size: 长文本分块大小（字符数）
+        """
+        self.logger = logger
+        self.min_delay = min_delay
+        self.max_delay = max_delay
+        self.short_text_threshold = short_text_threshold
+        self.long_text_threshold = long_text_threshold
+        self.chunk_size = chunk_size
+
+    def calculate_delay(self, text_length: int) -> float:
+        """根据文本长度计算延迟时间
+
+        参数:
+            text_length: 文本长度
+
+        返回:
+            延迟时间（秒）
+        """
+        if text_length <= self.short_text_threshold:
+            # 短文本使用较大延迟
+            return self.max_delay
+        elif text_length >= self.long_text_threshold:
+            # 长文本使用较小延迟
+            return self.min_delay
+        else:
+            # 中等长度文本使用线性插值计算延迟
+            # 使用对数函数使延迟变化更平滑
+            ratio = math.log(text_length / self.short_text_threshold) / math.log(
+                self.long_text_threshold / self.short_text_threshold
+            )
+            return self.max_delay - ratio * (self.max_delay - self.min_delay)
+
+    def split_text_into_chunks(self, text: str) -> List[str]:
+        """将文本分割成小块
+
+        参数:
+            text: 要分割的文本
+
+        返回:
+            文本块列表
+        """
+        return [
+            text[i : i + self.chunk_size] for i in range(0, len(text), self.chunk_size)
+        ]
+
+    async def optimize_stream_output(
+        self,
+        text: str,
+        create_response_chunk: Callable[[str], Any],
+        format_chunk: Callable[[Any], str],
+    ) -> AsyncGenerator[str, None]:
+        """优化流式输出
+
+        参数:
+            text: 要输出的文本
+            create_response_chunk: 创建响应块的函数，接收文本，返回响应块
+            format_chunk: 格式化响应块的函数，接收响应块，返回格式化后的字符串
+
+        返回:
+            异步生成器，生成格式化后的响应块
+        """
+        if not text:
+            return
+
+        # 计算智能延迟时间
+        delay = self.calculate_delay(len(text))
+        # if self.logger:
+        #     self.logger.info(f"Text length: {len(text)}, delay: {delay:.4f}s")
+
+        # 根据文本长度决定输出方式
+        if len(text) >= self.long_text_threshold:
+            # 长文本：分块输出
+            chunks = self.split_text_into_chunks(text)
+            # if self.logger:
+            #     self.logger.info(f"Long text: splitting into {len(chunks)} chunks")
+            for chunk_text in chunks:
+                chunk_response = create_response_chunk(chunk_text)
+                yield format_chunk(chunk_response)
+                await asyncio.sleep(delay)
+        else:
+            # 短文本：逐字符输出
+            for char in text:
+                char_chunk = create_response_chunk(char)
+                yield format_chunk(char_chunk)
+                await asyncio.sleep(delay)
+
+
+# 创建默认的优化器实例，可以直接导入使用
+openai_optimizer = StreamOptimizer(
+    logger=logger_openai,
+    min_delay=settings.STREAM_MIN_DELAY,
+    max_delay=settings.STREAM_MAX_DELAY,
+    short_text_threshold=settings.STREAM_SHORT_TEXT_THRESHOLD,
+    long_text_threshold=settings.STREAM_LONG_TEXT_THRESHOLD,
+    chunk_size=settings.STREAM_CHUNK_SIZE,
+)
+
+gemini_optimizer = StreamOptimizer(
+    logger=logger_gemini,
+    min_delay=settings.STREAM_MIN_DELAY,
+    max_delay=settings.STREAM_MAX_DELAY,
+    short_text_threshold=settings.STREAM_SHORT_TEXT_THRESHOLD,
+    long_text_threshold=settings.STREAM_LONG_TEXT_THRESHOLD,
+    chunk_size=settings.STREAM_CHUNK_SIZE,
+)

app/log/logger.py

@@ -133,3 +133,43 @@ def get_retry_logger():
 
 def get_image_create_logger():
     return Logger.setup_logger("image_create")
+
+
+def get_exceptions_logger():
+    return Logger.setup_logger("exceptions")
+
+
+def get_application_logger():
+    return Logger.setup_logger("application")
+
+
+def get_initialization_logger():
+    return Logger.setup_logger("initialization")
+
+
+def get_middleware_logger():
+    return Logger.setup_logger("middleware")
+
+
+def get_routes_logger():
+    return Logger.setup_logger("routes")
+
+
+def get_config_routes_logger():
+    return Logger.setup_logger("config_routes")
+
+
+def get_config_logger():
+    return Logger.setup_logger("config")
+
+
+def get_database_logger():
+    return Logger.setup_logger("database")
+
+
+def get_log_routes_logger():
+    return Logger.setup_logger("log_routes")
+
+
+def get_stats_logger():
+    return Logger.setup_logger("stats")

app/main.py

@@ -1,130 +1,18 @@
-from fastapi import FastAPI, Request
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import HTMLResponse, RedirectResponse
-from fastapi.templating import Jinja2Templates
-from app.core.logger import get_main_logger
-from app.core.security import verify_auth_token
-from app.services.key_manager import get_key_manager_instance
-from app.core.config import settings
+"""
+应用程序入口模块
+"""
 
-from app.api import gemini_routes, openai_routes
 import uvicorn
 
+from app.core.application import create_app
+from app.log.logger import get_main_logger
+
+# 创建应用程序实例
+app = create_app()
 
 # 配置日志
 logger = get_main_logger()
 
-app = FastAPI()
-
-# 配置Jinja2模板
-templates = Jinja2Templates(directory="app/templates")
-
-# 创建 KeyManager 实例
-key_manager = None
-
-@app.on_event("startup")
-async def startup_event():
-    global key_manager
-    logger.info("Application starting up...")
-    try:
-        key_manager = await get_key_manager_instance(settings.API_KEYS)
-        logger.info("KeyManager initialized successfully")
-    except Exception as e:
-        logger.error(f"Failed to initialize KeyManager: {str(e)}")
-        raise
-
-# 添加中间件来处理未经身份验证的请求
-@app.middleware("http")
-async def auth_middleware(request: Request, call_next):
-    # 允许 gemini_routes 和 openai_routes 中的端点绕过身份验证
-    if (request.url.path not in ["/", "/auth"] and 
-        not request.url.path.startswith("/static") and
-        not request.url.path.startswith("/gemini") and
-        not request.url.path.startswith("/v1") and
-        not request.url.path.startswith("/v1beta") and
-        not request.url.path.startswith("/health") and
-        not request.url.path.startswith("/hf")):
-        auth_token = request.cookies.get("auth_token")
-        if not auth_token or not verify_auth_token(auth_token):
-            logger.warning(f"Unauthorized access attempt to {request.url.path}")
-            return RedirectResponse(url="/")
-        logger.debug("Request authenticated successfully")
-    response = await call_next(request)
-    return response
-
-# 添加请求日志中间件
-# app.add_middleware(RequestLoggingMiddleware)
-
-# 配置CORS中间件
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  # 生产环境建议配置具体的域名
-    allow_credentials=True,
-    allow_methods=["GET", "POST", "PUT", "DELETE", "OPTIONS"],  # 明确指定允许的HTTP方法
-    allow_headers=["*"],  # 生产环境建议配置具体的请求头
-    expose_headers=["*"],  # 允许前端访问的响应头
-    max_age=600,  # 预检请求缓存时间(秒)
-)
-
-# 包含所有路由
-app.include_router(openai_routes.router)
-app.include_router(gemini_routes.router)
-app.include_router(gemini_routes.router_v1beta)
-
-
-@app.get("/", response_class=HTMLResponse)
-async def auth_page(request: Request):
-    return templates.TemplateResponse("auth.html", {"request": request})
-
-
-@app.post("/auth")
-async def authenticate(request: Request):
-    try:
-        form = await request.form()
-        auth_token = form.get("auth_token")
-        if not auth_token:
-            logger.warning("Authentication attempt with empty token")
-            return RedirectResponse(url="/", status_code=302)
-        
-        if verify_auth_token(auth_token):
-            logger.info("Successful authentication")
-            response = RedirectResponse(url="/keys", status_code=302)
-            response.set_cookie(key="auth_token", value=auth_token, httponly=True, max_age=3600)
-            return response
-        logger.warning("Failed authentication attempt with invalid token")
-        return RedirectResponse(url="/", status_code=302)
-    except Exception as e:
-        logger.error(f"Authentication error: {str(e)}")
-        return RedirectResponse(url="/", status_code=302)
-
-@app.get("/keys", response_class=HTMLResponse)
-async def keys_page(request: Request):
-    try:
-        auth_token = request.cookies.get("auth_token")
-        if not auth_token or not verify_auth_token(auth_token):
-            logger.warning("Unauthorized access attempt to keys page")
-            return RedirectResponse(url="/", status_code=302)
-        
-        keys_status = await key_manager.get_keys_by_status()
-        total = len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"])
-        logger.info(f"Keys status retrieved successfully. Total keys: {total}")
-        return templates.TemplateResponse("keys_status.html", {
-            "request": request,
-            "valid_keys": keys_status["valid_keys"],
-            "invalid_keys": keys_status["invalid_keys"],
-            "total": total
-        })
-    except Exception as e:
-        logger.error(f"Error retrieving keys status: {str(e)}")
-        raise
-
-
-@app.get("/health")
-async def health_check(request: Request):
-    logger.info("Health check endpoint called")
-    return {"status": "healthy"}
-    
-    
 if __name__ == "__main__":
     logger.info("Starting application server...")
     uvicorn.run(app, host="0.0.0.0", port=8001)

app/middleware/middleware.py

@@ -0,0 +1,73 @@
+"""
+中间件配置模块，负责设置和配置应用程序的中间件
+"""
+
+from fastapi import FastAPI, Request
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import RedirectResponse
+from starlette.middleware.base import BaseHTTPMiddleware
+
+# from app.middleware.request_logging_middleware import RequestLoggingMiddleware
+from app.core.constants import API_VERSION
+from app.core.security import verify_auth_token
+from app.log.logger import get_middleware_logger
+
+logger = get_middleware_logger()
+
+
+class AuthMiddleware(BaseHTTPMiddleware):
+    """
+    认证中间件，处理未经身份验证的请求
+    """
+
+    async def dispatch(self, request: Request, call_next):
+        # 允许特定路径绕过身份验证
+        if (
+            request.url.path not in ["/", "/auth"]
+            and not request.url.path.startswith("/static")
+            and not request.url.path.startswith("/gemini")
+            and not request.url.path.startswith("/v1")
+            and not request.url.path.startswith(f"/{API_VERSION}")
+            and not request.url.path.startswith("/health")
+            and not request.url.path.startswith("/hf")
+        ):
+
+            auth_token = request.cookies.get("auth_token")
+            if not auth_token or not verify_auth_token(auth_token):
+                logger.warning(f"Unauthorized access attempt to {request.url.path}")
+                return RedirectResponse(url="/")
+            logger.debug("Request authenticated successfully")
+
+        response = await call_next(request)
+        return response
+
+
+def setup_middlewares(app: FastAPI) -> None:
+    """
+    设置应用程序的中间件
+
+    Args:
+        app: FastAPI应用程序实例
+    """
+    # 添加认证中间件
+    app.add_middleware(AuthMiddleware)
+
+    # 添加请求日志中间件（可选，默认注释掉）
+    # app.add_middleware(RequestLoggingMiddleware)
+
+    # 配置CORS中间件
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=["*"],  # 生产环境建议配置具体的域名
+        allow_credentials=True,
+        allow_methods=[
+            "GET",
+            "POST",
+            "PUT",
+            "DELETE",
+            "OPTIONS",
+        ],  # 明确指定允许的HTTP方法
+        allow_headers=["*"],  # 生产环境建议配置具体的请求头
+        expose_headers=["*"],  # 允许前端访问的响应头
+        max_age=600,  # 预检请求缓存时间(秒)
+    )

app/middleware/request_logging_middleware.py

@@ -1,7 +1,9 @@
+import json
+
 from fastapi import Request
 from starlette.middleware.base import BaseHTTPMiddleware
-import json
-from app.core.logger import get_request_logger
+
+from app.log.logger import get_request_logger
 
 logger = get_request_logger()
 
@@ -20,7 +22,9 @@ class RequestLoggingMiddleware(BaseHTTPMiddleware):
                 # 尝试格式化JSON
                 try:
                     formatted_body = json.loads(body_str)
-                    logger.info(f"Formatted request body:\n{json.dumps(formatted_body, indent=2, ensure_ascii=False)}")
+                    logger.info(
+                        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.")
         except Exception as e:

app/router/config_routes.py

@@ -0,0 +1,48 @@
+"""
+配置路由模块
+"""
+from typing import Any, Dict
+from fastapi import APIRouter, HTTPException, Request
+from fastapi.responses import RedirectResponse
+
+from app.core.security import verify_auth_token
+from app.log.logger import get_config_routes_logger
+from app.service.config.config_service import ConfigService
+
+# 创建路由
+router = APIRouter(prefix="/api/config", tags=["config"])
+
+logger = get_config_routes_logger()
+
+
+@router.get("", response_model=Dict[str, Any])
+async def get_config(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 config page")
+        return RedirectResponse(url="/", status_code=302)
+    return await ConfigService.get_config()
+
+
+@router.put("", response_model=Dict[str, Any])
+async def update_config(config_data: Dict[str, Any], 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 config page")
+        return RedirectResponse(url="/", status_code=302)
+    try:
+        return await ConfigService.update_config(config_data)
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=str(e))
+
+
+@router.post("/reset", response_model=Dict[str, Any])
+async def reset_config(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 config page")
+        return RedirectResponse(url="/", status_code=302)
+    try:
+        return await ConfigService.reset_config()
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=str(e))

app/router/gemini_routes.py

@@ -0,0 +1,237 @@
+from fastapi import APIRouter, Depends, HTTPException
+from fastapi.responses import StreamingResponse, JSONResponse
+from copy import deepcopy
+from app.config.config import settings
+from app.log.logger import get_gemini_logger
+from app.core.security import SecurityService
+from app.domain.gemini_models import GeminiContent, GeminiRequest
+from app.service.chat.gemini_chat_service import GeminiChatService
+from app.service.key.key_manager import KeyManager, get_key_manager_instance
+from app.service.model.model_service import ModelService
+from app.handler.retry_handler import RetryHandler
+from app.core.constants import API_VERSION
+
+# 路由设置
+router = APIRouter(prefix=f"/gemini/{API_VERSION}")
+router_v1beta = APIRouter(prefix=f"/{API_VERSION}")
+logger = get_gemini_logger()
+
+# 初始化服务
+security_service = SecurityService()
+model_service = ModelService()
+
+
+async def get_key_manager():
+    """获取密钥管理器实例"""
+    return await get_key_manager_instance()
+
+
+async def get_next_working_key(key_manager: KeyManager = Depends(get_key_manager)):
+    """获取下一个可用的API密钥"""
+    return await key_manager.get_next_working_key()
+
+
+async def get_chat_service(key_manager: KeyManager = Depends(get_key_manager)):
+    """获取Gemini聊天服务实例"""
+    return GeminiChatService(settings.BASE_URL, key_manager)
+
+
+@router.get("/models")
+@router_v1beta.get("/models")
+async def list_models(
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    key_manager: KeyManager = Depends(get_key_manager)
+):
+    """获取可用的Gemini模型列表"""
+    logger.info("-" * 50 + "list_gemini_models" + "-" * 50)
+    logger.info("Handling Gemini models list request")
+    
+    api_key = await key_manager.get_first_valid_key()
+    logger.info(f"Using API key: {api_key}")
+    
+    models_json = model_service.get_gemini_models(api_key)
+    model_mapping = {x.get("name", "").split("/", maxsplit=1)[1]: x for x in models_json["models"]}
+    
+    # 添加搜索模型
+    if model_service.search_models:
+        for name in model_service.search_models:
+            model = model_mapping.get(name)
+            if not model:
+                continue
+                
+            item = deepcopy(model)
+            item["name"] = f"models/{name}-search"
+            display_name = f'{item.get("displayName")} For Search'
+            item["displayName"] = display_name
+            item["description"] = display_name
+            
+            models_json["models"].append(item)
+    
+    # 添加图像生成模型
+    if model_service.image_models:
+        for name in model_service.image_models:
+            model = model_mapping.get(name)
+            if not model:
+                continue
+                
+            item = deepcopy(model)
+            item["name"] = f"models/{name}-image"
+            display_name = f'{item.get("displayName")} For Image'
+            item["displayName"] = display_name
+            item["description"] = display_name
+            
+            models_json["models"].append(item)
+            
+    return models_json
+
+
+@router.post("/models/{model_name}:generateContent")
+@router_v1beta.post("/models/{model_name}:generateContent")
+@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
+async def generate_content(
+    model_name: str,
+    request: GeminiRequest,
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    api_key: str = Depends(get_next_working_key),
+    chat_service: GeminiChatService = Depends(get_chat_service)
+):
+    """非流式生成内容"""
+    logger.info("-" * 50 + "gemini_generate_content" + "-" * 50)
+    logger.info(f"Handling Gemini content generation request for model: {model_name}")
+    logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
+    logger.info(f"Using API key: {api_key}")
+    
+    if not model_service.check_model_support(model_name):
+        raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
+    
+    try:
+        response = await chat_service.generate_content(
+            model=model_name,
+            request=request,
+            api_key=api_key
+        )
+        return response
+    except Exception as e:
+        logger.error(f"Chat completion failed after retries: {str(e)}")
+        raise HTTPException(status_code=500, detail="Chat completion failed") from e
+
+
+@router.post("/models/{model_name}:streamGenerateContent")
+@router_v1beta.post("/models/{model_name}:streamGenerateContent")
+@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
+async def stream_generate_content(
+    model_name: str,
+    request: GeminiRequest,
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    api_key: str = Depends(get_next_working_key),
+    chat_service: GeminiChatService = Depends(get_chat_service)
+):
+    """流式生成内容"""
+    logger.info("-" * 50 + "gemini_stream_generate_content" + "-" * 50)
+    logger.info(f"Handling Gemini streaming content generation for model: {model_name}")
+    logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
+    logger.info(f"Using API key: {api_key}")
+    
+    if not model_service.check_model_support(model_name):
+        raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
+    
+    try:
+        response_stream = chat_service.stream_generate_content(
+            model=model_name,
+            request=request,
+            api_key=api_key
+        )
+        return StreamingResponse(response_stream, media_type="text/event-stream")
+    except Exception as e:
+        logger.error(f"Streaming request failed: {str(e)}")
+        raise HTTPException(status_code=500, detail="Streaming request failed") from e
+
+@router.post("/reset-all-fail-counts")
+async def reset_all_key_fail_counts(key_type: str = None, key_manager: KeyManager = Depends(get_key_manager)):
+    """批量重置Gemini API密钥的失败计数，可选择性地仅重置有效或无效密钥"""
+    logger.info("-" * 50 + "reset_all_gemini_key_fail_counts" + "-" * 50)
+    logger.info(f"Received reset request with key_type: {key_type}")
+    
+    try:
+        # 获取分类后的密钥
+        keys_by_status = await key_manager.get_keys_by_status()
+        valid_keys = keys_by_status.get("valid_keys", {})
+        invalid_keys = keys_by_status.get("invalid_keys", {})
+        
+        # 根据类型选择要重置的密钥
+        keys_to_reset = []
+        if key_type == "valid":
+            keys_to_reset = list(valid_keys.keys())
+            logger.info(f"Resetting only valid keys, count: {len(keys_to_reset)}")
+        elif key_type == "invalid":
+            keys_to_reset = list(invalid_keys.keys())
+            logger.info(f"Resetting only invalid keys, count: {len(keys_to_reset)}")
+        else:
+            # 重置所有密钥
+            await key_manager.reset_failure_counts()
+            return JSONResponse({"success": True, "message": "所有密钥的失败计数已重置"})
+        
+        # 批量重置指定类型的密钥
+        for key in keys_to_reset:
+            await key_manager.reset_key_failure_count(key)
+        
+        return JSONResponse({
+            "success": True,
+            "message": f"{key_type}密钥的失败计数已重置",
+            "reset_count": len(keys_to_reset)
+        })
+    except Exception as e:
+        logger.error(f"Failed to reset key failure counts: {str(e)}")
+        return JSONResponse({"success": False, "message": f"批量重置失败: {str(e)}"}, status_code=500)
+
+
+@router.post("/reset-fail-count/{api_key}")
+async def reset_key_fail_count(api_key: str, key_manager: KeyManager = Depends(get_key_manager)):
+    """重置指定Gemini API密钥的失败计数"""
+    logger.info("-" * 50 + "reset_gemini_key_fail_count" + "-" * 50)
+    logger.info(f"Resetting failure count for API key: {api_key}")
+    
+    try:
+        result = await key_manager.reset_key_failure_count(api_key)
+        if result:
+            return JSONResponse({"success": True, "message": "失败计数已重置"})
+        return JSONResponse({"success": False, "message": "未找到指定密钥"}, status_code=404)
+    except Exception as e:
+        logger.error(f"Failed to reset key failure count: {str(e)}")
+        return JSONResponse({"success": False, "message": f"重置失败: {str(e)}"}, status_code=500)
+
+@router.post("/verify-key/{api_key}")
+async def verify_key(api_key: str, chat_service: GeminiChatService = Depends(get_chat_service), key_manager: KeyManager = Depends(get_key_manager)):
+    """验证Gemini API密钥的有效性"""
+    logger.info("-" * 50 + "verify_gemini_key" + "-" * 50)
+    logger.info("Verifying API key validity")
+    
+    try:
+        # 使用generate_content接口测试key的有效性
+        gemini_request = GeminiRequest(
+            contents=[
+                GeminiContent(
+                    role="user",
+                    parts=[{"text": "hi"}]
+                )
+            ]
+        )
+        
+        response = await chat_service.generate_content(
+            settings.TEST_MODEL,
+            gemini_request,
+            api_key
+        )
+        
+        if response:
+            return JSONResponse({"status": "valid"})        
+    except Exception as e:
+        logger.error(f"Key verification failed: {str(e)}")
+        
+        # 验证出现异常时增加失败计数
+        async with key_manager.failure_count_lock:
+            if api_key in key_manager.key_failure_counts:
+                key_manager.key_failure_counts[api_key] += 1
+                logger.warning(f"Verification exception for key: {api_key}, incrementing failure count")
+        
+        return JSONResponse({"status": "invalid", "error": str(e)})

app/router/log_routes.py

@@ -0,0 +1,71 @@
+"""
+日志路由模块
+"""
+from typing import Any, Dict, List, Optional
+from datetime import datetime
+from pydantic import BaseModel
+from fastapi import APIRouter, HTTPException, Request, Query
+from fastapi.responses import RedirectResponse
+
+from app.core.security import verify_auth_token
+from app.log.logger import get_log_routes_logger
+from app.database.services import get_error_logs, get_error_logs_count
+
+# 创建路由
+router = APIRouter(prefix="/api/logs", tags=["logs"])
+
+logger = get_log_routes_logger()
+
+
+# Define a response model that includes the total count for pagination
+class ErrorLogResponse(BaseModel):
+    logs: List[Dict[str, Any]]
+    total: int
+
+@router.get("/errors", response_model=ErrorLogResponse)
+async def get_error_logs_api(
+    request: Request,
+    limit: int = Query(20, ge=1, le=1000), # Default to 20 to match frontend
+    offset: int = Query(0, ge=0),
+    key_search: Optional[str] = Query(None, description="Search term for Gemini key (partial match)"),
+    error_search: Optional[str] = Query(None, description="Search term for error type or log message"),
+    start_date: Optional[datetime] = Query(None, description="Start datetime for filtering (YYYY-MM-DDTHH:MM)"),
+    end_date: Optional[datetime] = Query(None, description="End datetime for filtering (YYYY-MM-DDTHH:MM)")
+):
+    """
+    获取错误日志
+    
+    Args:
+        request: 请求对象
+        limit: 限制数量
+        offset: 偏移量
+    
+    Returns:
+        ErrorLogResponse: An object containing the list of logs and the total count.
+    """
+    auth_token = request.cookies.get("auth_token")
+    if not auth_token or not verify_auth_token(auth_token):
+        logger.warning("Unauthorized access attempt to error logs")
+        return RedirectResponse(url="/", status_code=302)
+    
+    try:
+        # Fetch logs with search parameters
+        logs = await get_error_logs(
+            limit=limit,
+            offset=offset,
+            key_search=key_search,
+            error_search=error_search,
+            start_date=start_date,
+            end_date=end_date
+        )
+        # Fetch total count with the same search parameters
+        total_count = await get_error_logs_count(
+            key_search=key_search,
+            error_search=error_search,
+            start_date=start_date,
+            end_date=end_date
+        )
+        return ErrorLogResponse(logs=logs, total=total_count)
+    except Exception as e:
+        logger.exception(f"Failed to get error logs: {str(e)}") # Use logger.exception for stack trace
+        raise HTTPException(status_code=500, detail=f"Failed to get error logs: {str(e)}")

app/router/openai_routes.py

@@ -1,66 +1,88 @@
-from fastapi import HTTPException, APIRouter, Depends
+from fastapi import APIRouter, Depends, HTTPException
 from fastapi.responses import StreamingResponse
 
-from app.core.config import settings
-from app.core.logger import get_openai_logger
+from app.config.config import settings
 from app.core.security import SecurityService
-from app.schemas.openai_models import ChatRequest, EmbeddingRequest, ImageGenerationRequest
-from app.services.chat.retry_handler import RetryHandler
-from app.services.embedding_service import EmbeddingService
-from app.services.image_create_service import ImageCreateService
-from app.services.key_manager import KeyManager, get_key_manager_instance
-from app.services.model_service import ModelService
-from app.services.openai_chat_service import OpenAIChatService
+from app.domain.openai_models import (
+    ChatRequest,
+    EmbeddingRequest,
+    ImageGenerationRequest,
+)
+from app.handler.retry_handler import RetryHandler
+from app.log.logger import get_openai_logger
+from app.service.chat.openai_chat_service import OpenAIChatService
+from app.service.embedding.embedding_service import EmbeddingService
+from app.service.image.image_create_service import ImageCreateService
+from app.service.key.key_manager import KeyManager, get_key_manager_instance
+from app.service.model.model_service import ModelService
 
 router = APIRouter()
 logger = get_openai_logger()
 
 # 初始化服务
-security_service = SecurityService(settings.ALLOWED_TOKENS, settings.AUTH_TOKEN)
-model_service = ModelService(settings.MODEL_SEARCH)
-embedding_service = EmbeddingService(settings.BASE_URL)
+security_service = SecurityService()
+model_service = ModelService()
+embedding_service = EmbeddingService()
 image_create_service = ImageCreateService()
 
+
 async def get_key_manager():
     return await get_key_manager_instance()
 
-async def get_next_working_key_wrapper(key_manager: KeyManager = Depends(get_key_manager)):
+
+async def get_next_working_key_wrapper(
+    key_manager: KeyManager = Depends(get_key_manager),
+):
     return await key_manager.get_next_working_key()
 
+
+async def get_openai_chat_service(key_manager: KeyManager = Depends(get_key_manager)):
+    """获取OpenAI聊天服务实例"""
+    return OpenAIChatService(settings.BASE_URL, key_manager)
+
+
 @router.get("/v1/models")
 @router.get("/hf/v1/models")
 async def list_models(
     _=Depends(security_service.verify_authorization),
-    key_manager: KeyManager = Depends(get_key_manager)
+    key_manager: KeyManager = Depends(get_key_manager),
 ):
     logger.info("-" * 50 + "list_models" + "-" * 50)
     logger.info("Handling models list request")
-    api_key = await key_manager.get_next_working_key()
+    api_key = await key_manager.get_first_valid_key()
     logger.info(f"Using API key: {api_key}")
     try:
         return model_service.get_gemini_openai_models(api_key)
     except Exception as e:
         logger.error(f"Error getting models list: {str(e)}")
-        raise HTTPException(status_code=500, detail="Internal server error while fetching models list") from e
+        raise HTTPException(
+            status_code=500, detail="Internal server error while fetching models list"
+        ) from e
 
 
 @router.post("/v1/chat/completions")
 @router.post("/hf/v1/chat/completions")
-@RetryHandler(max_retries=3, key_manager=Depends(get_key_manager), key_arg="api_key")
+@RetryHandler(max_retries=settings.MAX_RETRIES, key_arg="api_key")
 async def chat_completion(
     request: ChatRequest,
     _=Depends(security_service.verify_authorization),
     api_key: str = Depends(get_next_working_key_wrapper),
-    key_manager: KeyManager = Depends(get_key_manager)
+    key_manager: KeyManager = Depends(get_key_manager), # 保留 key_manager 用于获取 paid_key
+    chat_service: OpenAIChatService = Depends(get_openai_chat_service),
 ):
     # 如果model是imagen3,使用paid_key
     if request.model == f"{settings.CREATE_IMAGE_MODEL}-chat":
         api_key = await key_manager.get_paid_key()
-    chat_service = OpenAIChatService(settings.BASE_URL, key_manager)
     logger.info("-" * 50 + "chat_completion" + "-" * 50)
     logger.info(f"Handling chat completion request for model: {request.model}")
     logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
     logger.info(f"Using API key: {api_key}")
+
+    if not model_service.check_model_support(request.model):
+        raise HTTPException(
+            status_code=400, detail=f"Model {request.model} is not supported"
+        )
+
     try:
         # 如果model是imagen3,使用paid_key
         if request.model == f"{settings.CREATE_IMAGE_MODEL}-chat":
@@ -76,6 +98,7 @@ async def chat_completion(
         logger.error(f"Chat completion failed after retries: {str(e)}")
         raise HTTPException(status_code=500, detail="Chat completion failed") from e
 
+
 @router.post("/v1/images/generations")
 @router.post("/hf/v1/images/generations")
 async def generate_image(
@@ -91,14 +114,17 @@ async def generate_image(
         return response
     except Exception as e:
         logger.error(f"Image generation request failed: {str(e)}")
-        raise HTTPException(status_code=500, detail="Image generation request failed") from e
+        raise HTTPException(
+            status_code=500, detail="Image generation request failed"
+        ) from e
+
 
 @router.post("/v1/embeddings")
 @router.post("/hf/v1/embeddings")
 async def embedding(
     request: EmbeddingRequest,
     _=Depends(security_service.verify_authorization),
-    key_manager: KeyManager = Depends(get_key_manager)
+    key_manager: KeyManager = Depends(get_key_manager),
 ):
     logger.info("-" * 50 + "embedding" + "-" * 50)
     logger.info(f"Handling embedding request for model: {request.model}")
@@ -114,11 +140,12 @@ async def embedding(
         logger.error(f"Embedding request failed: {str(e)}")
         raise HTTPException(status_code=500, detail="Embedding request failed") from e
 
+
 @router.get("/v1/keys/list")
 @router.get("/hf/v1/keys/list")
 async def get_keys_list(
     _=Depends(security_service.verify_auth_token),
-    key_manager: KeyManager = Depends(get_key_manager)
+    key_manager: KeyManager = Depends(get_key_manager),
 ):
     """获取有效和无效的API key列表"""
     logger.info("-" * 50 + "get_keys_list" + "-" * 50)
@@ -129,13 +156,12 @@ async def get_keys_list(
             "status": "success",
             "data": {
                 "valid_keys": keys_status["valid_keys"],
-                "invalid_keys": keys_status["invalid_keys"]
+                "invalid_keys": keys_status["invalid_keys"],
             },
-            "total": len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"])
+            "total": len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"]),
         }
     except Exception as e:
         logger.error(f"Error getting keys list: {str(e)}")
         raise HTTPException(
-            status_code=500,
-            detail="Internal server error while fetching keys list"
+            status_code=500, detail="Internal server error while fetching keys list"
         ) from e

app/router/routes.py

@@ -0,0 +1,190 @@
+"""
+路由配置模块，负责设置和配置应用程序的路由
+"""
+
+from fastapi import FastAPI, Request
+from fastapi.responses import HTMLResponse, RedirectResponse
+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.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
+
+logger = get_routes_logger()
+
+# 配置Jinja2模板
+templates = Jinja2Templates(directory="app/templates")
+
+
+def setup_routers(app: FastAPI) -> None:
+    """
+    设置应用程序的路由
+
+    Args:
+        app: FastAPI应用程序实例
+    """
+    # 包含API路由
+    app.include_router(openai_routes.router)
+    app.include_router(gemini_routes.router)
+    app.include_router(gemini_routes.router_v1beta)
+    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
+
+    # 添加页面路由
+    setup_page_routes(app)
+
+    # 添加健康检查路由
+    setup_health_routes(app)
+    setup_api_stats_routes(app) # Add API stats routes
+
+
+def setup_page_routes(app: FastAPI) -> None:
+    """
+    设置页面相关的路由
+
+    Args:
+        app: FastAPI应用程序实例
+    """
+
+    @app.get("/", response_class=HTMLResponse)
+    async def auth_page(request: Request):
+        """认证页面"""
+        return templates.TemplateResponse("auth.html", {"request": request})
+
+    @app.post("/auth")
+    async def authenticate(request: Request):
+        """处理认证请求"""
+        try:
+            form = await request.form()
+            auth_token = form.get("auth_token")
+            if not auth_token:
+                logger.warning("Authentication attempt with empty token")
+                return RedirectResponse(url="/", status_code=302)
+
+            if verify_auth_token(auth_token):
+                logger.info("Successful authentication")
+                response = RedirectResponse(url="/config", status_code=302)
+                response.set_cookie(
+                    key="auth_token", value=auth_token, httponly=True, max_age=3600
+                )
+                return response
+            logger.warning("Failed authentication attempt with invalid token")
+            return RedirectResponse(url="/", status_code=302)
+        except Exception as e:
+            logger.error(f"Authentication error: {str(e)}")
+            return RedirectResponse(url="/", status_code=302)
+
+    @app.get("/keys", response_class=HTMLResponse)
+    async def keys_page(request: Request):
+        """密钥管理页面"""
+        try:
+            auth_token = request.cookies.get("auth_token")
+            if not auth_token or not verify_auth_token(auth_token):
+                logger.warning("Unauthorized access attempt to keys page")
+                return RedirectResponse(url="/", status_code=302)
+
+            key_manager = await get_key_manager_instance()
+            keys_status = await key_manager.get_keys_by_status()
+            total_keys = len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"])
+            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()
+            logger.info(f"API stats retrieved: {api_stats}")
+
+            logger.info(f"Keys status retrieved successfully. Total keys: {total_keys}")
+            return templates.TemplateResponse(
+                "keys_status.html",
+                {
+                    "request": request,
+                    "valid_keys": keys_status["valid_keys"],
+                    "invalid_keys": keys_status["invalid_keys"],
+                    "total_keys": total_keys, # Renamed for clarity
+                    "valid_key_count": valid_key_count, # Added count
+                    "invalid_key_count": invalid_key_count, # Added count
+                    "api_stats": api_stats, # <-- Pass stats to template
+                },
+            )
+        except Exception as e:
+            logger.error(f"Error retrieving keys status or API stats: {str(e)}")
+            # Optionally, render template with error or default stats
+            # For now, re-raise to show error page
+            raise
+            
+    @app.get("/config", response_class=HTMLResponse)
+    async def config_page(request: Request):
+        """配置编辑页面"""
+        try:
+            auth_token = request.cookies.get("auth_token")
+            if not auth_token or not verify_auth_token(auth_token):
+                logger.warning("Unauthorized access attempt to config page")
+                return RedirectResponse(url="/", status_code=302)
+                
+            logger.info("Config page accessed successfully")
+            return templates.TemplateResponse("config_editor.html", {"request": request})
+        except Exception as e:
+            logger.error(f"Error accessing config page: {str(e)}")
+            raise
+            
+    @app.get("/logs", response_class=HTMLResponse)
+    async def logs_page(request: Request):
+        """错误日志页面"""
+        try:
+            auth_token = request.cookies.get("auth_token")
+            if not auth_token or not verify_auth_token(auth_token):
+                logger.warning("Unauthorized access attempt to logs page")
+                return RedirectResponse(url="/", status_code=302)
+                
+            logger.info("Logs page accessed successfully")
+            return templates.TemplateResponse("error_logs.html", {"request": request})
+        except Exception as e:
+            logger.error(f"Error accessing logs page: {str(e)}")
+            raise
+
+
+def setup_health_routes(app: FastAPI) -> None:
+    """
+    设置健康检查相关的路由
+
+    Args:
+        app: FastAPI应用程序实例
+    """
+
+    @app.get("/health")
+    async def health_check(request: Request):
+        """健康检查端点"""
+        logger.info("Health check endpoint called")
+        return {"status": "healthy"}
+
+
+def setup_api_stats_routes(app: FastAPI) -> None:
+    """
+    设置 API 统计相关的路由
+
+    Args:
+        app: FastAPI应用程序实例
+    """
+    @app.get("/api/stats/details")
+    async def api_stats_details(request: Request, period: str):
+        """获取指定时间段内的 API 调用详情"""
+        try:
+            # 验证认证
+            auth_token = request.cookies.get("auth_token")
+            if not auth_token or not verify_auth_token(auth_token):
+                logger.warning("Unauthorized access attempt to API stats details")
+                # Returning JSON error instead of redirect for API endpoint
+                return {"error": "Unauthorized"}, 401
+
+            logger.info(f"Fetching API call details for period: {period}")
+            details = await get_api_call_details(period)
+            return details
+        except ValueError as e:
+            logger.warning(f"Invalid period requested for API stats details: {period} - {str(e)}")
+            return {"error": str(e)}, 400
+        except Exception as e:
+            logger.error(f"Error fetching API stats details for period {period}: {str(e)}")
+            return {"error": "Internal server error"}, 500

app/router/scheduler_routes.py

@@ -0,0 +1,63 @@
+"""
+定时任务控制路由模块
+"""
+
+from fastapi import APIRouter, Request, HTTPException, status # 移除 Depends, 添加 Request
+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
+
+logger = get_routes_logger()
+
+router = APIRouter(
+    prefix="/api/scheduler",
+    tags=["Scheduler"]
+    # 移除全局依赖
+)
+
+# 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.post("/start", summary="启动定时任务")
+async def start_scheduler_endpoint(request: Request): # 添加 request 参数
+    """Start the background scheduler task"""
+    """
+    await verify_token(request) # 在函数开始处进行认证检查
+    """
+    try:
+        logger.info("Received request to start scheduler.")
+        start_scheduler() # 调用 key_checker 中的函数
+        return JSONResponse(content={"message": "Scheduler started successfully."}, status_code=status.HTTP_200_OK)
+    except Exception as e:
+        logger.error(f"Error starting scheduler: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Failed to start scheduler: {str(e)}"
+        )
+
+@router.post("/stop", summary="停止定时任务")
+async def stop_scheduler_endpoint(request: Request): # 添加 request 参数
+    """Stop the background scheduler task"""
+    """
+    await verify_token(request) # 在函数开始处进行认证检查
+    """
+    try:
+        logger.info("Received request to stop scheduler.")
+        stop_scheduler() # 调用 key_checker 中的函数
+        return JSONResponse(content={"message": "Scheduler stopped successfully."}, status_code=status.HTTP_200_OK)
+    except Exception as e:
+        logger.error(f"Error stopping scheduler: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Failed to stop scheduler: {str(e)}"
+        )

app/scheduler/key_checker.py

@@ -0,0 +1,100 @@
+from apscheduler.schedulers.asyncio import AsyncIOScheduler
+from app.service.key.key_manager import get_key_manager_instance
+from app.service.chat.gemini_chat_service import GeminiChatService
+from app.domain.gemini_models import GeminiRequest, GeminiContent
+from app.config.config import settings
+from app.log.logger import Logger # 导入 Logger 类
+
+logger = Logger.setup_logger("scheduler") # 使用 Logger.setup_logger
+
+async def check_failed_keys():
+    """
+    定时检查失败次数大于0的API密钥，并尝试验证它们。
+    如果验证成功，重置失败计数；如果失败，增加失败计数。
+    """
+    logger.info("Starting scheduled check for failed API keys...")
+    try:
+        key_manager = await get_key_manager_instance()
+        # 确保 KeyManager 已经初始化
+        if not key_manager or not hasattr(key_manager, 'key_failure_counts'):
+            logger.warning("KeyManager instance not available or not initialized. Skipping check.")
+            return
+
+        # 创建 GeminiChatService 实例用于验证
+        # 注意：这里直接创建实例，而不是通过依赖注入，因为这是后台任务
+        chat_service = GeminiChatService(settings.BASE_URL, key_manager)
+
+        # 获取需要检查的 key 列表 (失败次数 > 0)
+        keys_to_check = []
+        async with key_manager.failure_count_lock: # 访问共享数据需要加锁
+            # 复制一份以避免在迭代时修改字典
+            failure_counts_copy = key_manager.key_failure_counts.copy()
+            keys_to_check = [key for key, count in failure_counts_copy.items() if count > 0] # 检查所有失败次数大于0的key
+
+        if not keys_to_check:
+            logger.info("No keys with failure count > 0 found. Skipping verification.")
+            return
+
+        logger.info(f"Found {len(keys_to_check)} keys with failure count > 0 to verify.")
+
+        for key in keys_to_check:
+            # 隐藏部分 key 用于日志记录
+            log_key = f"{key[:4]}...{key[-4:]}" if len(key) > 8 else key
+            logger.info(f"Verifying key: {log_key}...")
+            try:
+                # 构造测试请求
+                gemini_request = GeminiRequest(
+                    contents=[
+                        GeminiContent(
+                            role="user",
+                            parts=[{"text": "hi"}] # 使用简单的文本进行验证
+                        )
+                    ]
+                )
+                # 调用 generate_content 进行验证
+                await chat_service.generate_content(
+                    settings.TEST_MODEL, # 使用配置中定义的测试模型
+                    gemini_request,
+                    key
+                )
+                # 如果没有抛出异常，说明 key 有效
+                logger.info(f"Key {log_key} verification successful. Resetting failure count.")
+                await key_manager.reset_key_failure_count(key)
+            except Exception as e:
+                # 验证失败，增加失败计数
+                logger.warning(f"Key {log_key} verification failed: {str(e)}. Incrementing failure count.")
+                # 直接操作计数器，需要加锁
+                async with key_manager.failure_count_lock:
+                    # 再次检查 key 是否存在且失败次数未达上限
+                    if key in key_manager.key_failure_counts and key_manager.key_failure_counts[key] < key_manager.MAX_FAILURES:
+                        key_manager.key_failure_counts[key] += 1
+                        logger.info(f"Failure count for key {log_key} incremented to {key_manager.key_failure_counts[key]}.")
+                    elif key in key_manager.key_failure_counts:
+                         logger.warning(f"Key {log_key} reached MAX_FAILURES ({key_manager.MAX_FAILURES}). Not incrementing further.")
+
+
+    except Exception as e:
+        logger.error(f"An error occurred during the scheduled key check: {str(e)}", exc_info=True)
+
+def setup_scheduler():
+    """设置并启动 APScheduler"""
+    scheduler = AsyncIOScheduler(timezone=str(settings.TIMEZONE)) # 从配置读取时区
+    # 添加定时任务，例如每小时执行一次 (可以调整)
+    scheduler.add_job(check_failed_keys, 'interval', hours=settings.CHECK_INTERVAL_HOURS)
+    scheduler.start()
+    logger.info(f"Scheduler started. Key check job scheduled to run every {settings.CHECK_INTERVAL_HOURS} hour(s).")
+    return scheduler
+
+# 可以在这里添加一个全局的 scheduler 实例，以便在应用关闭时优雅地停止
+scheduler_instance = None
+
+def start_scheduler():
+    global scheduler_instance
+    if scheduler_instance is None:
+        scheduler_instance = setup_scheduler()
+
+def stop_scheduler():
+    global scheduler_instance
+    if scheduler_instance and scheduler_instance.running:
+        scheduler_instance.shutdown()
+        logger.info("Scheduler stopped.")

app/service/chat/gemini_chat_service.py

@@ -0,0 +1,299 @@
+# app/services/chat_service.py
+
+import json
+import re
+import datetime # Add datetime import
+import time # Add time import
+from typing import Any, AsyncGenerator, Dict, List
+from app.config.config import settings
+from app.domain.gemini_models import GeminiRequest
+from app.handler.response_handler import GeminiResponseHandler
+from app.handler.stream_optimizer import gemini_optimizer
+from app.log.logger import get_gemini_logger
+from app.service.client.api_client import GeminiApiClient
+from app.service.key.key_manager import KeyManager
+from app.database.services import add_error_log, add_request_log # Import add_request_log
+
+logger = get_gemini_logger()
+
+
+def _has_image_parts(contents: List[Dict[str, Any]]) -> bool:
+    """判断消息是否包含图片部分"""
+    for content in contents:
+        if "parts" in content:
+            for part in content["parts"]:
+                if "image_url" in part or "inline_data" in part:
+                    return True
+    return False
+
+
+def _build_tools(model: str, payload: Dict[str, Any]) -> List[Dict[str, Any]]:
+    """构建工具"""
+    
+    def _merge_tools(tools: List[Dict[str, Any]]) -> Dict[str, Any]:
+        record = dict()
+        for item in tools:
+            if not item or not isinstance(item, dict):
+                continue
+
+            for k, v in item.items():
+                if k == "functionDeclarations" and v and isinstance(v, list):
+                    functions = record.get("functionDeclarations", [])
+                    functions.extend(v)
+                    record["functionDeclarations"] = functions
+                else:
+                    record[k] = v
+        return record
+
+    tool = dict()
+    if payload and isinstance(payload, dict) and "tools" in payload:
+        if payload.get("tools") and isinstance(payload.get("tools"), dict):
+            payload["tools"] = [payload.get("tools")]
+        items = payload.get("tools", [])
+        if items and isinstance(items, list):
+            tool.update(_merge_tools(items))
+
+    if (
+        settings.TOOLS_CODE_EXECUTION_ENABLED
+        and not (model.endswith("-search") or "-thinking" in model)
+        and not _has_image_parts(payload.get("contents", []))
+    ):
+        tool["codeExecution"] = {}
+    if model.endswith("-search"):
+        tool["googleSearch"] = {}
+
+    # 解决 "Tool use with function calling is unsupported" 问题
+    if tool.get("functionDeclarations"):
+        tool.pop("googleSearch", None)
+        tool.pop("codeExecution", None)
+
+    return [tool] if tool else []
+
+
+def _get_safety_settings(model: str) -> List[Dict[str, str]]:
+    """获取安全设置"""
+    if model == "gemini-2.0-flash-exp":
+        return [
+            {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "OFF"},
+        ]
+    return [
+        {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"},
+    ]
+
+
+def _build_payload(model: str, request: GeminiRequest) -> Dict[str, Any]:
+    """构建请求payload"""
+    request_dict = request.model_dump()
+    if request.generationConfig:
+        if request.generationConfig.maxOutputTokens is None:
+            # 如果未指定最大输出长度，则不传递该字段，解决截断的问题
+            request_dict["generationConfig"].pop("maxOutputTokens")
+    
+    payload = {
+        "contents": request_dict.get("contents", []),
+        "tools": _build_tools(model, request_dict),
+        "safetySettings": _get_safety_settings(model),
+        "generationConfig": request_dict.get("generationConfig", {}),
+        "systemInstruction": request_dict.get("systemInstruction", ""),
+    }
+
+    if model.endswith("-image") or model.endswith("-image-generation"):
+        payload.pop("systemInstruction")
+        payload["generationConfig"]["responseModalities"] = ["Text", "Image"]
+    return payload
+
+
+class GeminiChatService:
+    """聊天服务"""
+
+    def __init__(self, base_url: str, key_manager: KeyManager):
+        self.api_client = GeminiApiClient(base_url, settings.TIME_OUT)
+        self.key_manager = key_manager
+        self.response_handler = GeminiResponseHandler()
+
+    def _extract_text_from_response(self, response: Dict[str, Any]) -> str:
+        """从响应中提取文本内容"""
+        if not response.get("candidates"):
+            return ""
+
+        candidate = response["candidates"][0]
+        content = candidate.get("content", {})
+        parts = content.get("parts", [])
+
+        if parts and "text" in parts[0]:
+            return parts[0].get("text", "")
+        return ""
+
+    def _create_char_response(
+        self, original_response: Dict[str, Any], text: str
+    ) -> Dict[str, Any]:
+        """创建包含指定文本的响应"""
+        response_copy = json.loads(json.dumps(original_response))  # 深拷贝
+        if response_copy.get("candidates") and response_copy["candidates"][0].get(
+            "content", {}
+        ).get("parts"):
+            response_copy["candidates"][0]["content"]["parts"][0]["text"] = text
+        return response_copy
+
+    async def generate_content(
+        self, model: str, request: GeminiRequest, api_key: str
+    ) -> Dict[str, Any]:
+        """生成内容"""
+        payload = _build_payload(model, request)
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now() # Record request time
+        is_success = False
+        status_code = None
+        response = None
+
+        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)
+        except Exception as e:
+            is_success = False
+            error_log_msg = str(e)
+            logger.error(f"Normal API call failed with error: {error_log_msg}")
+            # Try to parse status code from exception
+            match = re.search(r"status code (\d+)", error_log_msg)
+            if match:
+                status_code = int(match.group(1))
+            else:
+                status_code = 500 # Default to 500 if parsing fails
+
+            # Log error to error log table
+            await add_error_log(
+                gemini_key=api_key,
+                model_name=model,
+                error_type="gemini_chat_service",
+                error_log=error_log_msg,
+                error_code=status_code,
+                request_msg=payload
+            )
+            raise e # Re-throw exception for upstream handling
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            # Log request to request log table
+            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
+            )
+
+    async def stream_generate_content(
+        self, model: str, request: GeminiRequest, api_key: str
+    ) -> AsyncGenerator[str, None]:
+        """流式生成内容"""
+        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
+
+        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."
+                        )
+                        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

app/service/chat/openai_chat_service.py

@@ -0,0 +1,404 @@
+# app/services/chat_service.py
+
+import json
+import re
+import datetime # Add datetime import
+import time # Add time import
+from copy import deepcopy
+from typing import Any, AsyncGenerator, Dict, List, Optional, Union
+
+from app.config.config import settings
+from app.domain.openai_models import ChatRequest, ImageGenerationRequest
+from app.handler.message_converter import OpenAIMessageConverter
+from app.handler.response_handler import OpenAIResponseHandler
+from app.handler.stream_optimizer import openai_optimizer
+from app.log.logger import get_openai_logger
+from app.service.client.api_client import GeminiApiClient
+from app.service.image.image_create_service import ImageCreateService
+from app.service.key.key_manager import KeyManager
+from app.database.services import add_error_log, add_request_log # Import add_request_log
+
+logger = get_openai_logger()
+
+
+def _has_image_parts(contents: List[Dict[str, Any]]) -> bool:
+    """判断消息是否包含图片部分"""
+    for content in contents:
+        if "parts" in content:
+            for part in content["parts"]:
+                if "image_url" in part or "inline_data" in part:
+                    return True
+    return False
+
+
+def _build_tools(
+    request: ChatRequest, messages: List[Dict[str, Any]]
+) -> List[Dict[str, Any]]:
+    """构建工具"""
+    tool = dict()
+    model = request.model
+
+    if (
+        settings.TOOLS_CODE_EXECUTION_ENABLED
+        and not (
+            model.endswith("-search")
+            or "-thinking" in model
+            or model.endswith("-image")
+            or model.endswith("-image-generation")
+        )
+        and not _has_image_parts(messages)
+    ):
+        tool["codeExecution"] = {}
+    if model.endswith("-search"):
+        tool["googleSearch"] = {}
+
+    # 将 request 中的 tools 合并到 tools 中
+    if request.tools:
+        function_declarations = []
+        for item in request.tools:
+            if not item or not isinstance(item, dict):
+                continue
+
+            if item.get("type", "") == "function" and item.get("function"):
+                function = deepcopy(item.get("function"))
+                parameters = function.get("parameters", {})
+                if parameters.get("type") == "object" and not parameters.get("properties", {}):
+                    function.pop("parameters", None)
+
+                function_declarations.append(function)
+
+        if function_declarations:
+            # 按照 function 的 name 去重
+            names, functions = set(), []
+            for fc in function_declarations:
+                if fc.get("name") not in names:
+                    names.add(fc.get("name"))
+                    functions.append(fc)
+
+            tool["functionDeclarations"] = functions
+
+    # 解决 "Tool use with function calling is unsupported" 问题
+    if tool.get("functionDeclarations"):
+        tool.pop("googleSearch", None)
+        tool.pop("codeExecution", None)
+
+    return [tool] if tool else []
+
+
+def _get_safety_settings(model: str) -> List[Dict[str, str]]:
+    """获取安全设置"""
+    # if (
+    #     "2.0" in model
+    #     and "gemini-2.0-flash-thinking-exp" not in model
+    #     and "gemini-2.0-pro-exp" not in model
+    # ):
+    if model == "gemini-2.0-flash-exp":
+        return [
+            {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"},
+            {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "OFF"},
+        ]
+    return [
+        {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"},
+        {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"},
+    ]
+
+
+def _build_payload(
+    request: ChatRequest,
+    messages: List[Dict[str, Any]],
+    instruction: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """构建请求payload"""
+    payload = {
+        "contents": messages,
+        "generationConfig": {
+            "temperature": request.temperature,
+            "stopSequences": request.stop,
+            "topP": request.top_p,
+            "topK": request.top_k,
+        },
+        "tools": _build_tools(request, messages),
+        "safetySettings": _get_safety_settings(request.model),
+    }
+    if request.max_tokens is not None:
+        payload["generationConfig"]["maxOutputTokens"] = request.max_tokens
+    if request.model.endswith("-image") or request.model.endswith("-image-generation"):
+        payload["generationConfig"]["responseModalities"] = ["Text", "Image"]
+
+    if (
+        instruction
+        and isinstance(instruction, dict)
+        and instruction.get("role") == "system"
+        and instruction.get("parts")
+        and not request.model.endswith("-image")
+        and not request.model.endswith("-image-generation")
+    ):
+        payload["systemInstruction"] = instruction
+
+    return payload
+
+
+class OpenAIChatService:
+    """聊天服务"""
+
+    def __init__(self, base_url: str, key_manager: KeyManager = None):
+        self.message_converter = OpenAIMessageConverter()
+        self.response_handler = OpenAIResponseHandler(config=None)
+        self.api_client = GeminiApiClient(base_url, settings.TIME_OUT)
+        self.key_manager = key_manager
+        self.image_create_service = ImageCreateService()
+
+    def _extract_text_from_openai_chunk(self, chunk: Dict[str, Any]) -> str:
+        """从OpenAI响应块中提取文本内容"""
+        if not chunk.get("choices"):
+            return ""
+
+        choice = chunk["choices"][0]
+        if "delta" in choice and "content" in choice["delta"]:
+            return choice["delta"]["content"]
+        return ""
+
+    def _create_char_openai_chunk(
+        self, original_chunk: Dict[str, Any], text: str
+    ) -> Dict[str, Any]:
+        """创建包含指定文本的OpenAI响应块"""
+        chunk_copy = json.loads(json.dumps(original_chunk))  # 深拷贝
+        if chunk_copy.get("choices") and "delta" in chunk_copy["choices"][0]:
+            chunk_copy["choices"][0]["delta"]["content"] = text
+        return chunk_copy
+
+    async def create_chat_completion(
+        self,
+        request: ChatRequest,
+        api_key: str,
+    ) -> Union[Dict[str, Any], AsyncGenerator[str, None]]:
+        """创建聊天完成"""
+        # 转换消息格式
+        messages, instruction = self.message_converter.convert(request.messages)
+
+        # 构建请求payload
+        payload = _build_payload(request, messages, instruction)
+
+        if request.stream:
+            return self._handle_stream_completion(request.model, payload, api_key)
+        return await self._handle_normal_completion(request.model, payload, api_key)
+
+    async def _handle_normal_completion(
+        self, model: str, payload: Dict[str, Any], api_key: str
+    ) -> Dict[str, Any]:
+        """处理普通聊天完成"""
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now()
+        is_success = False
+        status_code = None
+        response = None
+        try:
+            response = await self.api_client.generate_content(payload, model, api_key)
+            is_success = True
+            status_code = 200 # Assume 200 on success
+            return self.response_handler.handle_response(
+                response, model, stream=False, finish_reason="stop"
+            )
+        except Exception as e:
+            is_success = False
+            error_log_msg = str(e)
+            logger.error(f"Normal API call failed with error: {error_log_msg}")
+            # Try to parse status code from exception
+            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
+
+            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_log=error_log_msg,
+                error_code=status_code,
+                request_msg=payload
+            )
+            raise e # Re-throw exception
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            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
+            )
+
+    async def _handle_stream_completion(
+        self, model: str, payload: Dict[str, Any], api_key: str
+    ) -> AsyncGenerator[str, None]:
+        """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
+
+        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."
+                        )
+                        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,
+    ) -> Union[Dict[str, Any], AsyncGenerator[str, None]]:
+
+        image_generate_request = ImageGenerationRequest()
+        image_generate_request.prompt = request.messages[-1]["content"]
+        image_res = self.image_create_service.generate_images_chat(
+            image_generate_request
+        )
+
+        if request.stream:
+            return self._handle_stream_image_completion(request.model, image_res)
+        else:
+            return self._handle_normal_image_completion(request.model, image_res)
+
+    async def _handle_stream_image_completion(
+        self, model: str, image_data: str
+    ) -> AsyncGenerator[str, None]:
+        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"
+        yield "data: [DONE]\n\n"
+        logger.info("Image chat streaming completed successfully")
+
+    def _handle_normal_image_completion(
+        self, model: str, image_data: str
+    ) -> Dict[str, Any]:
+
+        return self.response_handler.handle_image_chat_response(
+            image_data, model, stream=False, finish_reason="stop"
+        )

app/service/client/api_client.py

@@ -4,6 +4,8 @@ from typing import Dict, Any, AsyncGenerator
 import httpx
 from abc import ABC, abstractmethod
 
+from app.core.constants import DEFAULT_TIMEOUT
+
 
 class ApiClient(ABC):
     """API客户端基类"""
@@ -20,17 +22,25 @@ class ApiClient(ABC):
 class GeminiApiClient(ApiClient):
     """Gemini API客户端"""
 
-    def __init__(self, base_url: str, timeout: int = 300):
+    def __init__(self, base_url: str, timeout: int = DEFAULT_TIMEOUT):
         self.base_url = base_url
         self.timeout = timeout
 
-    def generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:
-        timeout = httpx.Timeout(self.timeout, read=self.timeout)
+    def _get_real_model(self, model: str) -> str:
         if model.endswith("-search"):
             model = model[:-7]
-        with httpx.Client(timeout=timeout) as client:
+        if model.endswith("-image"):
+            model = model[:-6]
+
+        return model
+
+    async def generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:
+        timeout = httpx.Timeout(self.timeout, read=self.timeout)
+        model = self._get_real_model(model)
+
+        async with httpx.AsyncClient(timeout=timeout) as client:
             url = f"{self.base_url}/models/{model}:generateContent?key={api_key}"
-            response = client.post(url, json=payload)
+            response = await client.post(url, json=payload)
             if response.status_code != 200:
                 error_content = response.text
                 raise Exception(f"API call failed with status code {response.status_code}, {error_content}")
@@ -38,8 +48,8 @@ class GeminiApiClient(ApiClient):
 
     async def stream_generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> AsyncGenerator[str, None]:
         timeout = httpx.Timeout(self.timeout, read=self.timeout)
-        if model.endswith("-search"):
-            model = model[:-7]
+        model = self._get_real_model(model)
+        
         async with httpx.AsyncClient(timeout=timeout) as client:
             url = f"{self.base_url}/models/{model}:streamGenerateContent?alt=sse&key={api_key}"
             async with client.stream(method="POST", url=url, json=payload) as response:

app/service/config/config_service.py

@@ -0,0 +1,148 @@
+"""
+配置服务模块
+"""
+import datetime
+import json
+from typing import Any, Dict, List
+
+from dotenv import find_dotenv, load_dotenv
+from sqlalchemy import insert, update
+
+from app.config.config import settings
+from app.database.connection import database
+from app.database.models import Settings
+from app.config.config import Settings as ConfigSettings
+from app.database.services import get_all_settings
+from app.service.key.key_manager import get_key_manager_instance, reset_key_manager_instance
+from app.log.logger import get_config_routes_logger
+
+logger = get_config_routes_logger()
+
+
+class ConfigService:
+    """配置服务类，用于管理应用程序配置"""
+    
+    @staticmethod
+    async def get_config() -> Dict[str, Any]:
+        return settings.model_dump()
+    
+    @staticmethod
+    async def update_config(config_data: Dict[str, Any]) -> Dict[str, Any]:
+        for key, value in config_data.items():
+            if hasattr(settings, key):
+                setattr(settings, key, value)
+                logger.info(f"Updated setting in memory: {key}") 
+        
+        # 获取现有设置
+        existing_settings_raw: List[Dict[str, Any]] = await get_all_settings()
+        existing_settings_map: Dict[str, Dict[str, Any]] = {s['key']: s for s in existing_settings_raw}
+        existing_keys = set(existing_settings_map.keys())
+
+        settings_to_update: List[Dict[str, Any]] = []
+        settings_to_insert: List[Dict[str, Any]] = []
+        now = datetime.datetime.now(datetime.timezone(datetime.timedelta(hours=8)))
+
+        # 准备要更新或插入的数据
+        for key, value in config_data.items():
+            # 处理不同类型的值
+            if isinstance(value, list):
+                db_value = json.dumps(value)
+            elif isinstance(value, bool):
+                db_value = str(value).lower()
+            else:
+                db_value = str(value)
+
+            # 仅当值发生变化时才更新
+            if key in existing_keys and existing_settings_map[key]['value'] == db_value:
+                continue 
+
+            description = f"{key}配置项" 
+
+            data = {
+                'key': key,
+                'value': db_value,
+                'description': description,
+                'updated_at': now
+            }
+
+            if key in existing_keys:
+                # Preserve original description if not explicitly provided
+                data['description'] = existing_settings_map[key].get('description', description)
+                settings_to_update.append(data)
+            else:
+                data['created_at'] = now
+                settings_to_insert.append(data)
+
+        # 在事务中执行批量插入和更新
+        if settings_to_insert or settings_to_update:
+            try:
+                async with database.transaction():
+                    if settings_to_insert:
+                        query_insert = insert(Settings).values(settings_to_insert)
+                        await database.execute(query=query_insert)
+                        logger.info(f"Bulk inserted {len(settings_to_insert)} settings.")
+
+                    if settings_to_update:
+                        for setting_data in settings_to_update:
+                            query_update = (
+                                update(Settings)
+                                .where(Settings.key == setting_data['key'])
+                                .values(
+                                    value=setting_data['value'],
+                                    description=setting_data['description'],
+                                    updated_at=setting_data['updated_at']
+                                )
+                            )
+                            await database.execute(query=query_update)
+                        logger.info(f"Updated {len(settings_to_update)} settings.")
+            except Exception as e:
+                logger.error(f"Failed to bulk update/insert settings: {str(e)}")
+                raise  # Re-raise the exception after logging
+
+        # 重置并重新初始化 KeyManager
+        try:
+            await reset_key_manager_instance()
+            await get_key_manager_instance(settings.API_KEYS)
+            logger.info("KeyManager instance re-initialized with updated settings.")
+        except Exception as e:
+            logger.error(f"Failed to re-initialize KeyManager: {str(e)}")
+            # Decide if this error should prevent returning the updated config
+            # For now, we log the error and continue
+
+        return await ConfigService.get_config()
+    
+    @staticmethod
+    async def reset_config() -> Dict[str, Any]:
+        """
+        重置配置：优先从系统环境变量加载，然后从 .env 文件加载，
+        更新内存中的 settings 对象，并刷新 KeyManager。
+
+        Returns:
+            Dict[str, Any]: 重置后的配置字典
+        """
+        # 1. 重新加载配置对象，它应该处理环境变量和 .env 的优先级
+        _reload_settings()
+        logger.info("Settings object reloaded, prioritizing system environment variables then .env file.")
+
+        # 2. 重置并重新初始化 KeyManager
+        try:
+            await reset_key_manager_instance()
+            # 确保使用更新后的 settings 中的 API_KEYS
+            await get_key_manager_instance(settings.API_KEYS)
+            logger.info("KeyManager instance re-initialized with reloaded settings.")
+        except Exception as e:
+            logger.error(f"Failed to re-initialize KeyManager during reset: {str(e)}")
+            # 根据需要决定是否抛出异常或继续
+            # 这里选择记录错误并继续
+
+        # 3. 返回更新后的配置
+        return await ConfigService.get_config()
+
+# 重新加载配置的函数
+def _reload_settings():
+    """重新加载环境变量并更新配置"""
+    # 显式加载 .env 文件，覆盖现有环境变量
+    load_dotenv(find_dotenv(), override=True)
+    # 更新现有 settings 对象的属性，而不是新建实例
+    for key, value in ConfigSettings().model_dump().items():
+        setattr(settings, key, value)

app/service/embedding/embedding_service.py

@@ -1,23 +1,21 @@
-from typing import Union, List
+from typing import List, Union
 
 import openai
 from openai.types import CreateEmbeddingResponse
-
-from app.core.logger import get_embeddings_logger
+from app.config.config import settings
+from app.log.logger import get_embeddings_logger
 
 logger = get_embeddings_logger()
 
 
 class EmbeddingService:
-    def __init__(self, base_url: str):
-        self.base_url = base_url
 
     async def create_embedding(
         self, input_text: Union[str, List[str]], model: str, api_key: str
     ) -> CreateEmbeddingResponse:
         """Create embeddings using OpenAI API"""
         try:
-            client = openai.OpenAI(api_key=api_key, base_url=self.base_url)
+            client = openai.OpenAI(api_key=api_key, base_url=settings.BASE_URL)
             response = client.embeddings.create(input=input_text, model=model)
             return response
         except Exception as e:

app/service/image/image_create_service.py

@@ -1,14 +1,15 @@
+import base64
 import time
 import uuid
 
 from google import genai
 from google.genai import types
-import base64
 
-from app.core.config import settings
-from app.core.logger import get_image_create_logger
-from app.core.uploader import ImageUploaderFactory
-from app.schemas.openai_models import ImageGenerationRequest
+from app.config.config import settings
+from app.core.constants import VALID_IMAGE_RATIOS
+from app.domain.openai_models import ImageGenerationRequest
+from app.log.logger import get_image_create_logger
+from app.utils.uploader import ImageUploaderFactory
 
 logger = get_image_create_logger()
 
@@ -26,35 +27,34 @@ class ImageCreateService:
         - {ratio:比例} 例如: {ratio:16:9} 使用16:9比例
         """
         import re
-        
+
         # 默认值
         n = 1
         aspect_ratio = self.aspect_ratio
-        
+
         # 解析n参数
-        n_match = re.search(r'{n:(\d+)}', prompt)
+        n_match = re.search(r"{n:(\d+)}", prompt)
         if n_match:
             n = int(n_match.group(1))
             if n < 1 or n > 4:
                 raise ValueError(f"Invalid n value: {n}. Must be between 1 and 4.")
-            prompt = prompt.replace(n_match.group(0), '').strip()
-            
-        # 解析ratio参数    
-        ratio_match = re.search(r'{ratio:(\d+:\d+)}', prompt)
+            prompt = prompt.replace(n_match.group(0), "").strip()
+
+        # 解析ratio参数
+        ratio_match = re.search(r"{ratio:(\d+:\d+)}", prompt)
         if ratio_match:
             aspect_ratio = ratio_match.group(1)
-            valid_ratios = ["1:1", "3:4", "4:3", "9:16", "16:9"]
-            if aspect_ratio not in valid_ratios:
+            if aspect_ratio not in VALID_IMAGE_RATIOS:
                 raise ValueError(
-                    f"Invalid ratio: {aspect_ratio}. Must be one of: {', '.join(valid_ratios)}"
+                    f"Invalid ratio: {aspect_ratio}. Must be one of: {', '.join(VALID_IMAGE_RATIOS)}"
                 )
-            prompt = prompt.replace(ratio_match.group(0), '').strip()
-            
+            prompt = prompt.replace(ratio_match.group(0), "").strip()
+
         return prompt, n, aspect_ratio
 
     def generate_images(self, request: ImageGenerationRequest):
         client = genai.Client(api_key=self.paid_key)
-        
+
         if request.size == "1024x1024":
             self.aspect_ratio = "1:1"
         elif request.size == "1792x1024":
@@ -67,13 +67,15 @@ class ImageCreateService:
             )
 
         # 解析prompt中的参数
-        cleaned_prompt, prompt_n, prompt_ratio = self.parse_prompt_parameters(request.prompt)
+        cleaned_prompt, prompt_n, prompt_ratio = self.parse_prompt_parameters(
+            request.prompt
+        )
         request.prompt = cleaned_prompt
-        
+
         # 如果prompt中指定了n，则覆盖请求中的n
         if prompt_n > 1:
             request.n = prompt_n
-            
+
         # 如果prompt中指定了ratio，则覆盖默认的aspect_ratio
         if prompt_ratio != self.aspect_ratio:
             self.aspect_ratio = prompt_ratio
@@ -96,27 +98,49 @@ class ImageCreateService:
             for index, generated_image in enumerate(response.generated_images):
                 image_data = generated_image.image.image_bytes
                 image_uploader = None
-                if settings.UPLOAD_PROVIDER  == "smms":
-                    image_uploader = ImageUploaderFactory.create(provider=settings.UPLOAD_PROVIDER,api_key=settings.SMMS_SECRET_TOKEN)
+
+                if request.response_format == "b64_json":
+                    base64_image = base64.b64encode(image_data).decode("utf-8")
+                    images_data.append(
+                        {"b64_json": base64_image, "revised_prompt": request.prompt}
+                    )
+                else:
                     current_date = time.strftime("%Y/%m/%d")
                     filename = f"{current_date}/{uuid.uuid4().hex[:8]}.png"
-                    upload_response = image_uploader.upload(image_data,filename)
-                    
-                if request.response_format == "b64_json":
-                    base64_image = base64.b64encode(image_data).decode('utf-8')
-                    images_data.append({
-                        "b64_json": base64_image,
-                        "revised_prompt": request.prompt
-                    })
-                else:
-                    images_data.append({
-                        "url": f"{upload_response.data.url}",
-                        "revised_prompt": request.prompt
-                    })
+
+                    if settings.UPLOAD_PROVIDER == "smms":
+                        image_uploader = ImageUploaderFactory.create(
+                            provider=settings.UPLOAD_PROVIDER,
+                            api_key=settings.SMMS_SECRET_TOKEN,
+                        )
+                    elif settings.UPLOAD_PROVIDER == "picgo":
+                        image_uploader = ImageUploaderFactory.create(
+                            provider=settings.UPLOAD_PROVIDER,
+                            api_key=settings.PICGO_API_KEY,
+                        )
+                    elif settings.UPLOAD_PROVIDER == "cloudflare_imgbed":
+                        image_uploader = ImageUploaderFactory.create(
+                            provider=settings.UPLOAD_PROVIDER,
+                            base_url=settings.CLOUDFLARE_IMGBED_URL,
+                            auth_code=settings.CLOUDFLARE_IMGBED_AUTH_CODE,
+                        )
+                    else:
+                        raise ValueError(
+                            f"Unsupported upload provider: {settings.UPLOAD_PROVIDER}"
+                        )
+
+                    upload_response = image_uploader.upload(image_data, filename)
+
+                    images_data.append(
+                        {
+                            "url": f"{upload_response.data.url}",
+                            "revised_prompt": request.prompt,
+                        }
+                    )
 
             response_data = {
                 "created": int(time.time()),  # Current timestamp
-                "data": images_data
+                "data": images_data,
             }
             return response_data
         else:
@@ -128,9 +152,13 @@ class ImageCreateService:
         if image_datas:
             markdown_images = []
             for index, image_data in enumerate(image_datas):
-                if 'url' in image_data:
-                    markdown_images.append(f"![Generated Image {index+1}]({image_data['url']})")
+                if "url" in image_data:
+                    markdown_images.append(
+                        f"![Generated Image {index+1}]({image_data['url']})"
+                    )
                 else:
                     # 如果是base64格式，创建data URL
-                    markdown_images.append(f"![Generated Image {index+1}](data:image/png;base64,{image_data['b64_json']})")
+                    markdown_images.append(
+                        f"![Generated Image {index+1}](data:image/png;base64,{image_data['b64_json']})"
+                    )
             return "\n".join(markdown_images)

app/service/key/key_manager.py

@@ -1,10 +1,11 @@
 import asyncio
 from itertools import cycle
 from typing import Dict
-from app.core.logger import get_key_manager_logger
-from app.core.config import settings
 
 
+from app.config.config import settings
+from app.log.logger import get_key_manager_logger
+
 logger = get_key_manager_logger()
 
 
@@ -20,7 +21,7 @@ class KeyManager:
 
     async def get_paid_key(self) -> str:
         return self.paid_key
-        
+
     async def get_next_key(self) -> str:
         """获取下一个API key"""
         async with self.key_cycle_lock:
@@ -36,6 +37,16 @@ class KeyManager:
         async with self.failure_count_lock:
             for key in self.key_failure_counts:
                 self.key_failure_counts[key] = 0
+                
+    async def reset_key_failure_count(self, key: str) -> bool:
+        """重置指定key的失败计数"""
+        async with self.failure_count_lock:
+            if key in self.key_failure_counts:
+                self.key_failure_counts[key] = 0
+                logger.info(f"Reset failure count for key: {key}")
+                return True
+            logger.warning(f"Attempt to reset failure count for non-existent key: {key}")
+            return False
 
     async def get_next_working_key(self) -> str:
         """获取下一可用的API key"""
@@ -51,7 +62,7 @@ class KeyManager:
                 # await self.reset_failure_counts() 取消重置
                 return current_key
 
-    async def handle_api_failure(self, api_key: str) -> str:
+    async def handle_api_failure(self, api_key: str,retries: int) -> str:
         """处理API调用失败"""
         async with self.failure_count_lock:
             self.key_failure_counts[api_key] += 1
@@ -59,8 +70,10 @@ class KeyManager:
                 logger.warning(
                     f"API key {api_key} has failed {self.MAX_FAILURES} times"
                 )
-
-        return await self.get_next_working_key()
+        if retries < settings.MAX_RETRIES:
+            return await self.get_next_working_key()
+        else: 
+            return ""
 
     def get_fail_count(self, key: str) -> int:
         """获取指定密钥的失败次数"""
@@ -70,7 +83,7 @@ class KeyManager:
         """获取分类后的API key列表，包括失败次数"""
         valid_keys = {}
         invalid_keys = {}
-        
+
         async with self.failure_count_lock:
             for key in self.api_keys:
                 fail_count = self.key_failure_counts[key]
@@ -78,16 +91,21 @@ class KeyManager:
                     valid_keys[key] = fail_count
                 else:
                     invalid_keys[key] = fail_count
-        
-        return {
-            "valid_keys": valid_keys,
-            "invalid_keys": invalid_keys
-        }
-        
-        
+
+        return {"valid_keys": valid_keys, "invalid_keys": invalid_keys}
+
+    async def get_first_valid_key(self) -> str:
+        """获取第一个有效的API key"""
+        async with self.failure_count_lock:
+            for key in self.key_failure_counts:
+                if self.key_failure_counts[key] < self.MAX_FAILURES:
+                    return key
+        return self.api_keys[0]
+
 _singleton_instance = None
 _singleton_lock = asyncio.Lock()
 
+
 async def get_key_manager_instance(api_keys: list = None) -> KeyManager:
     """
     获取 KeyManager 单例实例。
@@ -102,4 +120,14 @@ async def get_key_manager_instance(api_keys: list = None) -> KeyManager:
             if api_keys is None:
                 raise ValueError("API keys are required to initialize the KeyManager")
             _singleton_instance = KeyManager(api_keys)
+            logger.info("KeyManager instance created.")
         return _singleton_instance
+
+    
+async def reset_key_manager_instance():
+    """重置 KeyManager 单例实例"""
+    global _singleton_instance
+    async with _singleton_lock:
+        if _singleton_instance:
+            _singleton_instance = None
+            logger.info("KeyManager instance reset.")

app/service/model/model_service.py

@@ -1,23 +1,32 @@
-import requests
 from datetime import datetime, timezone
-from typing import Optional, Dict, Any
-from app.core.logger import get_model_logger
-from app.core.config import settings
+from typing import Any, Dict, Optional
+
+import requests
+
+from app.config.config import settings
+from app.log.logger import get_model_logger
 
 logger = get_model_logger()
 
-class ModelService:
-    def __init__(self, model_search: list):
-        self.model_search = model_search
-        self.base_url = "https://generativelanguage.googleapis.com/v1beta"
 
+class ModelService:
     def get_gemini_models(self, api_key: str) -> Optional[Dict[str, Any]]:
-        url = f"{self.base_url}/models?key={api_key}"
+        url = f"{settings.BASE_URL}/models?key={api_key}"
 
         try:
             response = requests.get(url)
             if response.status_code == 200:
                 gemini_models = response.json()
+
+                filtered_models_list = []
+                for model in gemini_models.get("models", []):
+                    model_id = model["name"].split("/")[-1]
+                    if model_id not in settings.FILTERED_MODELS:
+                        filtered_models_list.append(model)
+                    else:
+                        logger.info(f"Filtered out model: {model_id}")
+
+                gemini_models["models"] = filtered_models_list
                 return gemini_models
             else:
                 logger.error(f"Error: {response.status_code}")
@@ -36,7 +45,7 @@ class ModelService:
             return None
 
     def convert_to_openai_models_format(
-            self, gemini_models: Dict[str, Any]
+        self, gemini_models: Dict[str, Any]
     ) -> Dict[str, Any]:
         openai_format = {"object": "list", "data": [], "success": True}
 
@@ -53,13 +62,31 @@ class ModelService:
             }
             openai_format["data"].append(openai_model)
 
-            if model_id in self.model_search:
+            if model_id in settings.SEARCH_MODELS:
                 search_model = openai_model.copy()
                 search_model["id"] = f"{model_id}-search"
                 openai_format["data"].append(search_model)
+            if model_id in settings.IMAGE_MODELS:
+                image_model = openai_model.copy()
+                image_model["id"] = f"{model_id}-image"
+                openai_format["data"].append(image_model)
 
         if settings.CREATE_IMAGE_MODEL:
             image_model = openai_model.copy()
             image_model["id"] = f"{settings.CREATE_IMAGE_MODEL}-chat"
             openai_format["data"].append(image_model)
         return openai_format
+
+    def check_model_support(self, model: str) -> bool:
+        if not model or not isinstance(model, str):
+            return False
+
+        model = model.strip()
+        if model.endswith("-search"):
+            model = model[:-7]
+            return model in settings.SEARCH_MODELS
+        if model.endswith("-image"):
+            model = model[:-6]
+            return model in settings.IMAGE_MODELS
+
+        return model not in settings.FILTERED_MODELS

app/service/stats_service.py

@@ -0,0 +1,123 @@
+# app/service/stats_service.py
+
+import datetime
+from sqlalchemy import select, func
+
+from app.database.connection import database
+from app.database.models import RequestLog
+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)
+
+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_current_month() -> 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() -> 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()
+
+        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(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()
+    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}")
+
+    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
+
+        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
+
+    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

app/services/chat/message_converter.py

@@ -1,53 +0,0 @@
-# app/services/chat/message_converter.py
-
-from abc import ABC, abstractmethod
-from typing import List, Dict, Any
-
-
-class MessageConverter(ABC):
-    """消息转换器基类"""
-
-    @abstractmethod
-    def convert(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
-        pass
-
-
-def _convert_image(image_url: str) -> Dict[str, Any]:
-    if image_url.startswith("data:image"):
-        return {
-            "inline_data": {
-                "mime_type": "image/jpeg",
-                "data": image_url.split(",")[1]
-            }
-        }
-    return {
-        "image_url": {
-            "url": image_url
-        }
-    }
-
-
-class OpenAIMessageConverter(MessageConverter):
-    """OpenAI消息格式转换器"""
-
-    def convert(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
-        converted_messages = []
-        for msg in messages:
-            role = "user" if msg["role"] == "user" else "model"
-            parts = []
-
-            if isinstance(msg["content"], str):
-                parts.append({"text": msg["content"]})
-            elif isinstance(msg["content"], list):
-                for content in msg["content"]:
-                    if isinstance(content, str):
-                        parts.append({"text": content})
-                    elif isinstance(content, dict):
-                        if content["type"] == "text":
-                            parts.append({"text": content["text"]})
-                        elif content["type"] == "image_url":
-                            parts.append(_convert_image(content["image_url"]["url"]))
-
-            converted_messages.append({"role": role, "parts": parts})
-
-        return converted_messages

app/services/gemini_chat_service.py

@@ -1,104 +0,0 @@
-# app/services/chat_service.py
-
-import json
-from typing import Dict, Any, AsyncGenerator, List
-from app.core.logger import get_gemini_logger
-from app.services.chat.api_client import GeminiApiClient
-from app.schemas.gemini_models import GeminiRequest
-from app.core.config import settings
-from app.services.chat.response_handler import GeminiResponseHandler
-from app.services.key_manager import KeyManager
-
-logger = get_gemini_logger()
-
-
-def _has_image_parts(contents: List[Dict[str, Any]]) -> bool:
-    """判断消息是否包含图片部分"""
-    for content in contents:
-        if "parts" in content:
-            for part in content["parts"]:
-                if "image_url" in part or "inline_data" in part:
-                    return True
-    return False
-
-
-def _build_tools(model: str, payload: Dict[str, Any]) -> List[Dict[str, Any]]:
-    """构建工具"""
-    tools = []
-    if settings.TOOLS_CODE_EXECUTION_ENABLED and not (
-            model.endswith("-search") or "-thinking" in model
-    ) and not _has_image_parts(payload.get("contents", [])):
-        tools.append({"code_execution": {}})
-    if model.endswith("-search"):
-        tools.append({"googleSearch": {}})
-    return tools
-
-
-def _get_safety_settings(model: str) -> List[Dict[str, str]]:
-    """获取安全设置"""
-    if model == "gemini-2.0-flash-exp":
-        return [
-            {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "OFF"}
-        ]
-    return [
-        {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"}
-    ]
-
-
-def _build_payload(model: str, request: GeminiRequest) -> Dict[str, Any]:
-    """构建请求payload"""
-    payload = request.model_dump()
-    return {
-        "contents": payload.get("contents", []),
-        "tools": _build_tools(model, payload),
-        "safetySettings": _get_safety_settings(model),
-        "generationConfig": payload.get("generationConfig", {}),
-        "systemInstruction": payload.get("systemInstruction", [])
-    }
-
-
-class GeminiChatService:
-    """聊天服务"""
-
-    def __init__(self, base_url: str, key_manager: KeyManager):
-        self.api_client = GeminiApiClient(base_url)
-        self.key_manager = key_manager
-        self.response_handler = GeminiResponseHandler()
-
-    def generate_content(self, model: str, request: GeminiRequest, api_key: str) -> Dict[str, Any]:
-        """生成内容"""
-        payload = _build_payload(model, request)
-        response = self.api_client.generate_content(payload, model, api_key)
-        return self.response_handler.handle_response(response, model, stream=False)
-
-    async def stream_generate_content(self, model: str, request: GeminiRequest, api_key: str) -> AsyncGenerator[str, None]:
-        """流式生成内容"""
-        retries = 0
-        max_retries = 3
-        payload = _build_payload(model, request)
-        while retries < max_retries:
-            try:
-                async for line in self.api_client.stream_generate_content(payload, model, api_key):
-                    # print(line)
-                    if line.startswith("data:"):
-                        line = line[6:]
-                        line = json.dumps(self.response_handler.handle_response(json.loads(line), model, stream=True))
-                        yield "data: " + line + "\n\n"
-                logger.info("Streaming completed successfully")
-                break
-            except Exception as e:
-                retries += 1
-                logger.warning(f"Streaming API call failed with error: {str(e)}. Attempt {retries} of {max_retries}")
-                api_key = await self.key_manager.handle_api_failure(api_key)
-                logger.info(f"Switched to new API key: {api_key}")
-                if retries >= max_retries:
-                    logger.error(f"Max retries ({max_retries}) reached for streaming. Raising error")
-                    break

app/services/openai_chat_service.py

@@ -1,192 +0,0 @@
-# app/services/chat_service.py
-
-import json
-from typing import Dict, Any, AsyncGenerator, List, Union
-from app.core.logger import get_openai_logger
-from app.services.chat.message_converter import OpenAIMessageConverter
-from app.services.chat.response_handler import OpenAIResponseHandler
-from app.services.chat.api_client import GeminiApiClient
-from app.schemas.openai_models import ChatRequest, ImageGenerationRequest
-from app.core.config import settings
-from app.services.image_create_service import ImageCreateService
-from app.services.key_manager import KeyManager
-
-logger = get_openai_logger()
-
-
-def _has_image_parts(contents: List[Dict[str, Any]]) -> bool:
-    """判断消息是否包含图片部分"""
-    for content in contents:
-        if "parts" in content:
-            for part in content["parts"]:
-                if "image_url" in part or "inline_data" in part:
-                    return True
-    return False
-
-
-def _build_tools(
-        request: ChatRequest, messages: List[Dict[str, Any]]
-) -> List[Dict[str, Any]]:
-    """构建工具"""
-    tools = []
-    model = request.model
-
-    if (
-            settings.TOOLS_CODE_EXECUTION_ENABLED
-            and not (model.endswith("-search") or "-thinking" in model)
-            and not _has_image_parts(messages)
-    ):
-        tools.append({"code_execution": {}})
-    if model.endswith("-search"):
-        tools.append({"googleSearch": {}})
-    return tools
-
-
-def _get_safety_settings(model: str) -> List[Dict[str, str]]:
-    """获取安全设置"""
-    # if (
-    #     "2.0" in model
-    #     and "gemini-2.0-flash-thinking-exp" not in model
-    #     and "gemini-2.0-pro-exp" not in model
-    # ):
-    if model == "gemini-2.0-flash-exp":
-        return [
-            {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "OFF"},
-            {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "OFF"},
-        ]
-    return [
-        {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"},
-        {"category": "HARM_CATEGORY_CIVIC_INTEGRITY", "threshold": "BLOCK_NONE"},
-    ]
-
-
-def _build_payload(
-        request: ChatRequest, messages: List[Dict[str, Any]]
-) -> Dict[str, Any]:
-    """构建请求payload"""
-    return {
-        "contents": messages,
-        "generationConfig": {
-            "temperature": request.temperature,
-            "maxOutputTokens": request.max_tokens,
-            "stopSequences": request.stop,
-            "topP": request.top_p,
-            "topK": request.top_k,
-        },
-        "tools": _build_tools(request, messages),
-        "safetySettings": _get_safety_settings(request.model),
-    }
-
-
-class OpenAIChatService:
-    """聊天服务"""
-    def __init__(self, base_url: str, key_manager: KeyManager = None):
-        self.message_converter = OpenAIMessageConverter()
-        self.response_handler = OpenAIResponseHandler(config=None)
-        self.api_client = GeminiApiClient(base_url)
-        self.key_manager = key_manager
-        self.image_create_service = ImageCreateService()
-
-    async def create_chat_completion(
-            self,
-            request: ChatRequest,
-            api_key: str,
-    ) -> Union[Dict[str, Any], AsyncGenerator[str, None]]:
-        """创建聊天完成"""
-        # 转换消息格式
-        messages = self.message_converter.convert(request.messages)
-
-        # 构建请求payload
-        payload = _build_payload(request, messages)
-
-        if request.stream:
-            return self._handle_stream_completion(request.model, payload, api_key)
-        return self._handle_normal_completion(request.model, payload, api_key)
-
-    def _handle_normal_completion(
-            self, model: str, payload: Dict[str, Any], api_key: str
-    ) -> Dict[str, Any]:
-        """处理普通聊天完成"""
-        response = self.api_client.generate_content(payload, model, api_key)
-        return self.response_handler.handle_response(
-            response, model, stream=False, finish_reason="stop"
-        )
-
-    async def _handle_stream_completion(
-            self, model: str, payload: Dict[str, Any], api_key: str
-    ) -> AsyncGenerator[str, None]:
-        """处理流式聊天完成，添加重试逻辑"""
-        retries = 0
-        max_retries = 3
-        while retries < max_retries:
-            try:
-                async for line in self.api_client.stream_generate_content(
-                        payload, model, api_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:
-                            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("Streaming completed successfully")
-                break  # 成功后退出循环
-            except Exception as e:
-                retries += 1
-                logger.warning(
-                    f"Streaming API call failed with error: {str(e)}. Attempt {retries} of {max_retries}"
-                )
-                api_key = await self.key_manager.handle_api_failure(api_key)
-                logger.info(f"Switched to new API key: {api_key}")
-                if retries >= max_retries:
-                    logger.error(
-                        f"Max retries ({max_retries}) reached for streaming. Raising error"
-                    )
-                    yield f"data: {json.dumps({'error': 'Streaming failed after retries'})}\n\n"
-                    yield "data: [DONE]\n\n"
-                    break
-
-    async def create_image_chat_completion(
-            self,
-            request: ChatRequest,
-    ) -> Union[Dict[str, Any], AsyncGenerator[str, None]]:
-        
-        image_generate_request = ImageGenerationRequest()
-        image_generate_request.prompt = request.messages[-1]["content"]
-        image_res = self.image_create_service.generate_images_chat(image_generate_request)
-        
-        if request.stream:
-            return self._handle_stream_image_completion(request.model,image_res)
-        else:
-            return self._handle_normal_image_completion(request.model,image_res)
-        
-    async def _handle_stream_image_completion(
-            self, model: str, image_data: str
-    ) -> AsyncGenerator[str, None]:
-        if image_data:
-            openai_chunk = self.response_handler.handle_image_chat_response(
-                image_data, model, stream=True, finish_reason=None
-            )
-            if openai_chunk:
-                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
-    ) -> Dict[str, Any]:
-        
-        return self.response_handler.handle_image_chat_response(
-            image_data, model, stream=False, finish_reason="stop"
-        )

app/static/js/config_editor.js

@@ -0,0 +1,607 @@
+document.addEventListener('DOMContentLoaded', function() {
+    // 初始化配置
+    initConfig();
+    
+    // 标签切换
+    const tabButtons = document.querySelectorAll('.tab-btn');
+    tabButtons.forEach(button => {
+        button.addEventListener('click', function(e) {
+            // 防止事件冒泡
+            e.stopPropagation();
+            const tabId = this.getAttribute('data-tab');
+            switchTab(tabId);
+        });
+    });
+    
+    // 上传提供商切换
+    const uploadProviderSelect = document.getElementById('UPLOAD_PROVIDER');
+    if (uploadProviderSelect) {
+        uploadProviderSelect.addEventListener('change', function() {
+            toggleProviderConfig(this.value);
+        });
+    }
+    
+    // 切换按钮事件
+    const toggleSwitches = document.querySelectorAll('.toggle-switch');
+    toggleSwitches.forEach(toggleSwitch => {
+        toggleSwitch.addEventListener('click', function(e) {
+            // 防止事件冒泡
+            e.stopPropagation();
+            const checkbox = this.querySelector('input[type="checkbox"]');
+            if (checkbox) {
+                checkbox.checked = !checkbox.checked;
+            }
+        });
+    });
+    
+    // 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);
+
+    // --- 新增：API Key 模态框和搜索相关 ---
+    const apiKeyModal = document.getElementById('apiKeyModal');
+    const addApiKeyBtn = document.getElementById('addApiKeyBtn');
+    const closeApiKeyModalBtn = document.getElementById('closeApiKeyModalBtn');
+    const cancelAddApiKeyBtn = document.getElementById('cancelAddApiKeyBtn');
+    const confirmAddApiKeyBtn = document.getElementById('confirmAddApiKeyBtn');
+    const apiKeyBulkInput = document.getElementById('apiKeyBulkInput');
+    const apiKeySearchInput = document.getElementById('apiKeySearchInput');
+
+    // --- 新增：重置确认模态框相关 ---
+    const resetConfirmModal = document.getElementById('resetConfirmModal');
+    const closeResetModalBtn = document.getElementById('closeResetModalBtn');
+    const cancelResetBtn = document.getElementById('cancelResetBtn');
+    const confirmResetBtn = document.getElementById('confirmResetBtn');
+    // --- 结束：新增 ---
+
+
+    // 打开模态框
+    if (addApiKeyBtn) {
+        addApiKeyBtn.addEventListener('click', () => {
+            if (apiKeyModal) {
+                apiKeyModal.classList.add('show');
+            }
+            if (apiKeyBulkInput) apiKeyBulkInput.value = ''; // 清空输入框
+        });
+    }
+
+    // 关闭模态框 (X 按钮)
+    if (closeApiKeyModalBtn) {
+        closeApiKeyModalBtn.addEventListener('click', () => {
+            if (apiKeyModal) {
+                apiKeyModal.classList.remove('show');
+            }
+        });
+    }
+
+    // 关闭模态框 (取消按钮)
+    if (cancelAddApiKeyBtn) {
+        cancelAddApiKeyBtn.addEventListener('click', () => {
+            if (apiKeyModal) {
+                apiKeyModal.classList.remove('show');
+            }
+        });
+    }
+
+    // 点击模态框外部关闭 (处理两个模态框)
+    window.addEventListener('click', (event) => {
+        if (event.target == apiKeyModal) {
+            apiKeyModal.classList.remove('show');
+        }
+        if (event.target == resetConfirmModal) { // 新增对重置模态框的处理
+            resetConfirmModal.classList.remove('show');
+        }
+    });
+
+    // 确认添加 API Key
+    if (confirmAddApiKeyBtn) {
+        confirmAddApiKeyBtn.addEventListener('click', handleBulkAddApiKeys);
+    }
+
+    // API Key 搜索 (稍后实现具体逻辑)
+    if (apiKeySearchInput) {
+        apiKeySearchInput.addEventListener('input', handleApiKeySearch);
+    }
+    // --- 结束：API Key 相关 ---
+
+    // --- 新增：重置确认模态框事件监听 (移到 DOMContentLoaded 内部) ---
+    if (closeResetModalBtn) {
+        closeResetModalBtn.addEventListener('click', () => {
+            if (resetConfirmModal) {
+                resetConfirmModal.classList.remove('show');
+            }
+        });
+    }
+    if (cancelResetBtn) {
+        cancelResetBtn.addEventListener('click', () => {
+            if (resetConfirmModal) {
+                resetConfirmModal.classList.remove('show');
+            }
+        });
+    }
+    if (confirmResetBtn) {
+        // 调用之前定义的 executeReset 函数
+        confirmResetBtn.addEventListener('click', () => {
+             if (resetConfirmModal) {
+                 resetConfirmModal.classList.remove('show'); // 关闭模态框
+             }
+             executeReset(); // 执行重置逻辑
+        });
+    }
+    // --- 结束：重置相关 ---
+
+}); // <-- DOMContentLoaded 结束括号
+
+// 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'];
+        }
+        
+        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: [''],
+            ALLOWED_TOKENS: [''],
+            IMAGE_MODELS: ['gemini-1.5-pro-latest'],
+            SEARCH_MODELS: ['gemini-1.5-flash-latest'],
+            FILTERED_MODELS: ['gemini-1.0-pro-latest'],
+            UPLOAD_PROVIDER: 'smms'
+        };
+        
+        populateForm(defaultConfig);
+        toggleProviderConfig('smms');
+    }
+}
+
+// 填充表单
+function populateForm(config) {
+    for (const [key, value] of Object.entries(config)) {
+        // 首先检查是否是数组类型
+        if (Array.isArray(value)) {
+            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);
+            // }
+                });
+            }
+            // 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)
+                element.value = value ?? ''; // 使用空字符串作为默认值
+            }
+        }
+        // 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)
+    const uploadProvider = document.getElementById('UPLOAD_PROVIDER');
+    if (uploadProvider) {
+        toggleProviderConfig(uploadProvider.value);
+    }
+}
+
+// --- 新增：处理批量添加 API Key 的逻辑 ---
+function handleBulkAddApiKeys() {
+    const apiKeyBulkInput = document.getElementById('apiKeyBulkInput');
+    const apiKeyContainer = document.getElementById('API_KEYS_container');
+    const apiKeyModal = document.getElementById('apiKeyModal');
+
+    if (!apiKeyBulkInput || !apiKeyContainer || !apiKeyModal) return;
+
+    const bulkText = apiKeyBulkInput.value;
+    const keyRegex = /AIzaSy\S{33}/g; // 全局匹配
+    const extractedKeys = bulkText.match(keyRegex) || [];
+
+    // 获取当前已有的 keys
+    const currentKeyInputs = apiKeyContainer.querySelectorAll('.array-input');
+    const currentKeys = Array.from(currentKeyInputs).map(input => input.value).filter(key => key.trim() !== '');
+
+    // 合并并去重
+    const combinedKeys = new Set([...currentKeys, ...extractedKeys]);
+    const uniqueKeys = Array.from(combinedKeys);
+
+    // 清空现有列表显示
+    const existingItems = apiKeyContainer.querySelectorAll('.array-item');
+    existingItems.forEach(item => item.remove());
+
+    // 重新填充列表
+    uniqueKeys.forEach(key => {
+        addArrayItemWithValue('API_KEYS', key);
+    });
+
+    // 关闭模态框
+    apiKeyModal.classList.remove('show');
+    showNotification(`添加/更新了 ${uniqueKeys.length} 个唯一密钥`, 'success');
+}
+
+// --- 新增：处理 API Key 搜索的逻辑 ---
+function handleApiKeySearch() {
+    const apiKeySearchInput = document.getElementById('apiKeySearchInput');
+    const apiKeyContainer = document.getElementById('API_KEYS_container');
+
+    if (!apiKeySearchInput || !apiKeyContainer) return;
+
+    const searchTerm = apiKeySearchInput.value.toLowerCase();
+    const keyItems = apiKeyContainer.querySelectorAll('.array-item');
+
+    keyItems.forEach(item => {
+        const input = item.querySelector('.array-input');
+        if (input) {
+            const key = input.value.toLowerCase();
+            if (key.includes(searchTerm)) {
+                item.style.display = 'flex'; // 或者 'block'，取决于你的布局
+            } else {
+                item.style.display = 'none';
+            }
+        }
+    });
+}
+
+// 切换标签
+function switchTab(tabId) {
+    // 更新标签按钮状态
+    const tabButtons = document.querySelectorAll('.tab-btn');
+    tabButtons.forEach(button => {
+        if (button.getAttribute('data-tab') === tabId) {
+            // 激活状态：主色背景，白色文字，添加阴影
+            button.classList.remove('bg-white', 'bg-opacity-50', 'text-gray-700', 'hover:bg-opacity-70');
+            button.classList.add('bg-primary-600', 'text-white', 'shadow-md');
+        } else {
+            // 非激活状态：白色背景，灰色文字，无阴影
+            button.classList.remove('bg-primary-600', 'text-white', 'shadow-md');
+            button.classList.add('bg-white', 'bg-opacity-50', 'text-gray-700', 'hover:bg-opacity-70');
+        }
+    });
+    
+    // 更新内容区域
+    const sections = document.querySelectorAll('.config-section');
+    sections.forEach(section => {
+        if (section.id === `${tabId}-section`) {
+            section.classList.add('active');
+        } else {
+            section.classList.remove('active');
+        }
+    });
+}
+
+// 切换上传提供商配置
+function toggleProviderConfig(provider) {
+    const providerConfigs = document.querySelectorAll('.provider-config');
+    providerConfigs.forEach(config => {
+        if (config.getAttribute('data-provider') === provider) {
+            config.classList.add('active');
+        } else {
+            config.classList.remove('active');
+        }
+    });
+}
+
+
+// 添加数组项
+function addArrayItem(key) {
+    const container = document.getElementById(`${key}_container`);
+    if (!container) return;
+    
+    addArrayItemWithValue(key, '');
+}
+
+// 添加带值的数组项
+function addArrayItemWithValue(key, value) {
+    const container = document.getElementById(`${key}_container`);
+    if (!container) return;
+    
+    const arrayItem = document.createElement('div');
+    arrayItem.className = 'array-item flex justify-between items-center mb-2'; // 使用 Flexbox 布局，垂直居中，底部增加间距
+    
+    const input = document.createElement('input');
+    input.type = 'text';
+    input.name = `${key}[]`;
+    input.value = value;
+    input.className = 'array-input flex-grow px-3 py-2 rounded-md border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 mr-2'; // 输入框占据大部分空间，添加样式和右边距
+    
+    const removeBtn = document.createElement('button');
+    removeBtn.type = 'button';
+    removeBtn.className = 'remove-btn text-gray-400 hover:text-red-500 focus:outline-none transition-colors duration-150 ml-2'; // 新的 Tailwind 样式
+    removeBtn.innerHTML = '<i class="fas fa-trash-alt"></i>'; // 改用垃圾桶图标
+    removeBtn.title = '删除'; // 添加悬停提示
+    removeBtn.addEventListener('click', function() {
+        arrayItem.remove();
+    });
+    
+    arrayItem.appendChild(input);
+    arrayItem.appendChild(removeBtn);
+    
+    // 插入到添加按钮之前
+    const controls = container.querySelector('.array-controls');
+    container.insertBefore(arrayItem, controls);
+}
+
+// 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 => {
+        if (!input.name.includes('[]')) {
+            if (input.type === 'number') {
+                formData[input.name] = parseFloat(input.value);
+            } else {
+                formData[input.name] = input.value;
+            }
+        }
+    });
+    
+    // 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 => {
+        const key = container.id.replace('_container', '');
+        const arrayInputs = container.querySelectorAll('.array-input');
+        formData[key] = Array.from(arrayInputs).map(input => input.value).filter(value => value.trim() !== '');
+    });
+    
+    return formData;
+}
+
+// 辅助函数：停止定时任务
+async function stopScheduler() {
+    try {
+        const response = await fetch('/api/scheduler/stop', { method: 'POST' });
+        if (!response.ok) {
+            console.warn(`停止定时任务失败: ${response.status}`);
+        } else {
+            console.log('定时任务已停止');
+        }
+    } catch (error) {
+        console.error('调用停止定时任务API时出错:', error);
+    }
+}
+
+// 辅助函数：启动定时任务
+async function startScheduler() {
+    try {
+        const response = await fetch('/api/scheduler/start', { method: 'POST' });
+        if (!response.ok) {
+            console.warn(`启动定时任务失败: ${response.status}`);
+        } else {
+            console.log('定时任务已启动');
+        }
+    } catch (error) {
+        console.error('调用启动定时任务API时出错:', error);
+    }
+}
+
+// 保存配置
+async function saveConfig() {
+    try {
+        const formData = collectFormData();
+
+        showNotification('正在保存配置...', 'info');
+
+        // 1. 停止定时任务
+        await stopScheduler();
+        
+        const response = await fetch('/api/config', {
+            method: 'PUT',
+            headers: {
+                'Content-Type': 'application/json'
+            },
+            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
+        await startScheduler();
+
+    } catch (error) {
+        console.error('保存配置失败:', error);
+        // 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) { 
+    // 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');
+        if (resetConfirmModal) {
+            resetConfirmModal.classList.add('show');
+        } else {
+            // Fallback if modal doesn't exist for some reason
+            console.error("Reset confirmation modal not found! Falling back to default confirm.");
+            // Fallback to original confirm behavior
+            if (!confirm('确定要重置所有配置吗？这将恢复到默认值。')) {
+                return;
+            }
+            // If confirmed, proceed with the reset logic directly (less ideal)
+            executeReset();
+        }
+    }
+}
+
+// --- 新增：将实际重置逻辑提取到一个单独的函数 ---
+async function executeReset() {
+    try {
+        showNotification('正在重置配置...', 'info');
+
+        // 1. 停止定时任务
+        await stopScheduler();
+        const response = await fetch('/api/config/reset', { method: 'POST' });
+        if (!response.ok) {
+            throw new Error(`HTTP error! status: ${response.status}`);
+        }
+        const config = await response.json();
+        populateForm(config);
+        showNotification('配置已重置为默认值', 'success');
+
+        // 3. 启动新的定时任务
+        await startScheduler();
+
+    } catch (error) {
+        console.error('重置配置失败:', error);
+        showNotification('重置配置失败: ' + error.message, 'error');
+        // 重置失败时，也尝试重启定时任务
+        await startScheduler();
+    }
+}
+// 显示通知
+function showNotification(message, type = 'info') {
+    const notification = document.getElementById('notification');
+    notification.textContent = message;
+    
+    // 设置适当的样式
+    if (type === 'error') {
+        notification.classList.add('bg-danger-500');
+        notification.classList.remove('bg-black');
+    } else {
+        notification.classList.remove('bg-danger-500');
+        notification.classList.add('bg-black');
+        
+        // 可以为不同类型设置不同的颜色
+        if (type === 'success') {
+            notification.style.backgroundColor = '#22c55e'; // 绿色
+        } else if (type === 'info') {
+            notification.style.backgroundColor = '#3b82f6'; // 蓝色
+        } else if (type === 'warning') {
+            notification.style.backgroundColor = '#f59e0b'; // 橙色
+        }
+    }
+    
+    // 应用过渡效果 - 与keys_status.js中一致
+    notification.style.opacity = "1";
+    notification.style.transform = "translate(-50%, 0)";
+    
+    // 设置自动消失
+    setTimeout(() => {
+        notification.style.opacity = "0";
+        notification.style.transform = "translate(-50%, 10px)";
+    }, 3000);
+}
+
+// 刷新页面
+function refreshPage(button) {
+    button.classList.add('loading');
+    location.reload();
+}
+
+// 滚动到顶部
+function scrollToTop() {
+    window.scrollTo({
+        top: 0,
+        behavior: 'smooth'
+    });
+}
+
+// 滚动到底部
+function scrollToBottom() {
+    window.scrollTo({
+        top: document.body.scrollHeight,
+        behavior: 'smooth'
+    });
+}
+
+// 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 {
+        scrollButtons.style.display = 'none';
+    }
+}

app/static/js/error_logs.js

@@ -0,0 +1,538 @@
+// 错误日志页面JavaScript (Updated for new structure, no Bootstrap)
+
+// 页面滚动功能
+function scrollToTop() {
+    window.scrollTo({ top: 0, behavior: 'smooth' });
+}
+
+function scrollToBottom() {
+    window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
+}
+
+// Refresh function removed as the buttons are gone.
+// If refresh functionality is needed elsewhere, it can be triggered directly by calling loadErrorLogs().
+
+// 全局变量
+let currentPage = 1;
+let pageSize = 10;
+// let totalPages = 1; // totalPages will be calculated dynamically based on API response if available, or based on fetched data length
+let errorLogs = []; // Store fetched logs for details view
+let currentSearch = { // Store current search parameters
+    key: '',
+    error: '',
+    startDate: '',
+    endDate: ''
+};
+
+// DOM Elements Cache
+let pageSizeSelector;
+// let refreshBtn; // Removed, as the button is deleted
+let tableBody;
+let paginationElement;
+let loadingIndicator;
+let noDataMessage;
+let errorMessage;
+let logDetailModal;
+let modalCloseBtns; // Collection of close buttons for the modal
+let keySearchInput;
+let errorSearchInput;
+let startDateInput;
+let endDateInput;
+let searchBtn;
+let pageInput; // 新增：页码输入框
+let goToPageBtn; // 新增：跳转按钮
+
+// 页面加载完成后执行
+document.addEventListener('DOMContentLoaded', function() {
+    // Cache DOM elements
+    pageSizeSelector = document.getElementById('pageSize');
+    // refreshBtn = document.getElementById('refreshBtn'); // Removed
+    tableBody = document.getElementById('errorLogsTable');
+    paginationElement = document.getElementById('pagination');
+    loadingIndicator = document.getElementById('loadingIndicator');
+    noDataMessage = document.getElementById('noDataMessage');
+    errorMessage = document.getElementById('errorMessage');
+    logDetailModal = document.getElementById('logDetailModal');
+    // Get all elements that should close the modal
+    modalCloseBtns = document.querySelectorAll('#closeLogDetailModalBtn, #closeModalFooterBtn');
+    keySearchInput = document.getElementById('keySearch');
+    errorSearchInput = document.getElementById('errorSearch');
+    startDateInput = document.getElementById('startDate');
+    endDateInput = document.getElementById('endDate');
+    searchBtn = document.getElementById('searchBtn');
+    pageInput = document.getElementById('pageInput'); // 新增
+    goToPageBtn = document.getElementById('goToPageBtn'); // 新增
+
+    // Initialize page size selector
+    if (pageSizeSelector) {
+        pageSizeSelector.value = pageSize;
+        pageSizeSelector.addEventListener('change', function() {
+            pageSize = parseInt(this.value);
+            currentPage = 1; // Reset to first page
+            loadErrorLogs();
+        });
+    }
+
+    // Refresh button event listener removed
+
+    // Initialize search button
+    if (searchBtn) {
+        searchBtn.addEventListener('click', function() {
+            // Update search parameters from input fields
+            currentSearch.key = keySearchInput ? keySearchInput.value.trim() : '';
+            currentSearch.error = errorSearchInput ? errorSearchInput.value.trim() : '';
+            currentSearch.startDate = startDateInput ? startDateInput.value : '';
+            currentSearch.endDate = endDateInput ? endDateInput.value : '';
+            currentPage = 1; // Reset to first page on new search
+            loadErrorLogs();
+        });
+    }
+
+    // Initialize modal close buttons
+    if (logDetailModal && modalCloseBtns) {
+        modalCloseBtns.forEach(btn => {
+            btn.addEventListener('click', closeLogDetailModal);
+        });
+        // Optional: Close modal if clicking outside the content
+        logDetailModal.addEventListener('click', function(event) {
+            if (event.target === logDetailModal) {
+                closeLogDetailModal();
+            }
+        });
+    }
+
+    // Initial load of error logs
+    loadErrorLogs();
+
+    // Add event listeners for copy buttons inside the modal
+    setupCopyButtons();
+
+    // 新增：为页码跳转按钮添加事件监听器
+    if (goToPageBtn && pageInput) {
+        goToPageBtn.addEventListener('click', function() {
+            const targetPage = parseInt(pageInput.value);
+            // 需要获取总页数来验证输入
+            // 暂时无法直接获取 totalPages，需要在 updatePagination 中存储或重新计算
+            // 简单的验证：必须是正整数
+            if (!isNaN(targetPage) && targetPage >= 1) {
+                // 理想情况下，应检查 targetPage <= totalPages
+                // 但 totalPages 可能未知，所以暂时只跳转
+                currentPage = targetPage;
+                loadErrorLogs();
+                pageInput.value = ''; // 清空输入框
+            } else {
+                showNotification('请输入有效的页码', 'error', 2000);
+                pageInput.value = ''; // 清空无效输入
+            }
+        });
+        // 允许按 Enter 键跳转
+        pageInput.addEventListener('keypress', function(event) {
+            if (event.key === 'Enter') {
+                goToPageBtn.click(); // 触发按钮点击
+            }
+        });
+    }
+});
+
+// Fallback copy function using document.execCommand
+function fallbackCopyTextToClipboard(text) {
+    const textArea = document.createElement("textarea");
+    textArea.value = text;
+
+    // Avoid scrolling to bottom
+    textArea.style.top = "0";
+    textArea.style.left = "0";
+    textArea.style.position = "fixed";
+
+    document.body.appendChild(textArea);
+    textArea.focus();
+    textArea.select();
+
+    let successful = false;
+    try {
+        successful = document.execCommand('copy');
+    } catch (err) {
+        console.error('Fallback copy failed:', err);
+        successful = false;
+    }
+
+    document.body.removeChild(textArea);
+    return successful;
+}
+
+// Helper function to handle feedback after copy attempt (both modern and fallback)
+function handleCopyResult(buttonElement, success) {
+     const originalIcon = buttonElement.querySelector('i').className; // Store original icon class
+     const iconElement = buttonElement.querySelector('i');
+     if (success) {
+        iconElement.className = 'fas fa-check text-success-500'; // Use checkmark icon class
+        showNotification('已复制到剪贴板', 'success', 2000);
+     } else {
+        iconElement.className = 'fas fa-times text-danger-500'; // Use error icon class
+        showNotification('复制失败', 'error', 3000);
+     }
+     setTimeout(() => { iconElement.className = originalIcon; }, success ? 2000 : 3000); // Restore original icon class
+}
+
+// Function to set up copy button listeners (using modern API with fallback)
+function setupCopyButtons() {
+    const copyButtons = document.querySelectorAll('.copy-btn');
+    copyButtons.forEach(button => {
+        button.addEventListener('click', function() {
+            const targetId = this.getAttribute('data-target');
+            const targetElement = document.getElementById(targetId);
+
+            if (targetElement) {
+                const textToCopy = targetElement.textContent;
+                let copySuccess = false;
+
+                // Try modern clipboard API first (requires HTTPS or localhost)
+                if (navigator.clipboard && window.isSecureContext) {
+                    navigator.clipboard.writeText(textToCopy).then(() => {
+                        handleCopyResult(this, true); // Use helper for feedback
+                    }).catch(err => {
+                        console.error('Clipboard API failed, attempting fallback:', err);
+                        // Attempt fallback if modern API fails
+                        copySuccess = fallbackCopyTextToClipboard(textToCopy);
+                        handleCopyResult(this, copySuccess); // Use helper for feedback
+                    });
+                } else {
+                    // Use fallback if modern API is not available or context is insecure
+                    console.warn("Clipboard API not available or context insecure. Using fallback copy method.");
+                    copySuccess = fallbackCopyTextToClipboard(textToCopy);
+                    handleCopyResult(this, copySuccess); // Use helper for feedback
+                }
+            } else {
+                console.error('Target element not found:', targetId);
+                showNotification('复制出错：找不到目标元素', 'error');
+            }
+        });
+    });
+}
+
+// 加载错误日志数据
+async function loadErrorLogs() {
+    showLoading(true);
+    showError(false);
+    showNoData(false);
+
+    const offset = (currentPage - 1) * pageSize;
+
+    try {
+        // Construct the API URL with search parameters
+        let apiUrl = `/api/logs/errors?limit=${pageSize}&offset=${offset}`;
+        if (currentSearch.key) {
+            apiUrl += `&key_search=${encodeURIComponent(currentSearch.key)}`;
+        }
+        if (currentSearch.error) {
+            apiUrl += `&error_search=${encodeURIComponent(currentSearch.error)}`;
+        }
+        if (currentSearch.startDate) {
+            apiUrl += `&start_date=${encodeURIComponent(currentSearch.startDate)}`;
+        }
+        if (currentSearch.endDate) {
+            apiUrl += `&end_date=${encodeURIComponent(currentSearch.endDate)}`;
+        }
+
+        const response = await fetch(apiUrl);
+        if (!response.ok) {
+            // Try to get error message from response body
+            let errorData;
+            try {
+                errorData = await response.json();
+            } catch (e) {
+                // Ignore if response is not JSON
+            }
+            throw new Error(errorData?.detail || `网络响应异常: ${response.statusText}`);
+        }
+        const data = await response.json();
+        // Assuming the API returns an object like { logs: [], total: count }
+        // If it only returns an array, we can't get the total count accurately for pagination
+        if (Array.isArray(data)) {
+            errorLogs = data;
+            renderErrorLogs(errorLogs); // Pass data directly
+            updatePagination(errorLogs.length, -1); // Indicate unknown total
+        } else if (data && Array.isArray(data.logs)) {
+            errorLogs = data.logs;
+            renderErrorLogs(errorLogs); // Pass logs array
+            updatePagination(errorLogs.length, data.total || -1); // Pass total count if available
+        } else {
+             throw new Error('无法识别的API响应格式');
+        }
+
+
+        showLoading(false);
+
+        if (errorLogs.length === 0) {
+            showNoData(true);
+        }
+    } catch (error) {
+        console.error('获取错误日志失败:', error);
+        showLoading(false);
+        showError(true, error.message); // Show specific error message
+    }
+}
+
+
+// 渲染错误日志表格
+function renderErrorLogs(logs) {
+    if (!tableBody) return;
+    tableBody.innerHTML = ''; // Clear previous entries
+
+    if (!logs || logs.length === 0) {
+        // Handled by showNoData
+        return;
+    }
+
+    const startIndex = (currentPage - 1) * pageSize; // Calculate starting index for the current page
+
+    logs.forEach((log, index) => { // Add index parameter to forEach
+        const row = document.createElement('tr');
+        const sequentialId = startIndex + index + 1; // Calculate sequential ID for the current page
+        // Format date
+        let formattedTime = 'N/A';
+        try {
+            const requestTime = new Date(log.request_time);
+            if (!isNaN(requestTime)) {
+                 formattedTime = requestTime.toLocaleString('zh-CN', {
+                    year: 'numeric', month: '2-digit', day: '2-digit',
+                    hour: '2-digit', minute: '2-digit', second: '2-digit', hour12: false
+                });
+            }
+        } catch (e) { console.error("Error formatting date:", e); }
+
+
+        // Truncate error log content for display
+        const errorLogContent = log.error_log ? log.error_log.substring(0, 100) + (log.error_log.length > 100 ? '...' : '') : '无';
+
+        // Mask the Gemini key for display in the table
+        const maskKey = (key) => {
+            if (!key || key.length < 8) return key || '无'; // Don't mask short keys or null
+            return `${key.substring(0, 4)}...${key.substring(key.length - 4)}`;
+        };
+        const maskedKey = maskKey(log.gemini_key);
+
+        row.innerHTML = `
+            <td>${sequentialId}</td> <!-- Use sequential ID -->
+            <td title="${log.gemini_key || ''}">${maskedKey}</td>
+            <td>${log.error_type || '未知'}</td>
+            <td class="error-log-content" title="${log.error_log || ''}">${errorLogContent}</td>
+            <td>${log.model_name || '未知'}</td>
+            <td>${formattedTime}</td>
+            <td>
+                <button class="btn-view-details" data-log-id="${log.id}">
+                    查看详情
+                </button>
+            </td>
+        `;
+
+        tableBody.appendChild(row);
+    });
+
+    // Add event listeners to new 'View Details' buttons
+    document.querySelectorAll('.btn-view-details').forEach(button => {
+        button.addEventListener('click', function() {
+            const logId = parseInt(this.getAttribute('data-log-id'));
+            showLogDetails(logId);
+        });
+    });
+}
+
+// 显示错误日志详情 (Custom Modal Logic)
+function showLogDetails(logId) {
+    const log = errorLogs.find(l => l.id === logId);
+    if (!log || !logDetailModal) return;
+
+    // Format date
+     let formattedTime = 'N/A';
+     try {
+         const requestTime = new Date(log.request_time);
+         if (!isNaN(requestTime)) {
+              formattedTime = requestTime.toLocaleString('zh-CN', {
+                 year: 'numeric', month: '2-digit', day: '2-digit',
+                 hour: '2-digit', minute: '2-digit', second: '2-digit', hour12: false
+             });
+         }
+     } catch (e) { console.error("Error formatting date:", e); }
+
+
+    // Format request message (handle potential JSON)
+    let formattedRequestMsg = '无';
+    if (log.request_msg) {
+        try {
+            // Check if it's already an object/array
+            if (typeof log.request_msg === 'object' && log.request_msg !== null) {
+                 formattedRequestMsg = JSON.stringify(log.request_msg, null, 2);
+            }
+            // Check if it's a JSON string
+            else if (typeof log.request_msg === 'string' && log.request_msg.trim().startsWith('{') || log.request_msg.trim().startsWith('[')) {
+                formattedRequestMsg = JSON.stringify(JSON.parse(log.request_msg), null, 2);
+            }
+             else {
+                formattedRequestMsg = String(log.request_msg);
+            }
+        } catch (e) {
+            formattedRequestMsg = String(log.request_msg); // Fallback to string
+            console.warn("Could not parse request_msg as JSON:", e);
+        }
+    }
+
+    // Populate modal content (show full key in modal)
+    document.getElementById('modalGeminiKey').textContent = log.gemini_key || '无';
+    document.getElementById('modalErrorType').textContent = log.error_type || '未知';
+    document.getElementById('modalErrorLog').textContent = log.error_log || '无';
+    document.getElementById('modalRequestMsg').textContent = formattedRequestMsg;
+    document.getElementById('modalModelName').textContent = log.model_name || '未知';
+    document.getElementById('modalRequestTime').textContent = formattedTime;
+
+    // Show the modal
+    logDetailModal.classList.add('show');
+    // Optional: Prevent body scrolling when modal is open
+    document.body.style.overflow = 'hidden';
+}
+
+// Close Log Detail Modal
+function closeLogDetailModal() {
+     if (logDetailModal) {
+        logDetailModal.classList.remove('show');
+        // Optional: Restore body scrolling
+        document.body.style.overflow = '';
+     }
+}
+
+
+// 更新分页控件
+function updatePagination(currentItemCount, totalItems) {
+    if (!paginationElement) return;
+    paginationElement.innerHTML = ''; // Clear existing pagination
+
+    // Calculate total pages only if totalItems is known and valid
+    let totalPages = 1;
+    if (totalItems >= 0) {
+        totalPages = Math.max(1, Math.ceil(totalItems / pageSize));
+    } else if (currentItemCount < pageSize && currentPage === 1) {
+        // If less items than page size fetched on page 1, assume it's the only page
+        totalPages = 1;
+    } else {
+        // If total is unknown and more items might exist, we can't build full pagination
+        // We can show Prev/Next based on current page and if items were returned
+        console.warn("Total item count unknown, pagination will be limited.");
+        // Basic Prev/Next for unknown total
+        addPaginationLink(paginationElement, '&laquo;', currentPage > 1, () => { currentPage--; loadErrorLogs(); });
+        addPaginationLink(paginationElement, currentPage.toString(), true, null, true); // Current page number (non-clickable)
+        addPaginationLink(paginationElement, '&raquo;', currentItemCount === pageSize, () => { currentPage++; loadErrorLogs(); }); // Next enabled if full page was returned
+        return; // Exit here for limited pagination
+    }
+
+
+    const maxPagesToShow = 5; // Max number of page links to show
+    let startPage = Math.max(1, currentPage - Math.floor(maxPagesToShow / 2));
+    let endPage = Math.min(totalPages, startPage + maxPagesToShow - 1);
+
+    // Adjust startPage if endPage reaches the limit first
+     if (endPage === totalPages) {
+        startPage = Math.max(1, endPage - maxPagesToShow + 1);
+    }
+
+
+    // Previous Button
+    addPaginationLink(paginationElement, '&laquo;', currentPage > 1, () => { currentPage--; loadErrorLogs(); });
+
+    // First Page Button
+    if (startPage > 1) {
+        addPaginationLink(paginationElement, '1', true, () => { currentPage = 1; loadErrorLogs(); });
+        if (startPage > 2) {
+            addPaginationLink(paginationElement, '...', false); // Ellipsis
+        }
+    }
+
+    // Page Number Buttons
+    for (let i = startPage; i <= endPage; i++) {
+        addPaginationLink(paginationElement, i.toString(), true, () => { currentPage = i; loadErrorLogs(); }, i === currentPage);
+    }
+
+     // Last Page Button
+    if (endPage < totalPages) {
+        if (endPage < totalPages - 1) {
+             addPaginationLink(paginationElement, '...', false); // Ellipsis
+        }
+        addPaginationLink(paginationElement, totalPages.toString(), true, () => { currentPage = totalPages; loadErrorLogs(); });
+    }
+
+
+    // Next Button
+    addPaginationLink(paginationElement, '&raquo;', currentPage < totalPages, () => { currentPage++; loadErrorLogs(); });
+}
+
+// Helper function to add pagination links
+function addPaginationLink(parentElement, text, enabled, clickHandler, isActive = false) {
+    const pageItem = document.createElement('li');
+    // 移除 'page-item' 和 'active' 类，使用 Tailwind 类进行样式化
+    // pageItem.className = `page-item ${!enabled ? 'disabled' : ''} ${isActive ? 'active' : ''}`;
+
+    const pageLink = document.createElement('a');
+    // 使用 Tailwind 类进行样式化
+    pageLink.className = `px-3 py-1 rounded-md text-sm transition duration-150 ease-in-out ${
+        isActive
+            ? 'bg-primary-600 text-white font-semibold shadow-md cursor-default' // 突出当前页样式
+            : enabled
+                ? 'bg-white text-gray-700 hover:bg-primary-50 hover:text-primary-600 border border-gray-300' // 可点击页码样式
+                : 'bg-gray-100 text-gray-400 cursor-not-allowed border border-gray-200' // 禁用状态样式 (如 '...')
+    }`;
+    pageLink.href = '#'; // Prevent page jump
+    pageLink.innerHTML = text;
+
+    if (enabled && clickHandler) {
+        pageLink.addEventListener('click', function(e) {
+            e.preventDefault();
+            clickHandler();
+        });
+    } else if (!enabled) {
+         pageLink.addEventListener('click', e => e.preventDefault()); // Prevent click on disabled or active
+    } else if (isActive) {
+        pageLink.addEventListener('click', e => e.preventDefault()); // Prevent click on active page
+    }
+
+    // 不再需要 li 元素，直接将 a 元素添加到父元素
+    // pageItem.appendChild(pageLink);
+    parentElement.appendChild(pageLink);
+}
+
+
+// 显示/隐藏状态指示器 (using 'active' class)
+function showLoading(show) {
+    if (loadingIndicator) loadingIndicator.style.display = show ? 'block' : 'none';
+}
+
+function showNoData(show) {
+     if (noDataMessage) noDataMessage.style.display = show ? 'block' : 'none';
+}
+
+function showError(show, message = '加载错误日志失败，请稍后重试。') {
+    if (errorMessage) {
+        errorMessage.style.display = show ? 'block' : 'none';
+        if (show) {
+            // Update the error message content
+            const p = errorMessage.querySelector('p');
+            if (p) p.textContent = message;
+        }
+    }
+}
+
+// Function to show temporary status notifications (like copy success)
+function showNotification(message, type = 'success', duration = 3000) {
+    const notificationElement = document.getElementById('copyStatus'); // Or a more generic ID if needed
+    if (!notificationElement) return;
+
+    notificationElement.textContent = message;
+    notificationElement.className = `notification ${type} show`; // Add 'show' class
+
+    // Hide after duration
+    setTimeout(() => {
+        notificationElement.classList.remove('show');
+    }, duration);
+}
+
+// Example Usage (if copy functionality is added later):
+// showNotification('密钥已复制!', 'success');
+// showNotification('复制失败!', 'error');

app/static/js/keys_status.js

@@ -0,0 +1,616 @@
+// 统计数据可视化交互效果
+
+function copyToClipboard(text) {
+    if (navigator.clipboard && navigator.clipboard.writeText) {
+        return navigator.clipboard.writeText(text);
+    } else {
+        return new Promise((resolve, reject) => {
+            const textArea = document.createElement("textarea");
+            textArea.value = text;
+            textArea.style.position = "fixed";
+            document.body.appendChild(textArea);
+            textArea.focus();
+            textArea.select();
+            try {
+                const successful = document.execCommand('copy');
+                document.body.removeChild(textArea);
+                if (successful) {
+                    resolve();
+                } else {
+                    reject(new Error('复制失败'));
+                }
+            } catch (err) {
+                document.body.removeChild(textArea);
+                reject(err);
+            }
+        });
+    }
+}
+
+// 添加统计项动画效果
+function initStatItemAnimations() {
+    const statItems = document.querySelectorAll('.stat-item');
+    statItems.forEach(item => {
+        item.addEventListener('mouseenter', () => {
+            item.style.transform = 'scale(1.05)';
+            const icon = item.querySelector('.stat-icon');
+            if (icon) {
+                icon.style.opacity = '0.2';
+                icon.style.transform = 'scale(1.1) rotate(0deg)';
+            }
+        });
+        
+        item.addEventListener('mouseleave', () => {
+            item.style.transform = '';
+            const icon = item.querySelector('.stat-icon');
+            if (icon) {
+                icon.style.opacity = '';
+                icon.style.transform = '';
+            }
+        });
+    });
+}
+
+function copyKeys(type) {
+    const keys = Array.from(document.querySelectorAll(`#${type}Keys .key-text`)).map(span => span.dataset.fullKey);
+    
+    if (keys.length === 0) {
+        showNotification('没有可复制的密钥', 'error');
+        return;
+    }
+    
+    const keysText = keys.join('\n');
+    
+    copyToClipboard(keysText)
+        .then(() => {
+            showNotification(`已成功复制${keys.length}个${type === 'valid' ? '有效' : '无效'}密钥`);
+        })
+        .catch((err) => {
+            console.error('无法复制文本: ', err);
+            showNotification('复制失败，请重试', 'error');
+        });
+}
+
+function copyKey(key) {
+    copyToClipboard(key)
+        .then(() => {
+            showNotification(`已成功复制密钥`);
+        })
+        .catch((err) => {
+            console.error('无法复制文本: ', err);
+            showNotification('复制失败，请重试', 'error');
+        });
+}
+
+// 移除 showCopyStatus 函数，因为它已被 showNotification 替代
+
+async function verifyKey(key, button) {
+    try {
+        // 禁用按钮并显示加载状态
+        button.disabled = true;
+        const originalHtml = button.innerHTML;
+        button.innerHTML = '<i class="fas fa-spinner fa-spin"></i> 验证中';
+
+        try {
+            const response = await fetch(`/gemini/v1beta/verify-key/${key}`, {
+                method: 'POST'
+            });
+            const data = await response.json();
+
+            // 根据验证结果更新UI并显示模态提示框
+            if (data.success || data.status === 'valid') {
+                // 验证成功，显示成功结果
+                button.style.backgroundColor = '#27ae60';
+                // 使用结果模态框显示成功消息
+                showResultModal(true, '密钥验证成功');
+                // 模态框关闭时会自动刷新页面
+            } else {
+                // 验证失败，显示失败结果
+                const errorMsg = data.error || '密钥无效';
+                button.style.backgroundColor = '#e74c3c';
+                // 使用结果模态框显示失败消息，但不自动刷新页面
+                showResultModal(false, '密钥验证失败: ' + errorMsg, true); // 改为true以在关闭时刷新
+            }
+        } catch (fetchError) {
+            console.error('API请求失败:', fetchError);
+            showResultModal(false, '验证请求失败: ' + fetchError.message, true); // 改为true以在关闭时刷新
+        } finally {
+            // 1秒后恢复按钮原始状态
+            setTimeout(() => {
+                button.innerHTML = originalHtml;
+                button.disabled = false;
+                button.style.backgroundColor = '';
+            }, 1000);
+        }
+    } catch (error) {
+        console.error('验证失败:', error);
+        button.disabled = false;
+        button.innerHTML = '<i class="fas fa-check-circle"></i> 验证';
+        showResultModal(false, '验证处理失败: ' + error.message, true); // 改为true以在关闭时刷新
+    }
+}
+
+async function resetKeyFailCount(key, button) {
+    try {
+        // 禁用按钮并显示加载状态
+        button.disabled = true;
+        const originalHtml = button.innerHTML;
+        button.innerHTML = '<i class="fas fa-spinner fa-spin"></i> 重置中';
+
+        const response = await fetch(`/gemini/v1beta/reset-fail-count/${key}`, {
+            method: 'POST'
+        });
+        const data = await response.json();
+
+        // 根据重置结果更新UI
+        if (data.success) {
+            showNotification('失败计数重置成功');
+            // 成功时保留绿色背景一会儿
+            button.style.backgroundColor = '#27ae60';
+            // 稍后刷新页面
+            setTimeout(() => location.reload(), 1000);
+        } else {
+            const errorMsg = data.message || '重置失败';
+            showNotification('重置失败: ' + errorMsg, 'error');
+            // 失败时保留红色背景一会儿
+            button.style.backgroundColor = '#e74c3c';
+        }
+
+        // 立即恢复按钮状态，除非成功或失败时需要短暂显示颜色
+        if (!data.success) {
+             // 如果失败，1秒后恢复按钮
+             setTimeout(() => {
+                 button.innerHTML = originalHtml;
+                 button.disabled = false;
+                 button.style.backgroundColor = '';
+             }, 1000);
+        } else {
+             // 如果成功，在刷新前恢复按钮（虽然用户可能看不到）
+             button.innerHTML = originalHtml;
+             button.disabled = false;
+             // 背景色会在刷新时重置
+        }
+
+    } catch (error) {
+        console.error('重置失败:', error);
+        showNotification('重置请求失败: ' + error.message, 'error');
+        // 确保在捕获到错误时恢复按钮状态
+        button.innerHTML = originalHtml; // 需要确保 originalHtml 在此作用域可用
+        button.disabled = false;
+        button.innerHTML = '<i class="fas fa-redo-alt"></i> 重置';
+    }
+}
+
+function showResetModal(type) {
+    const modalElement = document.getElementById('resetModal');
+    const titleElement = document.getElementById('resetModalTitle');
+    const messageElement = document.getElementById('resetModalMessage');
+    const confirmButton = document.getElementById('confirmResetBtn');
+    
+    // 设置标题和消息
+    titleElement.textContent = '批量重置失败次数';
+    messageElement.textContent = `确定要批量重置${type === 'valid' ? '有效' : '无效'}密钥的失败次数吗？`;
+    
+    // 设置确认按钮事件
+    confirmButton.onclick = () => executeResetAll(type);
+    
+    // 显示模态框
+    modalElement.classList.remove('hidden');
+}
+
+function closeResetModal() {
+    document.getElementById('resetModal').classList.add('hidden');
+}
+
+// 触发显示模态框
+function resetAllKeysFailCount(type, event) {
+    // 阻止事件冒泡
+    if (event) {
+        event.stopPropagation();
+    }
+    
+    // 显示模态确认框
+    showResetModal(type);
+}
+
+// 执行批量重置
+// 关闭模态框并根据参数决定是否刷新页面
+function closeResultModal(reload = true) {
+    document.getElementById('resultModal').classList.add('hidden');
+    if (reload) {
+        location.reload(); // 操作完成后刷新页面
+    }
+}
+
+// 显示操作结果模态框
+function showResultModal(success, message, autoReload = true) {
+    const modalElement = document.getElementById('resultModal');
+    const titleElement = document.getElementById('resultModalTitle');
+    const messageElement = document.getElementById('resultModalMessage');
+    const iconElement = document.getElementById('resultIcon');
+    const confirmButton = document.getElementById('resultModalConfirmBtn');
+    
+    // 设置标题
+    titleElement.textContent = success ? '操作成功' : '操作失败';
+    
+    // 设置图标
+    if (success) {
+        iconElement.innerHTML = '<i class="fas fa-check-circle text-success-500"></i>';
+        iconElement.className = 'text-5xl mb-3 text-success-500';
+    } else {
+        iconElement.innerHTML = '<i class="fas fa-times-circle"></i>';
+        iconElement.className = 'text-5xl mb-3 text-danger-500';
+    }
+    
+    // 设置消息
+    messageElement.textContent = message;
+    
+    // 设置确认按钮点击事件
+    confirmButton.onclick = () => closeResultModal(autoReload);
+    
+    // 显示模态框
+    modalElement.classList.remove('hidden');
+}
+
+async function executeResetAll(type) {
+    try {
+        // 关闭确认模态框
+        closeResetModal();
+        
+        // 使用data-reset-type属性直接找到对应的重置按钮
+        const resetButton = document.querySelector(`button[data-reset-type="${type}"]`);
+        
+        if (!resetButton) {
+            // 如果找不到按钮，显示错误并返回
+            showResultModal(false, `找不到${type === 'valid' ? '有效' : '无效'}密钥区域的批量重置按钮`);
+            return;
+        }
+        
+        // 禁用按钮并显示加载状态
+        resetButton.disabled = true;
+        const originalHtml = resetButton.innerHTML;
+        resetButton.innerHTML = '<i class="fas fa-spinner fa-spin"></i> 重置中';
+
+        try {
+            // 调用API，传递类型参数
+            const response = await fetch(`/gemini/v1beta/reset-all-fail-counts?key_type=${type}`, {
+                method: 'POST'
+            });
+            
+            if (!response.ok) {
+                throw new Error(`服务器返回错误: ${response.status}`);
+            }
+            
+            const data = await response.json();
+
+            // 根据重置结果显示模态框
+            if (data.success) {
+                const message = data.reset_count ?
+                    `成功重置${data.reset_count}个${type === 'valid' ? '有效' : '无效'}密钥的失败次数` :
+                    '所有失败次数重置成功';
+                showResultModal(true, message);
+            } else {
+                const errorMsg = data.message || '批量重置失败';
+                showResultModal(false, '批量重置失败: ' + errorMsg);
+            }
+        } catch (fetchError) {
+            console.error('API请求失败:', fetchError);
+            showResultModal(false, '批量重置请求失败: ' + fetchError.message);
+        } finally {
+            // 立即恢复按钮状态
+             resetButton.innerHTML = originalHtml;
+             resetButton.disabled = false;
+        }
+    } catch (error) {
+        console.error('批量重置失败:', error);
+        showResultModal(false, '批量重置处理失败: ' + error.message);
+    }
+}
+
+function scrollToTop() {
+    window.scrollTo({ top: 0, behavior: 'smooth' });
+}
+
+function scrollToBottom() {
+    window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
+}
+
+// 移除这个函数，因为它可能正在干扰按钮的显示
+// HTML中已经设置了滚动按钮为flex显示，不需要JavaScript额外控制
+function updateScrollButtons() {
+    // 不执行任何操作
+}
+
+function refreshPage(button) {
+    button.classList.add('loading');
+    button.disabled = true;
+    
+    setTimeout(() => {
+        window.location.reload();
+    }, 300);
+}
+
+// 重写切换区域显示/隐藏函数，以更好地支持新样式
+function toggleSection(header, sectionId) {
+    const toggleIcon = header.querySelector('.toggle-icon');
+    const content = header.nextElementSibling;
+    
+    if (toggleIcon && content) {
+        // 添加旋转动画
+        toggleIcon.classList.toggle('collapsed');
+        
+        // 控制内容区域的可见性
+        if (!content.classList.contains('collapsed')) {
+            // 收起内容
+            content.style.maxHeight = '0px';
+            content.style.opacity = '0';
+            content.style.overflow = 'hidden';
+            content.classList.add('collapsed');
+            
+            // 为动画添加延迟
+            setTimeout(() => {
+                content.style.padding = '0';
+            }, 100);
+        } else {
+            // 展开内容
+            content.classList.remove('collapsed');
+            content.style.padding = '1rem';
+            content.style.maxHeight = '2000px'; // 使用足够大的高度
+            content.style.opacity = '1';
+            
+            // 为动画添加延迟
+            setTimeout(() => {
+                content.style.overflow = 'visible';
+            }, 300);
+        }
+    }
+}
+
+// 筛选有效密钥（根据失败次数阈值）
+function filterValidKeys() {
+    const thresholdInput = document.getElementById('failCountThreshold');
+    const validKeyItems = document.querySelectorAll('#validKeys li');
+    // 读取阈值，如果输入无效或为空，则默认为0（不过滤）
+    const threshold = parseInt(thresholdInput.value, 10);
+    const filterThreshold = isNaN(threshold) || threshold < 0 ? 0 : threshold;
+
+    validKeyItems.forEach(item => {
+        const failCount = parseInt(item.dataset.failCount, 10);
+        // 如果失败次数大于等于阈值，则显示，否则隐藏
+        if (failCount >= filterThreshold) {
+            item.style.display = ''; // 显示
+        } else {
+            item.style.display = 'none'; // 隐藏
+        }
+    });
+}
+
+// 初始化
+document.addEventListener('DOMContentLoaded', () => {
+    // 初始化统计区块动画
+    initStatItemAnimations();
+    
+    // 添加数字滚动动画效果
+    const animateCounters = () => {
+        const statValues = document.querySelectorAll('.stat-value');
+        statValues.forEach(valueElement => {
+            const finalValue = parseInt(valueElement.textContent, 10);
+            if (!isNaN(finalValue)) {
+                // 保存原始值以便稍后恢复
+                if (!valueElement.dataset.originalValue) {
+                    valueElement.dataset.originalValue = valueElement.textContent;
+                }
+                
+                // 数字滚动动画
+                let startValue = 0;
+                const duration = 1500;
+                const startTime = performance.now();
+                
+                const updateCounter = (currentTime) => {
+                    const elapsedTime = currentTime - startTime;
+                    if (elapsedTime < duration) {
+                        const progress = elapsedTime / duration;
+                        // 使用缓动函数使动画更自然
+                        const easeOutValue = 1 - Math.pow(1 - progress, 3);
+                        const currentValue = Math.floor(easeOutValue * finalValue);
+                        valueElement.textContent = currentValue;
+                        requestAnimationFrame(updateCounter);
+                    } else {
+                        // 恢复为原始值，以确保准确性
+                        valueElement.textContent = valueElement.dataset.originalValue;
+                    }
+                };
+                
+                requestAnimationFrame(updateCounter);
+            }
+        });
+    };
+    
+    // 在页面加载后启动数字动画
+    setTimeout(animateCounters, 300);
+    
+    // 添加卡片悬停效果
+    document.querySelectorAll('.stats-card').forEach(card => {
+        card.addEventListener('mouseenter', () => {
+            card.classList.add('shadow-lg');
+            card.style.transform = 'translateY(-2px)';
+        });
+        
+        card.addEventListener('mouseleave', () => {
+            card.classList.remove('shadow-lg');
+            card.style.transform = '';
+        });
+    });
+    
+    // 监听展开/折叠事件
+    document.querySelectorAll('.stats-card-title').forEach(header => {
+        header.addEventListener('click', () => {
+            const card = header.closest('.stats-card');
+            if (card) {
+                card.classList.toggle('active');
+            }
+        });
+    });
+    
+    // 添加筛选输入框事件监听
+    const thresholdInput = document.getElementById('failCountThreshold');
+    if (thresholdInput) {
+        // 使用 'input' 事件实时响应输入变化
+        thresholdInput.addEventListener('input', filterValidKeys);
+        // 初始加载时应用一次筛选
+        filterValidKeys();
+    }
+
+    // 添加自动刷新功能，每60秒刷新一次
+    const autoRefreshInterval = 60000; // 60秒
+    setInterval(() => {
+        console.log('自动刷新 keys_status 页面...');
+        location.reload();
+    }, autoRefreshInterval);
+});
+
+// Service Worker registration
+if ('serviceWorker' in navigator) {
+    window.addEventListener('load', () => {
+        navigator.serviceWorker.register('/static/service-worker.js')
+            .then(registration => {
+                console.log('ServiceWorker注册成功:', registration.scope);
+            })
+            .catch(error => {
+                console.log('ServiceWorker注册失败:', error);
+            });
+    });
+}
+function toggleKeyVisibility(button) {
+    const keyContainer = button.closest('.flex.items-center.gap-1');
+    const keyTextSpan = keyContainer.querySelector('.key-text');
+    const eyeIcon = button.querySelector('i');
+    const fullKey = keyTextSpan.dataset.fullKey;
+    const maskedKey = fullKey.substring(0, 4) + '...' + fullKey.substring(fullKey.length - 4);
+
+    if (keyTextSpan.textContent === maskedKey) {
+        keyTextSpan.textContent = fullKey;
+        eyeIcon.classList.remove('fa-eye');
+        eyeIcon.classList.add('fa-eye-slash');
+        button.title = '隐藏密钥';
+    } else {
+        keyTextSpan.textContent = maskedKey;
+        eyeIcon.classList.remove('fa-eye-slash');
+        eyeIcon.classList.add('fa-eye');
+        button.title = '显示密钥';
+    }
+}
+
+// --- API 调用详情模态框逻辑 ---
+
+// 显示 API 调用详情模态框
+async function showApiCallDetails(period) {
+    const modal = document.getElementById('apiCallDetailsModal');
+    const contentArea = document.getElementById('apiCallDetailsContent');
+    const titleElement = document.getElementById('apiCallDetailsModalTitle');
+
+    if (!modal || !contentArea || !titleElement) {
+        console.error('无法找到 API 调用详情模态框元素');
+        showNotification('无法显示详情，页面元素缺失', 'error');
+        return;
+    }
+
+    // 设置标题
+    let periodText = '';
+    switch (period) {
+        case '1m': periodText = '最近 1 分钟'; break;
+        case '1h': periodText = '最近 1 小时'; break;
+        case '24h': periodText = '最近 24 小时'; break;
+        default: periodText = '指定时间段';
+    }
+    titleElement.textContent = `${periodText} API 调用详情`;
+
+    // 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 {
+        // 调用后端 API 获取数据
+        const response = await fetch(`/api/stats/details?period=${period}`);
+        if (!response.ok) {
+            throw new Error(`服务器错误: ${response.status}`);
+        }
+        const data = await response.json();
+
+        // 渲染数据
+        renderApiCallDetails(data, contentArea);
+
+    } catch (error) {
+        console.error('获取 API 调用详情失败:', 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: ${error.message}</p>
+            </div>`;
+    }
+}
+
+// 关闭 API 调用详情模态框
+function closeApiCallDetailsModal() {
+    const modal = document.getElementById('apiCallDetailsModal');
+    if (modal) {
+        modal.classList.add('hidden');
+    }
+}
+
+// 渲染 API 调用详情到模态框
+function renderApiCallDetails(data, container) {
+    if (!data || data.length === 0) {
+        container.innerHTML = `
+            <div class="text-center py-10 text-gray-500">
+                <i class="fas fa-info-circle text-3xl"></i>
+                <p class="mt-2">该时间段内没有 API 调用记录。</p>
+            </div>`;
+        return;
+    }
+
+    // 创建表格
+    let tableHtml = `
+        <table class="min-w-full divide-y divide-gray-200">
+            <thead class="bg-gray-50">
+                <tr>
+                    <th scope="col" class="px-4 py-2 text-left text-xs font-medium text-gray-500 uppercase tracking-wider">时间</th>
+                    <th scope="col" class="px-4 py-2 text-left text-xs font-medium text-gray-500 uppercase tracking-wider">密钥 (部分)</th>
+                    <th scope="col" class="px-4 py-2 text-left text-xs font-medium text-gray-500 uppercase tracking-wider">模型</th>
+                    <th scope="col" class="px-4 py-2 text-left text-xs font-medium text-gray-500 uppercase tracking-wider">状态</th>
+                </tr>
+            </thead>
+            <tbody class="bg-white divide-y divide-gray-200">
+    `;
+
+    // 填充表格行
+    data.forEach(call => {
+        const timestamp = new Date(call.timestamp).toLocaleString();
+        const keyDisplay = call.key ? `${call.key.substring(0, 4)}...${call.key.substring(call.key.length - 4)}` : 'N/A';
+        const statusClass = call.status === 'success' ? 'text-success-600' : 'text-danger-600';
+        const statusIcon = call.status === 'success' ? 'fa-check-circle' : 'fa-times-circle';
+
+        tableHtml += `
+            <tr>
+                <td class="px-4 py-2 whitespace-nowrap text-sm text-gray-700">${timestamp}</td>
+                <td class="px-4 py-2 whitespace-nowrap text-sm text-gray-500 font-mono">${keyDisplay}</td>
+                <td class="px-4 py-2 whitespace-nowrap text-sm text-gray-500">${call.model || 'N/A'}</td>
+                <td class="px-4 py-2 whitespace-nowrap text-sm ${statusClass}">
+                    <i class="fas ${statusIcon} mr-1"></i>
+                    ${call.status}
+                </td>
+            </tr>
+        `;
+    });
+
+    tableHtml += `
+            </tbody>
+        </table>
+    `;
+
+    container.innerHTML = tableHtml;
+}

app/static/manifest.json

@@ -0,0 +1,17 @@
+{
+  "name": "Gemini Balance",
+  "short_name": "GBalance",
+  "description": "Gemini API密钥管理工具",
+  "start_url": "/",
+  "display": "standalone",
+  "background_color": "#667eea",
+  "theme_color": "#764ba2",
+  "icons": [
+    {
+      "src": "/static/icons/icon-192x192.png",
+      "sizes": "192x192",
+      "type": "image/png",
+      "purpose": "any maskable"
+    }
+  ]
+}

app/static/service-worker.js

@@ -0,0 +1,43 @@
+const CACHE_NAME = 'gbalance-cache-v1';
+const urlsToCache = [
+  '/',
+  '/static/manifest.json',
+  '/static/icons/icon-192x192.png'
+];
+
+self.addEventListener('install', event => {
+  event.waitUntil(
+    caches.open(CACHE_NAME)
+      .then(cache => {
+        console.log('Opened cache');
+        return cache.addAll(urlsToCache);
+      })
+  );
+});
+
+self.addEventListener('fetch', event => {
+  event.respondWith(
+    caches.match(event.request)
+      .then(response => {
+        if (response) {
+          return response;
+        }
+        return fetch(event.request);
+      })
+  );
+});
+
+self.addEventListener('activate', event => {
+  const cacheWhitelist = [CACHE_NAME];
+  event.waitUntil(
+    caches.keys().then(cacheNames => {
+      return Promise.all(
+        cacheNames.map(cacheName => {
+          if (cacheWhitelist.indexOf(cacheName) === -1) {
+            return caches.delete(cacheName);
+          }
+        })
+      );
+    })
+  );
+});

app/templates/auth.html

@@ -1,229 +1,124 @@
-<!DOCTYPE html>
-<html lang="zh-CN">
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>验证页面</title>
-    <link href="https://fonts.googleapis.com/css2?family=Roboto:wght@300;400;700&display=swap" rel="stylesheet">
-    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
-    <style>
-        body {
-            font-family: 'Roboto', sans-serif;
-            line-height: 1.6;
-            margin: 0;
-            padding: 0;
-            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
-            min-height: 100vh;
-            display: flex;
-            justify-content: center;
-            align-items: center;
-        }
-        .container {
-            max-width: 400px;
-            width: 90%;
-            background: rgba(255, 255, 255, 0.95);
-            padding: 40px;
-            border-radius: 20px;
-            box-shadow: 0 15px 35px rgba(0,0,0,0.2);
-            backdrop-filter: blur(10px);
-            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
-        }
+{% extends "base.html" %}
 
-        @media (max-width: 768px) {
-            .container {
-                width: 85%;
-                padding: 30px;
-            }
-            .logo i {
-                font-size: 40px;
-            }
-            h2 {
-                font-size: 22px;
-            }
-            input {
-                padding: 10px 10px 10px 35px;
-                font-size: 15px;
-            }
-            .input-group i {
-                font-size: 16px;
-            }
-            button {
-                padding: 12px;
-                font-size: 15px;
-            }
-        }
+{% block title %}验证页面 - Gemini Balance{% endblock %}
 
-        @media (max-width: 480px) {
-            .container {
-                width: 90%;
-                padding: 25px;
-            }
-            .logo i {
-                font-size: 36px;
-            }
-            h2 {
-                font-size: 20px;
-                margin-bottom: 25px;
-            }
-            form {
-                gap: 15px;
-            }
-            input {
-                padding: 10px 10px 10px 32px;
-                font-size: 14px;
-            }
-            .input-group i {
-                font-size: 15px;
-                left: 10px;
-            }
-            button {
-                padding: 10px;
-                font-size: 14px;
-            }
-            .error-message {
-                font-size: 14px;
-                padding: 8px;
-                margin-top: 12px;
-            }
-        }
-        .container:hover {
-            transform: translateY(-5px);
-            box-shadow: 0 20px 40px rgba(0,0,0,0.25);
-        }
-        .logo {
-            text-align: center;
-            margin-bottom: 30px;
-            animation: fadeIn 1s ease;
-        }
-        .logo i {
-            font-size: 48px;
-            color: #764ba2;
-            margin-bottom: 15px;
-        }
-        h2 {
-            color: #2c3e50;
-            text-align: center;
-            margin-bottom: 30px;
-            font-weight: 700;
-            font-size: 24px;
-            animation: slideDown 0.5s ease;
-        }
-        form {
-            display: flex;
-            flex-direction: column;
-            gap: 20px;
-        }
-        .input-group {
-            position: relative;
-            animation: slideUp 0.5s ease;
-        }
-        .input-group i {
-            position: absolute;
-            left: 12px;
-            top: 50%;
-            transform: translateY(-50%);
-            color: #764ba2;
-            font-size: 18px;
-        }
-        input {
-            width: 100%;
-            padding: 12px 12px 12px 40px;
-            border: 2px solid #e0e0e0;
-            border-radius: 10px;
-            font-size: 16px;
-            box-sizing: border-box;
-            transition: all 0.3s ease;
-            background: rgba(255, 255, 255, 0.9);
-        }
-        input:focus {
-            border-color: #764ba2;
-            box-shadow: 0 0 10px rgba(118, 75, 162, 0.2);
-            outline: none;
-        }
-        button {
-            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
-            color: white;
-            border: none;
-            padding: 14px;
-            border-radius: 10px;
-            cursor: pointer;
-            font-size: 16px;
-            font-weight: bold;
-            transition: all 0.3s ease;
-            position: relative;
-            overflow: hidden;
-        }
-        button:hover {
-            transform: translateY(-2px);
-            box-shadow: 0 5px 15px rgba(118, 75, 162, 0.3);
-        }
-        button:active {
-            transform: translateY(0);
-        }
-        button::after {
-            content: '';
-            position: absolute;
-            top: 50%;
-            left: 50%;
-            width: 0;
-            height: 0;
-            background: rgba(255, 255, 255, 0.2);
-            border-radius: 50%;
-            transform: translate(-50%, -50%);
-            transition: width 0.6s, height 0.6s;
-        }
-        button:active::after {
-            width: 200px;
-            height: 200px;
-            opacity: 0;
-        }
-        .error-message {
-            color: #e74c3c;
-            margin-top: 15px;
-            text-align: center;
-            font-weight: bold;
-            padding: 10px;
-            border-radius: 5px;
-            background: rgba(231, 76, 60, 0.1);
-            animation: shake 0.5s ease;
-        }
-        @keyframes fadeIn {
-            from { opacity: 0; }
-            to { opacity: 1; }
-        }
-        @keyframes slideDown {
-            from { transform: translateY(-20px); opacity: 0; }
-            to { transform: translateY(0); opacity: 1; }
-        }
-        @keyframes slideUp {
-            from { transform: translateY(20px); opacity: 0; }
-            to { transform: translateY(0); opacity: 1; }
-        }
-        @keyframes shake {
-            0%, 100% { transform: translateX(0); }
-            25% { transform: translateX(-5px); }
-            75% { transform: translateX(5px); }
-        }
-    </style>
-</head>
-<body>
-    <div class="container">
-        <div class="logo">
-            <i class="fas fa-shield-alt"></i>
-        </div>
-        <h2>安全验证</h2>
-        <form id="auth-form" action="/auth" method="post">
-            <div class="input-group">
-                <i class="fas fa-key"></i>
-                <input type="password" id="auth-token" name="auth_token" required placeholder="请输入验证令牌">
+{% block head_extra_styles %}
+<style>
+    /* auth.html specific styles */
+    .auth-glass-card { /* Renamed to avoid conflict if base.html has .glass-card */
+        background: rgba(255, 255, 255, 0.85); /* Increased opacity */
+        backdrop-filter: blur(20px);
+        -webkit-backdrop-filter: blur(20px);
+        border: 1px solid rgba(255, 255, 255, 0.2);
+    }
+    .auth-bg-gradient { /* Renamed to avoid conflict if base.html has .bg-gradient */
+         background: linear-gradient(135deg, #4F46E5 0%, #7C3AED 50%, #EC4899 100%);
+    }
+    /* .input-icon class removed, using direct Tailwind classes now */
+    /* Keep button ripple effect if needed, or remove if base provides similar */
+    .auth-button { /* Renamed to avoid conflict */
+        position: relative;
+        overflow: hidden;
+    }
+    .auth-button:after {
+        content: '';
+        position: absolute;
+        top: 50%;
+        left: 50%;
+        width: 0;
+        height: 0;
+        background: rgba(255, 255, 255, 0.2);
+        border-radius: 50%;
+        transform: translate(-50%, -50%);
+        transition: width 0.6s, height 0.6s;
+    }
+    .auth-button:active:after {
+        width: 300px;
+        height: 300px;
+        opacity: 0;
+    }
+</style>
+{% endblock %}
+
+{% block content %}
+<div class="auth-bg-gradient min-h-screen flex flex-col justify-center items-center p-4">
+    <div class="glass-card rounded-2xl shadow-2xl p-10 max-w-md w-full mx-auto transform transition duration-500 hover:-translate-y-1 hover:shadow-3xl animate-fade-in">
+        <div class="flex justify-center mb-8 animate-slide-down">
+            <div class="rounded-full bg-primary-100 p-4 text-primary-600">
+                <i class="fas fa-shield-alt text-4xl"></i>
             </div>
-            <button type="submit">
-                验证访问
+        </div>
+        
+        <h2 class="text-3xl font-extrabold text-center text-transparent bg-clip-text bg-gradient-to-r from-primary-600 to-primary-700 mb-8 animate-slide-down">
+             <img src="/static/icons/logo.png" alt="Gemini Balance Logo" class="h-9 inline-block align-middle mr-2">
+             Gemini Balance
+        </h2>
+        
+        <form id="auth-form" action="/auth" method="post" class="space-y-6 animate-slide-up">
+            <div class="relative">
+                <i class="fas fa-key absolute left-3 top-1/2 transform -translate-y-1/2 text-gray-500"></i>
+                <input
+                    type="password"
+                    id="auth-token"
+                    name="auth_token"
+                    required
+                    placeholder="请输入验证令牌"
+                    class="w-full pl-10 pr-4 py-4 rounded-xl border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 transition duration-300 bg-white bg-opacity-90 text-gray-700"
+                >
+            </div>
+            
+            <button 
+                type="submit" 
+                class="w-full py-4 rounded-xl bg-gradient-to-r from-primary-600 to-primary-700 text-white font-semibold transition duration-300 transform hover:-translate-y-1 hover:shadow-lg"
+            >
+                登录
             </button>
         </form>
+        
         {% if error %}
-        <p class="error-message">{{ error }}</p>
+        <p class="mt-4 text-red-500 text-center font-medium p-3 bg-red-50 rounded-lg border border-red-200 animate-shake">
+            {{ error }}
+        </p>
         {% endif %}
     </div>
-</body>
-</html>
+    
+</div> <!-- Close auth-bg-gradient div -->
+<!-- Notification placeholder for base.html's showNotification -->
+<div id="notification" class="notification"></div>
+    
+{% endblock %}
+
+{% block body_scripts %}
+<script>
+    // auth.html specific JavaScript
+    document.addEventListener('DOMContentLoaded', function() {
+        const form = document.getElementById('auth-form');
+        if (form) {
+            form.addEventListener('submit', function(e) {
+                const token = document.getElementById('auth-token').value.trim();
+                if (!token) {
+                    e.preventDefault();
+                    // Use the base notification system
+                    showNotification('请输入验证令牌', 'error');
+                }
+            });
+        }
+        // Apply renamed classes
+        document.querySelectorAll('button[type="submit"]').forEach(button => {
+             button.classList.add('auth-button');
+        });
+        const card = document.querySelector('.auth-glass-card'); // Find the renamed card
+        if (card) {
+            // If the base template also defines .glass-card, remove it first
+            // card.classList.remove('glass-card');
+        } else {
+             // If the card wasn't found by the new name, try the old name and rename
+             const oldCard = document.querySelector('.glass-card');
+             if (oldCard) {
+                 oldCard.classList.remove('glass-card');
+                 oldCard.classList.add('auth-glass-card');
+             }
+        }
+    });
+</script>
+{% endblock %}

app/templates/base.html

@@ -0,0 +1,265 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>{% block title %}Gemini Balance{% endblock %}</title>
+    <link rel="manifest" href="/static/manifest.json">
+    <meta name="theme-color" content="#4F46E5">
+    <meta name="apple-mobile-web-app-capable" content="yes">
+    <meta name="apple-mobile-web-app-status-bar-style" content="black">
+    <meta name="apple-mobile-web-app-title" content="GBalance">
+    <link rel="icon" href="/static/icons/icon-192x192.png">
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script>
+        tailwind.config = {
+            theme: {
+                extend: {
+                    colors: {
+                        primary: {
+                            50: '#eef2ff',
+                            100: '#e0e7ff',
+                            200: '#c7d2fe',
+                            300: '#a5b4fc',
+                            400: '#818cf8',
+                            500: '#6366f1',
+                            600: '#4f46e5',
+                            700: '#4338ca',
+                            800: '#3730a3',
+                            900: '#312e81',
+                        },
+                        success: {
+                            50: '#ecfdf5',
+                            500: '#10b981',
+                            600: '#059669'
+                        },
+                        danger: {
+                            50: '#fef2f2',
+                            500: '#ef4444',
+                            600: '#dc2626'
+                        }
+                    },
+                    fontFamily: {
+                        sans: ['Inter', 'sans-serif'],
+                        mono: ['JetBrains Mono', 'SFMono-Regular', 'Menlo', 'Monaco', 'Consolas', 'monospace'],
+                    },
+                    animation: {
+                        'fade-in': 'fadeIn 0.5s ease-out',
+                        'slide-up': 'slideUp 0.5s ease-out',
+                        'slide-down': 'slideDown 0.5s ease-out',
+                        'shake': 'shake 0.5s ease-in-out',
+                        'spin': 'spin 1s linear infinite',
+                    },
+                    keyframes: {
+                        fadeIn: {
+                            '0%': { opacity: '0' },
+                            '100%': { opacity: '1' },
+                        },
+                        slideUp: {
+                            '0%': { transform: 'translateY(20px)', opacity: '0' },
+                            '100%': { transform: 'translateY(0)', opacity: '1' },
+                        },
+                        slideDown: {
+                            '0%': { transform: 'translateY(-20px)', opacity: '0' },
+                            '100%': { transform: 'translateY(0)', opacity: '1' },
+                        },
+                        shake: {
+                            '0%, 100%': { transform: 'translateX(0)' },
+                            '25%': { transform: 'translateX(-5px)' },
+                            '75%': { transform: 'translateX(5px)' },
+                        },
+                         spin: {
+                            '0%': { transform: 'rotate(0deg)' },
+                            '100%': { transform: 'rotate(360deg)' },
+                        },
+                    },
+                }
+            }
+        }
+    </script>
+    <style>
+        .glass-card {
+            background: rgba(255, 255, 255, 0.85); /* Slightly increased opacity for better readability */
+            backdrop-filter: blur(16px);
+            -webkit-backdrop-filter: blur(16px);
+            border: 1px solid rgba(255, 255, 255, 0.18); /* Subtle border */
+        }
+        .bg-gradient {
+            background: linear-gradient(135deg, #4F46E5 0%, #7C3AED 50%, #EC4899 100%);
+        }
+        /* Scrollbar styling */
+        ::-webkit-scrollbar {
+            width: 8px;
+            height: 8px;
+        }
+        ::-webkit-scrollbar-track {
+            background: rgba(243, 244, 246, 0.8); /* bg-gray-100 with opacity */
+            border-radius: 10px;
+        }
+        ::-webkit-scrollbar-thumb {
+            background: rgba(79, 70, 229, 0.4); /* primary-600 with opacity */
+            border-radius: 10px;
+        }
+        ::-webkit-scrollbar-thumb:hover {
+            background: rgba(79, 70, 229, 0.6); /* primary-600 with more opacity */
+        }
+        /* Basic modal styles */
+        .modal {
+            display: none;
+            position: fixed;
+            z-index: 50;
+            left: 0;
+            top: 0;
+            width: 100%;
+            height: 100%;
+            background-color: rgba(0,0,0,0.5);
+            backdrop-filter: blur(4px);
+        }
+        .modal.show {
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }
+        /* Loading spinner */
+        .loading-spin {
+            animation: spin 1s linear infinite;
+        }
+        @keyframes spin {
+            from { transform: rotate(0deg); }
+            to { transform: rotate(360deg); }
+        }
+        /* Notification */
+        .notification {
+            position: fixed;
+            bottom: 5rem; /* Adjusted from bottom-20 */
+            left: 50%;
+            transform: translateX(-50%);
+            padding: 0.75rem 1.25rem; /* px-5 py-3 */
+            border-radius: 0.5rem; /* rounded-lg */
+            background-color: rgba(0, 0, 0, 0.8);
+            color: white;
+            font-weight: 500; /* font-medium */
+            z-index: 50;
+            opacity: 0;
+            transition: opacity 0.3s ease-in-out, transform 0.3s ease-in-out;
+        }
+        .notification.show {
+            opacity: 1;
+            transform: translate(-50%, 0);
+        }
+        .notification.error {
+             background-color: rgba(220, 38, 38, 0.8); /* danger-600 with opacity */
+        }
+        /* Scroll buttons */
+        .scroll-buttons {
+            position: fixed;
+            right: 1.25rem; /* right-5 */
+            bottom: 5rem; /* bottom-20 */
+            display: flex;
+            flex-direction: column;
+            gap: 0.5rem; /* gap-2 */
+            z-index: 10;
+        }
+        .scroll-button {
+            width: 2.5rem; /* w-10 */
+            height: 2.5rem; /* h-10 */
+            background-color: #4f46e5; /* bg-primary-600 */
+            color: white;
+            border-radius: 9999px; /* rounded-full */
+            box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1), 0 2px 4px -1px rgba(0, 0, 0, 0.06); /* shadow-md */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            transition: all 0.3s ease-in-out;
+        }
+        .scroll-button:hover {
+            background-color: #4338ca; /* hover:bg-primary-700 */
+            box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.1), 0 4px 6px -2px rgba(0, 0, 0, 0.05); /* hover:shadow-lg */
+        }
+        {% block head_extra_styles %}
+        {% endblock %}
+    </style>
+    {% block head_extra_scripts %}{% endblock %}
+</head>
+<body class="bg-gradient min-h-screen text-gray-800 pt-6 pb-16">
+
+    {% block content %}{% endblock %}
+
+    <!-- 底部版权 -->
+    <div class="fixed bottom-0 left-0 w-full py-3 bg-white bg-opacity-80 backdrop-blur-md text-center text-sm text-gray-600 border-t border-gray-200">
+        © <span id="copyright-year"></span> by
+        <a href="https://linux.do/u/snaily" target="_blank" class="text-primary-600 hover:text-primary-800 transition duration-300">
+            <img src="https://linux.do/user_avatar/linux.do/snaily/288/306510_2.gif" alt="snaily" class="inline-block w-5 h-5 rounded-full align-middle mr-1">snaily
+        </a> |
+        <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>
+    </div>
+
+    <!-- 通用JS -->
+    <script>
+        // 设置版权年份
+        document.getElementById('copyright-year').textContent = new Date().getFullYear();
+
+        // 滚动到顶部/底部函数 (如果页面需要)
+        function scrollToTop() {
+            window.scrollTo({ top: 0, behavior: 'smooth' });
+        }
+        function scrollToBottom() {
+            window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
+        }
+
+        // 显示通知
+        function showNotification(message, type = 'success', duration = 3000) {
+            const notification = document.getElementById('notification') || createNotificationElement();
+            if (!notification) return;
+
+            notification.textContent = message;
+            notification.className = 'notification show'; // Reset classes
+            if (type === 'error') {
+                notification.classList.add('error');
+            }
+
+            // Clear previous timeout if exists
+            if (notification.timeoutId) {
+                clearTimeout(notification.timeoutId);
+            }
+
+            notification.timeoutId = setTimeout(() => {
+                notification.classList.remove('show');
+                // Optional: remove the element after fade out if dynamically created
+                // setTimeout(() => notification.remove(), 300);
+            }, duration);
+        }
+
+        // Helper to create notification element if it doesn't exist
+        function createNotificationElement() {
+            let notification = document.getElementById('notification');
+            if (!notification) {
+                notification = document.createElement('div');
+                notification.id = 'notification';
+                notification.className = 'notification';
+                document.body.appendChild(notification);
+            }
+            return notification;
+        }
+
+        // 页面刷新带加载状态
+        function refreshPage(button) {
+            if (button) {
+                const icon = button.querySelector('i');
+                if (icon) {
+                    icon.classList.add('loading-spin');
+                }
+            }
+            setTimeout(() => {
+                window.location.reload();
+            }, 300); // Short delay to show spinner
+        }
+
+    </script>
+    {% block body_scripts %}{% endblock %}
+</body>
+</html>

app/templates/config_editor.html

@@ -0,0 +1,451 @@
+{% extends "base.html" %}
+
+{% block title %}配置编辑器 - Gemini Balance{% endblock %}
+
+{% block head_extra_styles %}
+<style>
+    /* config_editor.html specific styles */
+    /* Animations (already in base.html, but keep fade-in class usage) */
+    .fade-in {
+        animation: fadeIn 0.3s ease forwards;
+    }
+    /* Modal specific styles (already in base.html) */
+    .array-container {
+        max-height: 300px;
+        overflow-y: auto;
+        padding-right: 5px; /* Keep specific padding if needed */
+    }
+    #API_KEYS_container { /* Keep specific ID styling if needed */
+        max-height: 300px;
+        overflow-y: auto;
+    }
+    .config-section {
+        display: none;
+    }
+    .config-section.active {
+        display: block;
+        animation: fadeIn 0.3s ease forwards; /* Use base animation */
+    }
+    .provider-config {
+        display: none;
+    }
+    .provider-config.active {
+        display: block;
+    }
+    /* Tailwind Toggle Switch Helper CSS */
+    .toggle-checkbox:checked {
+      @apply: right-0 border-primary-600;
+      right: 0;
+      border-color: #4F46E5;
+    }
+    .toggle-checkbox:checked + .toggle-label {
+      @apply: bg-primary-600;
+      background-color: #4F46E5;
+    }
+</style>
+{% endblock %}
+
+{% block content %}
+    <div class="container max-w-4xl mx-auto px-4">
+        <div class="glass-card rounded-2xl shadow-xl p-6 md:p-8">
+            <button class="absolute top-6 right-6 bg-white bg-opacity-20 hover:bg-opacity-30 rounded-full w-8 h-8 flex items-center justify-center text-primary-600 transition-all duration-300" onclick="refreshPage(this)">
+                <i class="fas fa-sync-alt"></i>
+            </button>
+            
+            <h1 class="text-3xl font-extrabold text-center text-transparent bg-clip-text bg-gradient-to-r from-primary-600 to-primary-700 mb-4">
+                 <img src="/static/icons/logo.png" alt="Gemini Balance Logo" class="h-9 inline-block align-middle mr-2">
+                 Gemini Balance - 配置编辑
+            </h1>
+            
+            <!-- Navigation Tabs -->
+            <div class="flex justify-center mb-8 overflow-x-auto pb-2 gap-2">
+                <a href="/config" class="whitespace-nowrap flex items-center justify-center gap-2 px-6 py-3 font-medium rounded-lg bg-primary-600 text-white shadow-md">
+                    <i class="fas fa-cog"></i> 配置编辑
+                </a>
+                <a href="/keys" class="whitespace-nowrap flex items-center justify-center gap-2 px-6 py-3 font-medium rounded-lg bg-white bg-opacity-50 hover:bg-opacity-70 text-gray-700 transition-all duration-200">
+                    <i class="fas fa-tachometer-alt"></i> 监控面板
+                </a>
+                <a href="/logs" class="whitespace-nowrap flex items-center justify-center gap-2 px-6 py-3 font-medium rounded-lg bg-white bg-opacity-50 hover:bg-opacity-70 text-gray-700 transition-all duration-200">
+                    <i class="fas fa-exclamation-triangle"></i> 错误日志
+                </a>
+            </div>
+            
+            <!-- Config Tabs -->
+            <div class="flex justify-center mb-6 flex-wrap gap-2">
+                <button class="tab-btn bg-primary-600 text-white px-5 py-2 rounded-full shadow-md font-medium text-sm" data-tab="api">
+                    API配置
+                </button>
+                <button class="tab-btn bg-white bg-opacity-50 text-gray-700 px-5 py-2 rounded-full font-medium text-sm hover:bg-opacity-70 transition-all duration-200" data-tab="model">
+                    模型配置
+                </button>
+                <button class="tab-btn bg-white bg-opacity-50 text-gray-700 px-5 py-2 rounded-full font-medium text-sm hover:bg-opacity-70 transition-all duration-200" data-tab="image">
+                    图像生成
+                </button>
+                <button class="tab-btn bg-white bg-opacity-50 text-gray-700 px-5 py-2 rounded-full font-medium text-sm hover:bg-opacity-70 transition-all duration-200" data-tab="stream">
+                    流式输出
+                </button>
+                <button class="tab-btn bg-white bg-opacity-50 text-gray-700 px-5 py-2 rounded-full font-medium text-sm hover:bg-opacity-70 transition-all duration-200" data-tab="scheduler">
+                    定时任务
+                </button>
+            </div>
+            
+            <!-- Save Status Banner (Removed - using notification component now) -->
+            
+            <!-- Configuration Form -->
+            <form id="configForm" class="mt-6">
+                <!-- API 相关配置 -->
+                <div class="config-section active bg-white bg-opacity-70 rounded-xl p-6 mb-6 shadow-lg" id="api-section">
+                    <h2 class="text-xl font-bold mb-6 pb-3 border-b border-gray-200 flex items-center gap-2">
+                        <i class="fas fa-key text-primary-600"></i> API相关配置
+                    </h2>
+                    
+                    <!-- API密钥列表 -->
+                    <div class="mb-6">
+                        <label for="API_KEYS" class="block font-semibold mb-2 text-gray-700">API密钥列表</label>
+                        <div class="mb-2">
+                            <input type="search" id="apiKeySearchInput" placeholder="搜索密钥..." class="w-full px-4 py-2 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        </div>
+                        <div class="array-container bg-white rounded-lg border border-gray-200 p-4 mb-2" id="API_KEYS_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" id="addApiKeyBtn">
+                                <i class="fas fa-plus"></i> 添加密钥
+                            </button>
+                        </div>
+                        <small class="text-gray-500 mt-1 block">Gemini API密钥列表，每行一个</small>
+                    </div>
+                    
+                    <!-- 允许的令牌列表 -->
+                    <div class="mb-6">
+                        <label for="ALLOWED_TOKENS" class="block font-semibold mb-2 text-gray-700">允许的令牌列表</label>
+                        <div class="array-container bg-white rounded-lg border border-gray-200 p-4 mb-2" id="ALLOWED_TOKENS_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('ALLOWED_TOKENS')">
+                                <i class="fas fa-plus"></i> 添加令牌
+                            </button>
+                        </div>
+                        <small class="text-gray-500 mt-1 block">允许访问API的令牌列表</small>
+                    </div>
+                    
+                    <!-- 认证令牌 -->
+                    <div class="mb-6">
+                        <label for="AUTH_TOKEN" class="block font-semibold mb-2 text-gray-700">认证令牌</label>
+                        <input type="text" id="AUTH_TOKEN" name="AUTH_TOKEN" placeholder="默认使用ALLOWED_TOKENS中的第一个" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">用于API认证的令牌</small>
+                    </div>
+                    
+                    <!-- API基础URL -->
+                    <div class="mb-6">
+                        <label for="BASE_URL" class="block font-semibold mb-2 text-gray-700">API基础URL</label>
+                        <input type="text" id="BASE_URL" name="BASE_URL" placeholder="https://generativelanguage.googleapis.com/v1beta" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">Gemini API的基础URL</small>
+                    </div>
+                    
+                    <!-- 最大失败次数 -->
+                    <div class="mb-6">
+                        <label for="MAX_FAILURES" class="block font-semibold mb-2 text-gray-700">最大失败次数</label>
+                        <input type="number" id="MAX_FAILURES" name="MAX_FAILURES" min="1" max="100" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">API密钥失败后标记为无效的次数</small>
+                    </div>
+                    
+                    <!-- 请求超时时间 -->
+                    <div class="mb-6">
+                        <label for="TIME_OUT" class="block font-semibold mb-2 text-gray-700">请求超时时间（秒）</label>
+                        <input type="number" id="TIME_OUT" name="TIME_OUT" min="1" max="600" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">API请求的超时时间</small>
+                    </div>
+                    
+                    <!-- 最大重试次数 -->
+                    <div class="mb-6">
+                        <label for="MAX_RETRIES" class="block font-semibold mb-2 text-gray-700">最大重试次数</label>
+                        <input type="number" id="MAX_RETRIES" name="MAX_RETRIES" min="0" max="10" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">API请求失败后的最大重试次数</small>
+                    </div>
+                </div>
+                
+                <!-- 模型相关配置 -->
+                <div class="config-section bg-white bg-opacity-70 rounded-xl p-6 mb-6 shadow-lg" id="model-section">
+                    <h2 class="text-xl font-bold mb-6 pb-3 border-b border-gray-200 flex items-center gap-2">
+                        <i class="fas fa-robot text-primary-600"></i> 模型相关配置
+                    </h2>
+                    
+                    <!-- 测试模型 -->
+                    <div class="mb-6">
+                        <label for="TEST_MODEL" class="block font-semibold mb-2 text-gray-700">测试模型</label>
+                        <input type="text" id="TEST_MODEL" name="TEST_MODEL" placeholder="gemini-1.5-flash" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">用于测试API密钥的模型</small>
+                    </div>
+                    
+                    <!-- 图像模型列表 -->
+                    <div class="mb-6">
+                        <label for="IMAGE_MODELS" class="block font-semibold mb-2 text-gray-700">图像模型列表</label>
+                        <div class="array-container bg-white rounded-lg border border-gray-200 p-4 mb-2" id="IMAGE_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('IMAGE_MODELS')">
+                                <i class="fas fa-plus"></i> 添加模型
+                            </button>
+                        </div>
+                        <small class="text-gray-500 mt-1 block">支持图像处理的模型列表</small>
+                    </div>
+                    
+                    <!-- 搜索模型列表 -->
+                    <div class="mb-6">
+                        <label for="SEARCH_MODELS" class="block font-semibold mb-2 text-gray-700">搜索模型列表</label>
+                        <div class="array-container bg-white rounded-lg border border-gray-200 p-4 mb-2" id="SEARCH_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('SEARCH_MODELS')">
+                                <i class="fas fa-plus"></i> 添加模型
+                            </button>
+                        </div>
+                        <small class="text-gray-500 mt-1 block">支持搜索功能的模型列表</small>
+                    </div>
+                    
+                    <!-- 过滤模型列表 -->
+                    <div class="mb-6">
+                        <label for="FILTERED_MODELS" class="block font-semibold mb-2 text-gray-700">过滤模型列表</label>
+                        <div class="array-container bg-white rounded-lg border border-gray-200 p-4 mb-2" id="FILTERED_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('FILTERED_MODELS')">
+                                <i class="fas fa-plus"></i> 添加模型
+                            </button>
+                        </div>
+                        <small class="text-gray-500 mt-1 block">需要过滤的模型列表</small>
+                    </div>
+                    
+                    <!-- 启用代码执行工具 -->
+                    <div class="mb-6 flex items-center justify-between">
+                        <label for="TOOLS_CODE_EXECUTION_ENABLED" class="font-semibold text-gray-700">启用代码执行工具</label>
+                        <div class="relative inline-block w-10 mr-2 align-middle select-none transition duration-200 ease-in">
+                            <input type="checkbox" name="TOOLS_CODE_EXECUTION_ENABLED" id="TOOLS_CODE_EXECUTION_ENABLED" class="toggle-checkbox absolute block w-6 h-6 rounded-full bg-white border-4 appearance-none cursor-pointer"/>
+                            <label for="TOOLS_CODE_EXECUTION_ENABLED" class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"></label>
+                        </div>
+                    </div>
+                    
+                    <!-- 显示搜索链接 -->
+                    <div class="mb-6 flex items-center justify-between">
+                        <label for="SHOW_SEARCH_LINK" class="font-semibold text-gray-700">显示搜索链接</label>
+                        <div class="relative inline-block w-10 mr-2 align-middle select-none transition duration-200 ease-in">
+                            <input type="checkbox" name="SHOW_SEARCH_LINK" id="SHOW_SEARCH_LINK" class="toggle-checkbox absolute block w-6 h-6 rounded-full bg-white border-4 appearance-none cursor-pointer"/>
+                            <label for="SHOW_SEARCH_LINK" class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"></label>
+                        </div>
+                    </div>
+                    
+                    <!-- 显示思考过程 -->
+                    <div class="mb-6 flex items-center justify-between">
+                        <label for="SHOW_THINKING_PROCESS" class="font-semibold text-gray-700">显示思考过程</label>
+                        <div class="relative inline-block w-10 mr-2 align-middle select-none transition duration-200 ease-in">
+                            <input type="checkbox" name="SHOW_THINKING_PROCESS" id="SHOW_THINKING_PROCESS" class="toggle-checkbox absolute block w-6 h-6 rounded-full bg-white border-4 appearance-none cursor-pointer"/>
+                            <label for="SHOW_THINKING_PROCESS" class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"></label>
+                        </div>
+                    </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">
+                        <i class="fas fa-image text-primary-600"></i> 图像生成配置
+                    </h2>
+                    
+                    <!-- 付费API密钥 -->
+                    <div class="mb-6">
+                        <label for="PAID_KEY" class="block font-semibold mb-2 text-gray-700">付费API密钥</label>
+                        <input type="text" id="PAID_KEY" name="PAID_KEY" placeholder="AIzaSyxxxxxxxxxxxxxxxxxxx" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">用于图像生成的付费API密钥</small>
+                    </div>
+                    
+                    <!-- 图像生成模型 -->
+                    <div class="mb-6">
+                        <label for="CREATE_IMAGE_MODEL" class="block font-semibold mb-2 text-gray-700">图像生成模型</label>
+                        <input type="text" id="CREATE_IMAGE_MODEL" name="CREATE_IMAGE_MODEL" placeholder="imagen-3.0-generate-002" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">用于图像生成的模型</small>
+                    </div>
+                    
+                    <!-- 上传提供商 -->
+                    <div class="mb-6">
+                        <label for="UPLOAD_PROVIDER" class="block font-semibold mb-2 text-gray-700">上传提供商</label>
+                        <select id="UPLOAD_PROVIDER" name="UPLOAD_PROVIDER" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 bg-white">
+                            <option value="smms" selected>SM.MS</option>
+                            <option value="picgo">PicGo</option>
+                            <option value="cloudflare">Cloudflare</option>
+                        </select>
+                        <small class="text-gray-500 mt-1 block">图片上传服务提供商</small>
+                    </div>
+                    
+                    <!-- SM.MS密钥 -->
+                    <div class="mb-6 provider-config active" data-provider="smms">
+                        <label for="SMMS_SECRET_TOKEN" class="block font-semibold mb-2 text-gray-700">SM.MS密钥</label>
+                        <input type="text" id="SMMS_SECRET_TOKEN" name="SMMS_SECRET_TOKEN" placeholder="XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">SM.MS图床的密钥</small>
+                    </div>
+                    
+                    <!-- PicGo API密钥 -->
+                    <div class="mb-6 provider-config" data-provider="picgo">
+                        <label for="PICGO_API_KEY" class="block font-semibold mb-2 text-gray-700">PicGo API密钥</label>
+                        <input type="text" id="PICGO_API_KEY" name="PICGO_API_KEY" placeholder="xxxx" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">PicGo的API密钥</small>
+                    </div>
+                    
+                    <!-- Cloudflare图床URL -->
+                    <div class="mb-6 provider-config" data-provider="cloudflare">
+                        <label for="CLOUDFLARE_IMGBED_URL" class="block font-semibold mb-2 text-gray-700">Cloudflare图床URL</label>
+                        <input type="text" id="CLOUDFLARE_IMGBED_URL" name="CLOUDFLARE_IMGBED_URL" placeholder="https://xxxxxxx.pages.dev/upload" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">Cloudflare图床的URL</small>
+                    </div>
+                    
+                    <!-- Cloudflare认证码 -->
+                    <div class="mb-6 provider-config" data-provider="cloudflare">
+                        <label for="CLOUDFLARE_IMGBED_AUTH_CODE" class="block font-semibold mb-2 text-gray-700">Cloudflare认证码</label>
+                        <input type="text" id="CLOUDFLARE_IMGBED_AUTH_CODE" name="CLOUDFLARE_IMGBED_AUTH_CODE" placeholder="xxxxxxxxx" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">Cloudflare图床的认证码</small>
+                    </div>
+                </div>
+                
+                <!-- 流式输出优化器配置 -->
+                <div class="config-section bg-white bg-opacity-70 rounded-xl p-6 mb-6 shadow-lg" id="stream-section">
+                    <h2 class="text-xl font-bold mb-6 pb-3 border-b border-gray-200 flex items-center gap-2">
+                        <i class="fas fa-stream text-primary-600"></i> 流式输出优化器
+                    </h2>
+                    
+                    <!-- 启用流式输出优化 -->
+                    <div class="mb-6 flex items-center justify-between">
+                        <label for="STREAM_OPTIMIZER_ENABLED" class="font-semibold text-gray-700">启用流式输出优化</label>
+                        <div class="relative inline-block w-10 mr-2 align-middle select-none transition duration-200 ease-in">
+                            <input type="checkbox" name="STREAM_OPTIMIZER_ENABLED" id="STREAM_OPTIMIZER_ENABLED" class="toggle-checkbox absolute block w-6 h-6 rounded-full bg-white border-4 appearance-none cursor-pointer"/>
+                            <label for="STREAM_OPTIMIZER_ENABLED" class="toggle-label block overflow-hidden h-6 rounded-full bg-gray-300 cursor-pointer"></label>
+                        </div>
+                    </div>
+                    
+                    <!-- 最小延迟 -->
+                    <div class="mb-6">
+                        <label for="STREAM_MIN_DELAY" class="block font-semibold mb-2 text-gray-700">最小延迟（秒）</label>
+                        <input type="number" id="STREAM_MIN_DELAY" name="STREAM_MIN_DELAY" min="0" max="1" step="0.001" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">流式输出的最小延迟时间</small>
+                    </div>
+                    
+                    <!-- 最大延迟 -->
+                    <div class="mb-6">
+                        <label for="STREAM_MAX_DELAY" class="block font-semibold mb-2 text-gray-700">最大延迟（秒）</label>
+                        <input type="number" id="STREAM_MAX_DELAY" name="STREAM_MAX_DELAY" min="0" max="1" step="0.001" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">流式输出的最大延迟时间</small>
+                    </div>
+                    
+                    <!-- 短文本阈值 -->
+                    <div class="mb-6">
+                        <label for="STREAM_SHORT_TEXT_THRESHOLD" class="block font-semibold mb-2 text-gray-700">短文本阈值</label>
+                        <input type="number" id="STREAM_SHORT_TEXT_THRESHOLD" name="STREAM_SHORT_TEXT_THRESHOLD" min="1" max="100" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">短文本的字符阈值</small>
+                    </div>
+                    
+                    <!-- 长文本阈值 -->
+                    <div class="mb-6">
+                        <label for="STREAM_LONG_TEXT_THRESHOLD" class="block font-semibold mb-2 text-gray-700">长文本阈值</label>
+                        <input type="number" id="STREAM_LONG_TEXT_THRESHOLD" name="STREAM_LONG_TEXT_THRESHOLD" min="1" max="1000" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">长文本的字符阈值</small>
+                    </div>
+                    
+                    <!-- 分块大小 -->
+                    <div class="mb-6">
+                        <label for="STREAM_CHUNK_SIZE" class="block font-semibold mb-2 text-gray-700">分块大小</label>
+                        <input type="number" id="STREAM_CHUNK_SIZE" name="STREAM_CHUNK_SIZE" min="1" max="100" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">流式输出的分块大小</small>
+                    </div>
+                </div>
+
+                <!-- 定时任务配置 -->
+                <div class="config-section bg-white bg-opacity-70 rounded-xl p-6 mb-6 shadow-lg" id="scheduler-section">
+                    <h2 class="text-xl font-bold mb-6 pb-3 border-b border-gray-200 flex items-center gap-2">
+                        <i class="fas fa-clock text-primary-600"></i> 定时任务配置
+                    </h2>
+
+                    <!-- 检查间隔 -->
+                    <div class="mb-6">
+                        <label for="CHECK_INTERVAL_HOURS" class="block font-semibold mb-2 text-gray-700">检查间隔（小时）</label>
+                        <input type="number" id="CHECK_INTERVAL_HOURS" name="CHECK_INTERVAL_HOURS" min="1" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">定时检查密钥状态的间隔时间（单位：小时）</small>
+                    </div>
+
+                    <!-- 时区 -->
+                    <div class="mb-6">
+                        <label for="TIMEZONE" class="block font-semibold mb-2 text-gray-700">时区</label>
+                        <input type="text" id="TIMEZONE" name="TIMEZONE" placeholder="例如: Asia/Shanghai" class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50">
+                        <small class="text-gray-500 mt-1 block">定时任务使用的时区，格式如 "Asia/Shanghai" 或 "UTC"</small>
+                    </div>
+                </div>
+                
+                <!-- Action Buttons -->
+                <div class="flex flex-col md:flex-row justify-center gap-4 mt-8">
+                    <button type="button" id="saveBtn" class="bg-gradient-to-r from-primary-600 to-primary-700 text-white px-8 py-3 rounded-xl font-semibold transition-all duration-300 transform hover:-translate-y-1 hover:shadow-lg flex items-center justify-center gap-2">
+                        <i class="fas fa-save"></i> 保存配置
+                    </button>
+                    <button type="button" id="resetBtn" class="bg-gradient-to-r from-gray-400 to-gray-500 text-white px-8 py-3 rounded-xl font-semibold transition-all duration-300 transform hover:-translate-y-1 hover:shadow-lg flex items-center justify-center gap-2">
+                        <i class="fas fa-undo"></i> 重置配置
+                    </button>
+                </div>
+            </form>
+        </div>
+    </div>
+    
+    <!-- Scroll buttons are now in base.html -->
+    <div class="scroll-buttons">
+         <button class="scroll-button" onclick="scrollToTop()" title="回到顶部">
+             <i class="fas fa-chevron-up"></i>
+         </button>
+         <button class="scroll-button" onclick="scrollToBottom()" title="滚动到底部">
+             <i class="fas fa-chevron-down"></i>
+         </button>
+     </div>
+    
+    <!-- Notification component is now in base.html -->
+    <div id="notification" class="notification"></div>
+    <!-- Footer is now in base.html -->
+    
+    <!-- API Key Add Modal -->
+    <div id="apiKeyModal" class="modal">
+        <div class="w-full max-w-lg mx-auto bg-white rounded-2xl shadow-2xl overflow-hidden animate-fade-in">
+            <div class="p-6">
+                <div class="flex justify-between items-center mb-4">
+                    <h2 class="text-xl font-bold text-gray-800">批量添加 API 密钥</h2>
+                    <button id="closeApiKeyModalBtn" class="text-gray-400 hover:text-gray-600 text-xl">&times;</button>
+                </div>
+                <p class="text-gray-600 mb-4">每行粘贴一个或多个密钥，将自动提取有效密钥并去重。</p>
+                <textarea id="apiKeyBulkInput" rows="10" placeholder="在此处粘贴 API 密钥..." class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 font-mono text-sm"></textarea>
+                <div class="flex justify-end gap-3 mt-6">
+                    <button type="button" id="confirmAddApiKeyBtn" class="bg-primary-600 hover:bg-primary-700 text-white px-6 py-2 rounded-lg font-medium transition">确认添加</button>
+                    <button type="button" id="cancelAddApiKeyBtn" class="bg-gray-200 hover:bg-gray-300 text-gray-700 px-6 py-2 rounded-lg font-medium transition">取消</button>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Reset Confirmation Modal -->
+    <div id="resetConfirmModal" class="modal">
+        <div class="w-full max-w-md mx-auto bg-white rounded-2xl shadow-2xl overflow-hidden animate-fade-in">
+            <div class="p-6">
+                <div class="flex justify-between items-center mb-4">
+                    <h2 class="text-xl font-bold text-gray-800">确认重置配置</h2>
+                    <button id="closeResetModalBtn" class="text-gray-400 hover:text-gray-600 text-xl">&times;</button>
+                </div>
+                <p class="text-gray-600 mb-6">确定要重置所有配置吗？<br>这将恢复到默认值，此操作不可撤销。</p>
+                <div class="flex justify-end gap-3">
+                    <button type="button" id="confirmResetBtn" class="bg-red-500 hover:bg-red-600 text-white px-6 py-2 rounded-lg font-medium transition">确认重置</button>
+                    <button type="button" id="cancelResetBtn" class="bg-primary-600 hover:bg-primary-700 text-white px-6 py-2 rounded-lg font-medium transition">取消</button>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+{% endblock %}
+
+{% block body_scripts %}
+    <script src="/static/js/config_editor.js"></script>
+    <!-- Add any other page-specific JS initialization here if needed -->
+{% endblock %}

app/templates/error_logs.html

@@ -0,0 +1,242 @@
+{% extends "base.html" %}
+
+{% block title %}错误日志管理 - Gemini Balance{% endblock %}
+
+{% block head_extra_styles %}
+<style>
+    /* error_logs.html specific styles */
+    /* Table styles */
+    .styled-table th {
+        position: sticky;
+        top: 0;
+        background: #f3f4f6; /* bg-gray-100 */
+        z-index: 10;
+    }
+    .styled-table tbody tr:hover {
+        background-color: #f9fafb; /* bg-gray-50 */
+    }
+    .styled-table td {
+         padding: 12px 20px;
+         vertical-align: middle;
+         white-space: nowrap;
+         overflow: hidden;
+         text-overflow: ellipsis;
+         max-width: 250px;
+    }
+    /* Ensure error log column does not wrap and remove max-width */
+    .styled-table td:nth-child(4) { /* Assuming error log is the 4th column */
+        /* max-width: none; */
+        white-space: nowrap;
+    }
+    .btn-view-details {
+        background-color: #eef2ff; /* primary-50 */
+        color: #4f46e5; /* primary-600 */
+        padding: 6px 12px;
+        border-radius: 6px;
+        font-weight: 500;
+        transition: all 0.2s ease-in-out;
+        border: 1px solid #c7d2fe; /* primary-200 */
+    }
+    .btn-view-details:hover {
+        background-color: #c7d2fe; /* primary-200 */
+        color: #4338ca; /* primary-700 */
+        box-shadow: 0 2px 4px rgba(0,0,0,0.05);
+    }
+    @media (max-width: 768px) {
+        .search-container {
+            grid-template-columns: 1fr;
+        }
+    }
+    /* Modal styles are in base.html */
+</style>
+{% endblock %}
+
+{% block content %}
+    <div class="container mx-auto px-4"> <!-- Removed max-width-7xl for wider content -->
+        <div class="glass-card rounded-2xl shadow-xl p-6 md:p-8">
+            <!-- Removed refresh button from top right -->
+            
+            <h1 class="text-3xl font-extrabold text-center text-transparent bg-clip-text bg-gradient-to-r from-primary-600 to-primary-700 mb-4">
+                 <img src="/static/icons/logo.png" alt="Gemini Balance Logo" class="h-9 inline-block align-middle mr-2">
+                 Gemini Balance - 错误日志
+            </h1>
+            
+            <!-- Navigation Tabs -->
+            <div class="flex justify-center mb-8 overflow-x-auto pb-2 gap-2">
+                <a href="/config" class="whitespace-nowrap flex items-center justify-center gap-2 px-6 py-3 font-medium rounded-lg bg-white bg-opacity-50 hover:bg-opacity-70 text-gray-700 transition-all duration-200">
+                    <i class="fas fa-cog"></i> 配置编辑
+                </a>
+                <a href="/keys" class="whitespace-nowrap flex items-center justify-center gap-2 px-6 py-3 font-medium rounded-lg bg-white bg-opacity-50 hover:bg-opacity-70 text-gray-700 transition-all duration-200">
+                    <i class="fas fa-tachometer-alt"></i> 监控面板
+                </a>
+                <a href="/logs" class="whitespace-nowrap flex items-center justify-center gap-2 px-6 py-3 font-medium rounded-lg bg-primary-600 text-white shadow-md">
+                    <i class="fas fa-exclamation-triangle"></i> 错误日志
+                </a>
+            </div>
+            
+            <!-- 主内容区域 -->
+            <div class="bg-white bg-opacity-70 rounded-xl p-6 shadow-lg animate-fade-in">
+                <h2 class="text-xl font-bold mb-6 pb-3 border-b border-gray-200 flex items-center gap-2">
+                    <i class="fas fa-bug text-primary-600"></i> 错误日志列表
+                </h2>
+                
+                <!-- 控制区域 (Refresh button removed, page size moved below) -->
+                <!-- Removed the original controls div -->
+                
+                <!-- 搜索控件 -->
+                <div class="grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-5 gap-3 mb-6">
+                    <input type="text" id="keySearch" placeholder="搜索密钥 (部分)" class="px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 col-span-1 lg:col-span-1">
+                    <input type="text" id="errorSearch" placeholder="搜索错误类型/日志" class="px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 col-span-1 lg:col-span-1">
+                    <div class="flex items-center gap-2 col-span-1 lg:col-span-2">
+                        <input type="datetime-local" id="startDate" class="px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 flex-1 text-sm">
+                        <span class="text-gray-700">至</span>
+                        <input type="datetime-local" id="endDate" class="px-4 py-3 rounded-lg border border-gray-300 focus:border-primary-500 focus:ring focus:ring-primary-200 focus:ring-opacity-50 flex-1 text-sm">
+                    </div>
+                    <button id="searchBtn" class="flex items-center justify-center gap-2 bg-primary-600 hover:bg-primary-700 text-white px-4 py-3 rounded-lg font-medium transition-all duration-200 col-span-1">
+                        <i class="fas fa-search"></i> 搜索
+                    </button>
+                </div>
+                
+                <!-- 表格容器 - Enhanced Styling -->
+                <div class="overflow-x-auto rounded-lg border border-gray-200 mb-6 bg-white"> <!-- Removed shadow, added border -->
+                    <table class="styled-table w-full min-w-full text-sm"> <!-- Added text-sm -->
+                        <thead>
+                            <tr class="bg-primary-50 text-left text-primary-800"> <!-- Changed header background and text color -->
+                                <th class="px-5 py-3 font-semibold rounded-tl-lg">ID</th> <!-- Increased padding, adjusted rounding -->
+                                <th class="px-5 py-3 font-semibold">Gemini密钥</th>
+                                <th class="px-5 py-3 font-semibold">错误类型</th>
+                                <th class="px-5 py-3 font-semibold">错误日志</th>
+                                <th class="px-5 py-3 font-semibold">模型名称</th>
+                                <th class="px-5 py-3 font-semibold">请求时间</th>
+                                <th class="px-5 py-3 font-semibold rounded-tr-lg">操作</th> <!-- Adjusted rounding -->
+                            </tr>
+                        </thead>
+                        <tbody id="errorLogsTable" class="divide-y divide-gray-200">
+                            <!-- 错误日志数据将通过JavaScript动态加载 -->
+                        </tbody>
+                    </table>
+                </div>
+                
+                <!-- 状态指示器 -->
+                <div id="loadingIndicator" class="flex items-center justify-center p-8 hidden">
+                    <div class="animate-spin rounded-full h-12 w-12 border-b-2 border-primary-600"></div>
+                    <p class="ml-4 text-lg text-gray-700 font-medium">加载中，请稍候...</p>
+                </div>
+                
+                <div id="noDataMessage" class="text-center py-12 text-gray-500 hidden">
+                    <i class="fas fa-inbox text-5xl mb-3"></i>
+                    <p class="text-lg">暂无错误日志数据</p>
+                </div>
+                
+                <div id="errorMessage" class="bg-danger-50 text-danger-600 p-4 rounded-lg font-medium text-center hidden">
+                    <i class="fas fa-exclamation-circle mr-2"></i>
+                    加载错误日志失败，请稍后重试。
+                </div>
+                
+                <!-- 分页与每页显示控件 -->
+                <div class="flex flex-col sm:flex-row justify-between items-center mt-6 gap-4">
+                     <!-- 每页显示控件 (Moved here) -->
+                     <div class="flex items-center gap-2 text-sm text-gray-700">
+                        <label for="pageSize" class="font-medium">每页显示:</label>
+                        <select id="pageSize" class="rounded-md border border-gray-300 focus:ring focus:ring-primary-200 focus:border-primary-500 px-2 py-1 bg-white text-sm">
+                            <option value="10">10</option>
+                            <option value="20" selected>20</option>
+                            <option value="50">50</option>
+                            <option value="100">100</option>
+                        </select>
+                        <span>条</span>
+                    </div>
+                    <!-- 分页控件 -->
+                    <div class="flex items-center gap-4"> <!-- Wrapper for pagination and input -->
+                        <ul class="pagination flex items-center gap-1" id="pagination">
+                            <!-- 分页控件将通过JavaScript动态加载 -->
+                        </ul>
+                        <!-- 页码输入跳转 -->
+                        <div class="flex items-center gap-1">
+                            <input type="number" id="pageInput" min="1" class="w-16 px-2 py-1 rounded-md border border-gray-300 text-sm focus:ring focus:ring-primary-200 focus:border-primary-500" placeholder="页码">
+                            <button id="goToPageBtn" class="px-3 py-1 bg-primary-600 hover:bg-primary-700 text-white text-sm rounded-md transition">跳转</button>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Scroll buttons are now in base.html -->
+    <div class="scroll-buttons">
+         <button class="scroll-button" onclick="scrollToTop()" title="回到顶部">
+             <i class="fas fa-chevron-up"></i>
+         </button>
+         <button class="scroll-button" onclick="scrollToBottom()" title="滚动到底部">
+             <i class="fas fa-chevron-down"></i>
+         </button>
+     </div>
+    
+    <!-- Notification component is now in base.html (use id="notification") -->
+    <div id="notification" class="notification"></div>
+    <!-- Footer is now in base.html -->
+    
+    <!-- 日志详情模态框 -->
+    <div id="logDetailModal" class="modal">
+        <div class="w-full max-w-6xl mx-auto bg-white rounded-2xl shadow-2xl overflow-hidden animate-fade-in"> <!-- Increased max-width to 6xl -->
+            <div class="p-6">
+                <div class="flex justify-between items-center border-b border-gray-200 pb-4 mb-4">
+                    <h2 class="text-xl font-bold text-gray-800">错误日志详情</h2>
+                    <button id="closeLogDetailModalBtn" class="text-gray-400 hover:text-gray-600 text-xl">&times;</button>
+                </div>
+                
+                <div class="space-y-4 max-h-[60vh] overflow-y-auto p-1">
+                    <div class="bg-gray-50 p-4 rounded-lg">
+                        <h6 class="text-sm font-semibold text-gray-600 mb-1">Gemini密钥:</h6>
+                        <pre id="modalGeminiKey" class="font-mono text-sm bg-gray-100 p-3 rounded overflow-x-auto"></pre>
+                    </div>
+                    
+                    <div class="bg-gray-50 p-4 rounded-lg">
+                        <h6 class="text-sm font-semibold text-gray-600 mb-1">错误类型:</h6>
+                        <p id="modalErrorType" class="text-danger-600 font-medium"></p>
+                    </div>
+                    
+                    <div class="bg-gray-50 p-4 rounded-lg relative group"> <!-- Added relative and group -->
+                        <h6 class="text-sm font-semibold text-gray-600 mb-1">错误日志:</h6>
+                        <pre id="modalErrorLog" class="font-mono text-sm bg-gray-100 p-3 rounded overflow-x-auto whitespace-pre-wrap"></pre>
+                        <button class="copy-btn absolute top-2 right-2 bg-gray-200 hover:bg-gray-300 text-gray-600 p-1.5 rounded opacity-0 group-hover:opacity-100 transition-opacity" data-target="modalErrorLog" title="复制错误日志">
+                            <i class="far fa-copy"></i>
+                        </button>
+                    </div>
+                    
+                    <div class="bg-gray-50 p-4 rounded-lg relative group"> <!-- Added relative and group -->
+                        <h6 class="text-sm font-semibold text-gray-600 mb-1">请求消息:</h6>
+                        <pre id="modalRequestMsg" class="font-mono text-sm bg-gray-100 p-3 rounded overflow-x-auto whitespace-pre-wrap"></pre>
+                         <button class="copy-btn absolute top-2 right-2 bg-gray-200 hover:bg-gray-300 text-gray-600 p-1.5 rounded opacity-0 group-hover:opacity-100 transition-opacity" data-target="modalRequestMsg" title="复制请求消息">
+                            <i class="far fa-copy"></i>
+                        </button>
+                    </div>
+                    
+                    <div class="bg-gray-50 p-4 rounded-lg">
+                        <h6 class="text-sm font-semibold text-gray-600 mb-1">模型名称:</h6>
+                        <p id="modalModelName" class="font-medium"></p>
+                    </div>
+                    
+                    <div class="bg-gray-50 p-4 rounded-lg">
+                        <h6 class="text-sm font-semibold text-gray-600 mb-1">请求时间:</h6>
+                        <p id="modalRequestTime" class="font-medium"></p>
+                    </div>
+                </div>
+                
+                <div class="flex justify-end mt-6">
+                    <button type="button" id="closeModalFooterBtn" class="bg-gray-200 hover:bg-gray-300 text-gray-800 px-6 py-2 rounded-lg font-medium transition">关闭</button>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+{% endblock %}
+
+{% block body_scripts %}
+    <script src="/static/js/error_logs.js"></script>
+    <script>
+        // error_logs.html specific JS initialization (if any)
+        // e.g., initialize date pickers or other elements if needed
+        // The main logic is in error_logs.js
+    </script>
+{% endblock %}

app/utils/__init__.py

@@ -0,0 +1,3 @@
+"""
+工具包初始化模块
+"""

app/utils/helpers.py

@@ -0,0 +1,148 @@
+"""
+通用工具函数模块
+"""
+import json
+import re
+import base64
+import requests
+from typing import Dict, Any, List, Optional, Tuple
+
+from app.core.constants import DATA_URL_PATTERN, IMAGE_URL_PATTERN, VALID_IMAGE_RATIOS
+
+
+def extract_mime_type_and_data(base64_string: str) -> Tuple[Optional[str], str]:
+    """
+    从 base64 字符串中提取 MIME 类型和数据
+    
+    Args:
+        base64_string: 可能包含 MIME 类型信息的 base64 字符串
+        
+    Returns:
+        tuple: (mime_type, encoded_data)
+    """
+    # 检查字符串是否以 "data:" 格式开始
+    if base64_string.startswith('data:'):
+        # 提取 MIME 类型和数据
+        pattern = DATA_URL_PATTERN
+        match = re.match(pattern, base64_string)
+        if match:
+            mime_type = "image/jpeg" if match.group(1) == "image/jpg" else match.group(1)
+            encoded_data = match.group(2)
+            return mime_type, encoded_data
+    
+    # 如果不是预期格式，假定它只是数据部分
+    return None, base64_string
+
+
+def convert_image_to_base64(url: str) -> str:
+    """
+    将图片URL转换为base64编码
+    
+    Args:
+        url: 图片URL
+        
+    Returns:
+        str: base64编码的图片数据
+        
+    Raises:
+        Exception: 如果获取图片失败
+    """
+    response = requests.get(url)
+    if response.status_code == 200:
+        # 将图片内容转换为base64
+        img_data = base64.b64encode(response.content).decode('utf-8')
+        return img_data
+    else:
+        raise Exception(f"Failed to fetch image: {response.status_code}")
+
+
+def format_json_response(data: Dict[str, Any], indent: int = 2) -> str:
+    """
+    格式化JSON响应
+    
+    Args:
+        data: 要格式化的数据
+        indent: 缩进空格数
+        
+    Returns:
+        str: 格式化后的JSON字符串
+    """
+    return json.dumps(data, indent=indent, ensure_ascii=False)
+
+
+def parse_prompt_parameters(prompt: str, default_ratio: str = "1:1") -> Tuple[str, int, str]:
+    """
+    从prompt中解析参数
+    
+    支持的格式:
+    - {n:数量} 例如: {n:2} 生成2张图片
+    - {ratio:比例} 例如: {ratio:16:9} 使用16:9比例
+    
+    Args:
+        prompt: 提示文本
+        default_ratio: 默认比例
+        
+    Returns:
+        tuple: (清理后的提示文本, 图片数量, 比例)
+    """
+    # 默认值
+    n = 1
+    aspect_ratio = default_ratio
+    
+    # 解析n参数
+    n_match = re.search(r'{n:(\d+)}', prompt)
+    if n_match:
+        n = int(n_match.group(1))
+        if n < 1 or n > 4:
+            raise ValueError(f"Invalid n value: {n}. Must be between 1 and 4.")
+        prompt = prompt.replace(n_match.group(0), '').strip()
+        
+    # 解析ratio参数    
+    ratio_match = re.search(r'{ratio:(\d+:\d+)}', prompt)
+    if ratio_match:
+        aspect_ratio = ratio_match.group(1)
+        if aspect_ratio not in VALID_IMAGE_RATIOS:
+            raise ValueError(
+                f"Invalid ratio: {aspect_ratio}. Must be one of: {', '.join(VALID_IMAGE_RATIOS)}"
+            )
+        prompt = prompt.replace(ratio_match.group(0), '').strip()
+        
+    return prompt, n, aspect_ratio
+
+
+def extract_image_urls_from_markdown(text: str) -> List[str]:
+    """
+    从Markdown文本中提取图片URL
+    
+    Args:
+        text: Markdown文本
+        
+    Returns:
+        List[str]: 图片URL列表
+    """
+    pattern = IMAGE_URL_PATTERN
+    matches = re.findall(pattern, text)
+    return [match[1] for match in matches]
+
+
+def is_valid_api_key(key: str) -> bool:
+    """
+    检查API密钥格式是否有效
+    
+    Args:
+        key: API密钥
+        
+    Returns:
+        bool: 如果密钥格式有效则返回True
+    """
+    # 检查Gemini API密钥格式
+    if key.startswith('AIza'):
+        return len(key) >= 30
+    
+    # 检查OpenAI API密钥格式
+    if key.startswith('sk-'):
+        return len(key) >= 30
+    
+    return False
+
+

app/utils/uploader.py

@@ -0,0 +1,393 @@
+import requests
+from app.domain.image_models import ImageMetadata, ImageUploader, UploadResponse
+from enum import Enum
+from typing import Optional, Any
+
+class UploadErrorType(Enum):
+    """上传错误类型枚举"""
+    NETWORK_ERROR = "network_error"  # 网络请求错误
+    AUTH_ERROR = "auth_error"        # 认证错误
+    INVALID_FILE = "invalid_file"    # 无效文件
+    SERVER_ERROR = "server_error"    # 服务器错误
+    PARSE_ERROR = "parse_error"      # 响应解析错误
+    UNKNOWN = "unknown"              # 未知错误
+
+
+class UploadError(Exception):
+    """图片上传错误异常类"""
+    
+    def __init__(
+        self,
+        message: str,
+        error_type: UploadErrorType = UploadErrorType.UNKNOWN,
+        status_code: Optional[int] = None,
+        details: Optional[dict] = None,
+        original_error: Optional[Exception] = None
+    ):
+        """
+        初始化上传错误异常
+        
+        Args:
+            message: 错误消息
+            error_type: 错误类型
+            status_code: HTTP状态码
+            details: 详细错误信息
+            original_error: 原始异常
+        """
+        self.message = message
+        self.error_type = error_type
+        self.status_code = status_code
+        self.details = details or {}
+        self.original_error = original_error
+        
+        # 构建完整错误信息
+        full_message = f"[{error_type.value}] {message}"
+        if status_code:
+            full_message = f"{full_message} (Status: {status_code})"
+        if details:
+            full_message = f"{full_message} - Details: {details}"
+            
+        super().__init__(full_message)
+    
+    @classmethod
+    def from_response(cls, response: Any, message: Optional[str] = None) -> "UploadError":
+        """
+        从HTTP响应创建错误实例
+        
+        Args:
+            response: HTTP响应对象
+            message: 自定义错误消息
+        """
+        try:
+            error_data = response.json()
+            details = error_data.get("data", {})
+            return cls(
+                message=message or error_data.get("message", "Unknown error"),
+                error_type=UploadErrorType.SERVER_ERROR,
+                status_code=response.status_code,
+                details=details
+            )
+        except Exception:
+            return cls(
+                message=message or "Failed to parse error response",
+                error_type=UploadErrorType.PARSE_ERROR,
+                status_code=response.status_code
+            )
+
+
+class SmMsUploader(ImageUploader):
+    API_URL = "https://sm.ms/api/v2/upload"
+    
+    def __init__(self, api_key: str):
+        self.api_key = api_key
+        
+    def upload(self, file: bytes, filename: str) -> UploadResponse:
+        try:
+            # 准备请求头
+            headers = {
+                "Authorization": f"Basic {self.api_key}"
+            }
+            
+            # 准备文件数据
+            files = {
+                "smfile": (filename, file, "image/png")
+            }
+            
+            # 发送请求
+            response = requests.post(
+                self.API_URL,
+                headers=headers,
+                files=files
+            )
+            
+            # 检查响应状态
+            response.raise_for_status()
+            
+            # 解析响应
+            result = response.json()
+            
+            # 验证上传是否成功
+            if not result.get("success"):
+                raise UploadError(result.get("message", "Upload failed"))
+                
+            # 转换为统一格式
+            data = result["data"]
+            image_metadata = ImageMetadata(
+                width=data["width"],
+                height=data["height"],
+                filename=data["filename"],
+                size=data["size"],
+                url=data["url"],
+                delete_url=data["delete"]
+            )
+            
+            return UploadResponse(
+                success=True,
+                code="success",
+                message="Upload success",
+                data=image_metadata
+            )
+            
+        except requests.RequestException as e:
+            # 处理网络请求相关错误
+            raise UploadError(f"Upload request failed: {str(e)}")
+        except (KeyError, ValueError) as e:
+            # 处理响应解析错误
+            raise UploadError(f"Invalid response format: {str(e)}")
+        except Exception as e:
+            # 处理其他未预期的错误
+            raise UploadError(f"Upload failed: {str(e)}")
+    
+    
+class QiniuUploader(ImageUploader):
+    def __init__(self, access_key: str, secret_key: str):
+        self.access_key = access_key
+        self.secret_key = secret_key
+        
+    def upload(self, file: bytes, filename: str) -> UploadResponse:
+        # 实现七牛云的具体上传逻辑
+        pass
+    
+    
+class PicGoUploader(ImageUploader):
+    """Chevereto API 图片上传器"""
+    
+    def __init__(self, api_key: str, api_url: str = "https://www.picgo.net/api/1/upload"):
+        """
+        初始化 Chevereto 上传器
+        
+        Args:
+            api_key: Chevereto API 密钥
+            api_url: Chevereto API 上传地址
+        """
+        self.api_key = api_key
+        self.api_url = api_url
+        
+    def upload(self, file: bytes, filename: str) -> UploadResponse:
+        """
+        上传图片到 Chevereto 服务
+        
+        Args:
+            file: 图片文件二进制数据
+            filename: 文件名
+            
+        Returns:
+            UploadResponse: 上传响应对象
+            
+        Raises:
+            UploadError: 上传失败时抛出异常
+        """
+        try:
+            # 准备请求头
+            headers = {
+                "X-API-Key": self.api_key
+            }
+            
+            # 准备文件数据
+            files = {
+                "source": (filename, file)
+            }
+            
+            # 发送请求
+            response = requests.post(
+                self.api_url,
+                headers=headers,
+                files=files
+            )
+            
+            # 检查响应状态
+            response.raise_for_status()
+            
+            # 解析响应
+            result = response.json()
+            
+            # 验证上传是否成功
+            if result.get("status_code") != 200:
+                error_message = "Upload failed"
+                if "error" in result:
+                    error_message = result["error"].get("message", error_message)
+                raise UploadError(
+                    message=error_message,
+                    error_type=UploadErrorType.SERVER_ERROR,
+                    status_code=result.get("status_code"),
+                    details=result.get("error")
+                )
+                
+            # 从响应中提取图片信息
+            image_data = result.get("image", {})
+            
+            # 构建图片元数据
+            image_metadata = ImageMetadata(
+                width=image_data.get("width", 0),
+                height=image_data.get("height", 0),
+                filename=image_data.get("filename", filename),
+                size=image_data.get("size", 0),
+                url=image_data.get("url", ""),
+                delete_url=image_data.get("delete_url", None)
+            )
+            
+            return UploadResponse(
+                success=True,
+                code="success",
+                message=result.get("success", {}).get("message", "Upload success"),
+                data=image_metadata
+            )
+            
+        except requests.RequestException as e:
+            # 处理网络请求相关错误
+            raise UploadError(
+                message=f"Upload request failed: {str(e)}",
+                error_type=UploadErrorType.NETWORK_ERROR,
+                original_error=e
+            )
+        except (KeyError, ValueError, TypeError) as e:
+            # 处理响应解析错误
+            raise UploadError(
+                message=f"Invalid response format: {str(e)}",
+                error_type=UploadErrorType.PARSE_ERROR,
+                original_error=e
+            )
+        except UploadError:
+            # 重新抛出已经是 UploadError 类型的异常
+            raise
+        except Exception as e:
+            # 处理其他未预期的错误
+            raise UploadError(
+                message=f"Upload failed: {str(e)}",
+                error_type=UploadErrorType.UNKNOWN,
+                original_error=e
+            )
+
+
+class CloudFlareImgBedUploader(ImageUploader):
+    """CloudFlare图床上传器"""
+    
+    def __init__(self, auth_code: str, api_url: str):
+        """
+        初始化CloudFlare图床上传器
+        
+        Args:
+            auth_code: 认证码
+            api_url: 上传API地址
+        """
+        self.auth_code = auth_code
+        self.api_url = api_url
+        
+    def upload(self, file: bytes, filename: str) -> UploadResponse:
+        """
+        上传图片到CloudFlare图床
+        
+        Args:
+            file: 图片文件二进制数据
+            filename: 文件名
+            
+        Returns:
+            UploadResponse: 上传响应对象
+            
+        Raises:
+            UploadError: 上传失败时抛出异常
+        """
+        try:
+            # 准备请求URL（添加认证码参数，如果存在）
+            if self.auth_code:
+                request_url = f"{self.api_url}?authCode={self.auth_code}&uploadNameType=origin"
+            else:
+                request_url = f"{self.api_url}?uploadNameType=origin"
+            
+            # 准备文件数据
+            files = {
+                "file": (filename, file)
+            }
+            
+            # 发送请求
+            response = requests.post(
+                request_url,
+                files=files
+            )
+            
+            # 检查响应状态
+            response.raise_for_status()
+            
+            # 解析响应
+            result = response.json()
+            
+            # 验证响应格式
+            if not result or not isinstance(result, list) or len(result) == 0:
+                raise UploadError(
+                    message="Invalid response format",
+                    error_type=UploadErrorType.PARSE_ERROR
+                )
+                
+            # 获取文件URL
+            file_path = result[0].get("src")
+            if not file_path:
+                raise UploadError(
+                    message="Missing file URL in response",
+                    error_type=UploadErrorType.PARSE_ERROR
+                )
+                
+            # 构建完整URL（如果返回的是相对路径）
+            base_url = self.api_url.split("/upload")[0]
+            full_url = file_path if file_path.startswith(("http://", "https://")) else f"{base_url}{file_path}"
+                
+            # 构建图片元数据（注意：CloudFlare-ImgBed不返回所有元数据，所以部分字段为默认值）
+            image_metadata = ImageMetadata(
+                width=0,  # CloudFlare-ImgBed不返回宽度
+                height=0,  # CloudFlare-ImgBed不返回高度
+                filename=filename,
+                size=0,  # CloudFlare-ImgBed不返回大小
+                url=full_url,
+                delete_url=None  # CloudFlare-ImgBed不返回删除URL
+            )
+            
+            return UploadResponse(
+                success=True,
+                code="success",
+                message="Upload success",
+                data=image_metadata
+            )
+            
+        except requests.RequestException as e:
+            # 处理网络请求相关错误
+            raise UploadError(
+                message=f"Upload request failed: {str(e)}",
+                error_type=UploadErrorType.NETWORK_ERROR,
+                original_error=e
+            )
+        except (KeyError, ValueError, TypeError, IndexError) as e:
+            # 处理响应解析错误
+            raise UploadError(
+                message=f"Invalid response format: {str(e)}",
+                error_type=UploadErrorType.PARSE_ERROR,
+                original_error=e
+            )
+        except UploadError:
+            # 重新抛出已经是 UploadError 类型的异常
+            raise
+        except Exception as e:
+            # 处理其他未预期的错误
+            raise UploadError(
+                message=f"Upload failed: {str(e)}",
+                error_type=UploadErrorType.UNKNOWN,
+                original_error=e
+            )
+    
+class ImageUploaderFactory:
+    @staticmethod
+    def create(provider: str, **credentials) -> ImageUploader:
+        if provider == "smms":
+            return SmMsUploader(credentials["api_key"])
+        elif provider == "qiniu":
+            return QiniuUploader(
+                credentials["access_key"], 
+                credentials["secret_key"]
+            )
+        elif provider == "picgo":
+            api_url = credentials.get("api_url", "https://www.picgo.net/api/1/upload")
+            return PicGoUploader(credentials["api_key"], api_url)
+        elif provider == "cloudflare_imgbed":
+            return CloudFlareImgBedUploader(
+                credentials["auth_code"],
+                credentials["base_url"]
+            )
+        raise ValueError(f"Unknown provider: {provider}")

docker-compose.yml

@@ -0,0 +1,9 @@
+version: '3'
+
+services:
+  gemini-balance:
+    build: .
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env

requirements.txt

@@ -9,3 +9,11 @@ uvicorn
 google-genai
 jinja2
 python-multipart
+cryptography # 支持 MySQL 8+ caching_sha2_password 验证
+# 数据库相关依赖
+pymysql
+sqlalchemy
+aiomysql
+databases
+python-dotenv
+apscheduler # 添加定时任务库