完成大量美化

feat: sync latest local code
2026-05-01 15:44:14 +08:00 · 2026-05-01 14:44:18 +08:00 · 2026-04-30 01:38:53 +08:00 · 2026-04-30 01:35:10 +08:00 · 2026-04-29 00:19:46 +08:00 · 2026-04-28 00:45:18 +08:00
4677 changed files with 778009 additions and 4734 deletions
--- a/.env
+++ b/.env
@@ -8,4 +8,9 @@ REGEX_FILE=/data/regex_rules.json
 # ---------- 服务地址 ----------
 COMFYUI_API_URL=http://comfyui:8188
 BACKEND_PORT=8000
-FRONTEND_PORT=8501
+FRONTEND_PORT=8501
+
+# 先配置 .env 文件
+MAIN_LLM_API_KEY=sk-Oh4o3fzV6Qe59B6DRwSskE48xe5D6bq1hkgDZqH1mmJOCN8j
+MAIN_LLM_BASE_URL=https://api.chatfire.cn/v1
+MAIN_LLM_MODEL=glm4.7
--- a/.gitignore
+++ b/.gitignore
--- a/.idea/codeStyles/codeStyleConfig.xml
+++ b/.idea/codeStyles/codeStyleConfig.xml
@@ -0,0 +1,5 @@
+<component name="ProjectCodeStyleConfiguration">
+  <state>
+    <option name="PREFERRED_PROJECT_CODE_STYLE" value="Default" />
+  </state>
+</component>
--- a/.idea/llm-workflow-engine.iml
+++ b/.idea/llm-workflow-engine.iml
@@ -3,6 +3,8 @@
  <component name="NewModuleRootManager">
    <content url="file://$MODULE_DIR$">
      <sourceFolder url="file://$MODULE_DIR$" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/backend" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/backend/api" isTestSource="false" />
    </content>
    <orderEntry type="jdk" jdkName="Python 3.9 (pythonProject1)" jdkType="Python SDK" />
    <orderEntry type="sourceFolder" forTests="false" />
--- a/FIX_GLOBAL_WORLDBOOK_SYNC.md
+++ b/FIX_GLOBAL_WORLDBOOK_SYNC.md
@@ -0,0 +1,195 @@
+# 全局世界书数据同步问题修复
+
+## 🐛 问题描述
+
+**现象**: 当世界书文件被删除后，LocalStorage中仍然保存着该世界书的全局状态，导致前端显示一个不存在的"幽灵"世界书。
+
+**原因**: `fetchWorldBooks` 函数从LocalStorage加载全局世界书后，没有清理那些已经不存在于后端的世界书。
+
+---
+
+## ✅ 解决方案
+
+### 修复位置
+**文件**: `frontend/src/Store/SideBarLeft/WorldBookSlice.jsx`  
+**函数**: `fetchWorldBooks` (第132-165行)
+
+### 修复逻辑
+
+```javascript
+// 从 LocalStorage 获取全局世界书列表
+let globalBooks = loadGlobalWorldBooks();
+
+// 清理 LocalStorage 中已不存在的世界书
+const existingWorldBookNames = new Set(data.map(wb => wb.name));
+const cleanedGlobalBooks = globalBooks.filter(wb => existingWorldBookNames.has(wb.name));
+
+// 如果有被清理的项，更新 LocalStorage
+if (cleanedGlobalBooks.length !== globalBooks.length) {
+  console.log(`清理了 ${globalBooks.length - cleanedGlobalBooks.length} 个不存在的全局世界书`);
+  saveGlobalWorldBooks(cleanedGlobalBooks);
+  globalBooks = cleanedGlobalBooks;
+}
+```
+
+### 工作流程
+
+1. **获取后端数据**: 调用 `GET /api/worldbooks/` 获取所有存在的世界书
+2. **加载LocalStorage**: 从LocalStorage读取全局世界书列表
+3. **对比清理**: 过滤掉LocalStorage中存在但后端不存在的世界书
+4. **更新存储**: 如果发现有被清理的项，更新LocalStorage
+5. **更新State**: 将清理后的列表设置到State中
+
+---
+
+## 🧪 测试场景
+
+### 场景1: 正常情况
+**步骤**:
+1. 创建世界书A和B
+2. 将A和B都设为全局
+3. 刷新页面
+
+**预期结果**:
+- ✅ 全局区域显示A和B
+- ✅ LocalStorage中有A和B
+
+### 场景2: 文件被删除
+**步骤**:
+1. 创建世界书A和B
+2. 将A和B都设为全局
+3. 手动删除世界书A的文件（或其他方式删除）
+4. 刷新页面
+
+**预期结果**:
+- ✅ 全局区域只显示B
+- ✅ LocalStorage中只保留B
+- ✅ 控制台输出: "清理了 1 个不存在的全局世界书"
+
+### 场景3: 通过UI删除
+**步骤**:
+1. 创建世界书A和B
+2. 将A和B都设为全局
+3. 在前端UI中删除世界书A
+4. 刷新页面
+
+**预期结果**:
+- ✅ 全局区域只显示B
+- ✅ LocalStorage中只保留B
+- ✅ 无错误信息
+
+---
+
+## 📊 数据流图
+
+```
+┌─────────────────┐
+│  页面加载/切换   │
+└────────┬────────┘
+         │
+         ▼
+┌─────────────────┐
+│ fetchWorldBooks │
+└────────┬────────┘
+         │
+         ├──► GET /api/worldbooks/ ──► 后端返回现有世界书列表
+         │
+         ├──► loadGlobalWorldBooks() ──► 从LocalStorage读取
+         │
+         ├──► 对比两个列表
+         │    ├─ 存在于LocalStorage但不存在于后端 → 清理
+         │    └─ 存在于两者 → 保留
+         │
+         ├──► saveGlobalWorldBooks() ──► 更新LocalStorage（如有变化）
+         │
+         └──► set state ──► 更新UI
+```
+
+---
+
+## 🔍 关键代码说明
+
+### 1. 使用Set提高查找效率
+```javascript
+const existingWorldBookNames = new Set(data.map(wb => wb.name));
+```
+- 将后端返回的世界书名称转换为Set
+- Set的查找时间复杂度为O(1)，比数组的O(n)更高效
+
+### 2. 过滤清理
+```javascript
+const cleanedGlobalBooks = globalBooks.filter(wb => 
+  existingWorldBookNames.has(wb.name)
+);
+```
+- 只保留那些在后端也存在的世界书
+- 自动移除"幽灵"世界书
+
+### 3. 条件更新
+```javascript
+if (cleanedGlobalBooks.length !== globalBooks.length) {
+  console.log(`清理了 ${globalBooks.length - cleanedGlobalBooks.length} 个不存在的全局世界书`);
+  saveGlobalWorldBooks(cleanedGlobalBooks);
+  globalBooks = cleanedGlobalBooks;
+}
+```
+- 只有在确实有变化时才更新LocalStorage
+- 避免不必要的写入操作
+- 提供调试信息
+
+---
+
+## ✨ 优势
+
+1. **自动清理**: 无需手动干预，自动同步LocalStorage和后端数据
+2. **性能优化**: 使用Set提高查找效率
+3. **用户友好**: 静默清理，只在控制台输出日志
+4. **数据一致性**: 确保LocalStorage中的数据始终与后端保持一致
+5. **无副作用**: 不影响正常的业务流程
+
+---
+
+## 📝 相关代码位置
+
+### LocalStorage操作函数
+```javascript
+// 辅助函数：从 LocalStorage 加载全局世界书
+const loadGlobalWorldBooks = () => {
+  try {
+    const stored = localStorage.getItem(GLOBAL_WORLDBOOKS_KEY);
+    return stored ? JSON.parse(stored) : [];
+  } catch (error) {
+    console.error('加载全局世界书失败:', error);
+    return [];
+  }
+};
+
+// 辅助函数：保存全局世界书到 LocalStorage
+const saveGlobalWorldBooks = (globalBooks) => {
+  try {
+    localStorage.setItem(GLOBAL_WORLDBOOKS_KEY, JSON.stringify(globalBooks));
+  } catch (error) {
+    console.error('保存全局世界书失败:', error);
+  }
+};
+```
+
+### 删除世界书时的清理
+```javascript
+// deleteWorldBook 函数中已经有清理逻辑
+deleteWorldBook: async (name) => {
+  // ...
+  const filteredGlobalBooks = state.globalWorldBooks.filter(wb => wb.name !== name);
+  saveGlobalWorldBooks(filteredGlobalBooks);
+  // ...
+}
+```
+
+---
+
+## 🎯 总结
+
+✅ **问题已修复**: 全局世界书现在会自动清理不存在的项  
+✅ **数据同步**: LocalStorage与后端数据保持一致  
+✅ **用户体验**: 不再显示"幽灵"世界书  
+✅ **代码健壮**: 增加了数据一致性检查机制
--- a/README.md
+++ b/README.md
@@ -0,0 +1,226 @@
+# LLM Workflow Engine
+
+一个基于 React + TypeScript + FastAPI 的 AI 聊天工作流引擎，支持流式对话、动态表格生成、图片生成等功能。
+
+## 🚀 技术栈
+
+### 前端
+- **React 18** - 用户界面框架
+- **TypeScript** - 类型安全的 JavaScript
+- **Vite** - 现代化的前端构建工具
+- **Zustand** - 轻量级状态管理
+- **React Markdown** - Markdown 渲染
+- **Tailwind CSS** - 实用优先的 CSS 框架
+
+### 后端
+- **FastAPI** - 现代化的 Python Web 框架
+- **Python 3.11** - 编程语言
+- **Uvicorn** - ASGI 服务器
+- **WebSockets** - 实时通信
+
+## 📁 项目结构
+
+```
+llm_workflow_engine/
+├── backend/                 # 后端服务
+│   ├── api/                # API 路由
+│   ├── core/               # 核心模型和配置
+│   ├── tools/              # 工具函数
+│   ├── workflows/          # 工作流定义
+│   ├── Dockerfile          # 后端 Docker 配置
+│   ├── main.py             # 后端入口
+│   └── requirements.txt    # Python 依赖
+├── frontend/               # 前端服务
+│   ├── src/
+│   │   ├── components/     # React 组件
+│   │   ├── Store/          # 状态管理
+│   │   ├── services/       # API 服务
+│   │   ├── types/          # TypeScript 类型定义
+│   │   ├── App.tsx         # 主应用组件
+│   │   └── main.tsx        # 入口文件
+│   ├── Dockerfile          # 前端 Docker 配置
+│   ├── nginx.conf          # Nginx 配置（生产环境）
+│   ├── package.json        # Node.js 依赖
+│   └── tsconfig.json       # TypeScript 配置
+├── data/                   # 数据存储
+├── docker-compose.yml      # Docker Compose 配置
+└── README.md              # 项目文档
+```
+
+## 🛠️ 安装和运行
+
+### 使用 Docker Compose（推荐）
+
+这是最简单的运行方式，适合开发和生产环境。
+
+1. **克隆项目**
+```bash
+git clone <repository-url>
+cd llm_workflow_engine
+```
+
+2. **配置环境变量**
+```bash
+# 复制环境变量模板
+cp .env.example .env
+
+# 根据需要编辑 .env 文件
+```
+
+3. **启动服务**
+```bash
+# 构建并启动所有服务
+docker-compose up --build
+
+# 或者在后台运行
+docker-compose up -d --build
+```
+
+4. **访问应用**
+- 前端界面: http://localhost:23338
+- 后端 API: http://localhost:23337
+- API 文档: http://localhost:23337/docs
+
+5. **停止服务**
+```bash
+docker-compose down
+```
+
+### 本地开发
+
+如果你想分别运行前后端进行开发：
+
+#### 后端开发
+
+1. **安装 Python 依赖**
+```bash
+cd backend
+pip install -r requirements.txt
+```
+
+2. **启动后端服务**
+```bash
+python -m uvicorn backend.main:app --host 0.0.0.0 --port 8000 --reload
+```
+
+#### 前端开发
+
+1. **安装 Node.js 依赖**
+```bash
+cd frontend
+npm install
+```
+
+2. **启动前端开发服务器**
+```bash
+npm run dev
+```
+
+3. **访问应用**
+- 前端界面: http://localhost:5173
+- 确保后端在 http://localhost:8000 运行
+
+## 🔧 配置说明
+
+### 环境变量
+
+#### 前端环境变量 (frontend/.env)
+```
+VITE_API_URL=http://localhost:23337/api
+VITE_WS_URL=ws://localhost:23337/api
+```
+
+#### 后端环境变量
+```
+PYTHONUNBUFFERED=1
+PYTHONDONTWRITEBYTECODE=1
+```
+
+### API 配置
+
+在前端界面中配置你的 API 密钥和端点：
+1. 打开左侧栏的 "API 配置" 标签
+2. 添加你的 API 配置（URL 和密钥）
+3. 选择要使用的 API
+
+## 📖 功能特性
+
+- ✅ **流式对话** - 实时显示 AI 回复
+- ✅ **多角色支持** - 支持多个聊天角色和会话
+- ✅ **消息编辑** - 可以编辑和删除历史消息
+- ✅ **HTML 渲染** - 支持 Markdown 和 HTML 渲染
+- ✅ **动态表格** - 自动生成和更新数据表格
+- ✅ **图片生成** - 集成图片生成工作流
+- ✅ **世界书** - 管理角色和世界设定
+- ✅ **预设管理** - 保存和加载不同的对话预设
+
+## 🐳 Docker 命令参考
+
+```bash
+# 构建并启动
+docker-compose up --build
+
+# 后台运行
+docker-compose up -d
+
+# 查看日志
+docker-compose logs -f
+
+# 停止服务
+docker-compose down
+
+# 重启服务
+docker-compose restart
+
+# 进入容器
+docker-compose exec backend bash
+docker-compose exec frontend sh
+
+# 清理所有容器和卷
+docker-compose down -v
+```
+
+## 🔍 开发工具
+
+### 前端
+```bash
+# 类型检查
+npm run type-check
+
+# 构建
+npm run build
+
+# 预览生产构建
+npm run preview
+```
+
+### 后端
+```bash
+# 运行测试（如果有的话）
+cd backend
+pytest
+
+# 代码格式化
+black .
+```
+
+## 📝 待办事项
+
+- [ ] 添加单元测试
+- [ ] 完善错误处理
+- [ ] 添加用户认证
+- [ ] 优化性能
+- [ ] 添加更多语言支持
+- [ ] 完善文档
+
+## 🤝 贡献
+
+欢迎提交 Issue 和 Pull Request！
+
+## 📄 许可证
+
+MIT License
+
+## 📞 联系方式
+
+如有问题，请提交 Issue 或联系维护者。
--- a/REMOVE_CONFIRM_DIALOG.md
+++ b/REMOVE_CONFIRM_DIALOG.md
@@ -0,0 +1,194 @@
+# 世界书删除确认弹窗移除
+
+## 📋 修改内容
+
+移除了世界书模块中所有的浏览器级别确认弹窗（`confirm`），改为直接执行删除操作。
+
+---
+
+## ✅ 已移除的确认弹窗
+
+### 1. 删除世界书条目
+**位置**: `WorldBook.jsx` 第338-349行
+
+**修改前**:
+```javascript
+const handleDeleteEntry = async () => {
+  if (!currentEntry || !currentWorldBook) return;
+
+  if (confirm('确定要删除此条目吗？')) {
+    try {
+      await deleteWorldBookEntry(currentWorldBook.name, currentEntry.uid);
+      setShowEditPanel(false);
+      setCurrentEntry(null);
+      await fetchWorldBookEntries(currentWorldBook.name, currentPage, pageSize);
+    } catch (err) {
+      console.error('删除条目失败:', err);
+    }
+  }
+};
+```
+
+**修改后**:
+```javascript
+const handleDeleteEntry = async () => {
+  if (!currentEntry || !currentWorldBook) return;
+
+  try {
+    await deleteWorldBookEntry(currentWorldBook.name, currentEntry.uid);
+    setShowEditPanel(false);
+    setCurrentEntry(null);
+    await fetchWorldBookEntries(currentWorldBook.name, currentPage, pageSize);
+  } catch (err) {
+    console.error('删除条目失败:', err);
+  }
+};
+```
+
+---
+
+### 2. 删除世界书
+**位置**: `WorldBook.jsx` 第354-365行
+
+**修改前**:
+```javascript
+const handleDeleteWorldBook = async () => {
+  if (!currentWorldBook) return;
+
+  if (confirm(`确定要删除世界书 "${currentWorldBook.name}" 吗？`)) {
+    try {
+      await deleteWorldBook(currentWorldBook.name);
+      resetCurrentWorldBook();
+    } catch (err) {
+      console.error('删除世界书失败:', err);
+    }
+  }
+};
+```
+
+**修改后**:
+```javascript
+const handleDeleteWorldBook = async () => {
+  if (!currentWorldBook) return;
+
+  try {
+    await deleteWorldBook(currentWorldBook.name);
+    resetCurrentWorldBook();
+  } catch (err) {
+    console.error('删除世界书失败:', err);
+  }
+};
+```
+
+---
+
+### 3. 编辑面板中的删除按钮
+**位置**: `WorldBook.jsx` 第1086-1096行
+
+**修改前**:
+```jsx
+<button
+    className="btn btn-danger"
+    onClick={() => {
+      if (window.confirm('确定要删除这个条目吗？')) {
+        handleDeleteEntry();
+      }
+    }}
+>
+  删除条目
+</button>
+```
+
+**修改后**:
+```jsx
+<button
+    className="btn btn-danger"
+    onClick={handleDeleteEntry}
+>
+  删除条目
+</button>
+```
+
+---
+
+## 🎯 影响范围
+
+### 用户交互变化
+
+**之前**:
+1. 点击删除按钮
+2. 弹出浏览器确认对话框
+3. 用户点击"确定"或"取消"
+4. 根据选择执行或删除操作
+
+**现在**:
+1. 点击删除按钮
+2. 立即执行删除操作
+3. 通过错误处理捕获异常
+
+---
+
+## ✨ 优势
+
+1. **更流畅的用户体验**: 减少交互步骤，操作更快捷
+2. **更现代的UI**: 避免使用浏览器原生弹窗，更符合现代Web应用风格
+3. **代码简化**: 减少了条件判断和嵌套层级
+4. **一致性**: 与其他删除操作保持一致（如果有其他模块也移除了confirm）
+
+---
+
+## ⚠️ 注意事项
+
+### 潜在风险
+- 用户可能误操作删除重要数据
+- 没有二次确认机制
+
+### 建议的替代方案（可选）
+如果未来需要添加确认机制，可以考虑：
+1. **自定义模态框**: 使用项目统一的Modal组件
+2. **Toast提示 + 撤销**: 删除后显示提示，提供短暂的撤销机会
+3. **软删除**: 先标记为删除，稍后真正删除
+
+---
+
+## 🧪 测试建议
+
+### 手动测试清单
+
+- [ ] 在世界书列表中选择一个世界书
+- [ ] 点击"删除"按钮，检查是否立即删除（无确认弹窗）
+- [ ] 在条目编辑面板中点击"删除条目"按钮，检查是否立即删除
+- [ ] 检查删除后的控制台是否有错误信息
+- [ ] 检查删除后UI是否正确更新
+
+### 边界情况测试
+
+- [ ] 删除不存在的世界书（应该被前端校验拦截）
+- [ ] 删除不存在的条目（应该被前端校验拦截）
+- [ ] 网络请求失败时的错误处理
+
+---
+
+## 📝 相关代码位置
+
+### 主要文件
+- `frontend/src/components/SideBarLeft/tabs/WorldBook/WorldBook.jsx`
+
+### 相关函数
+- `handleDeleteEntry()` - 删除条目
+- `handleDeleteWorldBook()` - 删除世界书
+
+### Store函数
+- `deleteWorldBookEntry()` - WorldBookSlice.jsx
+- `deleteWorldBook()` - WorldBookSlice.jsx
+
+---
+
+## 🎯 总结
+
+✅ **所有浏览器级别的确认弹窗已移除**  
+✅ **删除操作更加流畅和现代化**  
+✅ **代码结构更简洁**  
+✅ **用户体验得到提升**
+
+如果需要添加更优雅的确认机制，建议使用项目统一的UI组件而非浏览器原生弹窗。
--- a/TEST_API_CONFIG.md
+++ b/TEST_API_CONFIG.md
@@ -0,0 +1,428 @@
+# 🧪 API 配置功能测试指南
+
+## 📋 测试前准备
+
+### **1. 启动后端服务**
+
+```bash
+cd backend
+uvicorn main:app --reload --port 8000
+```
+
+确保看到：
+```
+INFO:     Application startup complete.
+INFO:     Uvicorn running on http://127.0.0.1:8000
+```
+
+---
+
+### **2. （可选）启动 ComfyUI**
+
+如果要测试 ComfyUI 连接：
+
+```bash
+# 本地运行
+python comfyui/main.py --listen 0.0.0.0 --port 8188
+
+# 或 Docker
+docker-compose up -d comfyui
+```
+
+---
+
+## 🚀 运行测试
+
+### **方法 1: 使用 Python 脚本（推荐）**
+
+```bash
+# 在项目根目录运行
+python test_api_config.py
+```
+
+**预期输出**：
+```
+============================================================
+  ComfyUI API 配置测试
+============================================================
+
+============================================================
+  测试 1: 列出工作流
+============================================================
+
+✅ 成功获取 1 个工作流
+
+  📄 default_txt2img.json
+     节点数: 7, 大小: 1234 bytes
+
+...
+
+============================================================
+  测试总结
+============================================================
+
+  ✅ 通过 - 列出工作流
+  ✅ 通过 - 获取工作流详情
+  ✅ 通过 - 上传工作流
+  ✅ 通过 - 删除工作流
+  ✅ 通过 - 测试 ComfyUI 连接
+  ✅ 通过 - 测试云端 API 连接
+
+  总计: 6/6 通过
+
+🎉 所有测试通过！
+```
+
+---
+
+### **方法 2: 使用 cURL 手动测试**
+
+#### **测试 1: 列出工作流**
+
+```bash
+curl http://localhost:8000/api/api-config/comfyui/workflows | jq
+```
+
+**预期响应**：
+```json
+[
+  {
+    "filename": "default_txt2img.json",
+    "name": "default_txt2img",
+    "nodes_count": 7,
+    "size": 1234
+  }
+]
+```
+
+---
+
+#### **测试 2: 获取工作流详情**
+
+```bash
+curl http://localhost:8000/api/api-config/comfyui/workflows/default_txt2img.json | jq
+```
+
+**预期响应**：
+```json
+{
+  "3": {
+    "inputs": {...},
+    "class_type": "KSampler",
+    "_meta": {"title": "K采样器"}
+  },
+  ...
+}
+```
+
+---
+
+#### **测试 3: 上传工作流**
+
+创建一个测试文件 `test_workflow.json`：
+
+```bash
+cat > test_workflow.json << 'EOF'
+{
+  "3": {
+    "inputs": {
+      "seed": 42,
+      "steps": 20,
+      "cfg": 8,
+      "sampler_name": "euler",
+      "scheduler": "normal",
+      "denoise": 1,
+      "model": ["4", 0],
+      "positive": ["6", 0],
+      "negative": ["7", 0],
+      "latent_image": ["5", 0]
+    },
+    "class_type": "KSampler"
+  },
+  "4": {
+    "inputs": {"ckpt_name": "test.safetensors"},
+    "class_type": "CheckpointLoaderSimple"
+  },
+  "5": {
+    "inputs": {"width": 512, "height": 512, "batch_size": 1},
+    "class_type": "EmptyLatentImage"
+  },
+  "6": {
+    "inputs": {"text": "test", "clip": ["4", 1]},
+    "class_type": "CLIPTextEncode"
+  },
+  "7": {
+    "inputs": {"text": "bad", "clip": ["4", 1]},
+    "class_type": "CLIPTextEncode"
+  },
+  "8": {
+    "inputs": {"samples": ["3", 0], "vae": ["4", 2]},
+    "class_type": "VAEDecode"
+  },
+  "9": {
+    "inputs": {"images": ["8", 0], "filename_prefix": "Test"},
+    "class_type": "SaveImage"
+  }
+}
+EOF
+```
+
+上传：
+
+```bash
+curl -X POST http://localhost:8000/api/api-config/comfyui/workflows/upload \
+  -F "file=@test_workflow.json" | jq
+```
+
+**预期响应**：
+```json
+{
+  "message": "Workflow uploaded successfully",
+  "filename": "test_workflow.json",
+  "size": 1234
+}
+```
+
+---
+
+#### **测试 4: 删除工作流**
+
+```bash
+curl -X DELETE http://localhost:8000/api/api-config/comfyui/workflows/test_workflow.json | jq
+```
+
+**预期响应**：
+```json
+{
+  "message": "Workflow 'test_workflow.json' deleted successfully"
+}
+```
+
+---
+
+#### **测试 5: 测试 ComfyUI 连接**
+
+```bash
+curl -X POST http://localhost:8000/api/api-config/test-comfyui-connection \
+  -H "Content-Type: application/json" \
+  -d '{"apiUrl": "http://localhost:8188"}' | jq
+```
+
+**如果 ComfyUI 正在运行**：
+```json
+{
+  "success": true,
+  "message": "连接成功",
+  "stats": {
+    "vram_total": 25769803776,
+    "vram_free": 24696061952,
+    "torch_version": "2.1.0+cu121",
+    "device": "cuda"
+  }
+}
+```
+
+**如果 ComfyUI 未运行**：
+```json
+{
+  "success": false,
+  "message": "无法连接到 ComfyUI，请检查地址和端口"
+}
+```
+
+---
+
+#### **测试 6: 测试云端 API 连接**
+
+```bash
+curl -X POST http://localhost:8000/api/api-config/test-cloud-connection \
+  -H "Content-Type: application/json" \
+  -d '{
+    "provider": "dall-e",
+    "apiKey": "sk-your-api-key-here",
+    "model": "dall-e-3"
+  }' | jq
+```
+
+**预期响应**（如果 API Key 有效）：
+```json
+{
+  "success": true,
+  "message": "连接成功，模型 dall-e-3 可用"
+}
+```
+
+---
+
+## ✅ 测试检查清单
+
+### **后端 API**
+- [ ] 列出工作流返回正确的列表
+- [ ] 获取工作流详情返回完整的 JSON
+- [ ] 上传工作流成功保存文件
+- [ ] 上传的工作流可以通过列表看到
+- [ ] 删除工作流成功移除文件
+- [ ] 默认工作流不可删除（返回 403）
+- [ ] ComfyUI 连接测试正确检测状态
+- [ ] 云端 API 连接测试验证 Key
+
+### **前端 UI**
+- [ ] 可以切换到"🎨 生图"标签
+- [ ] 模式切换卡片正常显示
+- [ ] 点击"本地 ComfyUI"显示本地配置
+- [ ] 点击"在线 API"显示云端配置
+- [ ] 表单输入正常工作
+- [ ] 工作流管理器显示默认工作流
+- [ ] 可以上传工作流文件
+- [ ] 可以删除工作流（非默认）
+- [ ] 测试连接按钮正常工作
+- [ ] 保存配置功能正常
+
+### **响应式设计**
+- [ ] 大屏幕（>768px）双列布局
+- [ ] 小屏幕（<768px）单列布局
+- [ ] 无页面级滚动条
+- [ ] 侧边栏可独立滚动
+- [ ] 无横向滚动
+
+---
+
+## 🐛 常见问题
+
+### **Q1: 测试脚本提示"Connection refused"**
+
+**原因**：后端服务未启动
+
+**解决**：
+```bash
+cd backend
+uvicorn main:app --reload --port 8000
+```
+
+---
+
+### **Q2: 上传工作流提示"Invalid ComfyUI workflow"**
+
+**原因**：JSON 格式不正确或缺少必要节点
+
+**解决**：
+- 确保包含 `KSampler` 节点
+- 使用 ComfyUI 的 "Save (API Format)" 导出
+- 检查 JSON 语法是否正确
+
+---
+
+### **Q3: 删除工作流提示"Cannot delete default workflow"**
+
+**这是正常的**！默认工作流受保护，不可删除。
+
+要测试删除功能，请先上传一个自定义工作流，然后删除它。
+
+---
+
+### **Q4: ComfyUI 连接测试失败**
+
+**可能原因**：
+1. ComfyUI 未启动
+2. 地址或端口错误
+3. Docker 网络问题
+
+**解决**：
+```bash
+# 检查 ComfyUI 是否运行
+curl http://localhost:8188/system_stats
+
+# Docker 环境下
+docker ps | grep comfyui
+docker logs comfyui
+```
+
+---
+
+## 📊 测试结果解读
+
+### **全部通过** ✅
+```
+总计: 6/6 通过
+🎉 所有测试通过！
+```
+→ API 配置功能完全正常，可以开始使用
+
+### **部分失败** ⚠️
+```
+总计: 4/6 通过
+⚠️  2 个测试失败，请检查日志
+```
+→ 查看失败的测试项，根据错误信息排查
+
+### **全部失败** ❌
+```
+总计: 0/6 通过
+```
+→ 检查后端服务是否正常运行
+→ 检查端口是否正确（8000）
+→ 查看后端日志
+
+---
+
+## 🎯 下一步
+
+测试通过后，你可以：
+
+1. **启动前端**
+   ```bash
+   cd frontend
+   npm run dev
+   ```
+
+2. **访问应用**
+   - 打开浏览器访问 `http://localhost:5173`
+   - 进入 API 配置页面
+   - 配置你的生图服务
+
+3. **开始生图**
+   - 配置完成后
+   - 在聊天界面输入生图请求
+   - 等待图片生成
+
+---
+
+## 📝 附录
+
+### **工作流文件格式**
+
+必须是 ComfyUI API 格式的 JSON：
+
+```json
+{
+  "node_id": {
+    "inputs": {...},
+    "class_type": "NodeType",
+    "_meta": {"title": "Display Name"}
+  }
+}
+```
+
+### **必需的节点类型**
+
+- `KSampler` - 采样器（必需）
+- `CheckpointLoaderSimple` - 模型加载器
+- `EmptyLatentImage` - 潜变量图像
+- `CLIPTextEncode` - 文本编码器（正向和负向）
+- `VAEDecode` - VAE 解码器
+- `SaveImage` - 保存图像
+
+### **API 端点列表**
+
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| GET | `/api/api-config/comfyui/workflows` | 列出工作流 |
+| POST | `/api/api-config/comfyui/workflows/upload` | 上传工作流 |
+| DELETE | `/api/api-config/comfyui/workflows/{filename}` | 删除工作流 |
+| GET | `/api/api-config/comfyui/workflows/{filename}` | 获取工作流详情 |
+| POST | `/api/api-config/test-comfyui-connection` | 测试 ComfyUI |
+| POST | `/api/api-config/test-cloud-connection` | 测试云端 API |
+
+---
+
+**祝测试顺利！** 🎉
--- a/WORLDBOOK_API_CHECK.md
+++ b/WORLDBOOK_API_CHECK.md
@@ -0,0 +1,217 @@
+# 世界书分页功能 - 前端API调用检查报告
+
+## ✅ 检查结果
+
+**所有前端世界书分页功能都能正确发出请求到后端API！**
+
+---
+
+## 📋 完整API映射表
+
+### 1. 世界书管理
+
+| 功能 | 前端Store函数 | HTTP方法 | API路径 | 后端路由函数 | 状态 |
+|------|--------------|----------|---------|-------------|------|
+| 获取世界书列表 | `fetchWorldBooks` | GET | `/api/worldbooks/` | `list_worldbooks` | ✅ |
+| 获取指定世界书 | `fetchWorldBook` | GET | `/api/worldbooks/{name}` | `get_worldbook` | ✅ |
+| 创建世界书 | `createWorldBook` | POST | `/api/worldbooks/` | `create_worldbook` | ✅ |
+| 更新世界书 | `updateWorldBook` | PUT | `/api/worldbooks/{name}` | `update_worldbook` | ✅ |
+| 删除世界书 | `deleteWorldBook` | DELETE | `/api/worldbooks/{name}` | `delete_worldbook` | ✅ |
+
+### 2. 条目管理（含分页）
+
+| 功能 | 前端Store函数 | HTTP方法 | API路径 | 后端路由函数 | 状态 |
+|------|--------------|----------|---------|-------------|------|
+| 获取条目列表（分页） | `fetchWorldBookEntries` | GET | `/api/worldbooks/{name}/entries?page={page}&page_size={page_size}` | `list_worldbook_entries` | ✅ |
+| 获取指定条目 | `fetchWorldBookEntry` | GET | `/api/worldbooks/{name}/entries/{uid}` | `get_worldbook_entry` | ✅ |
+| 创建条目 | `createWorldBookEntry` | POST | `/api/worldbooks/{name}/entries` | `create_worldbook_entry` | ✅ |
+| 更新条目 | `updateWorldBookEntry` | PUT | `/api/worldbooks/{name}/entries/{uid}` | `update_worldbook_entry` | ✅ |
+| 删除条目 | `deleteWorldBookEntry` | DELETE | `/api/worldbooks/{name}/entries/{uid}` | `delete_worldbook_entry` | ✅ |
+
+### 3. 导入导出
+
+| 功能 | 前端Store函数 | HTTP方法 | API路径 | 后端路由函数 | 状态 |
+|------|--------------|----------|---------|-------------|------|
+| 导入世界书 | `importWorldBook` | POST | `/api/worldbooks/{name}/import` | `import_worldbook` | ✅ |
+| 导出世界书 | `exportWorldBook` | GET | `/api/worldbooks/{name}/export?format={format}` | `export_worldbook` | ✅ |
+
+---
+
+## 🔍 关键功能验证
+
+### ✅ 下拉框读取所有世界书
+
+**位置**: `WorldBook.jsx` 第547行
+
+```jsx
+{worldBooks.map(book => (
+    <div key={book.name} className="dropdown-item">
+      ...
+    </div>
+))}
+```
+
+**数据来源**: 
+- `worldBooks` 来自 Store (第8行)
+- 通过 `fetchWorldBooks()` 加载 (第85行和第95行)
+
+**加载时机**:
+1. ✅ 组件挂载时立即加载（如果列表为空）
+2. ✅ 切换到世界书标签页时重新加载
+
+**API调用**:
+```javascript
+// WorldBookSlice.jsx 第135行
+const response = await fetch(`/api/worldbooks/`);
+```
+
+**后端路由**:
+```python
+# worldbooksRoute.py 第28行
+@router.get("/", response_model=List[Dict[str, Any]])
+async def list_worldbooks():
+```
+
+---
+
+## 🎯 分页功能验证
+
+### 前端实现
+
+**Store函数** (`WorldBookSlice.jsx` 第343-374行):
+```javascript
+fetchWorldBookEntries: async (name, page = 1, page_size = 20) => {
+  const response = await fetch(
+    `/api/worldbooks/${name}/entries?page=${page}&page_size=${page_size}`
+  );
+  // 解析响应并更新 state
+}
+```
+
+**组件调用**:
+- 选择世界书时: `fetchWorldBookEntries(book.name, 1, pageSize)` (第141行)
+- 切换页码时: `fetchWorldBookEntries(currentWorldBook.name, newPage, pageSize)` (第247行)
+- 改变每页数量: `fetchWorldBookEntries(currentWorldBook.name, 1, newPageSize)` (第259行)
+
+**分页状态**:
+```javascript
+entriesPagination: {
+  total: data.total || 0,
+  page: data.page || 1,
+  page_size: data.page_size || 20,
+  total_pages: data.total_pages || 0
+}
+```
+
+### 后端实现
+
+**API路由** (`worldbooksRoute.py` 第108-128行):
+```python
+@router.get("/{name}/entries", response_model=Dict[str, Any])
+async def list_worldbook_entries(
+    name: str,
+    page: int = 1,
+    page_size: int = 20
+):
+    return worldbook_service.list_entries(name, page, page_size)
+```
+
+**服务层** (`worldbook_service.py` 第168-198行):
+```python
+def list_entries(name: str, page: int = 1, page_size: int = 20) -> Dict[str, Any]:
+    all_entries = data.get("entries", [])
+    total = len(all_entries)
+    
+    start_idx = (page - 1) * page_size
+    end_idx = start_idx + page_size
+    paginated_entries = all_entries[start_idx:end_idx]
+    
+    return {
+        "entries": paginated_entries,
+        "total": total,
+        "page": page,
+        "page_size": page_size,
+        "total_pages": (total + page_size - 1) // page_size
+    }
+```
+
+---
+
+## 📊 数据格式
+
+### 后端返回格式（分页）
+
+```json
+{
+  "entries": [...],
+  "total": 30,
+  "page": 1,
+  "page_size": 20,
+  "total_pages": 2
+}
+```
+
+### 前端State结构
+
+```javascript
+{
+  worldBooks: [],              // 世界书列表
+  currentWorldBook: null,      // 当前选中的世界书
+  currentEntries: [],          // 当前页的条目列表
+  entriesPagination: {         // 分页信息
+    total: 0,
+    page: 1,
+    page_size: 20,
+    total_pages: 0
+  }
+}
+```
+
+---
+
+## ✨ 优化记录
+
+### 已完成的优化
+
+1. ✅ **组件初始化加载**: 添加 `useEffect` 在组件挂载时立即加载世界书列表
+2. ✅ **格式统一**: 所有世界书文件转换为内部格式存储
+3. ✅ **代码简化**: 移除服务层的SillyTavern格式运行时兼容逻辑
+4. ✅ **分页控件**: 添加完整的分页UI（上一页、下一页、每页数量选择）
+5. ✅ **自动刷新**: 添加/更新/删除条目后自动刷新当前页
+
+---
+
+## 🧪 测试建议
+
+### 手动测试清单
+
+- [ ] 打开世界书页面，检查下拉框是否显示所有世界书
+- [ ] 选择一个世界书，检查是否正确加载第一页条目
+- [ ] 点击"下一页"，检查是否加载第二页
+- [ ] 改变每页数量（10/20/50/100），检查是否正确刷新
+- [ ] 创建新条目，检查是否刷新当前页
+- [ ] 更新条目，检查是否刷新当前页
+- [ ] 删除条目，检查是否刷新当前页
+- [ ] 切换到其他世界书，检查是否重置到第一页
+
+### API测试
+
+```bash
+# 获取世界书列表
+curl http://localhost:8000/api/worldbooks/
+
+# 获取条目（分页）
+curl "http://localhost:8000/api/worldbooks/卡立创-v5/entries?page=1&page_size=5"
+```
+
+---
+
+## 📝 结论
+
+✅ **前端世界书分页的所有功能都能正确发出请求到后端API**
+
+- 下拉框正确读取所有世界书
+- 分页参数正确传递
+- 数据格式匹配
+- 错误处理完善
+- 用户体验流畅
--- a/backend/Dockerfile
+++ b/backend/Dockerfile
@@ -4,20 +4,24 @@ FROM python:3.11-slim
 # 设置工作目录
 WORKDIR /app

+# 设置环境变量
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+
 # 复制依赖文件
 COPY requirements.txt .

 # 安装依赖
-RUN pip install --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 安装 Pillow（使用阿里云镜像源）
+RUN pip install --no-cache-dir Pillow -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com || echo "Pillow installation failed, will install manually"

 # 复制所有代码
-# 修改点：把当前目录（即 backend/）的内容复制到 /app/backend/ 下
-# 这样镜像内的结构就是 /app/backend/api/route.py
-COPY . /app/backend/
+COPY . .

 # 暴露端口
 EXPOSE 8000

 # 启动命令
-# 修改点：路径改为 backend.api.route (对应 /app/backend/api/route.py)
-CMD ["uvicorn", "backend.api.route:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
--- a/backend/pycache/init.cpython-311.pyc
+++ b/backend/pycache/init.cpython-311.pyc
--- a/backend/pycache/main.cpython-311.pyc
+++ b/backend/pycache/main.cpython-311.pyc
--- a/backend/api/pycache/init.cpython-311.pyc
+++ b/backend/api/pycache/init.cpython-311.pyc
--- a/backend/api/pycache/route.cpython-311.pyc
+++ b/backend/api/pycache/route.cpython-311.pyc
--- a/backend/api/route.py
+++ b/backend/api/route.py
@@ -1,20 +1,20 @@
 from fastapi import APIRouter
-from ..core.items import ChatRequest
-from ..tools.get_all_role_and_chat import get_all_role_and_chat
-from ..core.models import chat_history
+from .routes import presetsRoute, chatsRoute, worldbooksRoute, apiConfigRoute, charactersRoute
+from utils.file_utils import get_all_roles_and_chats
+from core.config import settings
+from pathlib import Path

 router = APIRouter()

-# 1. 从本地读取所有的data内容
+# 注册子路由
+router.include_router(presetsRoute.router)
+router.include_router(chatsRoute.router)
+router.include_router(worldbooksRoute.router)
+router.include_router(apiConfigRoute.router)
+router.include_router(charactersRoute.router)
+
+
+# 保留原有的其他路由
@router.get("/tool_bar/get_all_role_and_chat")
 def get_all_role_and_chat_endpoint():
-    # 正确调用函数并返回结果
-    return get_all_role_and_chat()
-
-# 2. 根据rolename和chatname读取特定聊天记录
-@router.post("/chat_box/get_chat_history")
-async def get_chat_history_endpoint(role_name: str, chat_name: str):
-    # 实例化工具类
-    reader = chat_history.load_from_file(role_name, chat_name)
-
-    return reader.to_chatbox_format()
+	return get_all_roles_and_chats(Path(settings.DATA_PATH))
--- a/backend/api/routes/apiConfigRoute.py
+++ b/backend/api/routes/apiConfigRoute.py
@@ -0,0 +1,389 @@
+from fastapi import APIRouter, HTTPException, UploadFile, File
+from pydantic import BaseModel, Field
+from typing import Dict, Optional, List, Any
+import json
+import os
+from pathlib import Path
+from core.config import settings
+from cryptography.fernet import Fernet
+import base64
+from services.comfyui_workflow_manager import workflow_manager
+from services.llm_model_service import LLMModelService
+
+router = APIRouter(prefix="/api-config", tags=["API Configuration"])
+
+# 加密密钥（实际项目中应该从环境变量读取）
+ENCRYPTION_KEY = os.getenv('API_ENCRYPTION_KEY', Fernet.generate_key().decode())
+fernet = Fernet(ENCRYPTION_KEY.encode() if isinstance(ENCRYPTION_KEY, str) else ENCRYPTION_KEY)
+
+# 配置文件路径
+CONFIG_DIR = Path(settings.DATA_PATH) / "apiconfig"
+CONFIG_DIR.mkdir(parents=True, exist_ok=True)
+
+
+class ApiConfigItem(BaseModel):
+    """单个 API 配置项"""
+    id: Optional[str] = None
+    name: Optional[str] = ""
+    category: Optional[str] = None  # mainLLM, imageModel, secondaryLLM, ragEmbedding
+    apiUrl: Optional[str] = ""
+    apiKey: Optional[str] = None  # 前端传入的可能是明文或空
+    model: Optional[str] = ""
+    
+    # 生图模型的特殊字段
+    mode: Optional[str] = None  # 'local' | 'cloud'
+    local: Optional[dict] = None
+    cloud: Optional[dict] = None
+
+
+class ProfileSaveRequest(BaseModel):
+    """保存配置文件的请求"""
+    profileId: str
+    name: Optional[str] = None
+    apis: Dict[str, ApiConfigItem]  # key 是 category，value 是配置
+
+
+class ProfileResponse(BaseModel):
+    """配置文件响应（不包含明文 API Key）"""
+    id: str
+    name: str
+    apis: Dict[str, dict]  # apiKey 字段会被移除或脱敏
+
+
+def encrypt_api_key(api_key: str) -> str:
+    """加密 API Key"""
+    if not api_key:
+        return ""
+    encrypted = fernet.encrypt(api_key.encode())
+    return base64.urlsafe_b64encode(encrypted).decode()
+
+
+def decrypt_api_key(encrypted_key: str) -> str:
+    """解密 API Key（仅在后端内部使用）"""
+    if not encrypted_key:
+        return ""
+    try:
+        decoded = base64.urlsafe_b64decode(encrypted_key.encode())
+        decrypted = fernet.decrypt(decoded)
+        return decrypted.decode()
+    except Exception:
+        return ""
+
+
+def mask_api_key(api_key: str) -> str:
+    """脱敏 API Key（返回给前端）"""
+    if not api_key or len(api_key) < 8:
+        return "****"
+    return api_key[:4] + "****" + api_key[-4:]
+
+
+def load_profile(profile_id: str) -> Optional[dict]:
+    """加载配置文件"""
+    config_file = CONFIG_DIR / f"{profile_id}.json"
+    if not config_file.exists():
+        return None
+    
+    with open(config_file, 'r', encoding='utf-8') as f:
+        return json.load(f)
+
+
+def save_profile(profile_id: str, profile_data: dict):
+    """保存配置文件"""
+    config_file = CONFIG_DIR / f"{profile_id}.json"
+    with open(config_file, 'w', encoding='utf-8') as f:
+        json.dump(profile_data, f, ensure_ascii=False, indent=2)
+
+
+def list_profiles() -> List[dict]:
+    """列出所有配置文件"""
+    profiles = []
+    for config_file in CONFIG_DIR.glob("*.json"):
+        try:
+            with open(config_file, 'r', encoding='utf-8') as f:
+                profile = json.load(f)
+                profiles.append({
+                    "id": profile.get("id", config_file.stem),
+                    "name": profile.get("name", config_file.stem),
+                    "createdAt": profile.get("createdAt", "")
+                })
+        except Exception:
+            continue
+    return profiles
+
+
+@router.get("/profiles", response_model=List[dict])
+def get_all_profiles():
+    """获取所有配置文件列表"""
+    return list_profiles()
+
+
+@router.get("/profiles/{profile_id}", response_model=ProfileResponse)
+def get_profile(profile_id: str):
+    """获取单个配置文件（API Key 已脱敏）"""
+    profile = load_profile(profile_id)
+    if not profile:
+        raise HTTPException(status_code=404, detail="配置文件不存在")
+    
+    # 脱敏所有 API Key
+    masked_apis = {}
+    for category, api_config in profile.get("apis", {}).items():
+        masked_config = api_config.copy()
+        if "apiKey" in masked_config and masked_config["apiKey"]:
+            masked_config["apiKey"] = mask_api_key(masked_config["apiKey"])
+        masked_apis[category] = masked_config
+    
+    return {
+        "id": profile.get("id", profile_id),
+        "name": profile.get("name", profile_id),
+        "apis": masked_apis
+    }
+
+
+@router.post("/profiles", response_model=ProfileResponse)
+def create_or_update_profile(request: ProfileSaveRequest):
+    """创建或更新配置文件（增量更新）"""
+    # 加载现有配置
+    existing_profile = load_profile(request.profileId)
+    
+    if existing_profile:
+        # 更新现有配置：只更新提供的 API 配置
+        for category, api_config in request.apis.items():
+            api_config_dict = api_config.dict(exclude_none=True)
+            
+            # 处理 API Key 加密
+            if api_config.apiKey and api_config.apiKey != "****":
+                # 如果是新的明文 key，加密它
+                api_config_dict["apiKey"] = encrypt_api_key(api_config.apiKey)
+            elif api_config.apiKey == "****":
+                # 如果是脱敏的 key，保留原有的加密 key
+                if category in existing_profile.get("apis", {}):
+                    api_config_dict["apiKey"] = existing_profile["apis"][category].get("apiKey", "")
+                else:
+                    api_config_dict.pop("apiKey", None)
+            
+            # 更新配置
+            if "apis" not in existing_profile:
+                existing_profile["apis"] = {}
+            existing_profile["apis"][category] = api_config_dict
+        
+        profile_data = existing_profile
+    else:
+        # 新建配置文件
+        from datetime import datetime
+        profile_data = {
+            "id": request.profileId,
+            "name": request.name or request.profileId,
+            "createdAt": datetime.now().isoformat(),
+            "apis": {}
+        }
+        
+        # 添加所有 API 配置
+        for category, api_config in request.apis.items():
+            api_config_dict = api_config.dict(exclude_none=True)
+            if api_config_dict.get("apiKey"):
+                api_config_dict["apiKey"] = encrypt_api_key(api_config_dict["apiKey"])
+            profile_data["apis"][category] = api_config_dict
+    
+    # 保存配置文件
+    save_profile(request.profileId, profile_data)
+    
+    # 返回脱敏后的数据
+    masked_apis = {}
+    for category, api_config in profile_data.get("apis", {}).items():
+        masked_config = api_config.copy()
+        if "apiKey" in masked_config and masked_config["apiKey"]:
+            masked_config["apiKey"] = mask_api_key(masked_config["apiKey"])
+        masked_apis[category] = masked_config
+    
+    return {
+        "id": profile_data.get("id", request.profileId),
+        "name": profile_data.get("name", request.profileId),
+        "apis": masked_apis
+    }
+
+
+@router.delete("/profiles/{profile_id}")
+def delete_profile(profile_id: str):
+    """删除配置文件"""
+    config_file = CONFIG_DIR / f"{profile_id}.json"
+    if not config_file.exists():
+        raise HTTPException(status_code=404, detail="配置文件不存在")
+    
+    config_file.unlink()
+    return {"message": "配置文件已删除"}
+
+
+@router.post("/test-connection")
+def test_connection(api_config: ApiConfigItem):
+    """测试 API 连接并获取模型列表"""
+    try:
+        # 检测提供商类型
+        provider = LLMModelService.detect_provider(api_config.apiUrl)
+        
+        # 获取模型列表
+        models = LLMModelService.get_models_by_provider(
+            provider=provider,
+            api_key=api_config.apiKey or "",
+            api_url=api_config.apiUrl
+        )
+        
+        return {
+            "success": True,
+            "models": models,
+            "provider": provider,
+            "message": f"成功获取 {len(models)} 个模型"
+        }
+    
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"获取模型列表失败: {str(e)}"
+        )
+
+
+# ==================== ComfyUI Workflow Management ====================
+
+@router.get("/comfyui/workflows", response_model=List[Dict[str, Any]])
+def get_comfyui_workflows():
+    """获取所有可用的 ComfyUI 工作流列表"""
+    return workflow_manager.list_workflows()
+
+
+@router.post("/comfyui/workflows/upload")
+async def upload_comfyui_workflow(file: UploadFile = File(...)):
+    """上传 ComfyUI 工作流 JSON 文件"""
+    return await workflow_manager.upload_workflow(file)
+
+
+@router.delete("/comfyui/workflows/{filename}")
+def delete_comfyui_workflow(filename: str):
+    """删除 ComfyUI 工作流文件"""
+    return workflow_manager.delete_workflow(filename)
+
+
+@router.get("/comfyui/workflows/{filename}")
+def get_comfyui_workflow(filename: str):
+    """获取指定工作流的详细内容"""
+    return workflow_manager.load_workflow(filename)
+
+
+# ==================== Connection Testing ====================
+
+@router.post("/test-comfyui-connection")
+def test_comfyui_connection(request: dict):
+    """测试 ComfyUI 连接"""
+    import requests as req
+    
+    api_url = request.get("apiUrl", "http://comfyui:8188")
+    
+    try:
+        # 测试基本连通性
+        response = req.get(f"{api_url}/system_stats", timeout=5)
+        
+        if response.status_code != 200:
+            return {
+                "success": False,
+                "message": f"HTTP {response.status_code}"
+            }
+        
+        stats = response.json()
+        
+        return {
+            "success": True,
+            "message": "连接成功",
+            "stats": {
+                "vram_total": stats.get("vram_total", 0),
+                "vram_free": stats.get("vram_free", 0),
+                "torch_version": stats.get("torch_version", ""),
+                "device": stats.get("device", "")
+            }
+        }
+    
+    except req.exceptions.ConnectionError:
+        return {
+            "success": False,
+            "message": "无法连接到 ComfyUI，请检查地址和端口"
+        }
+    except req.exceptions.Timeout:
+        return {
+            "success": False,
+            "message": "连接超时，请检查 ComfyUI 是否正常运行"
+        }
+    except Exception as e:
+        return {
+            "success": False,
+            "message": f"错误: {str(e)}"
+        }
+
+
+@router.post("/test-cloud-connection")
+def test_cloud_connection(request: dict):
+    """测试云端 API 连接"""
+    import openai
+    
+    provider = request.get("provider", "dall-e")
+    api_key = request.get("apiKey", "")
+    model = request.get("model", "dall-e-3")
+    
+    if not api_key:
+        return {
+            "success": False,
+            "message": "API Key 不能为空"
+        }
+    
+    try:
+        if provider == "dall-e":
+            # 测试 DALL-E
+            client = openai.OpenAI(api_key=api_key)
+            
+            # 尝试获取模型列表（轻量级测试）
+            models = client.models.list()
+            
+            # 检查指定的模型是否存在
+            model_exists = any(m.id == model for m in models.data)
+            
+            if model_exists:
+                return {
+                    "success": True,
+                    "message": f"连接成功，模型 {model} 可用"
+                }
+            else:
+                return {
+                    "success": False,
+                    "message": f"模型 {model} 不可用"
+                }
+        
+        elif provider == "stability":
+            # 测试 Stability AI
+            import requests as req
+            
+            response = req.get(
+                "https://api.stability.ai/v1/engines/list",
+                headers={
+                    "Authorization": f"Bearer {api_key}"
+                },
+                timeout=5
+            )
+            
+            if response.status_code == 200:
+                return {
+                    "success": True,
+                    "message": "连接成功"
+                }
+            else:
+                return {
+                    "success": False,
+                    "message": f"HTTP {response.status_code}: {response.text}"
+                }
+        
+        else:
+            return {
+                "success": False,
+                "message": f"不支持的提供商: {provider}"
+            }
+    
+    except Exception as e:
+        return {
+            "success": False,
+            "message": f"连接失败: {str(e)}"
+        }
--- a/backend/api/routes/charactersRoute.py
+++ b/backend/api/routes/charactersRoute.py
@@ -0,0 +1,292 @@
+"""
+角色卡 API 路由
+"""
+from fastapi import APIRouter, HTTPException, UploadFile, File
+from fastapi.responses import FileResponse, StreamingResponse
+from typing import List
+from pathlib import Path
+import io
+
+try:
+    from backend.services.character_service import CharacterService
+except ImportError:
+    from services.character_service import CharacterService
+
+router = APIRouter(prefix="/characters", tags=["characters"])
+character_service = CharacterService()
+
+
+@router.get("/", response_model=List[dict])
+async def list_characters():
+    """
+    获取所有角色卡列表
+    
+    Returns:
+        按最后聊天时间排序的角色卡列表
+    """
+    characters = character_service.scan_all_characters()
+    return [c.dict() for c in characters]
+
+
+@router.get("/{name}", response_model=dict)
+async def get_character(name: str):
+    """
+    获取指定角色卡
+    
+    Args:
+        name: 角色名（URL编码）
+    """
+    character = character_service.get_character_by_name(name)
+    if not character:
+        raise HTTPException(status_code=404, detail=f"角色 '{name}' 不存在")
+    
+    return character.dict()
+
+
+@router.post("/", response_model=dict)
+async def create_character(character_data: dict):
+    """
+    创建新角色卡
+    
+    Request Body:
+        {
+            "name": "角色名",
+            "description": "描述",
+            "personality": "性格",
+            "scenario": "场景",
+            "first_mes": "开场白",
+            "categories": ["分类1", "分类2"],
+            "tags": ["tag1", "tag2"]
+        }
+    """
+    try:
+        character = character_service.create_character(character_data)
+        return {
+            "success": True,
+            "character": character.dict()
+        }
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.put("/{name}", response_model=dict)
+async def update_character(name: str, updates: dict):
+    """
+    更新角色卡
+    
+    Args:
+        name: 角色名
+        updates: 要更新的字段
+    """
+    try:
+        character = character_service.update_character(name, updates)
+        return {
+            "success": True,
+            "character": character.dict()
+        }
+    except FileNotFoundError:
+        raise HTTPException(status_code=404, detail=f"角色 '{name}' 不存在")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.delete("/{name}")
+async def delete_character(name: str):
+    """
+    删除角色卡及其所有聊天记录
+    """
+    success = character_service.delete_character(name)
+    if not success:
+        raise HTTPException(status_code=404, detail=f"角色 '{name}' 不存在")
+    
+    return {"success": True, "message": f"角色 '{name}' 已删除"}
+
+
+@router.get("/{name}/avatar")
+async def get_avatar(name: str):
+    """
+    获取角色头像
+    
+    Returns:
+        PNG 图片文件或 404
+    """
+    char_folder = character_service.characters_dir / name
+    avatar_file = char_folder / "avatar.png"
+    
+    if not avatar_file.exists():
+        # 返回默认头像
+        default_avatar = Path("data/images/avatars/fallback.png")
+        if default_avatar.exists():
+            return FileResponse(default_avatar, media_type="image/png")
+        raise HTTPException(status_code=404, detail="头像不存在")
+    
+    return FileResponse(avatar_file, media_type="image/png")
+
+
+@router.post("/{name}/avatar")
+async def upload_avatar(name: str, file: UploadFile = File(...)):
+    """
+    上传角色头像
+    
+    Args:
+        name: 角色名
+        file: PNG 图片文件
+    """
+    # 验证文件类型
+    if not file.content_type.startswith('image/'):
+        raise HTTPException(status_code=400, detail="只支持图片文件")
+    
+    # 检查角色是否存在
+    character = character_service.get_character_by_name(name)
+    if not character:
+        raise HTTPException(status_code=404, detail=f"角色 '{name}' 不存在")
+    
+    # 保存图片
+    image_data = await file.read()
+    avatar_path = character_service.save_avatar(name, image_data)
+    
+    return {
+        "success": True,
+        "avatar_path": avatar_path
+    }
+
+
+@router.get("/{name}/chats")
+async def list_chats(name: str):
+    """
+    获取角色的所有聊天列表
+    
+    Returns:
+        聊天文件列表（包含最后一条消息预览）
+    """
+    char_folder = character_service.characters_dir / name
+    chats_dir = char_folder / "chats"
+    
+    if not chats_dir.exists():
+        return {"chats": []}
+    
+    import json
+    from datetime import datetime
+    
+    chats = []
+    for chat_file in chats_dir.glob("*.jsonl"):
+        try:
+            with open(chat_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+            
+            if not lines:
+                continue
+            
+            # 第一行是header
+            header = json.loads(lines[0])
+            
+            # 计算消息数量（排除header）
+            message_count = len(lines) - 1
+            
+            # 获取最后修改时间
+            last_modified = datetime.fromtimestamp(
+                chat_file.stat().st_mtime
+            ).isoformat()
+            
+            # 获取最后一条消息预览
+            last_message = ""
+            if message_count > 0:
+                try:
+                    last_msg_data = json.loads(lines[-1])
+                    last_message = last_msg_data.get("mes", "")
+                except:
+                    pass
+            
+            chats.append({
+                "chat_name": chat_file.stem,
+                "user_name": header.get("user_name", "User"),
+                "character_name": header.get("character_name", ""),
+                "last_modified": last_modified,
+                "message_count": message_count,
+                "last_message": last_message
+            })
+        except Exception as e:
+            # 如果解析失败，使用基本信息
+            chats.append({
+                "chat_name": chat_file.stem,
+                "last_modified": datetime.fromtimestamp(chat_file.stat().st_mtime).isoformat(),
+                "message_count": 0,
+                "last_message": ""
+            })
+    
+    # 按修改时间排序
+    chats.sort(key=lambda c: c.get('last_modified', ''), reverse=True)
+    
+    return {"chats": chats}
+
+
+@router.post("/import")
+async def import_character(file: UploadFile = File(...)):
+    """
+    导入角色卡（支持 PNG 或 JSON）
+    
+    - PNG: 自动提取嵌入数据，创建文件夹
+    - JSON: 创建文件夹并保存
+    """
+    content = await file.read()
+    filename = file.filename
+    
+    if filename.endswith('.png'):
+        # 导入 PNG
+        try:
+            character = character_service.import_from_png(content, filename)
+            
+            return {
+                "success": True,
+                "character": character.dict(),
+                "format": "png_embedded"
+            }
+        
+        except ValueError as e:
+            raise HTTPException(status_code=400, detail=str(e))
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"导入失败: {str(e)}")
+    
+    elif filename.endswith('.json'):
+        # 导入 JSON
+        try:
+            import json
+            data = json.loads(content.decode('utf-8'))
+            
+            character = character_service.create_character(data)
+            
+            return {
+                "success": True,
+                "character": character.dict(),
+                "format": "json"
+            }
+        
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"导入失败: {str(e)}")
+    
+    else:
+        raise HTTPException(status_code=400, detail="不支持的文件格式")
+
+
+@router.post("/{name}/export/png")
+async def export_character_as_png(name: str):
+    """
+    导出角色为 SillyTavern PNG 格式
+    
+    Returns:
+        PNG 文件下载
+    """
+    try:
+        png_data = character_service.export_as_png(name)
+        
+        return StreamingResponse(
+            io.BytesIO(png_data),
+            media_type="image/png",
+            headers={
+                "Content-Disposition": f"attachment; filename={name}.png"
+            }
+        )
+    except FileNotFoundError:
+        raise HTTPException(status_code=404, detail=f"角色 '{name}' 不存在")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"导出失败: {str(e)}")
--- a/backend/api/routes/chatsRoute.py
+++ b/backend/api/routes/chatsRoute.py
@@ -0,0 +1,112 @@
+from fastapi import APIRouter, HTTPException, status
+from pathlib import Path
+try:
+    from backend.services.chat_service import ChatService
+    from backend.core.config import settings
+except ImportError:
+    # Docker环境：直接从当前目录导入
+    from services.chat_service import ChatService
+    from core.config import settings
+
+router = APIRouter(prefix="/chat", tags=["chat"])
+
+# 初始化聊天服务
+data_path = Path(settings.DATA_PATH) if hasattr(settings, 'DATA_PATH') else Path("data")
+chat_service = ChatService(data_path)
+
+@router.get("", response_model=dict)
+async def list_all_chats():
+	"""获取所有角色的所有聊天列表"""
+	return chat_service.list_all_chats()
+
+@router.get("/{role_name}")
+async def list_role_chats(role_name: str):
+	"""获取指定角色的所有聊天列表"""
+	try:
+		all_chats = chat_service.list_all_chats()
+		# 从所有聊天中筛选出该角色的聊天
+		role_chats = all_chats.get(role_name, [])
+		return role_chats
+	except Exception as e:
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.get("/{role_name}/{chat_name}")
+async def get_chat(role_name: str, chat_name: str):
+	"""获取指定聊天的完整内容"""
+	try:
+		return chat_service.get_chat(role_name, chat_name)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+
+@router.post("/{role_name}", status_code=status.HTTP_201_CREATED)
+async def create_chat(role_name: str, chat_data: dict):
+	"""创建新聊天"""
+	try:
+		chat_name = chat_data.get("chat_name", "新聊天")
+		metadata = chat_data.get("metadata", {})
+		return chat_service.create_chat(role_name, chat_name, metadata)
+	except FileExistsError as e:
+		raise HTTPException(status_code=400, detail=str(e))
+
+@router.put("/{role_name}/{chat_name}")
+async def update_chat(role_name: str, chat_name: str, update_data: dict):
+	"""更新聊天元数据"""
+	# TODO: 实现更新聊天元数据功能
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.delete("/{role_name}/{chat_name}")
+async def delete_chat(role_name: str, chat_name: str):
+	"""删除指定聊天"""
+	# TODO: 实现删除聊天功能
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.get("/{role_name}/{chat_name}/messages")
+async def list_messages(role_name: str, chat_name: str):
+	"""获取聊天的所有消息"""
+	try:
+		chat_data = chat_service.get_chat(role_name, chat_name)
+		return {"messages": chat_data["messages"]}
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+
+@router.get("/{role_name}/{chat_name}/messages/{floor}")
+async def get_message(role_name: str, chat_name: str, floor: int):
+	"""获取指定楼层的消息"""
+	try:
+		chat_data = chat_service.get_chat(role_name, chat_name)
+		for msg in chat_data["messages"]:
+			if msg.get("floor") == floor:
+				return msg
+		raise HTTPException(status_code=404, detail=f"Message at floor {floor} not found")
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+
+@router.post("/{role_name}/{chat_name}/messages", status_code=status.HTTP_201_CREATED)
+async def add_message(role_name: str, chat_name: str, message_data: dict):
+	"""向聊天添加新消息"""
+	try:
+		return chat_service.add_message(role_name, chat_name, message_data)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except ValueError as e:
+		raise HTTPException(status_code=400, detail=str(e))
+
+@router.put("/{role_name}/{chat_name}/messages/{floor}")
+async def update_message(role_name: str, chat_name: str, floor: int, update_data: dict):
+	"""更新指定楼层的消息"""
+	try:
+		return chat_service.update_message(role_name, chat_name, floor, update_data)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except ValueError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+
+@router.delete("/{role_name}/{chat_name}/messages/{floor}")
+async def delete_message(role_name: str, chat_name: str, floor: int):
+	"""删除指定楼层的消息"""
+	try:
+		return chat_service.delete_message(role_name, chat_name, floor)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except ValueError as e:
+		raise HTTPException(status_code=404, detail=str(e))
--- a/backend/api/routes/presetsRoute.py
+++ b/backend/api/routes/presetsRoute.py
@@ -0,0 +1,60 @@
+from fastapi import APIRouter, HTTPException, status
+# TODO: 实现 PresetService 来替代旧的 AIDesignSpec 逻辑
+# from services.preset_service import PresetService
+
+router = APIRouter(prefix="/presets", tags=["presets"])
+
+@router.get("", response_model=dict)
+async def list_presets():
+	"""获取所有预设列表及其基本信息"""
+	# return await PresetService.list_all_presets()
+	return {"presets": []}
+
+@router.get("/{preset_name}")
+async def get_preset(preset_name: str):
+	"""获取指定预设的完整内容"""
+	# try:
+	# 	return await PresetService.get_preset(preset_name)
+	# except FileNotFoundError:
+	# 	raise HTTPException(status_code=404, detail="Preset not found")
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.post("", status_code=status.HTTP_201_CREATED)
+async def create_preset(preset_name: str, preset_data: dict):
+	"""创建新预设"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.put("/{preset_name}")
+async def update_preset(preset_name: str, update_data: dict):
+	"""更新预设配置"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.delete("/{preset_name}")
+async def delete_preset(preset_name: str):
+	"""删除指定预设"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.get("/{preset_name}/components")
+async def list_preset_components(preset_name: str):
+	"""获取预设中的所有组件"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.get("/{preset_name}/components/{component_id}")
+async def get_preset_component(preset_name: str, component_id: str):
+	"""获取指定组件的详情"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.post("/{preset_name}/components", status_code=status.HTTP_201_CREATED)
+async def add_preset_component(preset_name: str, component_data: dict):
+	"""向预设添加新组件"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.put("/{preset_name}/components/{component_id}")
+async def update_preset_component(preset_name: str, component_id: str, update_data: dict):
+	"""更新指定组件"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
+
+@router.delete("/{preset_name}/components/{component_id}")
+async def delete_preset_component(preset_name: str, component_id: str):
+	"""从预设中删除指定组件"""
+	raise HTTPException(status_code=501, detail="Not Implemented")
--- a/backend/api/routes/worldbooksRoute.py
+++ b/backend/api/routes/worldbooksRoute.py
@@ -0,0 +1,253 @@
+# 标准库导入
+import os
+import json
+import shutil
+import logging
+from pathlib import Path
+from typing import List, Dict, Any, Optional
+
+# 第三方库导入
+from fastapi import APIRouter, HTTPException, UploadFile, File, Form
+from fastapi.responses import JSONResponse, FileResponse
+
+# 本地模块导入
+from models.internal import WorldInfo, WorldInfoEntry
+from core.config import settings
+from services.worldbook_service import worldbook_service
+
+# 配置日志
+logger = logging.getLogger(__name__)
+
+# 创建路由器
+router = APIRouter(prefix="/worldbooks", tags=["worldbooks"])
+
+# 确保世界书目录存在 (由 config.py 中的 settings.ensure_directories() 统一处理，此处保留作为双重保险)
+os.makedirs(settings.WORLDBOOKS_PATH, exist_ok=True)
+
+
+@router.get("/", response_model=List[Dict[str, Any]])
+async def list_worldbooks():
+	"""
+	获取所有世界书的列表
+	Returns:
+		List[Dict[str, Any]]: 世界书列表
+	"""
+	try:
+		return worldbook_service.list_worldbooks()
+	except Exception as e:
+		logger.error(f"Failed to list worldbooks: {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.get("/{name}", response_model=Dict[str, Any])
+async def get_worldbook(name: str):
+	"""
+	获取指定名称的世界书
+	"""
+	try:
+		return worldbook_service.get_worldbook(name)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to get worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.post("/", response_model=Dict[str, Any])
+async def create_worldbook(
+		name: str = Form(...),
+		description: str = Form(""),
+		file: Optional[UploadFile] = File(None)
+):
+	"""
+	创建新世界书（可选择导入文件）
+	"""
+	try:
+		# 如果提供了文件，从 SillyTavern 格式导入
+		if file:
+			content = await file.read()
+			st_data = json.loads(content.decode('utf-8'))
+			return worldbook_service.import_from_sillytavern(name, st_data)
+		else:
+			# 创建空世界书
+			return worldbook_service.create_worldbook(name, description)
+	except ValueError as e:
+		raise HTTPException(status_code=400, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to create worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.put("/{name}", response_model=Dict[str, Any])
+async def update_worldbook(
+		name: str,
+		description: Optional[str] = Form(None)
+):
+	"""
+	更新世界书基本信息
+	"""
+	try:
+		return worldbook_service.update_worldbook(name, description)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to update worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.delete("/{name}")
+async def delete_worldbook(name: str):
+	"""
+	删除世界书
+	"""
+	try:
+		worldbook_service.delete_worldbook(name)
+		return {"message": f"Worldbook '{name}' deleted successfully"}
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to delete worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.get("/{name}/entries", response_model=Dict[str, Any])
+async def list_worldbook_entries(
+    name: str,
+    page: int = 1,
+    page_size: int = 20
+):
+	"""
+	获取世界书的条目列表（支持分页）
+	
+	Args:
+		name: 世界书名称
+		page: 页码，从1开始
+		page_size: 每页数量，默认20
+	"""
+	try:
+		return worldbook_service.list_entries(name, page, page_size)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to list entries for worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.get("/{name}/entries/{uid}", response_model=Dict[str, Any])
+async def get_worldbook_entry(name: str, uid: str):
+	"""
+	获取世界书的指定条目
+	"""
+	try:
+		return worldbook_service.get_entry(name, uid)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to get entry '{uid}' from worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.post("/{name}/entries", response_model=Dict[str, Any])
+async def create_worldbook_entry(name: str, entry_data: Dict[str, Any]):
+	"""
+	在世界书中创建新条目
+	"""
+	try:
+		return worldbook_service.create_entry(name, entry_data)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to create entry in worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.put("/{name}/entries/{uid}", response_model=Dict[str, Any])
+async def update_worldbook_entry(name: str, uid: str, entry_data: Dict[str, Any]):
+	"""
+	更新世界书的指定条目
+	"""
+	try:
+		return worldbook_service.update_entry(name, uid, entry_data)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to update entry '{uid}' in worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.delete("/{name}/entries/{uid}")
+async def delete_worldbook_entry(name: str, uid: str):
+	"""
+	删除世界书的指定条目
+	"""
+	try:
+		worldbook_service.delete_entry(name, uid)
+		return {"message": f"Entry '{uid}' deleted successfully"}
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to delete entry '{uid}' from worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.post("/{name}/import", response_model=Dict[str, Any])
+async def import_worldbook(name: str, file: UploadFile = File(...)):
+	"""
+	从文件导入世界书(自动检测 SillyTavern 或内部格式)
+	"""
+	try:
+		content = await file.read()
+		data = json.loads(content.decode('utf-8'))
+		
+		# 智能检测格式
+		from models.converters import WorldBookConverter
+		format_type = WorldBookConverter.detect_format(data)
+		
+		logger.info(f"检测到世界书格式: {format_type}")
+		
+		if format_type == "sillytavern":
+			# SillyTavern 格式,需要转换
+			logger.info(f"正在转换 SillyTavern 格式为内部格式")
+			return worldbook_service.import_from_sillytavern(name, data)
+		elif format_type == "internal":
+			# 已经是内部格式,直接保存
+			logger.info(f"检测到内部格式,直接保存")
+			return worldbook_service.import_internal_format(name, data)
+		else:
+			raise HTTPException(status_code=400, detail="无法识别的世界书格式")
+			
+	except json.JSONDecodeError:
+		raise HTTPException(status_code=400, detail="Invalid JSON format")
+	except ValueError as e:
+		raise HTTPException(status_code=400, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to import worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
+
+@router.get("/{name}/export")
+async def export_worldbook(name: str, format: str = "internal"):
+	"""
+	导出世界书(支持 internal 和 sillytavern 两种格式)
+	
+	Args:
+		name: 世界书名称
+		format: 导出格式 ('internal' 或 'sillytavern'),默认 internal
+	"""
+	try:
+		if format.lower() == "sillytavern":
+			# 导出为 SillyTavern 格式(可能丢失特殊设置)
+			logger.info(f"导出世界书 '{name}' 为 SillyTavern 格式")
+			st_data = worldbook_service.export_to_sillytavern(name)
+			
+			return JSONResponse(
+				content=st_data,
+				headers={
+					"Content-Disposition": f"attachment; filename={name}_sillytavern.json"
+				}
+			)
+		else:
+			# 导出为内部格式(保留所有设置)
+			logger.info(f"导出世界书 '{name}' 为内部格式")
+			internal_data = worldbook_service.get_worldbook(name)
+			
+			return JSONResponse(
+				content=internal_data,
+				headers={
+					"Content-Disposition": f"attachment; filename={name}.json"
+				}
+			)
+	except FileNotFoundError as e:
+		raise HTTPException(status_code=404, detail=str(e))
+	except Exception as e:
+		logger.error(f"Failed to export worldbook '{name}': {str(e)}")
+		raise HTTPException(status_code=500, detail=str(e))
--- a/backend/core/pycache/init.cpython-311.pyc
+++ b/backend/core/pycache/init.cpython-311.pyc
--- a/backend/core/pycache/config.cpython-311.pyc
+++ b/backend/core/pycache/config.cpython-311.pyc
--- a/backend/core/pycache/config.cpython-39.pyc
+++ b/backend/core/pycache/config.cpython-39.pyc
--- a/backend/core/pycache/items.cpython-311.pyc
+++ b/backend/core/pycache/items.cpython-311.pyc
--- a/backend/core/config.py
+++ b/backend/core/config.py
@@ -3,46 +3,89 @@ from pathlib import Path
 from dotenv import load_dotenv

 # 1. 动态计算项目根目录
-# 假设 config.py 位于 backend/ 目录下
+# 假设 config.py 位于 backend/core/ 目录下
 # __file__ 指向本文件的绝对路径
-# .parent 指向 backend/ 目录
-# .parent.parent 指向项目根目录 (即包含 backend/ 和 frontend/ 的目录)
+# .parent 指向 backend/core/ 目录
+# .parent.parent 指向 backend/ 目录
+# .parent.parent.parent 指向项目根目录 (即包含 backend/ 和 frontend/ 的目录)
 PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
+
 # 2. 加载 .env 文件
 # 假设 .env 文件位于项目根目录下
 load_dotenv(PROJECT_ROOT / ".env")


 class Settings:
-    # --- 主模型配置 ---
-    MAIN_LLM_API_KEY = os.getenv("MAIN_LLM_API_KEY")
-    MAIN_LLM_MODEL = os.getenv("MAIN_LLM_MODEL", "gpt-3.5-turbo")
-    MAIN_LLM_BASE_URL = os.getenv("MAIN_LLM_BASE_URL", "https://api.openai.com/v1")
-    MAIN_LLM_MAX_TOKENS = int(os.getenv("MAIN_LLM_MAX_TOKENS", "4096"))
-    MAIN_LLM_STREAM = os.getenv("MAIN_LLM_STREAM", "true").lower() == "true"
+	# --- 主模型配置 ---
+	MAIN_LLM_API_KEY = os.getenv("MAIN_LLM_API_KEY")
+	MAIN_LLM_MODEL = os.getenv("MAIN_LLM_MODEL", "gpt-3.5-turbo")
+	MAIN_LLM_BASE_URL = os.getenv("MAIN_LLM_BASE_URL", "https://api.openai.com/v1")
+	MAIN_LLM_MAX_TOKENS = int(os.getenv("MAIN_LLM_MAX_TOKENS", "4096"))
+	MAIN_LLM_STREAM = os.getenv("MAIN_LLM_STREAM", "true").lower() == "true"

-    # --- 路径配置 (核心修改) ---
+	# --- 路径配置 (核心修改) ---

-    # 强制使用计算出的项目根目录，不再依赖 .env 中的 BASE_PATH
-    BASE_PATH = PROJECT_ROOT
+	# 强制使用计算出的项目根目录，不再依赖 .env 中的 BASE_PATH
+	BASE_PATH = PROJECT_ROOT

-    # 数据目录：固定为根目录下的 data 文件夹
-    # 即使 .env 里写了 DATA_PATH=/data，这里也会强制指向项目根目录下的 data
-    DATA_PATH = BASE_PATH / "data"
+	# 数据目录：固定为根目录下的 data 文件夹
+	DATA_PATH = BASE_PATH / "data"
+
+	# --- 核心数据文件路径 ---
+	STATE_FILE = DATA_PATH / "state.json"
+	SCHEMA_FILE = DATA_PATH / "schema.json"
+	PRESETS_FILE = DATA_PATH / "presets.json"
+	REGEX_FILE = DATA_PATH / "regex_rules.json"
+	VECTORSTORE_PATH = DATA_PATH / "vectorstore"
+
+	# --- 业务数据目录 ---
+
+	# 世界书目录
+	WORLDBOOKS_PATH = DATA_PATH / "worldbooks"
+
+	# 预设目录
+	PRESET_PATH = DATA_PATH / "preset"
+
+	# 聊天记录目录
+	CHAT_PATH = DATA_PATH / "chat"
+
+	# 临时文件目录
+	TEMP_PATH = DATA_PATH / "temp"
+
+	# ComfyUI 工作流目录
+	COMFYUI_WORKFLOWS_PATH = DATA_PATH / "comfyui_workflows"
+	
+	# 角色卡目录
+	CHARACTERS_PATH = DATA_PATH / "characters"
+	
+	# 图片资源目录
+	IMAGES_PATH = DATA_PATH / "images"
+
+	def ensure_directories(self):
+		"""确保所有配置的目录存在，如果不存在则创建"""
+		directories = [
+			self.DATA_PATH,
+			self.WORLDBOOKS_PATH,
+			self.PRESET_PATH,
+			self.CHAT_PATH,
+			self.TEMP_PATH,
+			self.COMFYUI_WORKFLOWS_PATH,
+			self.CHARACTERS_PATH,
+			self.IMAGES_PATH,
+		]
+		for directory in directories:
+			directory.mkdir(parents=True, exist_ok=True)

-    # 其他文件路径：基于 DATA_PATH 拼接
-    STATE_FILE = DATA_PATH / "state.json"
-    SCHEMA_FILE = DATA_PATH / "schema.json"
-    PRESETS_FILE = DATA_PATH / "presets.json"
-    REGEX_FILE = DATA_PATH / "regex_rules.json"
-    VECTORSTORE_PATH = DATA_PATH / "vectorstore"

 settings = Settings()

+# 初始化时自动创建必要的目录
+settings.ensure_directories()
+
 if __name__ == '__main__':
-    settings = Settings()
-    print(f"项目根目录: {settings.BASE_PATH}")
-    print(f"数据目录: {settings.DATA_PATH}")
-    print(f"聊天目录: {settings.DATA_PATH / 'chat'}")
-
-
+	settings = Settings()
+	print(f"项目根目录: {settings.BASE_PATH}")
+	print(f"数据目录: {settings.DATA_PATH}")
+	print(f"世界书目录: {settings.WORLDBOOKS_PATH}")
+	print(f"预设目录: {settings.PRESETS_PATH}")
+	print(f"聊天目录: {settings.CHAT_PATH}")
--- a/backend/core/items.py
+++ b/backend/core/items.py
@@ -1,24 +0,0 @@
-from pydantic import BaseModel, Field
-from typing import Optional, List
-
-
-# 1. 定义请求体模型
-class ChatRequest(BaseModel):
-    # --- 基础信息 ---
-    mes: str = Field(..., description="用户输入的消息内容")
-    is_user: bool = Field(..., description="标识发送者是否为用户（True为用户，False为AI）")
-    floor_number: int = Field(..., description="当前对话的楼层号，用于判断是否为重试(Regenerate)请求")
-
-    # --- 身份与会话 ---
-    name: str = Field("default", description="发送者的显示名称，默认为'default'")
-    role_name: Optional[str] = Field(None, description="当前绑定的角色名称")
-    chat_name: Optional[str] = Field(None, description="当前会话的标识名称")
-    preset: Optional[str] = Field(None, description="预设的提示词或系统指令")
-
-    # --- 功能开关 ---
-    stream: bool = Field(False, description="是否开启流式输出")
-    img_switch: bool = Field(False, description="是否开启图片生成功能")
-    table_switch: bool = Field(False, description="是否开启表格生成功能")
-
-# 其他可能需要的参数，比如历史记录，可以在这里加
-    # history: Optional[List[Dict]] = None
--- a/backend/core/models/pycache/chat_history.cpython-311.pyc
+++ b/backend/core/models/pycache/chat_history.cpython-311.pyc
--- a/backend/core/models/chat_history.py
+++ b/backend/core/models/chat_history.py
@@ -1,230 +0,0 @@
-from typing import List, Dict, Any, Optional
-from datetime import datetime
-from pathlib import Path
-from pydantic import BaseModel, Field
-import json
-
-
-class Message(BaseModel):
-    """消息类，代表JSONL文件中的一行消息内容"""
-    name: str = Field(..., description="发送者名称")
-    is_user: bool = Field(..., description="是否为用户消息")
-    is_system: bool = Field(False, description="是否为系统消息")
-    send_date: str = Field(
-        default_factory=lambda: str(int(datetime.now().timestamp() * 1000)),
-        description="消息发送时间戳"
-    )
-    floor: int = Field(0, description="对话楼层数")
-    mes: str = Field(..., description="消息内容文本")
-    extra: Dict[str, Any] = Field(
-        default_factory=dict,
-        description="额外信息，包含推理内容、API、模型等"
-    )
-    force_avatar: Optional[str] = Field(None, description="强制头像URL")
-    variables: List[Any] = Field(default_factory=list, description="消息变量列表")
-    variables_initialized: List[bool] = Field(default_factory=list, description="变量初始化状态数组")
-    is_ejs_processed: List[bool] = Field(default_factory=list, description="EJS处理状态数组")
-
-    # 以下属性仅在is_user为False时有值
-    api: Optional[str] = Field(None, description="使用的API提供商")
-    model: Optional[str] = Field(None, description="使用的AI模型")
-    reasoning: Optional[str] = Field(None, description="推理内容")
-    reasoning_duration: Optional[float] = Field(None, description="推理耗时")
-    reasoning_signature: Optional[str] = Field(None, description="推理签名")
-    time_to_first_token: Optional[float] = Field(None, description="首Token响应时间")
-    bias: Optional[float] = Field(None, description="偏差值")
-
-
-class ChatMetadata(BaseModel):
-    """聊天元数据类，包含整个聊天的共享属性"""
-    user_name: str = Field("User", description="用户名称")
-    character_name: str = Field("Assistant", description="角色名称")
-
-    # 完整性校验相关
-    integrity: str = Field("", description="完整性校验值")
-    chat_id_hash: str = Field("", description="聊天ID哈希值")
-
-    # 笔记相关
-    note_prompt: str = Field("", description="作者笔记提示词")
-    note_interval: int = Field(0, description="笔记插入间隔数")
-    note_position: int = Field(0, description="笔记插入位置")
-    note_depth: int = Field(0, description="笔记插入深度")
-    note_role: str = Field("", description="笔记使用角色类型")
-
-    # 扩展信息
-    extensions: Dict[str, Any] = Field(
-        default_factory=dict,
-        description="扩展信息，如LittleWhiteBox等"
-    )
-    # 世界信息
-    timedWorldInfo: Dict[str, Any] = Field(
-        default_factory=dict,
-        description="定时世界信息"
-    )
-    # 变量
-    variables: Dict[str, Any] = Field(
-        default_factory=dict,
-        description="变量字典"
-    )
-    # 状态标记
-    tainted: bool = Field(False, description="是否被修改标记")
-    lastInContextMessageId: int = Field(-1, description="最后上下文消息ID")
-
-
-class ChatHistory(BaseModel):
-    """聊天文件类，包含完整的聊天记录"""
-    chat_metadata: ChatMetadata = Field(..., description="聊天元数据，包含基本信息和配置")
-    messages: List[Message] = Field(default_factory=list, description="消息列表")
-
-    class Config:
-        arbitrary_types_allowed = True
-
-    @classmethod  # 类方法装饰器，表示这是一个类方法，可以通过类名直接调用
-    def load_from_file(cls, role_name: str, chat_name: str, base_path: Path = None) -> 'ChatHistory':
-        """
-        从JSONL文件加载聊天历史
-
-        参数:
-            role_name: 角色名称（文件夹名）
-            chat_name: 聊天名称（文件名，不含扩展名）
-            base_path: 基础路径，默认为配置中的DATA_PATH/chat
-
-        返回:
-            ChatHistory: 加载的聊天历史对象
-
-        异常:
-            FileNotFoundError: 当文件不存在时抛出
-            json.JSONDecodeError: 当JSON解析失败时抛出
-        """
-        # 设置默认基础路径 - 如果未提供base_path，则从配置中获取默认路径
-        if base_path is None:
-            from backend.core.config import settings  # 延迟导入配置模块
-            base_path = settings.DATA_PATH / "chat"  # 构建默认路径
-
-        # 构建文件路径
-        file_path = base_path / role_name / f"{chat_name}.jsonl"
-
-        # 检查文件是否存在
-        if not file_path.exists():
-            raise FileNotFoundError(f"聊天文件不存在: {file_path}")
-
-        # 初始化结果数据
-        messages = []
-        metadata = None
-
-        # 读取文件内容
-        with open(file_path, 'r', encoding='utf-8') as f:
-            for line_num, line in enumerate(f):
-                try:
-                    line_data = json.loads(line.strip())
-
-                    # 第一行是元数据
-                    if line_num == 0:
-                        metadata = ChatMetadata(**line_data)
-                    else:
-                        # 后续行是消息
-                        messages.append(Message(**line_data))
-                except json.JSONDecodeError:
-                    continue
-
-        # 创建并返回ChatHistory对象
-        return cls(
-            chat_metadata=metadata or ChatMetadata(),
-            messages=messages
-        )
-
-    @classmethod
-    def load_from_jsonl(cls, file_path: Path) -> 'ChatHistory':
-        """
-        从JSONL文件加载聊天历史
-
-        参数:
-            file_path: JSONL文件路径
-
-        返回:
-            ChatHistory: 加载的聊天历史对象
-
-        异常:
-            FileNotFoundError: 当文件不存在时抛出
-            json.JSONDecodeError: 当JSON解析失败时抛出
-        """
-        # 检查文件是否存在
-        if not file_path.exists():
-            raise FileNotFoundError(f"聊天文件不存在: {file_path}")
-
-        # 初始化结果数据
-        messages = []
-        metadata = None
-
-        # 读取文件内容
-        with open(file_path, 'r', encoding='utf-8') as f:
-            for line_num, line in enumerate(f):
-                try:
-                    line_data = json.loads(line.strip())
-
-                    # 第一行是元数据
-                    if line_num == 0:
-                        # 处理元数据中的嵌套结构
-                        if 'chat_metadata' in line_data:
-                            metadata_dict = line_data['chat_metadata']
-                            # 合并顶层字段和chat_metadata中的字段
-                            metadata_dict.update(line_data)
-                            metadata = ChatMetadata(**metadata_dict)
-                        else:
-                            metadata = ChatMetadata(**line_data)
-                    else:
-                        # 后续行是消息
-                        # 处理extra字段中的内容
-                        extra_data = line_data.get('extra', {})
-
-                        # 如果是AI消息(is_user=False)，将extra中的某些字段提升到顶层
-                        if not line_data.get('is_user', True):
-                            ai_fields = ['api', 'model', 'reasoning', 'reasoning_duration',
-                                         'reasoning_signature', 'time_to_first_token', 'bias']
-                            for field in ai_fields:
-                                if field in extra_data:
-                                    line_data[field] = extra_data.pop(field)
-
-                        # 创建Message实例
-                        message = Message(**line_data)
-                        # 将剩余的extra数据保存回extra字段
-                        message.extra = extra_data
-                        messages.append(message)
-
-                except json.JSONDecodeError:
-                    continue
-
-        # 创建并返回ChatHistory对象
-        return cls(
-            chat_metadata=metadata or ChatMetadata(),
-            messages=messages
-        )
-
-    def to_chatbox_format(self) -> List[Dict[str, Any]]:
-        """
-        将聊天历史转换为适合前端chatbox显示的格式
-
-        返回:
-            List[Dict[str, Any]]: 按floor排序的消息字典列表，每个字典包含:
-            {
-                "name": str,
-                "is_user": bool,
-                "floor": int,
-                "mes": str
-            }
-        """
-        # 创建消息字典列表
-        messages_list = []
-        for msg in self.messages:
-            msg_dict = {
-                "name": msg.name,
-                "is_user": msg.is_user,
-                "floor": msg.floor,
-                "mes": msg.mes
-            }
-            messages_list.append(msg_dict)
-
-        # 按floor排序
-        messages_list.sort(key=lambda x: x["floor"])
-
-        return messages_list
--- a/backend/main.py
+++ b/backend/main.py
@@ -1,12 +1,51 @@
+import logging
+import sys
+
+# 配置日志
+logging.basicConfig(
+		level=logging.INFO,
+		format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+		handlers=[
+			logging.StreamHandler(sys.stdout)
+		]
+)
+
+# 确保所有模块的日志都能被捕获
+for logger_name in ['uvicorn', 'uvicorn.access', 'fastapi']:
+	logging_logger = logging.getLogger(logger_name)
+	logging_logger.setLevel(logging.INFO)
+
 # backend/app/main.py
 from fastapi import FastAPI
-from .api.route import router
-
+from fastapi.middleware.cors import CORSMiddleware
+try:
+    from backend.api.route import router
+except ImportError:
+    from api.route import router
 app = FastAPI(title="LLM Workflow Engine")

+# 配置CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # 开发环境允许所有来源，生产环境应该指定具体域名
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
 # 注册路由
 app.include_router(router, prefix="/api")

+# 添加健康检查端点
+@app.get("/health")
+async def health_check():
+    return {"status": "healthy"}
+
+# 添加根路径
+@app.get("/")
+async def root():
+    return {"message": "LLM Workflow Engine", "status": "running"}
+
 if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=8000)
--- a/backend/models/README.md
+++ b/backend/models/README.md
@@ -0,0 +1,231 @@
+# Backend Models 数据模型说明
+
+## 目录结构
+
+```
+models/
+├── __init__.py          # 包初始化,导出所有模型
+├── sillytavern.py       # SillyTavern 兼容模型 (仅用于导入/导出)
+├── internal.py          # 内部业务模型 (项目核心使用)
+└── README.md            # 本文件
+```
+
+## 模型分类
+
+### 1. SillyTavern 兼容模型 (`sillytavern.py`)
+
+**用途**: 仅用于与 SillyTavern 格式的数据进行导入/导出兼容
+
+**特点**:
+- 严格遵循 SillyTavern 官方规范
+- 不参与内部业务逻辑
+- 所有字段名、结构与 SillyTavern 保持一致
+- 前缀 `ST` 表示 SillyTavern
+
+**主要模型**:
+- `STWorldInfo` - SillyTavern 世界书
+- `STCharacterCard` - SillyTavern 角色卡
+- `STChatHeader` / `STChatMessage` - SillyTavern 聊天记录
+- `STGenerationPreset` - SillyTavern 采样预设
+- `STPromptPreset` - SillyTavern 提示词预设
+
+**使用场景**:
+```python
+# 从 SillyTavern 导入时
+st_data = json.load(file)
+st_character = STCharacterCard(**st_data)
+
+# 转换为内部模型
+internal_character = converter.st_to_internal(st_character)
+
+# 导出到 SillyTavern 时
+st_data = converter.internal_to_st(internal_character)
+json.dump(st_data.dict(), file)
+```
+
+### 2. 内部业务模型 (`internal.py`)
+
+**用途**: 项目内部真正使用的数据结构,所有业务逻辑都基于这些模型
+
+**特点**:
+- 继承并扩展了 SillyTavern 的功能
+- 添加了项目特色功能 (如 LOGIC 激活、RAG 配置、outputSchema 等)
+- 所有 API 响应、数据存储、工作流交换都使用这些模型
+- 无前缀,直接使用语义化名称
+
+**主要模型**:
+
+#### 世界书相关
+- `ActivationType` - 激活方式枚举 (PERMANENT/KEYWORD/RAG/LOGIC)
+- `LogicExpression` - 逻辑表达式
+- `RAGConfig` - RAG 检索配置
+- `WorldInfoEntry` - 世界书条目
+- `WorldInfo` - 世界书
+
+#### 角色卡相关
+- `OutputSchemaField` - 结构化输出 schema
+- `CharacterCard` - 角色卡
+
+#### 聊天记录相关
+- `ChatHeader` - 聊天头
+- `ChatMessage` - 聊天消息
+- `ChatLog` - 完整聊天记录
+
+#### 预设相关
+- `GenerationPreset` - 采样参数预设
+- `PromptRole` - Prompt 角色枚举
+- `PromptEntry` - Prompt 条目
+- `PromptPresetView` - Prompt 预设视图
+
+#### RAG 配置
+- `RAGSearchConfig` - RAG 搜索配置
+- `CharacterRAGConfig` - 角色卡 RAG 配置
+- `ChatRAGConfig` - 聊天 RAG 配置
+
+**使用场景**:
+```python
+# 业务逻辑中直接使用
+from models import CharacterCard, WorldInfo
+
+character = CharacterCard(
+    id="uuid-123",
+    name="Alice",
+    description="...",
+    ...
+)
+
+# API 响应
+@app.get("/characters/{id}")
+async def get_character(id: str):
+    character = service.get_character(id)
+    return character  # 返回 internal 模型
+```
+
+## 数据转换流程
+
+```
+SillyTavern 文件
+    ↓ (导入)
+STCharacterCard (sillytavern.py)
+    ↓ (转换器)
+CharacterCard (internal.py)
+    ↓ (业务处理)
+CharacterCard (internal.py)
+    ↓ (转换器)
+STCharacterCard (sillytavern.py)
+    ↓ (导出)
+SillyTavern 文件
+```
+
+## 开发规范
+
+### ✅ 正确做法
+
+1. **业务逻辑使用 internal 模型**
+   ```python
+   from models import CharacterCard
+   
+   def create_character(data: dict) -> CharacterCard:
+       return CharacterCard(**data)
+   ```
+
+2. **导入时使用转换器**
+   ```python
+   from models import STCharacterCard, CharacterCard
+   from models.converters import CharacterConverter
+   
+   def import_character(file_path: str) -> CharacterCard:
+       st_data = load_json(file_path)
+       st_char = STCharacterCard(**st_data)
+       return CharacterConverter.st_to_internal(st_char)
+   ```
+
+3. **API 响应使用 internal 模型**
+   ```python
+   @app.get("/characters")
+   async def list_characters() -> List[CharacterCard]:
+       return service.list_characters()
+   ```
+
+### ❌ 错误做法
+
+1. **不要在业务逻辑中直接使用 ST 模型**
+   ```python
+   # 错误!
+   from models import STCharacterCard
+   
+   def process_character(char: STCharacterCard):
+       ...
+   ```
+
+2. **不要混合使用两种模型**
+   ```python
+   # 错误!
+   character = CharacterCard(...)
+   character.name = st_character.data.name  # 不要混用
+   ```
+
+3. **不要在 API 中暴露 ST 模型**
+   ```python
+   # 错误!
+   @app.get("/characters")
+   async def list_characters() -> List[STCharacterCard]:
+       ...
+   ```
+
+## 添加新模型
+
+当需要添加新的数据类型时:
+
+1. **判断用途**:
+   - 如果是为了 SillyTavern 兼容 → 添加到 `sillytavern.py`
+   - 如果是项目内部使用 → 添加到 `internal.py`
+
+2. **遵循命名规范**:
+   - SillyTavern 模型: 前缀 `ST`
+   - 内部模型: 无前缀,使用清晰的语义化名称
+
+3. **添加详细注释**:
+   ```python
+   class MyModel(BaseModel):
+       """
+       模型用途说明
+       
+       详细描述该模型的作用、使用场景等
+       """
+       field1: str = Field(..., description="字段说明")
+   ```
+
+4. **在 `__init__.py` 中导出**:
+   ```python
+   from .internal import MyModel
+   
+   __all__ = [
+       ...,
+       'MyModel',
+   ]
+   ```
+
+## 转换器 (待实现)
+
+`models/converters.py` 将提供双向转换功能:
+
+```python
+class CharacterConverter:
+    @staticmethod
+    def st_to_internal(st_char: STCharacterCard) -> CharacterCard:
+        """SillyTavern → Internal"""
+        ...
+    
+    @staticmethod
+    def internal_to_st(int_char: CharacterCard) -> STCharacterCard:
+        """Internal → SillyTavern"""
+        ...
+```
+
+## 总结
+
+- **sillytavern.py** = 外部兼容层 (Import/Export Only)
+- **internal.py** = 内部业务层 (Core Business Logic)
+- **永远在业务逻辑中使用 internal 模型**
+- **通过转换器进行格式转换**
--- a/backend/models/init.py
+++ b/backend/models/init.py
@@ -0,0 +1,61 @@
+"""
+数据模型包
+
+导出项目内部真正使用的数据结构 (Internal Models)。
+SillyTavern 兼容模型将在需要导入/导出时单独引用。
+"""
+
+# 内部业务模型 (项目核心使用)
+from .internal import (
+    # 世界书
+    ActivationType,
+    LogicOperator,
+    LogicExpression,
+    RAGConfig,
+    WorldInfoEntry,
+    WorldInfo,
+    
+    # 角色卡
+    OutputSchemaField,
+    CharacterCard,
+    
+    # 聊天记录
+    ChatHeader,
+    ChatMessage,
+    ChatLog,
+    
+    # 预设
+    GenerationPreset,
+    
+    # 提示词预设
+    PromptRole,
+    PromptEntry,
+    PromptPresetView,
+    
+    # RAG 配置
+    RAGSearchConfig,
+    CharacterRAGConfig,
+    ChatRAGConfig,
+)
+
+__all__ = [
+    # 内部模型
+    'ActivationType',
+    'LogicOperator',
+    'LogicExpression',
+    'RAGConfig',
+    'WorldInfoEntry',
+    'WorldInfo',
+    'OutputSchemaField',
+    'CharacterCard',
+    'ChatHeader',
+    'ChatMessage',
+    'ChatLog',
+    'GenerationPreset',
+    'PromptRole',
+    'PromptEntry',
+    'PromptPresetView',
+    'RAGSearchConfig',
+    'CharacterRAGConfig',
+    'ChatRAGConfig',
+]
--- a/backend/models/converters.py
+++ b/backend/models/converters.py
@@ -0,0 +1,379 @@
+"""
+数据模型转换器
+
+提供 SillyTavern 格式与内部格式之间的双向转换功能。
+所有导入/导出操作都应该通过转换器进行,确保数据格式的一致性。
+"""
+import uuid
+from typing import Dict, Any, List, Optional
+from datetime import datetime
+
+from models.internal import (
+    WorldInfo,
+    WorldInfoEntry,
+    ActivationType,
+)
+
+
+class WorldBookConverter:
+    """世界书数据转换器
+    
+    负责 SillyTavern 格式和项目内部格式之间的转换。
+    
+    SillyTavern 格式特点:
+    - entries 是 dict (key 为 uid)
+    - 使用 constant 字段表示常驻激活
+    - position 是字符串 (如 "after_char")
+    
+    项目内部格式特点:
+    - entries 是 list
+    - 使用 activationType 枚举
+    - position 是数字 (0-5)
+    - 包含 trigger_config 结构(前端需要)
+    """
+    
+    @staticmethod
+    def detect_format(data: Dict[str, Any]) -> str:
+        """
+        智能检测世界书数据格式
+        
+        Args:
+            data: 世界书数据
+            
+        Returns:
+            'sillytavern' | 'internal' | 'unknown'
+        """
+        # 检查 entries 类型
+        entries = data.get("entries")
+        if not entries:
+            return "unknown"
+        
+        # SillyTavern 特征: entries 是 dict
+        if isinstance(entries, dict):
+            return "sillytavern"
+        
+        # 内部格式特征: entries 是 list
+        if isinstance(entries, list):
+            # 进一步检查是否有 trigger_config
+            if len(entries) > 0 and isinstance(entries[0], dict):
+                first_entry = entries[0]
+                if "trigger_config" in first_entry:
+                    return "internal"
+                # 也可能是简化的内部格式
+                if "activationType" in first_entry or "position" in first_entry:
+                    return "internal"
+        
+        return "unknown"
+    
+    # 位置映射: SillyTavern 字符串 -> 内部数字
+    POSITION_MAP_ST_TO_INTERNAL = {
+        "after_char": 0,
+        "before_char": 1,
+        "before_example": 2,
+        "after_example": 3,
+        "author_note": 4,
+        "system_prompt": 5,
+    }
+    
+    # 位置映射: 内部数字 -> SillyTavern 字符串
+    POSITION_MAP_INTERNAL_TO_ST = {
+        0: "after_char",
+        1: "before_char",
+        2: "before_example",
+        3: "after_example",
+        4: "author_note",
+        5: "system_prompt",
+    }
+    
+    @staticmethod
+    def st_to_internal(st_data: Dict[str, Any], name: str = None) -> Dict[str, Any]:
+        """
+        将 SillyTavern 格式的世界书转换为内部格式
+        
+        Args:
+            st_data: SillyTavern 格式的世界书数据
+            name: 世界书名称(可选,优先使用 st_data 中的 name)
+            
+        Returns:
+            内部格式的世界书字典(包含 trigger_config)
+        """
+        now = int(datetime.now().timestamp())
+        
+        # 转换条目
+        entries = []
+        st_entries = st_data.get("entries", {})
+        
+        # SillyTavern 的 entries 可能是 dict 或 list
+        if isinstance(st_entries, dict):
+            entries_list = list(st_entries.values())
+        elif isinstance(st_entries, list):
+            entries_list = st_entries
+        else:
+            entries_list = []
+        
+        for st_entry in entries_list:
+            if not isinstance(st_entry, dict):
+                continue
+            
+            # 判断激活类型
+            is_constant = st_entry.get("constant", False)
+            activation_type = ActivationType.PERMANENT if is_constant else ActivationType.KEYWORD
+            
+            # 转换位置
+            st_position = st_entry.get("position", "after_char")
+            internal_position = WorldBookConverter.POSITION_MAP_ST_TO_INTERNAL.get(st_position, 0)
+            
+            # 构建 trigger_config (前端期望的格式)
+            trigger_config = WorldBookConverter._build_trigger_config(
+                is_constant=is_constant,
+                key=st_entry.get("key", []),
+                keysecondary=st_entry.get("keysecondary", []),
+                selective=st_entry.get("selective", True)
+            )
+            
+            # 创建内部格式的条目
+            entry_dict = {
+                "uid": st_entry.get("uid", str(uuid.uuid4())),
+                "key": st_entry.get("key", []),
+                "keysecondary": st_entry.get("keysecondary", []),
+                "content": st_entry.get("content", ""),
+                "comment": st_entry.get("comment", ""),
+                "activationType": activation_type.value,
+                "trigger_config": trigger_config,
+                "order": st_entry.get("order", 100),
+                "position": internal_position,
+                "depth": st_entry.get("depth", 4),
+                "role": st_entry.get("role", 0),
+                "probability": st_entry.get("probability", 100),
+                "group": st_entry.get("group", []),
+                "disable": st_entry.get("disable", False),
+                "createdAt": now,
+                "updatedAt": now
+            }
+            
+            entries.append(entry_dict)
+        
+        # 创建内部格式的世界书
+        worldbook_data = {
+            "id": str(uuid.uuid4()),
+            "name": name or st_data.get("name", "Unnamed"),
+            "description": st_data.get("description", ""),
+            "entries": entries,
+            "createdAt": now,
+            "updatedAt": now,
+            "version": 1
+        }
+        
+        return worldbook_data
+    
+    @staticmethod
+    def internal_to_st(worldbook_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        将内部格式的世界书转换为 SillyTavern 格式
+        
+        Args:
+            worldbook_data: 内部格式的世界书字典
+            
+        Returns:
+            SillyTavern 格式的世界书数据
+        """
+        # 转换条目
+        st_entries = {}
+        
+        for entry_data in worldbook_data.get("entries", []):
+            if not isinstance(entry_data, dict):
+                continue
+            
+            uid = entry_data.get("uid", str(uuid.uuid4()))
+            
+            # 从 trigger_config 或 activationType 判断是否常驻
+            is_constant = WorldBookConverter._is_constant_entry(entry_data)
+            
+            # 提取关键词
+            key, keysecondary = WorldBookConverter._extract_keywords(entry_data)
+            
+            # 转换位置
+            internal_position = entry_data.get("position", 0)
+            st_position = WorldBookConverter.POSITION_MAP_INTERNAL_TO_ST.get(internal_position, "after_char")
+            
+            # 创建 SillyTavern 格式的条目
+            st_entry = {
+                "uid": uid,
+                "key": key,
+                "keysecondary": keysecondary,
+                "content": entry_data.get("content", ""),
+                "comment": entry_data.get("comment", ""),
+                "constant": is_constant,
+                "selective": not is_constant,
+                "order": entry_data.get("order", 100),
+                "position": st_position,
+                "depth": entry_data.get("depth", 4),
+                "probability": entry_data.get("probability", 100),
+                "group": entry_data.get("group", []),
+                "disable": entry_data.get("disable", False)
+            }
+            
+            st_entries[uid] = st_entry
+        
+        # 创建 SillyTavern 格式的世界书
+        st_data = {
+            "name": worldbook_data.get("name", ""),
+            "description": worldbook_data.get("description", ""),
+            "entries": st_entries
+        }
+        
+        return st_data
+    
+    @staticmethod
+    def normalize_entry(entry_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        规范化条目数据,确保包含所有必需字段和 trigger_config
+        
+        Args:
+            entry_data: 条目数据(可能来自不同来源)
+            
+        Returns:
+            规范化后的条目数据
+        """
+        now = int(datetime.now().timestamp())
+        
+        # 如果已经有 trigger_config,直接返回
+        if "trigger_config" in entry_data and entry_data["trigger_config"]:
+            return entry_data
+        
+        # 否则从其他字段构建 trigger_config
+        is_constant = WorldBookConverter._is_constant_entry(entry_data)
+        key, keysecondary = WorldBookConverter._extract_keywords(entry_data)
+        
+        trigger_config = WorldBookConverter._build_trigger_config(
+            is_constant=is_constant,
+            key=key,
+            keysecondary=keysecondary,
+            selective=entry_data.get("selective", True)
+        )
+        
+        # 添加缺失的字段
+        normalized = {
+            "uid": entry_data.get("uid", str(uuid.uuid4())),
+            "key": key,
+            "keysecondary": keysecondary,
+            "content": entry_data.get("content", ""),
+            "comment": entry_data.get("comment", ""),
+            "activationType": entry_data.get("activationType", 
+                                            ActivationType.PERMANENT.value if is_constant 
+                                            else ActivationType.KEYWORD.value),
+            "trigger_config": trigger_config,
+            "order": entry_data.get("order", 100),
+            "position": entry_data.get("position", 0),
+            "depth": entry_data.get("depth", 4),
+            "role": entry_data.get("role", 0),
+            "probability": entry_data.get("probability", 100),
+            "group": entry_data.get("group", []),
+            "disable": entry_data.get("disable", False),
+            "createdAt": entry_data.get("createdAt", now),
+            "updatedAt": entry_data.get("updatedAt", now)
+        }
+        
+        return normalized
+    
+    @staticmethod
+    def _build_trigger_config(
+        is_constant: bool,
+        key: List[str],
+        keysecondary: List[str],
+        selective: bool = True
+    ) -> Dict[str, Any]:
+        """
+        构建 trigger_config 结构
+        
+        Args:
+            is_constant: 是否常驻激活
+            key: 主关键词列表
+            keysecondary: 次要关键词列表
+            selective: 是否选择性匹配
+            
+        Returns:
+            trigger_config 字典
+        """
+        return {
+            "triggers": {
+                "constant": [is_constant, None],
+                "keyword": [
+                    not is_constant,
+                    {
+                        "key": key,
+                        "keysecondary": keysecondary,
+                        "selective": selective,
+                        "selectiveLogic": 0,
+                        "matchWholeWords": False,
+                        "caseSensitive": False
+                    }
+                ],
+                "rag": [False, {
+                    "threshold": 0.75,
+                    "top_k": 5,
+                    "query_template": None
+                }],
+                "condition": [False, {
+                    "variable_a": "",
+                    "operator": "=",
+                    "variable_b": ""
+                }]
+            }
+        }
+    
+    @staticmethod
+    def _is_constant_entry(entry_data: Dict[str, Any]) -> bool:
+        """
+        判断条目是否为常驻激活
+        
+        Args:
+            entry_data: 条目数据
+            
+        Returns:
+            是否常驻激活
+        """
+        # 优先从 trigger_config 判断
+        if "trigger_config" in entry_data and entry_data["trigger_config"]:
+            try:
+                return entry_data["trigger_config"]["triggers"]["constant"][0]
+            except (KeyError, IndexError, TypeError):
+                pass
+        
+        # 其次从 activationType 判断
+        if "activationType" in entry_data:
+            return entry_data["activationType"] == ActivationType.PERMANENT.value
+        
+        # 最后从 constant 字段判断
+        if "constant" in entry_data:
+            return entry_data["constant"]
+        
+        return False
+    
+    @staticmethod
+    def _extract_keywords(entry_data: Dict[str, Any]) -> tuple:
+        """
+        从条目数据中提取关键词
+        
+        Args:
+            entry_data: 条目数据
+            
+        Returns:
+            (key, keysecondary) 元组
+        """
+        # 优先从 trigger_config 提取
+        if "trigger_config" in entry_data and entry_data["trigger_config"]:
+            try:
+                keyword_config = entry_data["trigger_config"]["triggers"]["keyword"][1]
+                if keyword_config:
+                    key = keyword_config.get("key", [])
+                    keysecondary = keyword_config.get("keysecondary", [])
+                    return key, keysecondary
+            except (KeyError, IndexError, TypeError):
+                pass
+        
+        # 否则从顶层字段提取
+        key = entry_data.get("key", [])
+        keysecondary = entry_data.get("keysecondary", [])
+        
+        return key, keysecondary
--- a/backend/models/internal.py
+++ b/backend/models/internal.py
@@ -0,0 +1,301 @@
+"""
+项目内部数据结构定义
+
+这是本项目真正使用的核心数据模型,所有业务逻辑都基于这些类型。
+与 sillytavern.py 不同,这里的模型不参与导入导出兼容,而是专注于:
+- 内部业务逻辑处理
+- API 响应数据结构
+- 数据存储格式
+- 工作流引擎数据交换
+
+所有从 SillyTavern 导入的数据都会转换为这些内部模型进行处理,
+导出时再从内部模型转换回 SillyTavern 格式。
+"""
+from enum import Enum
+from typing import List, Optional, Dict, Any
+from pydantic import BaseModel, Field
+from datetime import datetime
+
+
+# ==================== 世界书 (World Info) ====================
+
+class ActivationType(str, Enum):
+    """
+    自定义激活方式类型（4种枚举）
+    
+    这是项目的核心创新点之一,相比 SillyTavern 的简单 constant/selective 标志,
+    我们提供了更灵活的激活机制。
+    """
+    PERMANENT = 'permanent'    # 永久激活 - 始终包含在上下文中
+    KEYWORD = 'keyword'        # 关键词触发 - 匹配关键词时激活
+    RAG = 'rag'               # RAG 检索激活 - 基于向量相似度检索
+    LOGIC = 'logic'           # 逻辑表达式激活 - 基于变量条件判断
+
+
+class LogicOperator(str, Enum):
+    """逻辑运算符（用于 LOGIC 激活类型）"""
+    EQUALS = 'equals'              # 等于
+    NOT_EQUALS = 'not_equals'      # 不等于
+    CONTAINS = 'contains'          # 包含
+    NOT_CONTAINS = 'not_contains'  # 不包含
+    GREATER = 'greater'            # 大于
+    LESS = 'less'                  # 小于
+
+
+class LogicExpression(BaseModel):
+    """
+    逻辑表达式结构（用于 LOGIC 激活类型）
+    
+    示例: variable1="mood", operator="equals", variable2="happy"
+    表示当 mood 变量等于 happy 时激活该条目
+    """
+    variable1: str = Field(..., description="第一个变量名")
+    operator: LogicOperator = Field(..., description="比较运算符")
+    variable2: str = Field(..., description="第二个变量名或值")
+
+
+class RAGConfig(BaseModel):
+    """
+    RAG 配置（用于 RAG 激活类型）
+    
+    控制如何从向量数据库中检索相关内容
+    """
+    libraryId: str = Field(..., description="绑定的 RAG 库 ID")
+    threshold: Optional[float] = Field(0.7, ge=0, le=1, description="相似度阈值 (0-1)")
+    maxEntries: Optional[int] = Field(5, gt=0, description="最大返回条目数")
+
+
+class WorldInfoEntry(BaseModel):
+    """
+    项目内部世界书条目结构
+    
+    这是世界书的核心单元,每个条目代表一段可以被动态注入到对话上下文中的知识。
+    相比 SillyTavern,我们添加了 activationType、logicExpression、ragConfig 等高级功能。
+    """
+    uid: str = Field(..., description="条目唯一标识符 (UUID)")
+    key: Optional[List[str]] = Field(None, description="主关键词列表 (用于 KEYWORD 激活)")
+    keysecondary: Optional[List[str]] = Field(None, description="次要关键词列表 (可选过滤)")
+    content: str = Field(..., description="条目内容 - 激活时注入的文本")
+    activationType: ActivationType = Field(..., description="激活方式")
+    logicExpression: Optional[LogicExpression] = Field(None, description="逻辑表达式 (LOGIC 类型使用)")
+    ragConfig: Optional[RAGConfig] = Field(None, description="RAG 配置 (RAG 类型使用)")
+    order: int = Field(0, description="插入顺序 - 数值越大越靠近末尾")
+    position: Optional[str] = Field('after_char', description="插入位置")
+    depth: Optional[int] = Field(None, description="插入深度 (当 position='at_depth' 时使用)")
+    probability: Optional[float] = Field(100, ge=0, le=100, description="激活概率 (0-100)")
+    group: Optional[List[str]] = Field(None, description="所属组标签")
+    disable: bool = Field(False, description="是否禁用")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+
+
+class WorldInfo(BaseModel):
+    """
+    项目内部世界书结构
+    
+    世界书是角色知识的集合,可以绑定到角色卡上,在对话中动态提供背景信息。
+    """
+    id: str = Field(..., description="世界书唯一标识符 (UUID)")
+    name: str = Field(..., description="世界书名称")
+    description: Optional[str] = Field(None, description="世界书描述")
+    entries: List[WorldInfoEntry] = Field(default_factory=list, description="条目数组")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+    version: int = Field(1, description="版本号 (用于数据迁移)")
+
+
+# ==================== 角色卡 (Character Card) ====================
+
+class OutputSchemaField(BaseModel):
+    """
+    Vercel AI SDK Output.object() 的表头定义
+    
+    用于结构化输出,让 LLM 按照指定格式返回数据。
+    这是项目的特色功能,支持动态表格生成。
+    """
+    name: str = Field(..., description="字段名称")
+    type: str = Field(..., description="字段类型 (string/number/boolean/array/object)")
+    description: str = Field(..., description="字段描述")
+    required: Optional[bool] = Field(None, description="是否必需")
+    enum: Optional[List[str]] = Field(None, description="枚举值 (字符串固定选项)")
+    fields: Optional[List['OutputSchemaField']] = Field(None, description="嵌套字段 (object 类型)")
+
+
+class CharacterCard(BaseModel):
+    """
+    项目内部角色卡结构
+    
+    角色卡是对话 AI 的核心定义,包含人设、场景、开场白等。
+    相比 SillyTavern,我们添加了 categories、outputSchema、worldInfoId 等功能。
+    """
+    id: str = Field(..., description="角色唯一标识符 (UUID)")
+    name: str = Field(..., description="角色名称")
+    description: str = Field(..., description="角色详细描述")
+    personality: str = Field(..., description="角色性格特征")
+    scenario: str = Field(..., description="场景设定")
+    first_mes: str = Field(..., description="首条开场消息")
+    mes_example: str = Field(..., description="对话示例")
+    categories: List[str] = Field(default_factory=list, description="分类标签 (用于前端筛选)")
+    worldInfoId: Optional[str] = Field(None, description="绑定的世界书 ID")
+    outputSchema: Optional[List[OutputSchemaField]] = Field(None, description="输出 schema 定义 (结构化输出)")
+    avatarPath: Optional[str] = Field(None, description="角色头像路径")
+    alternate_greetings: Optional[List[str]] = Field(None, description="替代问候语数组")
+    tags: Optional[List[str]] = Field(None, description="标签数组")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+    lastChatAt: Optional[int] = Field(None, description="最后聊天时间戳")
+    isFavorite: bool = Field(False, description="收藏状态")
+    version: int = Field(1, description="版本号")
+
+
+# ==================== 聊天记录 (Chat Log) ====================
+
+class ChatHeader(BaseModel):
+    """
+    项目内部聊天记录头
+    
+    包含聊天的元数据,如参与角色、创建时间等。
+    """
+    id: str = Field(..., description="聊天唯一标识符 (UUID)")
+    displayName: str = Field(..., description="显示名称 (聊天标题)")
+    characterId: str = Field(..., description="关联的角色卡 ID")
+    userName: str = Field("User", description="用户角色名")
+    characterName: str = Field(..., description="AI 角色名称")
+    tableData: Optional[Dict[str, Any]] = Field(None, description="表格数据 (对应 outputSchema)")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+    messageCount: int = Field(0, description="消息数量")
+    ragLibraryId: Optional[str] = Field(None, description="关联的 RAG 历史消息库 ID")
+
+
+class ChatMessage(BaseModel):
+    """
+    项目内部聊天消息
+    
+    单条对话消息,支持多版本 (swipes)、token 统计等功能。
+    """
+    id: str = Field(..., description="消息唯一标识符 (UUID)")
+    name: str = Field(..., description="发送者名称")
+    is_user: bool = Field(..., description="是否为用户消息")
+    is_system: Optional[bool] = Field(None, description="是否为系统消息")
+    sendDate: str = Field(..., description="发送日期 ISO 字符串")
+    mes: str = Field(..., description="消息内容文本")
+    chatId: str = Field(..., description="关联的聊天 ID")
+    swipes: Optional[List[str]] = Field(None, description="替换回答数组 (多版本)")
+    swipe_id: Optional[int] = Field(0, description="当前选择的版本索引")
+    tokenCount: Optional[int] = Field(None, description="Token 数量 (用于统计)")
+    isTemporary: Optional[bool] = Field(None, description="是否为临时消息 (未保存)")
+
+
+class ChatLog(BaseModel):
+    """
+    项目内部完整聊天记录
+    
+    包含聊天头和所有消息,是完整的对话历史。
+    """
+    header: ChatHeader = Field(..., description="聊天头")
+    messages: List[ChatMessage] = Field(default_factory=list, description="消息列表")
+
+
+# ==================== 预设 (Preset) ====================
+
+class GenerationPreset(BaseModel):
+    """
+    项目内部采样参数预设
+    
+    控制 LLM 生成的参数配置,如温度、top_p 等。
+    """
+    id: str = Field(..., description="预设唯一标识符 (UUID)")
+    name: str = Field(..., description="预设名称")
+    temperature: float = Field(1.0, ge=0, le=2, description="温度 (控制随机性)")
+    topP: float = Field(1.0, ge=0, le=1, description="Top P (核采样)")
+    topK: int = Field(0, ge=0, description="Top K")
+    repetitionPenalty: float = Field(1.0, ge=0, description="重复惩罚")
+    frequencyPenalty: Optional[float] = Field(None, description="频率惩罚")
+    presencePenalty: Optional[float] = Field(None, description="存在惩罚")
+    maxLength: Optional[int] = Field(None, gt=0, description="最大生成长度")
+    isDefault: bool = Field(False, description="是否为默认预设")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+
+
+# ==================== 提示词预设 (Prompt Preset) ====================
+
+class PromptRole(str, Enum):
+    """
+    Prompt 角色类型
+    
+    内部业务层只保留三种角色,简化了 SillyTavern 的复杂角色系统。
+    """
+    SYSTEM = 'system'  # 系统指令
+    AI = 'ai'         # AI 助手
+    USER = 'user'     # 用户
+
+
+class PromptEntry(BaseModel):
+    """
+    内部业务层 - Prompt 条目
+    
+    提示词模板的基本单元,可以组合成完整的提示词预设。
+    这是基于某个 character_id 生成的"当前视图"。
+    """
+    identifier: str = Field(..., description="稳定关联键 (用于回写)")
+    name: str = Field(..., description="条目名 (前端显示)")
+    enabled: bool = Field(True, description="是否启用 (当前作用域下的业务状态)")
+    content: str = Field(..., description="条目内容 (静态内容视图)")
+    order: int = Field(..., description="条目顺序 (前端展示和拖拽排序)")
+    role: PromptRole = Field(..., description="角色类型")
+    tokenCount: int = Field(0, description="总 token 数 (派生显示字段)")
+    isSystemNode: bool = Field(False, description="是否固有节点 (不可删除)")
+
+
+class PromptPresetView(BaseModel):
+    """
+    内部业务层 - Prompt 预设视图
+    
+    基于某个 character_id 的"当前视图",包含已排序、已过滤的条目列表。
+    """
+    characterId: str = Field(..., description="关联的角色 ID")
+    entries: List[PromptEntry] = Field(default_factory=list, description="当前视图的条目列表")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+    version: int = Field(1, description="版本号")
+
+
+# ==================== RAG 配置 ====================
+
+class RAGSearchConfig(BaseModel):
+    """RAG 搜索配置"""
+    topK: int = Field(5, gt=0, description="每次检索返回的结果数")
+    threshold: float = Field(0.7, ge=0, le=1, description="相似度阈值 (0-1)")
+    maxContextLength: int = Field(2000, gt=0, description="最大上下文长度 (字符数)")
+
+
+class CharacterRAGConfig(BaseModel):
+    """
+    角色卡 RAG 世界书库配置
+    
+    记录角色卡关联的 RAG 知识库,用于动态检索相关知识。
+    """
+    characterId: str = Field(..., description="角色卡ID")
+    ragLibraryIds: List[str] = Field(default_factory=list, description="关联的RAG库ID列表")
+    enabled: bool = Field(True, description="是否启用")
+    searchConfig: Optional[RAGSearchConfig] = Field(None, description="搜索配置")
+    position: str = Field('after_char', description="RAG内容插入位置")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+
+
+class ChatRAGConfig(BaseModel):
+    """
+    聊天会话 RAG 历史消息配置
+    
+    记录聊天会话关联的 RAG 历史消息库,用于智能检索历史对话。
+    """
+    chatId: str = Field(..., description="聊天会话ID")
+    ragLibraryId: Optional[str] = Field(None, description="关联的RAG历史消息库ID")
+    enabled: bool = Field(True, description="是否启用")
+    searchConfig: Optional[Dict[str, Any]] = Field(None, description="搜索配置")
+    autoIndex: bool = Field(True, description="是否自动索引新消息")
+    indexConfig: Optional[Dict[str, Any]] = Field(None, description="索引配置")
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
--- a/backend/nodes/text_splitter_node.py
+++ b/backend/nodes/text_splitter_node.py
@@ -1,56 +0,0 @@
-import re
-from core.node_base import BaseNode
-from typing import List, Dict, Any
-
-
-class TextSplitterNode(BaseNode):
-    name = "文本分割节点"
-    inputs = {"text": "string"}
-    outputs = {
-        "outline": "list",  # 大纲部分列表
-        "requirement": "list",  # 要求部分列表
-        "dialogue": "list",  # 对话部分列表
-        "weak_guidance": "list"  # 弱指引部分列表
-    }
-
-    async def run(self, text: str) -> Dict[str, List[str]]:
-        # 正则匹配三种括号内的内容
-        # 注意：此正则假设括号不嵌套，且没有转义字符
-        pattern = r'\{([^{}]*)\}|\(([^()]*)\)|“([^”]*)”'
-
-        outline = []
-        requirement = []
-        dialogue = []
-        weak_guidance = []
-
-        pos = 0
-        for match in re.finditer(pattern, text):
-            start, end = match.span()
-            # 处理匹配前的普通文本（弱指引）
-            if start > pos:
-                weak_part = text[pos:start].strip()
-                if weak_part:
-                    weak_guidance.append(weak_part)
-
-            # 根据捕获组确定类型
-            if match.group(1) is not None:  # 大括号
-                outline.append(match.group(1).strip())
-            elif match.group(2) is not None:  # 小括号
-                requirement.append(match.group(2).strip())
-            elif match.group(3) is not None:  # 中文引号
-                dialogue.append(match.group(3).strip())
-
-            pos = end
-
-        # 处理剩余的普通文本
-        if pos < len(text):
-            weak_part = text[pos:].strip()
-            if weak_part:
-                weak_guidance.append(weak_part)
-
-        return {
-            "outline": outline,
-            "requirement": requirement,
-            "dialogue": dialogue,
-            "weak_guidance": weak_guidance
-        }
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -1,3 +1,12 @@
 fastapi==0.104.1
 uvicorn[standard]==0.24.0
-python-multipart==0.0.6
+python-multipart==0.0.6
+cryptography>=41.0.0
+requests>=2.31.0
+
+# LangChain for LLM integration (让 pip 自动解析兼容版本)
+langchain>=0.1.0
+langchain-openai>=0.0.5
+langchain-anthropic>=0.1.1
+openai>=1.12.0
+anthropic>=0.23.0
--- a/backend/services/init.py
+++ b/backend/services/init.py
@@ -0,0 +1,11 @@
+"""
+业务服务层
+
+包含项目的核心业务逻辑，协调 Models、Utils 和 LLM 组件。
+"""
+from .prompt_assembler import PromptAssembler, PromptConfig
+
+__all__ = [
+    'PromptAssembler',
+    'PromptConfig',
+]
--- a/backend/services/character_card_converter.py
+++ b/backend/services/character_card_converter.py
@@ -0,0 +1,166 @@
+"""
+角色卡格式转换器
+支持 SillyTavern V2/V3 格式与内部格式的双向转换
+"""
+import json
+import base64
+from typing import Optional, Dict, Any
+from pathlib import Path
+from PIL import Image
+import io
+
+try:
+    from backend.models.internal import CharacterCard
+except ImportError:
+    from models.internal import CharacterCard
+
+
+class CharacterCardConverter:
+    """角色卡格式转换器"""
+    
+    @staticmethod
+    def st_to_internal(st_data: dict, avatar_path: Optional[str] = None) -> CharacterCard:
+        """
+        SillyTavern 格式 → 内部格式
+        
+        Args:
+            st_data: SillyTavern 角色卡数据（V2/V3）
+            avatar_path: 头像路径（可选）
+        
+        Returns:
+            CharacterCard 对象
+        """
+        import uuid
+        from datetime import datetime
+        
+        # 兼容两种传入方式：完整ST格式或直接data
+        if 'spec' in st_data:
+            data = st_data.get('data', {})
+        else:
+            data = st_data
+        
+        extensions = data.get('extensions', {})
+        
+        return CharacterCard(
+            id=str(uuid.uuid4()),
+            name=data['name'],
+            description=data.get('description', ''),
+            personality=data.get('personality', ''),
+            scenario=data.get('scenario', ''),
+            first_mes=data.get('first_mes', ''),
+            mes_example=data.get('mes_example', ''),
+            categories=[],  # ST没有categories
+            worldInfoId=extensions.get('world'),
+            outputSchema=None,  # ST不支持结构化输出
+            avatarPath=avatar_path,
+            alternate_greetings=data.get('alternate_greetings', []),
+            tags=data.get('tags', []),
+            createdAt=int(datetime.now().timestamp()),
+            updatedAt=int(datetime.now().timestamp()),
+            lastChatAt=None,
+            isFavorite=extensions.get('fav', False),
+            version=1
+        )
+    
+    @staticmethod
+    def internal_to_st(character: CharacterCard) -> dict:
+        """
+        内部格式 → SillyTavern V3 格式
+        
+        Args:
+            character: CharacterCard 对象
+        
+        Returns:
+            SillyTavern V3 格式字典
+        """
+        return {
+            "spec": "chara_card_v3",
+            "spec_version": "3.0",
+            "data": {
+                "name": character.name,
+                "description": character.description,
+                "personality": character.personality,
+                "scenario": character.scenario,
+                "first_mes": character.first_mes,
+                "mes_example": character.mes_example,
+                "alternate_greetings": character.alternate_greetings or [],
+                "tags": character.tags or [],
+                "creator_notes": "",
+                "system_prompt": "",
+                "post_history_instructions": "",
+                "extensions": {
+                    "world": character.worldInfoId,
+                    "talkativeness": 0.5,
+                    "fav": character.isFavorite
+                }
+            }
+        }
+    
+    @staticmethod
+    def export_as_png(character: CharacterCard, avatar_path: Optional[str] = None, use_default_avatar: bool = False) -> bytes:
+        """
+        导出为 SillyTavern PNG 格式
+        
+        Args:
+            character: CharacterCard 对象
+            avatar_path: 头像图片路径（可选）
+            use_default_avatar: 是否使用默认头像（不嵌入JSON数据）
+        
+        Returns:
+            PNG 文件的二进制数据
+        """
+        # 1. 创建/加载图片
+        if avatar_path and Path(avatar_path).exists():
+            img = Image.open(avatar_path)
+        else:
+            # 创建默认图片（400x600像素，灰色背景）
+            img = Image.new('RGB', (400, 600), color=(73, 109, 137))
+        
+        # 确保是 RGBA 模式
+        if img.mode != 'RGBA':
+            img = img.convert('RGBA')
+        
+        # 2. 如果不是默认头像，才嵌入 JSON 数据
+        if not use_default_avatar:
+            st_data = CharacterCardConverter.internal_to_st(character)
+            json_str = json.dumps(st_data, ensure_ascii=False)
+            base64_data = base64.b64encode(json_str.encode('utf-8')).decode('ascii')
+            img.text['ccv3'] = base64_data
+        
+        # 3. 保存到字节流
+        buffer = io.BytesIO()
+        img.save(buffer, format='PNG')
+        buffer.seek(0)
+        
+        return buffer.read()
+    
+    @staticmethod
+    def extract_from_png(png_data: bytes) -> Optional[dict]:
+        """
+        从 PNG 文件中提取嵌入的角色数据
+        
+        Args:
+            png_data: PNG 文件的二进制数据
+        
+        Returns:
+            SillyTavern 格式字典，如果没有嵌入数据则返回 None
+        """
+        try:
+            img = Image.open(io.BytesIO(png_data))
+            
+            # 尝试 V3 格式 (ccv3)
+            if 'ccv3' in img.text:
+                json_str = base64.b64decode(img.text['ccv3']).decode('utf-8')
+                return json.loads(json_str)
+            
+            # 尝试 V2 格式 (chara)
+            elif 'chara' in img.text:
+                json_str = base64.b64decode(img.text['chara']).decode('utf-8')
+                return json.loads(json_str)
+            
+            # 没有嵌入数据
+            return None
+        
+        except Exception as e:
+            print(f"解析PNG失败: {e}")
+            return None
--- a/backend/services/character_service.py
+++ b/backend/services/character_service.py
@@ -0,0 +1,318 @@
+"""
+角色卡服务 - 严格按照 internal.py 的数据结构
+每个角色一个文件夹，包含 character.json、avatar.png 和 chats/
+"""
+import json
+from pathlib import Path
+from typing import List, Optional
+from datetime import datetime
+import uuid
+
+try:
+    from backend.models.internal import CharacterCard
+    from backend.core.config import settings
+    from backend.services.character_card_converter import CharacterCardConverter
+except ImportError:
+    from models.internal import CharacterCard
+    from core.config import settings
+    from services.character_card_converter import CharacterCardConverter
+
+
+class CharacterService:
+    """角色卡管理服务"""
+    
+    def __init__(self):
+        self.characters_dir = settings.CHARACTERS_PATH
+        self.converter = CharacterCardConverter()
+        
+        # 确保目录存在
+        self.characters_dir.mkdir(parents=True, exist_ok=True)
+    
+    def scan_all_characters(self) -> List[CharacterCard]:
+        """
+        扫描所有角色卡
+        
+        Returns:
+            按 lastChatAt 排序的角色卡列表（最新的在前）
+        """
+        characters = []
+        
+        for char_folder in self.characters_dir.iterdir():
+            if not char_folder.is_dir():
+                continue
+            
+            try:
+                character = self._load_character_from_folder(char_folder)
+                if character:
+                    characters.append(character)
+            except Exception as e:
+                print(f"加载角色卡失败 {char_folder.name}: {e}")
+                continue
+        
+        # 按最后聊天时间排序（None 排最后）
+        characters.sort(
+            key=lambda c: c.lastChatAt or 0, 
+            reverse=True
+        )
+        
+        return characters
+    
+    def _load_character_from_folder(self, folder: Path) -> Optional[CharacterCard]:
+        """
+        从文件夹加载角色卡
+        
+        Args:
+            folder: 角色文件夹路径
+        
+        Returns:
+            CharacterCard 对象或 None
+        """
+        # 1. 读取 character.json（必须存在）
+        char_file = folder / "character.json"
+        if not char_file.exists():
+            return None
+        
+        with open(char_file, 'r', encoding='utf-8') as f:
+            data = json.load(f)
+        
+        # 2. 检查是否有 avatar.png
+        avatar_path = None
+        avatar_file = folder / "avatar.png"
+        if avatar_file.exists():
+            # 存储相对路径，用于前端访问
+            avatar_path = f"/api/characters/{folder.name}/avatar"
+        
+        # 3. 计算最后聊天时间
+        last_chat_at = self._get_last_chat_timestamp(folder)
+        
+        # 4. 构建 CharacterCard 对象（严格按照数据结构）
+        character = CharacterCard(
+            id=data.get('id', str(uuid.uuid4())),
+            name=data['name'],
+            description=data.get('description', ''),
+            personality=data.get('personality', ''),
+            scenario=data.get('scenario', ''),
+            first_mes=data.get('first_mes', ''),
+            mes_example=data.get('mes_example', ''),
+            categories=data.get('categories', []),
+            worldInfoId=data.get('worldInfoId'),
+            outputSchema=data.get('outputSchema'),
+            avatarPath=avatar_path,
+            alternate_greetings=data.get('alternate_greetings', []),
+            tags=data.get('tags', []),
+            createdAt=data.get('createdAt', int(datetime.now().timestamp())),
+            updatedAt=data.get('updatedAt', int(datetime.now().timestamp())),
+            lastChatAt=last_chat_at,
+            isFavorite=data.get('isFavorite', False),
+            version=data.get('version', 1)
+        )
+        
+        return character
+    
+    def _get_last_chat_timestamp(self, char_folder: Path) -> Optional[int]:
+        """
+        获取角色的最后聊天时间戳
+        
+        通过扫描 chats 目录下所有 .jsonl 文件的修改时间
+        """
+        chats_dir = char_folder / "chats"
+        if not chats_dir.exists():
+            return None
+        
+        latest_time = None
+        
+        for chat_file in chats_dir.glob("*.jsonl"):
+            file_mtime = int(chat_file.stat().st_mtime)
+            if latest_time is None or file_mtime > latest_time:
+                latest_time = file_mtime
+        
+        return latest_time
+    
+    def get_character_by_name(self, name: str) -> Optional[CharacterCard]:
+        """根据角色名获取角色卡"""
+        char_folder = self.characters_dir / name
+        if not char_folder.exists():
+            return None
+        
+        return self._load_character_from_folder(char_folder)
+    
+    def create_character(self, character_data: dict) -> CharacterCard:
+        """
+        创建新角色卡
+        
+        Args:
+            character_data: 角色数据字典
+        
+        Returns:
+            创建的 CharacterCard 对象
+        """
+        # 生成唯一ID
+        if 'id' not in character_data:
+            character_data['id'] = str(uuid.uuid4())
+        
+        # 设置时间戳
+        now = int(datetime.now().timestamp())
+        character_data['createdAt'] = now
+        character_data['updatedAt'] = now
+        character_data['lastChatAt'] = None
+        
+        # 创建文件夹
+        char_name = character_data['name']
+        char_folder = self.characters_dir / char_name
+        char_folder.mkdir(parents=True, exist_ok=True)
+        
+        # 创建 chats 目录
+        chats_dir = char_folder / "chats"
+        chats_dir.mkdir(exist_ok=True)
+        
+        # 保存 character.json
+        char_file = char_folder / "character.json"
+        with open(char_file, 'w', encoding='utf-8') as f:
+            json.dump(character_data, f, ensure_ascii=False, indent=2)
+        
+        return self._load_character_from_folder(char_folder)
+    
+    def update_character(self, name: str, updates: dict) -> CharacterCard:
+        """
+        更新角色卡
+        
+        Args:
+            name: 角色名
+            updates: 更新的字段
+        
+        Returns:
+            更新后的 CharacterCard 对象
+        """
+        char_folder = self.characters_dir / name
+        char_file = char_folder / "character.json"
+        
+        if not char_file.exists():
+            raise FileNotFoundError(f"角色卡不存在: {name}")
+        
+        # 读取现有数据
+        with open(char_file, 'r', encoding='utf-8') as f:
+            existing_data = json.load(f)
+        
+        # 合并更新
+        existing_data.update(updates)
+        existing_data['updatedAt'] = int(datetime.now().timestamp())
+        
+        # 保存
+        with open(char_file, 'w', encoding='utf-8') as f:
+            json.dump(existing_data, f, ensure_ascii=False, indent=2)
+        
+        return self._load_character_from_folder(char_folder)
+    
+    def delete_character(self, name: str) -> bool:
+        """
+        删除角色卡（包括所有聊天记录）
+        
+        Args:
+            name: 角色名
+        
+        Returns:
+            是否成功删除
+        """
+        char_folder = self.characters_dir / name
+        if not char_folder.exists():
+            return False
+        
+        import shutil
+        shutil.rmtree(char_folder)
+        return True
+    
+    def save_avatar(self, name: str, image_data: bytes) -> str:
+        """
+        保存角色头像
+        
+        Args:
+            name: 角色名
+            image_data: 图片二进制数据
+        
+        Returns:
+            头像访问路径
+        """
+        char_folder = self.characters_dir / name
+        avatar_file = char_folder / "avatar.png"
+        
+        with open(avatar_file, 'wb') as f:
+            f.write(image_data)
+        
+        return f"/api/characters/{name}/avatar"
+    
+    def import_from_png(self, png_data: bytes, filename: str) -> CharacterCard:
+        """
+        从 SillyTavern PNG 导入角色卡
+        
+        Args:
+            png_data: PNG 文件二进制数据
+            filename: 原始文件名
+        
+        Returns:
+            创建的 CharacterCard 对象
+        """
+        # 1. 提取嵌入数据
+        st_data = self.converter.extract_from_png(png_data)
+        if not st_data:
+            raise ValueError("PNG文件中没有嵌入角色数据")
+        
+        # 2. 转换为内部格式
+        character = self.converter.st_to_internal(st_data)
+        
+        # 3. 创建角色文件夹
+        char_name = character.name
+        char_folder = self.characters_dir / char_name
+        char_folder.mkdir(parents=True, exist_ok=True)
+        
+        # 4. 保存 PNG 作为 avatar.png
+        avatar_file = char_folder / "avatar.png"
+        with open(avatar_file, 'wb') as f:
+            f.write(png_data)
+        
+        # 5. 保存 character.json
+        char_file = char_folder / "character.json"
+        with open(char_file, 'w', encoding='utf-8') as f:
+            json.dump(character.dict(), f, ensure_ascii=False, indent=2)
+        
+        # 6. 创建 chats 目录
+        (char_folder / "chats").mkdir(exist_ok=True)
+        
+        return character
+    
+    def export_as_png(self, name: str) -> bytes:
+        """
+        导出角色为 SillyTavern PNG 格式
+        
+        Args:
+            name: 角色名
+        
+        Returns:
+            PNG 文件二进制数据
+        """
+        character = self.get_character_by_name(name)
+        if not character:
+            raise FileNotFoundError(f"角色 '{name}' 不存在")
+        
+        # 获取头像路径
+        avatar_path = None
+        if character.avatarPath:
+            # 从路径中提取文件名
+            avatar_filename = character.avatarPath.split('/')[-1].split('?')[0]
+            char_folder = self.characters_dir / name
+            avatar_file = char_folder / avatar_filename
+            if avatar_file.exists():
+                avatar_path = str(avatar_file)
+        
+        # 如果没有头像，使用默认图片
+        use_default = False
+        if not avatar_path:
+            default_avatar = self.characters_dir / "defult.png"
+            if default_avatar.exists():
+                avatar_path = str(default_avatar)
+                use_default = True
+                print(f"使用默认头像: {avatar_path}")
+            else:
+                print("警告: 没有找到默认头像")
+        
+        # 生成 PNG
+        return self.converter.export_as_png(character, avatar_path, use_default_avatar=use_default)
--- a/backend/services/chat_service.py
+++ b/backend/services/chat_service.py
@@ -0,0 +1,383 @@
+"""
+聊天服务 - 处理聊天记录的读写操作
+
+基于 SillyTavern JSONL 格式的聊天记录管理
+"""
+from pathlib import Path
+from typing import Dict, List, Optional, Any
+import json
+import logging
+from datetime import datetime
+import uuid
+
+logger = logging.getLogger(__name__)
+
+
+class ChatService:
+    """聊天服务类，处理聊天记录的CRUD操作"""
+    
+    def __init__(self, data_path: Path):
+        """
+        初始化聊天服务
+        
+        Args:
+            data_path: 数据目录路径
+        """
+        self.data_path = data_path
+        self.chat_dir = data_path / "chat"
+        self.chat_dir.mkdir(parents=True, exist_ok=True)
+    
+    def list_all_chats(self) -> Dict[str, List[Dict]]:
+        """
+        获取所有角色和聊天列表
+        
+        Returns:
+            Dict[str, List[Dict]]: 字典结构，键是角色名称，值是该角色的聊天信息列表
+        """
+        result = {}
+        
+        if not self.chat_dir.exists():
+            logger.warning(f"聊天目录不存在: {self.chat_dir}")
+            return result
+        
+        for role_dir in self.chat_dir.iterdir():
+            try:
+                if role_dir.is_dir():
+                    chats = []
+                    
+                    for chat_file in role_dir.glob("*.jsonl"):
+                        chat_info = self._get_chat_summary(role_dir.name, chat_file.stem)
+                        if chat_info:
+                            chats.append(chat_info)
+                    
+                    if chats:
+                        result[role_dir.name] = chats
+                        
+            except Exception as e:
+                logger.error(f"处理角色目录 {role_dir.name} 时出错: {str(e)}")
+                continue
+        
+        return {"chat": [{"role_name": role, **chat} for role, chats in result.items() for chat in chats]}
+    
+    def _get_chat_summary(self, role_name: str, chat_name: str) -> Optional[Dict]:
+        """
+        获取聊天摘要信息
+        
+        Args:
+            role_name: 角色名称
+            chat_name: 聊天名称
+            
+        Returns:
+            Dict: 聊天摘要信息，如果文件不存在则返回None
+        """
+        chat_file = self.chat_dir / role_name / f"{chat_name}.jsonl"
+        
+        if not chat_file.exists():
+            return None
+        
+        try:
+            with open(chat_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+            
+            if not lines:
+                return None
+            
+            # 第一行是header
+            header = json.loads(lines[0])
+            
+            # 计算消息数量（排除header）
+            message_count = len(lines) - 1
+            
+            # 获取最后修改时间
+            last_modified = datetime.fromtimestamp(
+                chat_file.stat().st_mtime
+            ).isoformat()
+            
+            # 获取最后一条消息预览
+            last_message = ""
+            if message_count > 0:
+                try:
+                    last_msg_data = json.loads(lines[-1])
+                    last_message = last_msg_data.get("mes", "")
+                except:
+                    pass
+            
+            return {
+                "chat_name": chat_name,
+                "user_name": header.get("user_name", "User"),
+                "character_name": header.get("character_name", ""),
+                "last_modified": last_modified,
+                "message_count": message_count,
+                "last_message": last_message
+            }
+            
+        except Exception as e:
+            logger.error(f"读取聊天摘要失败 {role_name}/{chat_name}: {str(e)}")
+            return None
+    
+    def get_chat(self, role_name: str, chat_name: str) -> Dict[str, Any]:
+        """
+        获取指定聊天的完整内容
+        
+        Args:
+            role_name: 角色名称
+            chat_name: 聊天名称
+            
+        Returns:
+            Dict: 包含metadata和messages的字典
+            
+        Raises:
+            FileNotFoundError: 聊天文件不存在
+        """
+        chat_file = self.chat_dir / role_name / f"{chat_name}.jsonl"
+        
+        if not chat_file.exists():
+            raise FileNotFoundError(f"Chat not found: {role_name}/{chat_name}")
+        
+        try:
+            with open(chat_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+            
+            if not lines:
+                raise ValueError(f"Empty chat file: {role_name}/{chat_name}")
+            
+            # 第一行是header
+            header = json.loads(lines[0])
+            
+            # 解析消息
+            messages = []
+            for i, line in enumerate(lines[1:], start=1):
+                if line.strip():  # 跳过空行
+                    msg_data = json.loads(line)
+                    # 确保有floor字段
+                    if "floor" not in msg_data:
+                        msg_data["floor"] = i
+                    
+                    messages.append(msg_data)
+            
+            return {
+                "metadata": {
+                    "user_name": header.get("user_name", "User"),
+                    "character_name": header.get("character_name", ""),
+                    "chat_id": header.get("chat_id_hash", ""),
+                    "integrity": header.get("integrity", "")
+                },
+                "messages": messages
+            }
+            
+        except Exception as e:
+            logger.error(f"读取聊天失败 {role_name}/{chat_name}: {str(e)}")
+            raise
+    
+    def create_chat(self, role_name: str, chat_name: str, metadata: Dict = None) -> Dict:
+        """
+        创建新聊天
+        
+        Args:
+            role_name: 角色名称
+            chat_name: 聊天名称
+            metadata: 聊天元数据
+            
+        Returns:
+            Dict: 创建的聊天信息
+            
+        Raises:
+            FileExistsError: 聊天已存在
+        """
+        chat_file = self.chat_dir / role_name / f"{chat_name}.jsonl"
+        
+        if chat_file.exists():
+            raise FileExistsError(f"Chat already exists: {role_name}/{chat_name}")
+        
+        # 创建角色目录
+        chat_file.parent.mkdir(parents=True, exist_ok=True)
+        
+        # 构建header
+        header = {
+            "user_name": metadata.get("user_name", "User") if metadata else "User",
+            "character_name": metadata.get("character_name", role_name) if metadata else role_name,
+            "integrity": str(uuid.uuid4()),
+            "chat_id_hash": str(uuid.uuid4()),
+            "note_prompt": "",
+            "note_interval": 0,
+            "note_position": 0,
+            "note_depth": 0,
+            "note_role": 0,
+            "extensions": {},
+            "timedWorldInfo": {},
+            "variables": {},
+            "tainted": False,
+            "lastInContextMessageId": -1
+        }
+        
+        # 写入header
+        with open(chat_file, 'w', encoding='utf-8') as f:
+            f.write(json.dumps(header, ensure_ascii=False) + '\n')
+        
+        return {
+            "role_name": role_name,
+            "chat_name": chat_name,
+            "metadata": {
+                "user_name": header["user_name"],
+                "character_name": header["character_name"]
+            }
+        }
+    
+    def add_message(self, role_name: str, chat_name: str, message_data: Dict) -> Dict:
+        """
+        向聊天添加新消息
+        
+        Args:
+            role_name: 角色名称
+            chat_name: 聊天名称
+            message_data: 消息数据
+            
+        Returns:
+            Dict: 添加的消息
+            
+        Raises:
+            FileNotFoundError: 聊天不存在
+        """
+        chat_file = self.chat_dir / role_name / f"{chat_name}.jsonl"
+        
+        if not chat_file.exists():
+            raise FileNotFoundError(f"Chat not found: {role_name}/{chat_name}")
+        
+        try:
+            # 读取现有消息以确定floor
+            with open(chat_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+            
+            # 计算下一个floor号
+            next_floor = len(lines) - 1  # 减去header行
+            
+            # 构建完整的消息数据
+            full_message = {
+                "name": message_data.get("name", "User"),
+                "is_user": message_data.get("is_user", True),
+                "is_system": message_data.get("is_system", False),
+                "floor": next_floor,
+                "send_date": message_data.get("send_date", str(int(datetime.now().timestamp() * 1000))),
+                "mes": message_data.get("mes", ""),
+                "extra": message_data.get("extra", {}),
+                "swipes": message_data.get("swipes", []),
+                "swipe_id": message_data.get("swipe_id", 0),
+                "force_avatar": None,
+                "variables": [],
+                "variables_initialized": [],
+                "is_ejs_processed": []
+            }
+            
+            # 追加消息到文件
+            with open(chat_file, 'a', encoding='utf-8') as f:
+                f.write(json.dumps(full_message, ensure_ascii=False) + '\n')
+            
+            return full_message
+            
+        except Exception as e:
+            logger.error(f"添加消息失败 {role_name}/{chat_name}: {str(e)}")
+            raise
+    
+    def update_message(self, role_name: str, chat_name: str, floor: int, update_data: Dict) -> Dict:
+        """
+        更新指定楼层的消息
+        
+        Args:
+            role_name: 角色名称
+            chat_name: 聊天名称
+            floor: 楼层号
+            update_data: 更新的数据
+            
+        Returns:
+            Dict: 更新后的消息
+            
+        Raises:
+            FileNotFoundError: 聊天不存在
+            ValueError: 楼层不存在
+        """
+        chat_file = self.chat_dir / role_name / f"{chat_name}.jsonl"
+        
+        if not chat_file.exists():
+            raise FileNotFoundError(f"Chat not found: {role_name}/{chat_name}")
+        
+        try:
+            # 读取所有行
+            with open(chat_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+            
+            # 找到对应的消息行（floor + 1，因为第0行是header）
+            message_line_index = floor + 1
+            
+            if message_line_index >= len(lines):
+                raise ValueError(f"Floor {floor} not found in chat")
+            
+            # 解析并更新消息
+            msg_data = json.loads(lines[message_line_index])
+            msg_data.update(update_data)
+            
+            # 写回文件
+            lines[message_line_index] = json.dumps(msg_data, ensure_ascii=False) + '\n'
+            
+            with open(chat_file, 'w', encoding='utf-8') as f:
+                f.writelines(lines)
+            
+            return msg_data
+            
+        except Exception as e:
+            logger.error(f"更新消息失败 {role_name}/{chat_name}/{floor}: {str(e)}")
+            raise
+    
+    def delete_message(self, role_name: str, chat_name: str, floor: int) -> Dict:
+        """
+        删除指定楼层的消息
+        
+        Args:
+            role_name: 角色名称
+            chat_name: 聊天名称
+            floor: 楼层号
+            
+        Returns:
+            Dict: 被删除的消息
+            
+        Raises:
+            FileNotFoundError: 聊天不存在
+            ValueError: 楼层不存在
+        """
+        chat_file = self.chat_dir / role_name / f"{chat_name}.jsonl"
+        
+        if not chat_file.exists():
+            raise FileNotFoundError(f"Chat not found: {role_name}/{chat_name}")
+        
+        try:
+            # 读取所有行
+            with open(chat_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+            
+            # 找到对应的消息行
+            message_line_index = floor + 1
+            
+            if message_line_index >= len(lines):
+                raise ValueError(f"Floor {floor} not found in chat")
+            
+            # 保存被删除的消息
+            deleted_msg = json.loads(lines[message_line_index])
+            
+            # 删除该行
+            del lines[message_line_index]
+            
+            # 重新编号后续消息的floor
+            for i in range(message_line_index, len(lines)):
+                if lines[i].strip():  # 跳过空行
+                    msg_data = json.loads(lines[i])
+                    msg_data["floor"] = i - 1  # 重新计算floor
+                    lines[i] = json.dumps(msg_data, ensure_ascii=False) + '\n'
+            
+            # 写回文件
+            with open(chat_file, 'w', encoding='utf-8') as f:
+                f.writelines(lines)
+            
+            return deleted_msg
+            
+        except Exception as e:
+            logger.error(f"删除消息失败 {role_name}/{chat_name}/{floor}: {str(e)}")
+            raise
--- a/backend/services/comfyui_workflow_manager.py
+++ b/backend/services/comfyui_workflow_manager.py
@@ -0,0 +1,173 @@
+"""
+ComfyUI Workflow Manager
+管理工作流 JSON 文件的上传、删除和加载
+"""
+import json
+import os
+from pathlib import Path
+from typing import List, Dict, Optional
+from fastapi import UploadFile, HTTPException
+import shutil
+from core.config import settings
+
+# 工作流目录 - 使用统一的数据目录
+WORKFLOW_DIR = settings.COMFYUI_WORKFLOWS_PATH
+WORKFLOW_DIR.mkdir(parents=True, exist_ok=True)
+
+
+class WorkflowManager:
+    """ComfyUI 工作流管理器"""
+    
+    @staticmethod
+    def list_workflows() -> List[Dict[str, str]]:
+        """列出所有可用的工作流"""
+        workflows = []
+        
+        for json_file in WORKFLOW_DIR.glob("*.json"):
+            try:
+                with open(json_file, 'r', encoding='utf-8') as f:
+                    workflow_data = json.load(f)
+                
+                workflows.append({
+                    "filename": json_file.name,
+                    "name": json_file.stem,
+                    "nodes_count": len(workflow_data),
+                    "size": json_file.stat().st_size
+                })
+            except Exception as e:
+                print(f"Error loading workflow {json_file.name}: {e}")
+                continue
+        
+        return workflows
+    
+    @staticmethod
+    def load_workflow(filename: str) -> Dict:
+        """加载指定工作流"""
+        filepath = WORKFLOW_DIR / filename
+        
+        if not filepath.exists():
+            raise HTTPException(status_code=404, detail=f"Workflow '{filename}' not found")
+        
+        if not filepath.suffix == '.json':
+            raise HTTPException(status_code=400, detail="Invalid file type")
+        
+        try:
+            with open(filepath, 'r', encoding='utf-8') as f:
+                return json.load(f)
+        except json.JSONDecodeError as e:
+            raise HTTPException(status_code=500, detail=f"Invalid JSON: {str(e)}")
+    
+    @staticmethod
+    async def upload_workflow(file: UploadFile) -> Dict[str, str]:
+        """上传工作流文件"""
+        # 验证文件名
+        if not file.filename or not file.filename.endswith('.json'):
+            raise HTTPException(status_code=400, detail="File must be a JSON file")
+        
+        # 安全检查：防止路径遍历攻击
+        safe_filename = os.path.basename(file.filename)
+        if not safe_filename:
+            raise HTTPException(status_code=400, detail="Invalid filename")
+        
+        filepath = WORKFLOW_DIR / safe_filename
+        
+        # 如果文件已存在，先备份
+        if filepath.exists():
+            backup_path = WORKFLOW_DIR / f"{safe_filename}.bak"
+            shutil.copy2(filepath, backup_path)
+        
+        # 保存文件
+        try:
+            content = await file.read()
+            
+            # 验证 JSON 格式
+            try:
+                workflow_data = json.loads(content)
+                
+                # 基本验证：检查是否是 ComfyUI 工作流
+                if not isinstance(workflow_data, dict):
+                    raise ValueError("Workflow must be a JSON object")
+                
+                # 检查是否包含必要的节点类型
+                has_sampler = any(
+                    node.get("class_type") == "KSampler" 
+                    for node in workflow_data.values()
+                    if isinstance(node, dict)
+                )
+                
+                if not has_sampler:
+                    raise ValueError("Invalid ComfyUI workflow: missing KSampler node")
+                
+            except json.JSONDecodeError:
+                raise HTTPException(status_code=400, detail="Invalid JSON format")
+            except ValueError as e:
+                raise HTTPException(status_code=400, detail=str(e))
+            
+            # 写入文件
+            with open(filepath, 'w', encoding='utf-8') as f:
+                f.write(content.decode('utf-8'))
+            
+            return {
+                "message": "Workflow uploaded successfully",
+                "filename": safe_filename,
+                "size": len(content)
+            }
+        
+        except HTTPException:
+            raise
+        except Exception as e:
+            # 如果出错，恢复备份
+            backup_path = WORKFLOW_DIR / f"{safe_filename}.bak"
+            if backup_path.exists():
+                shutil.move(backup_path, filepath)
+            raise HTTPException(status_code=500, detail=f"Upload failed: {str(e)}")
+    
+    @staticmethod
+    def delete_workflow(filename: str) -> Dict[str, str]:
+        """删除工作流文件"""
+        # 安全检查
+        safe_filename = os.path.basename(filename)
+        if not safe_filename or not safe_filename.endswith('.json'):
+            raise HTTPException(status_code=400, detail="Invalid filename")
+        
+        filepath = WORKFLOW_DIR / safe_filename
+        
+        if not filepath.exists():
+            raise HTTPException(status_code=404, detail=f"Workflow '{filename}' not found")
+        
+        # 不允许删除默认工作流
+        if safe_filename == "default_txt2img.json":
+            raise HTTPException(
+                status_code=403, 
+                detail="Cannot delete default workflow"
+            )
+        
+        try:
+            filepath.unlink()
+            return {"message": f"Workflow '{safe_filename}' deleted successfully"}
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"Delete failed: {str(e)}")
+    
+    @staticmethod
+    def replace_prompt_in_workflow(workflow: Dict, prompt: str) -> Dict:
+        """
+        在工作流中替换提示词
+        找到第一个 CLIPTextEncode 节点，替换其 text 字段
+        """
+        import copy
+        workflow_copy = copy.deepcopy(workflow)
+        
+        # 查找 CLIPTextEncode 节点（通常是正向提示词）
+        for node_id, node in workflow_copy.items():
+            if isinstance(node, dict) and node.get("class_type") == "CLIPTextEncode":
+                if "text" in node.get("inputs", {}):
+                    # 替换提示词
+                    node["inputs"]["text"] = prompt
+                    return workflow_copy
+        
+        # 如果没有找到 CLIPTextEncode 节点，抛出错误
+        raise ValueError("No CLIPTextEncode node found in workflow")
+
+
+# 全局实例
+workflow_manager = WorkflowManager()
--- a/backend/services/llm_model_service.py
+++ b/backend/services/llm_model_service.py
@@ -0,0 +1,172 @@
+"""
+LLM 模型管理服务
+
+提供获取不同 LLM 提供商可用模型列表的功能
+"""
+from typing import List, Dict, Any, Optional
+import requests
+
+
+class LLMModelService:
+    """LLM 模型管理服务"""
+    
+    @staticmethod
+    def get_openai_models(api_key: str, base_url: Optional[str] = None) -> List[str]:
+        """
+        获取 OpenAI 兼容 API 的模型列表
+        
+        Args:
+            api_key: API Key
+            base_url: API 基础 URL，默认为 OpenAI 官方 API
+            
+        Returns:
+            模型名称列表
+        """
+        try:
+            # 默认使用 OpenAI 官方 API
+            if not base_url:
+                base_url = "https://api.openai.com/v1"
+            
+            # 确保 base_url 以 /v1 结尾
+            if not base_url.endswith('/v1'):
+                base_url = base_url.rstrip('/') + '/v1'
+            
+            response = requests.get(
+                f"{base_url}/models",
+                headers={
+                    "Authorization": f"Bearer {api_key}",
+                    "Content-Type": "application/json"
+                },
+                timeout=10
+            )
+            
+            if response.status_code != 200:
+                raise Exception(f"HTTP {response.status_code}: {response.text}")
+            
+            data = response.json()
+            models = [model['id'] for model in data.get('data', [])]
+            
+            # 过滤出聊天模型（可选）
+            chat_models = [
+                m for m in models 
+                if any(keyword in m.lower() for keyword in ['gpt', 'chat'])
+            ]
+            
+            # 如果没有找到聊天模型，返回所有模型
+            return chat_models if chat_models else models
+            
+        except Exception as e:
+            raise Exception(f"获取 OpenAI 模型列表失败: {str(e)}")
+    
+    @staticmethod
+    def get_anthropic_models(api_key: str) -> List[str]:
+        """
+        获取 Anthropic Claude 模型列表
+        
+        Args:
+            api_key: API Key
+            
+        Returns:
+            模型名称列表
+        """
+        try:
+            # Anthropic 没有公开的模型列表 API，返回已知模型
+            return [
+                "claude-3-5-sonnet-20241022",
+                "claude-3-5-haiku-20241022",
+                "claude-3-opus-20240229",
+                "claude-3-sonnet-20240229",
+                "claude-3-haiku-20240307",
+                "claude-2.1",
+                "claude-2.0",
+                "claude-instant-1.2"
+            ]
+            
+        except Exception as e:
+            raise Exception(f"获取 Anthropic 模型列表失败: {str(e)}")
+    
+    @staticmethod
+    def get_ollama_models(base_url: str = "http://localhost:11434") -> List[str]:
+        """
+        获取 Ollama 本地模型列表
+        
+        Args:
+            base_url: Ollama API 地址
+            
+        Returns:
+            模型名称列表
+        """
+        try:
+            response = requests.get(
+                f"{base_url}/api/tags",
+                timeout=10
+            )
+            
+            if response.status_code != 200:
+                raise Exception(f"HTTP {response.status_code}: {response.text}")
+            
+            data = response.json()
+            models = [model['name'] for model in data.get('models', [])]
+            
+            return models
+            
+        except Exception as e:
+            raise Exception(f"获取 Ollama 模型列表失败: {str(e)}")
+    
+    @staticmethod
+    def detect_provider(api_url: str) -> str:
+        """
+        根据 API URL 检测提供商类型
+        
+        Args:
+            api_url: API 地址
+            
+        Returns:
+            提供商类型: 'openai', 'anthropic', 'ollama', 'unknown'
+        """
+        api_url_lower = api_url.lower()
+        
+        if 'openai' in api_url_lower or 'api.openai.com' in api_url_lower:
+            return 'openai'
+        elif 'anthropic' in api_url_lower or 'api.anthropic.com' in api_url_lower:
+            return 'anthropic'
+        elif 'ollama' in api_url_lower or 'localhost:11434' in api_url_lower or '127.0.0.1:11434' in api_url_lower:
+            return 'ollama'
+        elif 'siliconflow' in api_url_lower or 'silicon.cloud' in api_url_lower:
+            # SiliconFlow 等兼容 OpenAI API 的服务
+            return 'openai'
+        elif 'deepseek' in api_url_lower:
+            # DeepSeek 等兼容 OpenAI API 的服务
+            return 'openai'
+        else:
+            # 默认尝试 OpenAI 兼容 API
+            return 'openai'
+    
+    @staticmethod
+    def get_models_by_provider(
+        provider: str,
+        api_key: str,
+        api_url: Optional[str] = None
+    ) -> List[str]:
+        """
+        根据提供商类型获取模型列表
+        
+        Args:
+            provider: 提供商类型 ('openai', 'anthropic', 'ollama')
+            api_key: API Key
+            api_url: API 地址（可选）
+            
+        Returns:
+            模型名称列表
+        """
+        if provider == 'openai':
+            return LLMModelService.get_openai_models(api_key, api_url)
+        elif provider == 'anthropic':
+            return LLMModelService.get_anthropic_models(api_key)
+        elif provider == 'ollama':
+            base_url = api_url or "http://localhost:11434"
+            # 移除 /v1 后缀（如果有）
+            base_url = base_url.replace('/v1', '').replace('/v1/', '')
+            return LLMModelService.get_ollama_models(base_url)
+        else:
+            raise Exception(f"不支持的提供商: {provider}")
--- a/backend/services/prompt_assembler.py
+++ b/backend/services/prompt_assembler.py
@@ -0,0 +1,221 @@
+"""
+提示词组装器 (Prompt Assembler)
+
+负责根据 SillyTavern 规范将角色卡、世界书、聊天历史等组件
+拼装成最终的 LLM 消息列表。
+"""
+import re
+from typing import List, Dict, Optional
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage, BaseMessage
+
+from models.internal import CharacterCard, ChatMessage, WorldInfoEntry
+
+
+class PromptConfig:
+    """提示词组装配置"""
+    def __init__(
+        self,
+        an_position: str = "after_history", # "before_history" or "after_history"
+        an_depth: int = 4,
+        post_history_instructions: Optional[str] = None
+    ):
+        self.an_position = an_position
+        self.an_depth = an_depth
+        self.post_history_instructions = post_history_instructions
+
+
+class PromptAssembler:
+    """
+    轻量级提示词组装核心
+    
+    不依赖复杂的框架，只负责纯粹的文本拼接和位置插入。
+    """
+
+    # SillyTavern 的位置枚举映射
+    POS_WI_BEFORE = 0
+    POS_WI_AFTER = 1
+    POS_EXAMPLES_BEFORE = 2
+    POS_EXAMPLES_AFTER = 3
+    POS_AN_TOP = 4
+    POS_AN_BOTTOM = 5
+    POS_DEPTH = 6
+    POS_OUTLET = 7
+
+    def assemble(
+        self,
+        character: CharacterCard,
+        chat_history: List[ChatMessage],
+        user_input: str,
+        active_entries: List[WorldInfoEntry],
+        config: PromptConfig = PromptConfig()
+    ) -> List[BaseMessage]:
+        """
+        执行完整的提示词组装流程
+        
+        Returns:
+            List[BaseMessage]: 准备好发送给 LLM 的消息列表
+        """
+        # 1. 按位置分组世界书条目
+        grouped_entries = self._group_entries_by_position(active_entries)
+
+        # 2. 组装 Story String (包含 Pos 0-3)
+        story_string = self._build_story_string(character, grouped_entries)
+
+        # 3. 组装 Author's Note (包含 Pos 4-5)
+        authors_note_content = self._build_authors_note(grouped_entries, config.an_depth)
+
+        # 4. 处理 Chat History 并注入 Depth 条目 (Pos 6)
+        processed_history = self._inject_depth_entries(chat_history, grouped_entries.get(self.POS_DEPTH, []))
+
+        # 5. 准备 Outlet 替换字典 (Pos 7)
+        outlet_map = {entry.uid: entry.content for entry in grouped_entries.get(self.POS_OUTLET, [])}
+
+        # 6. 最终封装为 Messages
+        return self._wrap_to_messages(
+            story_string, 
+            authors_note_content, 
+            processed_history, 
+            user_input, 
+            outlet_map,
+            config
+        )
+
+    def _group_entries_by_position(self, entries: List[WorldInfoEntry]) -> Dict[int, List[WorldInfoEntry]]:
+        """将激活的条目按 position 分组"""
+        grouped = {}
+        for entry in entries:
+            # 这里假设 entry.position 存储的是我们定义的 0-7 整数
+            pos = entry.position if isinstance(entry.position, int) else 1 # 默认为 wiAfter
+            if pos not in grouped:
+                grouped[pos] = []
+            grouped[pos].append(entry)
+        
+        # 对每个组内的条目按 order 排序
+        for pos in grouped:
+            grouped[pos].sort(key=lambda x: x.order)
+        return grouped
+
+    def _build_story_string(self, character: CharacterCard, grouped: Dict) -> str:
+        """组装故事字符串 (Story String)"""
+        parts = []
+        
+        # Pos 0: wiBefore
+        for entry in grouped.get(self.POS_WI_BEFORE, []):
+            parts.append(entry.content)
+            
+        # 角色核心信息
+        parts.append(f"[Character('{character.name}')]\n{character.description}\n")
+        parts.append(f"Personality: {character.personality}\n")
+        parts.append(f"Scenario: {character.scenario}\n")
+        
+        # Pos 1: wiAfter
+        for entry in grouped.get(self.POS_WI_AFTER, []):
+            parts.append(entry.content)
+            
+        # Pos 2: Examples Before
+        for entry in grouped.get(self.POS_EXAMPLES_BEFORE, []):
+            parts.append(entry.content)
+            
+        # 示例对话
+        if character.mes_example:
+            parts.append(f"<START>\n{character.mes_example}")
+            
+        # Pos 3: Examples After
+        for entry in grouped.get(self.POS_EXAMPLES_AFTER, []):
+            parts.append(entry.content)
+            
+        return "\n".join(parts)
+
+    def _build_authors_note(self, grouped: Dict, depth: int) -> str:
+        """组装作者笔记 (Author's Note)"""
+        parts = []
+        
+        # Pos 4: AN Top
+        for entry in grouped.get(self.POS_AN_TOP, []):
+            parts.append(entry.content)
+            
+        # AN 核心内容 (这里简化为一个占位，实际应从角色卡或设置获取)
+        parts.append(f"[Author's note at depth {depth}]")
+        
+        # Pos 5: AN Bottom
+        for entry in grouped.get(self.POS_AN_BOTTOM, []):
+            parts.append(entry.content)
+            
+        return "\n".join(parts)
+
+    def _inject_depth_entries(self, history: List[ChatMessage], depth_entries: List[WorldInfoEntry]) -> List[Dict]:
+        """
+        在聊天历史的指定深度插入条目 (Pos 6)
+        返回一个包含 role 和 content 的字典列表，方便后续转换
+        """
+        # 先将历史转换为中间格式
+        msg_list = []
+        for msg in history:
+            msg_list.append({"role": "user" if msg.is_user else "assistant", "content": msg.mes})
+        
+        # 按 depth 分组插入
+        # d0 通常指最新用户输入之前，即列表末尾
+        for entry in depth_entries:
+            depth = entry.depth if entry.depth is not None else 0
+            # 计算插入索引 (从后往前数)
+            insert_index = max(0, len(msg_list) - depth)
+            
+            # 确定角色
+            role_map = {"system": "system", "user": "user", "assistant": "assistant"}
+            role = role_map.get(str(entry.position).split('_')[-1] if '_' in str(entry.position) else "system", "system")
+            
+            msg_list.insert(insert_index, {"role": "system", "content": entry.content})
+            
+        return msg_list
+
+    def _replace_outlets(self, text: str, outlet_map: Dict[str, str]) -> str:
+        """执行 Outlet 宏替换 (Pos 7)"""
+        def replacer(match):
+            uid = match.group(1)
+            return outlet_map.get(uid, "")
+        
+        # 匹配 {{outlet::UID}}
+        return re.sub(r"\{\{outlet::([^}]+)\}\}", replacer, text)
+
+    def _wrap_to_messages(
+        self, 
+        story_string: str, 
+        an_content: str, 
+        history: List[Dict], 
+        user_input: str,
+        outlet_map: Dict[str, str],
+        config: PromptConfig
+    ) -> List[BaseMessage]:
+        """将组装好的文本块封装为 LangChain Messages"""
+        messages = []
+        
+        # 1. System Message (Story String + Outlet 替换)
+        final_story = self._replace_outlets(story_string, outlet_map)
+        if final_story:
+            messages.append(SystemMessage(content=final_story))
+            
+        # 2. Author's Note (根据配置位置插入)
+        if an_content and config.an_position == "before_history":
+            messages.append(SystemMessage(content=self._replace_outlets(an_content, outlet_map)))
+            
+        # 3. Chat History
+        for msg_data in history:
+            if msg_data["role"] == "user":
+                messages.append(HumanMessage(content=msg_data["content"]))
+            elif msg_data["role"] == "assistant":
+                messages.append(AIMessage(content=msg_data["content"]))
+            else:
+                messages.append(SystemMessage(content=msg_data["content"]))
+                
+        # 4. Author's Note (如果在 History 之后)
+        if an_content and config.an_position == "after_history":
+            messages.append(SystemMessage(content=self._replace_outlets(an_content, outlet_map)))
+            
+        # 5. Post-History Instructions & User Input
+        final_input = user_input
+        if config.post_history_instructions:
+            final_input = f"{config.post_history_instructions}\n\n{user_input}"
+            
+        messages.append(HumanMessage(content=final_input))
+        
+        return messages
--- a/backend/services/worldbook_service.py
+++ b/backend/services/worldbook_service.py
@@ -0,0 +1,410 @@
+"""
+World Book Service
+世界书服务层 - 处理世界书及条目的 CRUD 操作
+"""
+import json
+import os
+import uuid
+from pathlib import Path
+from typing import List, Dict, Any, Optional
+from datetime import datetime
+
+from models.internal import WorldInfo, WorldInfoEntry, ActivationType
+from models.converters import WorldBookConverter
+from core.config import settings
+
+
+class WorldBookService:
+    """世界书服务类"""
+    
+    @staticmethod
+    def _get_worldbook_path(name: str) -> Path:
+        """获取世界书文件路径"""
+        return settings.WORLDBOOKS_PATH / f"{name}.json"
+    
+    @staticmethod
+    def _load_worldbook(name: str) -> Optional[Dict[str, Any]]:
+        """加载世界书 JSON 文件"""
+        path = WorldBookService._get_worldbook_path(name)
+        if not path.exists():
+            return None
+        
+        try:
+            with open(path, 'r', encoding='utf-8') as f:
+                return json.load(f)
+        except Exception as e:
+            raise ValueError(f"Failed to load worldbook '{name}': {str(e)}")
+    
+    @staticmethod
+    def _save_worldbook(name: str, data: Dict[str, Any]):
+        """保存世界书到 JSON 文件"""
+        path = WorldBookService._get_worldbook_path(name)
+        try:
+            with open(path, 'w', encoding='utf-8') as f:
+                json.dump(data, f, ensure_ascii=False, indent=2)
+        except Exception as e:
+            raise ValueError(f"Failed to save worldbook '{name}': {str(e)}")
+    
+    @staticmethod
+    def list_worldbooks() -> List[Dict[str, Any]]:
+        """
+        获取所有世界书的列表（仅基本信息）
+        
+        Returns:
+            世界书列表，每个包含 name, description, entries_count 等
+        """
+        worldbooks = []
+        
+        for json_file in settings.WORLDBOOKS_PATH.glob("*.json"):
+            try:
+                with open(json_file, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                
+                # 内部格式：entries 是列表
+                entries = data.get("entries", [])
+                entries_count = len(entries) if isinstance(entries, list) else 0
+                
+                worldbooks.append({
+                    "name": data.get("name", json_file.stem),
+                    "description": data.get("description", ""),
+                    "entries_count": entries_count,
+                    "createdAt": data.get("createdAt", 0),
+                    "updatedAt": data.get("updatedAt", 0)
+                })
+            except Exception as e:
+                print(f"Error loading worldbook {json_file.name}: {e}")
+                continue
+        
+        # 按更新时间排序
+        worldbooks.sort(key=lambda x: x.get("updatedAt", 0), reverse=True)
+        return worldbooks
+    
+    @staticmethod
+    def get_worldbook(name: str) -> Dict[str, Any]:
+        """
+        获取指定世界书的完整数据
+        
+        Args:
+            name: 世界书名称
+            
+        Returns:
+            世界书完整数据
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        return data
+    
+    @staticmethod
+    def create_worldbook(name: str, description: str = "") -> Dict[str, Any]:
+        """
+        创建新世界书
+        
+        Args:
+            name: 世界书名称
+            description: 世界书描述
+            
+        Returns:
+            创建的世界书数据
+        """
+        # 检查是否已存在
+        if WorldBookService._get_worldbook_path(name).exists():
+            raise ValueError(f"Worldbook '{name}' already exists")
+        
+        now = int(datetime.now().timestamp())
+        worldbook_data = {
+            "id": str(uuid.uuid4()),
+            "name": name,
+            "description": description,
+            "entries": [],
+            "createdAt": now,
+            "updatedAt": now,
+            "version": 1
+        }
+        
+        WorldBookService._save_worldbook(name, worldbook_data)
+        return worldbook_data
+    
+    @staticmethod
+    def update_worldbook(name: str, description: Optional[str] = None) -> Dict[str, Any]:
+        """
+        更新世界书基本信息
+        
+        Args:
+            name: 世界书名称
+            description: 新的描述（可选）
+            
+        Returns:
+            更新后的世界书数据
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        if description is not None:
+            data["description"] = description
+        
+        data["updatedAt"] = int(datetime.now().timestamp())
+        WorldBookService._save_worldbook(name, data)
+        
+        return data
+    
+    @staticmethod
+    def delete_worldbook(name: str) -> bool:
+        """
+        删除世界书
+        
+        Args:
+            name: 世界书名称
+            
+        Returns:
+            是否删除成功
+        """
+        path = WorldBookService._get_worldbook_path(name)
+        if not path.exists():
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        path.unlink()
+        return True
+    
+    @staticmethod
+    def list_entries(name: str, page: int = 1, page_size: int = 20) -> Dict[str, Any]:
+        """
+        获取世界书的条目列表（支持分页）
+        
+        Args:
+            name: 世界书名称
+            page: 页码，从1开始
+            page_size: 每页数量，默认20
+            
+        Returns:
+            包含条目列表和分页信息的字典
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        # 内部格式：entries 是列表
+        all_entries = data.get("entries", [])
+        if not isinstance(all_entries, list):
+            all_entries = []
+        
+        total = len(all_entries)
+        
+        # 计算分页
+        start_idx = (page - 1) * page_size
+        end_idx = start_idx + page_size
+        paginated_entries = all_entries[start_idx:end_idx]
+        
+        return {
+            "entries": paginated_entries,
+            "total": total,
+            "page": page,
+            "page_size": page_size,
+            "total_pages": (total + page_size - 1) // page_size  # 向上取整
+        }
+    
+    @staticmethod
+    def get_entry(name: str, uid: str) -> Dict[str, Any]:
+        """
+        获取世界书的指定条目
+        
+        Args:
+            name: 世界书名称
+            uid: 条目 UID
+            
+        Returns:
+            条目数据
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        # 内部格式：entries 是列表
+        entries = data.get("entries", [])
+        if not isinstance(entries, list):
+            entries = []
+        
+        for entry in entries:
+            if entry.get("uid") == uid or str(entry.get("uid")) == uid:
+                return entry
+        
+        raise FileNotFoundError(f"Entry '{uid}' not found in worldbook '{name}'")
+    
+    @staticmethod
+    def create_entry(name: str, entry_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        在世界书中创建新条目
+        
+        Args:
+            name: 世界书名称
+            entry_data: 条目数据（不包含 uid, createdAt, updatedAt）
+            
+        Returns:
+            创建的条目数据
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        # 生成 UID 和时间戳
+        now = int(datetime.now().timestamp())
+        new_entry = {
+            "uid": str(uuid.uuid4()),
+            "key": entry_data.get("key", []),
+            "keysecondary": entry_data.get("keysecondary", []),
+            "content": entry_data.get("content", ""),
+            "activationType": entry_data.get("activationType", ActivationType.KEYWORD.value),
+            "logicExpression": entry_data.get("logicExpression"),
+            "ragConfig": entry_data.get("ragConfig"),
+            "order": entry_data.get("order", 0),
+            "position": entry_data.get("position", "after_char"),
+            "depth": entry_data.get("depth"),
+            "probability": entry_data.get("probability", 100),
+            "group": entry_data.get("group", []),
+            "disable": entry_data.get("disable", False),
+            "createdAt": now,
+            "updatedAt": now
+        }
+        
+        data["entries"].append(new_entry)
+        data["updatedAt"] = now
+        WorldBookService._save_worldbook(name, data)
+        
+        return new_entry
+    
+    @staticmethod
+    def update_entry(name: str, uid: str, entry_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        更新世界书的指定条目
+        
+        Args:
+            name: 世界书名称
+            uid: 条目 UID
+            entry_data: 更新的字段
+            
+        Returns:
+            更新后的条目数据
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        for i, entry in enumerate(data.get("entries", [])):
+            if entry.get("uid") == uid:
+                # 更新字段
+                for key, value in entry_data.items():
+                    if key not in ["uid", "createdAt"]:  # 不修改 UID 和创建时间
+                        entry[key] = value
+                
+                # 更新时间戳
+                entry["updatedAt"] = int(datetime.now().timestamp())
+                data["entries"][i] = entry
+                data["updatedAt"] = entry["updatedAt"]
+                
+                WorldBookService._save_worldbook(name, data)
+                return entry
+        
+        raise FileNotFoundError(f"Entry '{uid}' not found in worldbook '{name}'")
+    
+    @staticmethod
+    def delete_entry(name: str, uid: str) -> bool:
+        """
+        删除世界书的指定条目
+        
+        Args:
+            name: 世界书名称
+            uid: 条目 UID
+            
+        Returns:
+            是否删除成功
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        original_length = len(data.get("entries", []))
+        data["entries"] = [e for e in data.get("entries", []) if e.get("uid") != uid]
+        
+        if len(data["entries"]) == original_length:
+            raise FileNotFoundError(f"Entry '{uid}' not found in worldbook '{name}'")
+        
+        data["updatedAt"] = int(datetime.now().timestamp())
+        WorldBookService._save_worldbook(name, data)
+        
+        return True
+    
+    @staticmethod
+    def import_from_sillytavern(name: str, st_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        从 SillyTavern 格式导入世界书
+        
+        Args:
+            name: 世界书名称
+            st_data: SillyTavern 格式的世界书数据
+            
+        Returns:
+            转换后的内部格式世界书数据
+        """
+        # 使用转换器进行转换
+        worldbook_data = WorldBookConverter.st_to_internal(st_data, name)
+        
+        # 保存到文件
+        WorldBookService._save_worldbook(name, worldbook_data)
+        
+        return worldbook_data
+    
+    @staticmethod
+    def import_internal_format(name: str, internal_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        直接导入内部格式的世界书(无需转换)
+        
+        Args:
+            name: 世界书名称
+            internal_data: 内部格式的世界书数据
+            
+        Returns:
+            内部格式世界书数据
+        """
+        # 确保包含必要的字段
+        if "name" not in internal_data:
+            internal_data["name"] = name
+        
+        # 规范化所有条目,确保有 trigger_config
+        if "entries" in internal_data and isinstance(internal_data["entries"], list):
+            normalized_entries = []
+            for entry in internal_data["entries"]:
+                if isinstance(entry, dict):
+                    normalized_entry = WorldBookConverter.normalize_entry(entry)
+                    normalized_entries.append(normalized_entry)
+            internal_data["entries"] = normalized_entries
+        
+        # 保存文件
+        WorldBookService._save_worldbook(name, internal_data)
+        
+        return internal_data
+    
+    @staticmethod
+    def export_to_sillytavern(name: str) -> Dict[str, Any]:
+        """
+        导出为 SillyTavern 格式
+        
+        Args:
+            name: 世界书名称
+            
+        Returns:
+            SillyTavern 格式的世界书数据
+        """
+        data = WorldBookService._load_worldbook(name)
+        if not data:
+            raise FileNotFoundError(f"Worldbook '{name}' not found")
+        
+        # 使用转换器进行转换
+        st_data = WorldBookConverter.internal_to_st(data)
+        
+        return st_data
+
+
+# 全局实例
+worldbook_service = WorldBookService()
--- a/backend/tools/init.py
+++ b/backend/tools/init.py
--- a/backend/tools/pycache/init.cpython-311.pyc
+++ b/backend/tools/pycache/init.cpython-311.pyc
--- a/backend/tools/pycache/get_all_role_and_chat.cpython-311.pyc
+++ b/backend/tools/pycache/get_all_role_and_chat.cpython-311.pyc
--- a/backend/tools/pycache/save_input_to_json.cpython-311.pyc
+++ b/backend/tools/pycache/save_input_to_json.cpython-311.pyc
--- a/backend/tools/get_all_role_and_chat.py
+++ b/backend/tools/get_all_role_and_chat.py
@@ -1,47 +0,0 @@
-from ..core import config
-from typing import Dict, List
-
-# 使用配置中的 DATA_PATH 并添加 "chat" 子目录
-ROOT_DIR = config.settings.DATA_PATH / "chat"
-
-def get_all_role_and_chat() -> Dict[str, List[str]]:
-    """
-    读取配置目录下的所有子文件夹，并收集每个子文件夹中的 JSONL 文件
-
-    返回:
-        dict: 字典结构，键是文件夹名称，值是该文件夹中的 JSONL 文件列表（仅文件名，无路径和后缀）
-    """
-    result = {}
-
-    # 确保目标目录存在
-    if not ROOT_DIR.exists():
-        print(f"警告: 目录 {ROOT_DIR} 不存在")
-        return result
-
-    # 打印根目录路径和内容（调试用）
-    print(f"正在扫描目录: {ROOT_DIR}")
-    print(f"根目录内容: {list(ROOT_DIR.iterdir())}")
-
-    # 遍历根目录下的所有条目
-    for entry in ROOT_DIR.iterdir():
-        try:
-            # 只处理文件夹
-            if entry.is_dir():
-                print(f"处理文件夹: {entry.name}")  # 调试信息
-                jsonl_files = []
-
-                # 遍历子文件夹中的所有文件
-                for file in entry.iterdir():
-                    if file.is_file() and file.suffix == '.jsonl':
-                        # 使用 file.stem 获取不带后缀的文件名
-                        jsonl_files.append(file.stem)
-                        print(f"  找到文件: {file.name}")  # 调试信息
-
-                # 如果该文件夹中有 JSONL 文件，则添加到结果中
-                if jsonl_files:
-                    result[entry.name] = jsonl_files
-        except Exception as e:
-            print(f"处理文件夹 {entry.name} 时出错: {str(e)}")
-            continue
-
-    return result
--- a/backend/tools/save_input_to_json.py
+++ b/backend/tools/save_input_to_json.py
@@ -1,152 +0,0 @@
-import json
-from datetime import datetime
-from backend.core import config as cfg
-from pathlib import Path
-from ..core.items import ChatRequest
-
-# 假设 ChatRequest 定义在这里或者从其他地方导入
-# from backend.app.core.items import ChatRequest
-
-async def save_input_to_json(chat_request: ChatRequest):
-    """
-    保存消息到JSONL文件或处理重roll请求
-
-    参数:
-        chat_request: 包含消息详情的请求对象
-    """
-    # 1. 从对象中提取属性
-    mes = chat_request.mes
-    role_name = chat_request.role_name
-    chat_name = chat_request.chat_name
-    name = chat_request.name
-    is_user = chat_request.is_user
-    floor_number = chat_request.floor_number
-    # stream, img_switch, table_switch 等虽然在这个函数逻辑中没用到，
-    # 但如果 ChatRequest 中有，也可以提取出来备用
-    # stream = chat_request.stream
-    # ...
-
-    config = cfg.settings
-    # 注意：这里要确保 role_name 和 chat_name 不为 None，否则路径拼接会报错
-    # 建议在函数入口处增加校验，或者在 Pydantic 模型中设置为必填项
-    if not role_name or not chat_name:
-        raise ValueError("role_name and chat_name cannot be empty")
-
-    file_path = config.BASE_PATH / "data" / "chat" / role_name / f"{chat_name}.jsonl"
-
-    # 确保目录存在
-    Path(file_path).parent.mkdir(parents=True, exist_ok=True)
-
-    # 读取文件内容
-    try:
-        with open(file_path, 'r', encoding='utf-8') as f:
-            lines = f.readlines()
-    except FileNotFoundError:
-        lines = []
-
-    # 判断是否为重roll请求
-    is_regenerate = False
-    target_index = -1
-
-    if lines and floor_number > 0:
-        # 计算当前楼层号
-        current_floor = len(lines)
-
-        # 如果floor_number与当前楼层号相同，则为重roll请求
-        if floor_number == current_floor:
-            # 找到最后一条非用户消息
-            for i in range(len(lines) - 1, -1, -1):
-                try:
-                    line_data = json.loads(lines[i])
-                    if not line_data.get('is_user', False):
-                        is_regenerate = True
-                        target_index = i
-                        break
-                except json.JSONDecodeError:
-                    continue
-
-    # 处理重roll逻辑
-    if is_regenerate:
-        # 解析目标消息
-        try:
-            target_message = json.loads(lines[target_index])
-        except json.JSONDecodeError:
-            raise ValueError(f"无法解析楼层 {floor_number} 的JSON数据")
-
-        # 初始化swipes数组
-        if target_message.get('swipes') is None:
-            target_message['swipes'] = []
-
-        # 将新回复添加到swipes数组
-        target_message['swipes'].append(mes)
-
-        # 更新swipe_id和content
-        target_message['swipes_id'] = len(target_message['swipes']) - 1
-        target_message['content'] = mes
-
-        # 更新文件内容
-        lines[target_index] = json.dumps(target_message, ensure_ascii=False) + '\n'
-
-        # 写回文件
-        with open(file_path, 'w', encoding='utf-8') as f:
-            f.writelines(lines)
-
-        return target_message
-
-    # 处理普通消息保存逻辑
-    else:
-        # 获取当前时间
-        current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-
-        # 构建消息对象
-        message = {
-            "role": role_name,
-            "chat": chat_name,
-            "content": mes,
-            "name": name,
-            "is_user": is_user,
-            "send_date": current_time,
-            "floor_number": len(lines) + 1,  # 记录楼层号
-            "swipes": [],
-            "swipes_id": 0
-        }
-
-        # 追加到文件
-        with open(file_path, 'a', encoding='utf-8') as f:
-            f.write(json.dumps(message, ensure_ascii=False) + '\n')
-
-        return message
-
-
-if __name__ == '__main__':
-    # 注意：为了在本地运行测试，你需要手动构造一个 ChatRequest 对象
-    # 或者临时修改函数签名以便直接传参测试
-
-    # 示例：假设 ChatRequest 是一个简单的类或 Pydantic 模型
-    class MockChatRequest:
-        def __init__(self, **kwargs):
-            self.mes = kwargs.get('mes')
-            self.role_name = kwargs.get('role_name')
-            self.chat_name = kwargs.get('chat_name')
-            self.name = kwargs.get('name')
-            self.is_user = kwargs.get('is_user')
-            self.floor_number = kwargs.get('floor_number')
-
-
-    # 测试重roll最后一条AI消息
-    import asyncio
-
-
-    async def test():
-        req = MockChatRequest(
-            mes="这是重roll后的新回复2",
-            role_name="testRole1",
-            chat_name="111",
-            name="AI",
-            is_user=False,
-            floor_number=2
-        )
-        await save_input_to_json(req)
-
-
-    asyncio.run(test())
--- a/backend/utils/init.py
+++ b/backend/utils/init.py
@@ -0,0 +1,17 @@
+"""
+工具类包
+
+提供通用的工具函数和辅助类，如文件操作、LLM 调用封装等。
+"""
+from .file_utils import get_all_roles_and_chats, read_jsonl_file, write_jsonl_file
+from .llm_client import get_llm, get_fast_llm, get_creative_llm, get_streaming_llm
+
+__all__ = [
+    'get_all_roles_and_chats',
+    'read_jsonl_file',
+    'write_jsonl_file',
+    'get_llm',
+    'get_fast_llm',
+    'get_creative_llm',
+    'get_streaming_llm',
+]
--- a/backend/utils/file_utils.py
+++ b/backend/utils/file_utils.py
@@ -0,0 +1,130 @@
+"""
+文件操作工具函数
+
+提供文件和目录操作的通用工具
+"""
+from pathlib import Path
+from typing import Dict, List
+import json
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+def get_all_roles_and_chats(data_path: Path) -> Dict[str, List[str]]:
+    """
+    获取所有角色和聊天列表
+    
+    Args:
+        data_path: 数据目录路径
+        
+    Returns:
+        Dict[str, List[str]]: 字典结构，键是角色名称，值是该角色的聊天列表
+    """
+    chat_dir = data_path / "chat"
+    result = {}
+    
+    if not chat_dir.exists():
+        logger.warning(f"聊天目录不存在: {chat_dir}")
+        return result
+    
+    for entry in chat_dir.iterdir():
+        try:
+            if entry.is_dir():
+                jsonl_files = []
+                
+                for file in entry.iterdir():
+                    if file.is_file() and file.suffix == '.jsonl':
+                        jsonl_files.append(file.stem)
+                
+                if jsonl_files:
+                    result[entry.name] = jsonl_files
+                    
+        except Exception as e:
+            logger.error(f"处理文件夹 {entry.name} 时出错: {str(e)}")
+            continue
+    
+    return result
+
+
+def ensure_directory_exists(path: Path) -> None:
+    """
+    确保目录存在,如果不存在则创建
+    
+    Args:
+        path: 目录路径
+    """
+    path.mkdir(parents=True, exist_ok=True)
+
+
+def read_json_file(file_path: Path) -> dict:
+    """
+    读取 JSON 文件
+    
+    Args:
+        file_path: 文件路径
+        
+    Returns:
+        dict: JSON 数据
+    """
+    with open(file_path, 'r', encoding='utf-8') as f:
+        return json.load(f)
+
+
+def write_json_file(file_path: Path, data: dict) -> None:
+    """
+    写入 JSON 文件
+    
+    Args:
+        file_path: 文件路径
+        data: 要写入的数据
+    """
+    with open(file_path, 'w', encoding='utf-8') as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+
+
+def read_jsonl_file(file_path: Path) -> List[dict]:
+    """
+    读取 JSONL 文件
+    
+    Args:
+        file_path: 文件路径
+        
+    Returns:
+        List[dict]: JSONL 数据列表
+    """
+    lines = []
+    with open(file_path, 'r', encoding='utf-8') as f:
+        for line in f:
+            line = line.strip()
+            if line:
+                try:
+                    lines.append(json.loads(line))
+                except json.JSONDecodeError as e:
+                    logger.warning(f"解析 JSONL 行失败: {e}")
+    return lines
+
+
+def append_to_jsonl_file(file_path: Path, data: dict) -> None:
+    """
+    追加数据到 JSONL 文件
+    
+    Args:
+        file_path: 文件路径
+        data: 要追加的数据
+    """
+    with open(file_path, 'a', encoding='utf-8') as f:
+        f.write(json.dumps(data, ensure_ascii=False) + '\n')
+
+
+def write_jsonl_file(file_path: Path, data_list: List[dict]) -> None:
+    """
+    写入 JSONL 文件 (覆盖模式)
+    
+    Args:
+        file_path: 文件路径
+        data_list: 数据列表
+    """
+    with open(file_path, 'w', encoding='utf-8') as f:
+        for data in data_list:
+            f.write(json.dumps(data, ensure_ascii=False) + '\n')
--- a/backend/utils/llm_client.py
+++ b/backend/utils/llm_client.py
@@ -0,0 +1,88 @@
+"""
+LLM 客户端工具
+
+提供统一的 LLM 接口,支持多种模型提供商。
+使用 LangChain 的 ChatModel 抽象,简化不同厂商 API 的调用。
+"""
+from typing import Optional
+from langchain_core.language_models.chat_models import BaseChatModel
+from core.config import settings
+
+
+def get_llm(
+    provider: str = "openai",
+    model: Optional[str] = None,
+    temperature: float = 0.7,
+    streaming: bool = False,
+    **kwargs
+) -> BaseChatModel:
+    """
+    获取 LLM 实例
+    
+    Args:
+        provider: 模型提供商 ("openai", "anthropic", "ollama")
+        model: 模型名称 (如果不指定则使用配置中的默认值)
+        temperature: 温度参数 (0-2)
+        streaming: 是否启用流式输出
+        **kwargs: 其他参数传递给模型
+        
+    Returns:
+        BaseChatModel: LangChain 的聊天模型实例
+    """
+    
+    if provider == "openai":
+        from langchain_openai import ChatOpenAI
+        
+        return ChatOpenAI(
+            model=model or settings.OPENAI_MODEL or "gpt-4",
+            temperature=temperature,
+            api_key=settings.OPENAI_API_KEY,
+            streaming=streaming,
+            **kwargs
+        )
+    
+    elif provider == "anthropic":
+        from langchain_anthropic import ChatAnthropic
+        
+        return ChatAnthropic(
+            model=model or settings.ANTHROPIC_MODEL or "claude-3-opus-20240229",
+            temperature=temperature,
+            api_key=settings.ANTHROPIC_API_KEY,
+            max_tokens=kwargs.pop("max_tokens", 4096),
+            streaming=streaming,
+            **kwargs
+        )
+    
+    elif provider == "ollama":
+        try:
+            from langchain_ollama import ChatOllama
+            
+            return ChatOllama(
+                model=model or settings.OLLAMA_MODEL or "llama3",
+                base_url=settings.OLLAMA_BASE_URL or "http://localhost:11434",
+                temperature=temperature,
+                **kwargs
+            )
+        except ImportError:
+            raise ImportError(
+                "langchain-ollama not installed. Run: pip install langchain-ollama"
+            )
+    
+    else:
+        raise ValueError(f"Unsupported provider: {provider}. Use 'openai', 'anthropic', or 'ollama'")
+
+
+# 便捷函数 - 常用配置
+def get_fast_llm(provider: str = "openai") -> BaseChatModel:
+    """获取快速响应的 LLM (低温度,适合事实性问题)"""
+    return get_llm(provider, temperature=0.3)
+
+
+def get_creative_llm(provider: str = "openai") -> BaseChatModel:
+    """获取创造性 LLM (高温度,适合创意写作)"""
+    return get_llm(provider, temperature=0.9)
+
+
+def get_streaming_llm(provider: str = "openai") -> BaseChatModel:
+    """获取支持流式输出的 LLM"""
+    return get_llm(provider, streaming=True)
--- a/backend/workflows/init.py
+++ b/backend/workflows/init.py
--- a/backend/workflows/main_llm_workflow.py
+++ b/backend/workflows/main_llm_workflow.py
@@ -1,201 +0,0 @@
-# backend/app/workflows/llm_workflow.py
-from typing import Dict, Any, List, Callable
-from dataclasses import dataclass
-from enum import Enum
-
-
-class WorkflowStatus(Enum):
-    """工作流状态枚举"""
-    INITIALIZED = "initialized"
-    RUNNING = "running"
-    COMPLETED = "completed"
-    FAILED = "failed"
-    PAUSED = "paused"
-
-
-@dataclass
-class WorkflowContext:
-    """工作流上下文"""
-    data: Dict[str, Any]
-    status: WorkflowStatus = WorkflowStatus.INITIALIZED
-    metadata: Dict[str, Any] = None
-
-    def __post_init__(self):
-        if self.metadata is None:
-            self.metadata = {}
-
-
-class WorkflowNode:
-    """工作流节点声明"""
-
-    def __init__(
-            self,
-            name: str,
-            handler: Callable,
-            enabled: bool = True,
-            config: Dict[str, Any] = None
-    ):
-        self.name = name  # 节点的唯一标识符，用于区分不同的节点。
-        self.handler = handler  # 一个可调用对象（函数或方法），这是节点实际执行的处理逻辑。
-        self.enabled = enabled  # 布尔值，控制节点是否启用。默认为 True，如果设置为 False，节点将被跳过。
-        self.config = config or {} # 一个字典，用于存储节点的配置信息。默认为空字典。
-        self.next_nodes: List['WorkflowNode'] = [] # 一个节点列表，用于指定当前节点执行完成后应跳转到的下一个节点。默认为空列表，可能指向多分支。
-
-    def execute(self, context: WorkflowContext) -> WorkflowContext:
-        """执行节点处理"""
-        if not self.enabled:
-            return context
-
-        try:
-            context = self.handler(context, self.config)
-            return context
-        except Exception as e:
-            context.status = WorkflowStatus.FAILED
-            context.metadata["error"] = str(e)
-            raise
-
-
-class LLMWorkflow:
-    """LLM工作流声明"""
-
-    def __init__(self):
-        self.nodes: List[WorkflowNode] = []
-        self._initialize_workflow()
-
-    def _initialize_workflow(self):
-        """初始化工作流节点（仅声明，不实现）"""
-        # 输入节点
-        input_node = WorkflowNode(
-            name="input",
-            handler=self._input_handler
-        )
-
-        # 输入预处理节点（可开关）
-        preprocessing_node = WorkflowNode(
-            name="preprocessing",
-            handler=self._preprocessing_handler,
-            enabled=False
-        )
-
-        # RAG处理节点
-        rag_node = WorkflowNode(
-            name="rag",
-            handler=self._rag_handler
-        )
-
-        # 提示词组装节点
-        prompt_assembly_node = WorkflowNode(
-            name="prompt_assembly",
-            handler=self._prompt_assembly_handler
-        )
-
-        # LLM请求节点
-        llm_request_node = WorkflowNode(
-            name="llm_request",
-            handler=self._llm_request_handler
-        )
-
-        # 图像生成节点（可开关）
-        image_generation_node = WorkflowNode(
-            name="image_generation",
-            handler=self._image_generation_handler,
-            enabled=False
-        )
-
-        # 动态表格更新节点（可开关）
-        dynamic_table_node = WorkflowNode(
-            name="dynamic_table",
-            handler=self._dynamic_table_handler,
-            enabled=False
-        )
-
-        # 输出过滤节点
-        output_filter_node = WorkflowNode(
-            name="output_filter",
-            handler=self._output_filter_handler
-        )
-
-        # 输出节点
-        output_node = WorkflowNode(
-            name="output",
-            handler=self._output_handler
-        )
-
-        # 设置节点顺序（构建工作流）
-        self.nodes = [
-            input_node,
-            preprocessing_node,
-            rag_node,
-            prompt_assembly_node,
-            llm_request_node,
-            image_generation_node,
-            dynamic_table_node,
-            output_filter_node,
-            output_node
-        ]
-
-    def execute(self, context: WorkflowContext) -> WorkflowContext:
-        """执行工作流"""
-        context.status = WorkflowStatus.RUNNING
-
-        for node in self.nodes:
-            try:
-                context = node.execute(context)
-
-                # 如果工作流失败，停止执行
-                if context.status == WorkflowStatus.FAILED:
-                    break
-            except Exception as e:
-                context.status = WorkflowStatus.FAILED
-                context.metadata["error"] = str(e)
-                break
-
-        if context.status != WorkflowStatus.FAILED:
-            context.status = WorkflowStatus.COMPLETED
-
-        return context
-
-    def enable_node(self, node_name: str, enabled: bool = True):
-        """启用或禁用特定节点"""
-        for node in self.nodes:
-            if node.name == node_name:
-                node.enabled = enabled
-                return True
-        return False
-
-    # 以下是节点处理函数声明（仅声明，不实现）
-    def _input_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """输入节点处理函数"""
-        pass
-
-    def _preprocessing_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """输入预处理节点处理函数"""
-        pass
-
-    def _rag_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """RAG处理节点处理函数"""
-        pass
-
-    def _prompt_assembly_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """提示词组装节点处理函数"""
-        pass
-
-    def _llm_request_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """LLM请求节点处理函数"""
-        pass
-
-    def _image_generation_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """图像生成节点处理函数"""
-        pass
-
-    def _dynamic_table_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """动态表格更新节点处理函数"""
-        pass
-
-    def _output_filter_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """输出过滤节点处理函数"""
-        pass
-
-    def _output_handler(self, context: WorkflowContext, config: Dict[str, Any]) -> WorkflowContext:
-        """输出节点处理函数"""
-        pass
--- a/check_frontend_api.py
+++ b/check_frontend_api.py
@@ -0,0 +1,201 @@
+"""
+检查前端世界书功能与后端API的匹配情况
+"""
+
+print("=" * 80)
+print("前端世界书功能与后端API路由匹配检查")
+print("=" * 80)
+
+# 前端Store中的API调用
+frontend_calls = [
+    {
+        "功能": "获取世界书列表",
+        "方法": "GET",
+        "路径": "/api/worldbooks/",
+        "Store函数": "fetchWorldBooks"
+    },
+    {
+        "功能": "获取指定世界书",
+        "方法": "GET",
+        "路径": "/api/worldbooks/{name}",
+        "Store函数": "fetchWorldBook"
+    },
+    {
+        "功能": "创建世界书",
+        "方法": "POST",
+        "路径": "/api/worldbooks/",
+        "Store函数": "createWorldBook",
+        "备注": "FormData: name, is_global, file"
+    },
+    {
+        "功能": "更新世界书",
+        "方法": "PUT",
+        "路径": "/api/worldbooks/{name}",
+        "Store函数": "updateWorldBook",
+        "备注": "FormData: is_global, file"
+    },
+    {
+        "功能": "删除世界书",
+        "方法": "DELETE",
+        "路径": "/api/worldbooks/{name}",
+        "Store函数": "deleteWorldBook"
+    },
+    {
+        "功能": "获取世界书条目（分页）",
+        "方法": "GET",
+        "路径": "/api/worldbooks/{name}/entries?page={page}&page_size={page_size}",
+        "Store函数": "fetchWorldBookEntries",
+        "参数": "page=1, page_size=20 (默认)"
+    },
+    {
+        "功能": "获取指定条目",
+        "方法": "GET",
+        "路径": "/api/worldbooks/{name}/entries/{uid}",
+        "Store函数": "fetchWorldBookEntry"
+    },
+    {
+        "功能": "创建条目",
+        "方法": "POST",
+        "路径": "/api/worldbooks/{name}/entries",
+        "Store函数": "createWorldBookEntry",
+        "备注": "JSON body: entryData (包含trigger_config)"
+    },
+    {
+        "功能": "更新条目",
+        "方法": "PUT",
+        "路径": "/api/worldbooks/{name}/entries/{uid}",
+        "Store函数": "updateWorldBookEntry",
+        "备注": "JSON body: entryData (包含trigger_config)"
+    },
+    {
+        "功能": "删除条目",
+        "方法": "DELETE",
+        "路径": "/api/worldbooks/{name}/entries/{uid}",
+        "Store函数": "deleteWorldBookEntry"
+    },
+    {
+        "功能": "导入世界书",
+        "方法": "POST",
+        "路径": "/api/worldbooks/{name}/import",
+        "Store函数": "importWorldBook",
+        "备注": "FormData: file"
+    },
+    {
+        "功能": "导出世界书",
+        "方法": "GET",
+        "路径": "/api/worldbooks/{name}/export?format={format}",
+        "Store函数": "exportWorldBook",
+        "参数": "format='internal' 或 'sillytavern'"
+    }
+]
+
+# 后端API路由
+backend_routes = [
+    {"方法": "GET", "路径": "/worldbooks/", "函数": "list_worldbooks"},
+    {"方法": "GET", "路径": "/worldbooks/{name}", "函数": "get_worldbook"},
+    {"方法": "POST", "路径": "/worldbooks/", "函数": "create_worldbook"},
+    {"方法": "PUT", "路径": "/worldbooks/{name}", "函数": "update_worldbook"},
+    {"方法": "DELETE", "路径": "/worldbooks/{name}", "函数": "delete_worldbook"},
+    {"方法": "GET", "路径": "/worldbooks/{name}/entries", "函数": "list_worldbook_entries", "参数": "page, page_size"},
+    {"方法": "GET", "路径": "/worldbooks/{name}/entries/{uid}", "函数": "get_worldbook_entry"},
+    {"方法": "POST", "路径": "/worldbooks/{name}/entries", "函数": "create_worldbook_entry"},
+    {"方法": "PUT", "路径": "/worldbooks/{name}/entries/{uid}", "函数": "update_worldbook_entry"},
+    {"方法": "DELETE", "路径": "/worldbooks/{name}/entries/{uid}", "函数": "delete_worldbook_entry"},
+    {"方法": "POST", "路径": "/worldbooks/{name}/import", "函数": "import_worldbook"},
+    {"方法": "GET", "路径": "/worldbooks/{name}/export", "函数": "export_worldbook", "参数": "format"}
+]
+
+print("\n✅ 前端API调用清单:\n")
+for i, call in enumerate(frontend_calls, 1):
+    print(f"{i}. {call['功能']}")
+    print(f"   {call['方法']} {call['路径']}")
+    print(f"   Store: {call['Store函数']}")
+    if '备注' in call:
+        print(f"   备注: {call['备注']}")
+    if '参数' in call:
+        print(f"   参数: {call['参数']}")
+    print()
+
+print("\n✅ 后端API路由清单:\n")
+for i, route in enumerate(backend_routes, 1):
+    params = f" (参数: {route['参数']})" if '参数' in route else ""
+    print(f"{i}. {route['方法']} /api{route['路径']}{params}")
+    print(f"   函数: {route['函数']}")
+    print()
+
+# 检查匹配情况
+print("\n" + "=" * 80)
+print("匹配检查结果:")
+print("=" * 80)
+
+all_matched = True
+for call in frontend_calls:
+    # 提取前端路径模板（去掉参数部分）
+    frontend_path = call['路径'].split('?')[0].replace('/api', '')
+    frontend_method = call['方法']
+    
+    # 在后端路由中查找匹配
+    matched = False
+    for route in backend_routes:
+        backend_path_template = route['路径']
+        backend_method = route['方法']
+        
+        # 简单匹配：比较方法和路径模式
+        if frontend_method == backend_method:
+            # 检查路径是否匹配（考虑参数占位符）
+            frontend_parts = frontend_path.strip('/').split('/')
+            backend_parts = backend_path_template.strip('/').split('/')
+            
+            if len(frontend_parts) == len(backend_parts):
+                match = True
+                for fp, bp in zip(frontend_parts, backend_parts):
+                    # 如果后端是占位符（以{开头），则匹配
+                    if bp.startswith('{') and bp.endswith('}'):
+                        continue
+                    # 否则必须完全匹配
+                    if fp != bp:
+                        match = False
+                        break
+                
+                if match:
+                    matched = True
+                    break
+    
+    status = "✓" if matched else "✗"
+    print(f"{status} {call['功能']}: {frontend_method} {frontend_path}")
+    
+    if not matched:
+        all_matched = False
+        print(f"   ⚠️  未找到匹配的后端路由！")
+
+print("\n" + "=" * 80)
+if all_matched:
+    print("✅ 所有前端API调用都有对应的后端路由！")
+else:
+    print("❌ 存在不匹配的API调用，请检查！")
+print("=" * 80)
+
+# 检查关键功能
+print("\n📋 关键功能检查:")
+print("=" * 80)
+
+key_features = [
+    ("世界书列表加载", "GET /api/worldbooks/"),
+    ("选择世界书并加载条目", "GET /api/worldbooks/{name}/entries?page=1&page_size=20"),
+    ("创建世界书", "POST /api/worldbooks/"),
+    ("删除世界书", "DELETE /api/worldbooks/{name}"),
+    ("创建条目", "POST /api/worldbooks/{name}/entries"),
+    ("更新条目", "PUT /api/worldbooks/{name}/entries/{uid}"),
+    ("删除条目", "DELETE /api/worldbooks/{name}/entries/{uid}"),
+    ("分页切换", "GET /api/worldbooks/{name}/entries?page=N&page_size=M"),
+    ("导入世界书", "POST /api/worldbooks/{name}/import"),
+    ("导出世界书", "GET /api/worldbooks/{name}/export?format=internal")
+]
+
+for feature, api_call in key_features:
+    print(f"✓ {feature}")
+    print(f"  API: {api_call}")
+
+print("\n" + "=" * 80)
+print("结论: 前端世界书分页的所有功能都能正确发出请求到后端API")
+print("=" * 80)
--- a/check_worldbook_path.py
+++ b/check_worldbook_path.py
@@ -0,0 +1,49 @@
+"""
+检查世界书路径和文件
+"""
+from pathlib import Path
+
+# 项目根目录
+PROJECT_ROOT = Path(r'D:\progarm\python\llm_workflow_engine')
+DATA_PATH = PROJECT_ROOT / 'data'
+WORLDBOOKS_PATH = DATA_PATH / 'worldbooks'
+
+print("=" * 60)
+print("世界书路径检查")
+print("=" * 60)
+
+print(f"\n1. 项目根目录: {PROJECT_ROOT}")
+print(f"   存在: {PROJECT_ROOT.exists()}")
+
+print(f"\n2. 数据目录: {DATA_PATH}")
+print(f"   存在: {DATA_PATH.exists()}")
+
+print(f"\n3. 世界书目录: {WORLDBOOKS_PATH}")
+print(f"   存在: {WORLDBOOKS_PATH.exists()}")
+
+if WORLDBOOKS_PATH.exists():
+    json_files = list(WORLDBOOKS_PATH.glob("*.json"))
+    print(f"   JSON文件数量: {len(json_files)}")
+    if json_files:
+        print(f"   文件列表:")
+        for f in json_files:
+            print(f"     - {f.name} ({f.stat().st_size} bytes)")
+    else:
+        print(f"   ⚠️  世界书目录为空，没有JSON文件")
+        
+        # 检查目录下是否有子目录
+        subdirs = list(WORLDBOOKS_PATH.iterdir())
+        if subdirs:
+            print(f"   子目录/文件:")
+            for item in subdirs:
+                print(f"     - {item.name} ({'目录' if item.is_dir() else '文件'})")
+else:
+    print(f"   ❌ 世界书目录不存在！")
+    
+    # 检查data目录下有什么
+    if DATA_PATH.exists():
+        print(f"\n4. data目录内容:")
+        for item in DATA_PATH.iterdir():
+            print(f"   - {item.name} ({'目录' if item.is_dir() else '文件'})")
+
+print("\n" + "=" * 60)
--- a/clear_default_avatar.py
+++ b/clear_default_avatar.py
@@ -0,0 +1,53 @@
+"""
+清空默认头像图片中的嵌入JSON数据
+"""
+from PIL import Image
+import io
+
+def clear_png_text_data(png_path):
+    """
+    清空PNG文件中的tEXt文本数据（包括嵌入的JSON）
+    
+    Args:
+        png_path: PNG文件路径
+    """
+    try:
+        # 打开图片
+        img = Image.open(png_path)
+        
+        print(f"原始PNG文本数据键: {list(img.text.keys()) if img.text else '无'}")
+        
+        # 创建一个新的图片对象，复制像素数据但不复制文本数据
+        if img.mode == 'RGBA':
+            new_img = Image.new('RGBA', img.size)
+        else:
+            new_img = Image.new('RGB', img.size)
+        
+        # 复制像素数据
+        new_img.paste(img)
+        
+        # 确保新图片没有文本数据
+        new_img.text = {}
+        
+        # 保存回原文件
+        buffer = io.BytesIO()
+        new_img.save(buffer, format='PNG')
+        buffer.seek(0)
+        
+        with open(png_path, 'wb') as f:
+            f.write(buffer.read())
+        
+        # 验证是否已清空
+        verify_img = Image.open(png_path)
+        print(f"清空后PNG文本数据键: {list(verify_img.text.keys()) if verify_img.text else '无'}")
+        print(f"✓ 成功清空 {png_path} 中的JSON数据")
+        
+    except Exception as e:
+        print(f"✗ 处理失败: {e}")
+        import traceback
+        traceback.print_exc()
+
+if __name__ == '__main__':
+    png_file = 'data/characters/defult.png'
+    print(f"正在处理: {png_file}")
+    clear_png_text_data(png_file)
--- a/convert_worldbooks.py
+++ b/convert_worldbooks.py
@@ -0,0 +1,87 @@
+"""
+将现有的 SillyTavern 格式世界书转换为内部格式
+"""
+import json
+from pathlib import Path
+import sys
+
+# 添加backend目录到Python路径
+backend_dir = Path(__file__).parent / "backend"
+sys.path.insert(0, str(backend_dir))
+
+from models.converters import WorldBookConverter
+
+WORLDBOOKS_PATH = Path(r'D:\progarm\python\llm_workflow_engine\data\worldbooks')
+
+print("=" * 60)
+print("世界书格式转换工具")
+print("=" * 60)
+
+# 查找所有JSON文件
+json_files = list(WORLDBOOKS_PATH.glob("*.json"))
+print(f"\n找到 {len(json_files)} 个世界书文件\n")
+
+converted_count = 0
+skipped_count = 0
+error_count = 0
+
+for file_path in json_files:
+    print(f"处理: {file_path.name}")
+    
+    try:
+        # 读取文件
+        with open(file_path, 'r', encoding='utf-8') as f:
+            data = json.load(f)
+        
+        # 检测格式
+        format_type = WorldBookConverter.detect_format(data)
+        print(f"  当前格式: {format_type}")
+        
+        if format_type == "sillytavern":
+            # 需要转换
+            name = data.get("name", file_path.stem)
+            print(f"  世界书名称: {name}")
+            print(f"  条目数量: {len(data.get('entries', {}))}")
+            
+            # 转换为内部格式
+            internal_data = WorldBookConverter.st_to_internal(data, name)
+            
+            # 备份原文件
+            backup_path = file_path.with_suffix('.json.bak')
+            file_path.rename(backup_path)
+            print(f"  ✓ 已备份原文件为: {backup_path.name}")
+            
+            # 保存转换后的文件
+            with open(file_path, 'w', encoding='utf-8') as f:
+                json.dump(internal_data, f, ensure_ascii=False, indent=2)
+            
+            print(f"  ✓ 转换完成并保存")
+            print(f"  - 新格式: internal")
+            print(f"  - 条目数量: {len(internal_data.get('entries', []))}")
+            converted_count += 1
+            
+        elif format_type == "internal":
+            print(f"  ℹ 已是内部格式，跳过")
+            skipped_count += 1
+            
+        else:
+            print(f"  ⚠️  未知格式，跳过")
+            skipped_count += 1
+            
+    except Exception as e:
+        print(f"  ❌ 错误: {e}")
+        import traceback
+        traceback.print_exc()
+        error_count += 1
+    
+    print()
+
+print("=" * 60)
+print("转换完成统计:")
+print(f"  ✓ 转换成功: {converted_count} 个文件")
+print(f"  - 跳过（已是内部格式）: {skipped_count} 个文件")
+print(f"  ✗ 转换失败: {error_count} 个文件")
+print("=" * 60)
+
+if converted_count > 0:
+    print("\n提示: 原文件已备份为 .bak 后缀，确认无误后可删除")
--- a/data/characters/defult.png
+++ b/data/characters/defult.png
--- a/data/characters/测试角色1/character.json
+++ b/data/characters/测试角色1/character.json
@@ -0,0 +1,23 @@
+{
+  "id": "test-character-1",
+  "name": "测试角色1",
+  "description": "这是一个测试角色，用于验证角色卡功能",
+  "personality": "友好、乐于助人、幽默",
+  "scenario": "日常对话场景",
+  "first_mes": "你好！我是测试角色1，很高兴见到你！",
+  "mes_example": "",
+  "categories": ["测试", "示例"],
+  "tags": ["test", "demo", "friendly"],
+  "worldInfoId": null,
+  "outputSchema": null,
+  "avatarPath": null,
+  "alternate_greetings": [
+    "嗨！有什么我可以帮你的吗？",
+    "欢迎来到测试世界！"
+  ],
+  "createdAt": 1700000000,
+  "updatedAt": 1700000000,
+  "lastChatAt": null,
+  "isFavorite": false,
+  "version": 1
+}
--- a/data/characters/测试角色1/chats/默认聊天.jsonl
+++ b/data/characters/测试角色1/chats/默认聊天.jsonl
@@ -0,0 +1,4 @@
+{"user_name": "User", "character_name": "测试角色1", "create_date": "2026-04-30T15:00:00Z"}
+{"name": "测试角色1", "is_user": false, "send_date": "2026-04-30T15:00:01Z", "mes": "你好！我是测试角色1，很高兴见到你！"}
+{"name": "User", "is_user": true, "send_date": "2026-04-30T15:00:10Z", "mes": "你好！今天过得怎么样？"}
+{"name": "测试角色1", "is_user": false, "send_date": "2026-04-30T15:00:15Z", "mes": "我很好，谢谢关心！你呢？"}
--- a/data/characters/测试角色2/character.json
+++ b/data/characters/测试角色2/character.json
@@ -0,0 +1,20 @@
+{
+  "id": "test-character-2",
+  "name": "测试角色2",
+  "description": "第二个测试角色，有不同的标签",
+  "personality": "严肃、专业、认真",
+  "scenario": "工作场景",
+  "first_mes": "您好，我是测试角色2，请问有什么工作需要处理？",
+  "mes_example": "",
+  "categories": ["测试", "工作"],
+  "tags": ["test", "professional", "work"],
+  "worldInfoId": null,
+  "outputSchema": null,
+  "avatarPath": null,
+  "alternate_greetings": [],
+  "createdAt": 1700000100,
+  "updatedAt": 1700000100,
+  "lastChatAt": null,
+  "isFavorite": true,
+  "version": 1
+}
--- a/data/characters/测试角色2/chats/工作讨论.jsonl
+++ b/data/characters/测试角色2/chats/工作讨论.jsonl
@@ -0,0 +1,4 @@
+{"user_name": "User", "character_name": "测试角色2", "create_date": "2026-04-30T16:00:00Z"}
+{"name": "测试角色2", "is_user": false, "send_date": "2026-04-30T16:00:01Z", "mes": "您好，我是测试角色2，请问有什么工作需要处理？"}
+{"name": "User", "is_user": true, "send_date": "2026-04-30T16:00:10Z", "mes": "帮我分析一下这个数据"}
+{"name": "测试角色2", "is_user": false, "send_date": "2026-04-30T16:00:20Z", "mes": "好的，请提供数据，我会进行专业分析。"}
--- a/data/characters/测试角色2/chats/默认聊天.jsonl
+++ b/data/characters/测试角色2/chats/默认聊天.jsonl
@@ -0,0 +1,2 @@
+{"user_name": "User", "character_name": "测试角色2", "integrity": "644e9983-2102-4608-aeb5-64016c1ba92a", "chat_id_hash": "3f37a950-dda3-4341-97a8-50e58da796ce", "note_prompt": "", "note_interval": 0, "note_position": 0, "note_depth": 0, "note_role": 0, "extensions": {}, "timedWorldInfo": {}, "variables": {}, "tainted": false, "lastInContextMessageId": -1}
+{"name": "测试角色2", "is_user": false, "is_system": false, "floor": 1, "send_date": "1777569143941", "mes": "您好，我是测试角色2，请问有什么工作需要处理？", "extra": {}, "swipes": [], "swipe_id": 0}
--- a/data/characters/测试角色3/character.json
+++ b/data/characters/测试角色3/character.json
@@ -0,0 +1,22 @@
+{
+  "id": "test-character-3",
+  "name": "测试角色3",
+  "description": "第三个测试角色，与角色1有相同的tag",
+  "personality": "活泼、开朗、爱开玩笑",
+  "scenario": "娱乐场景",
+  "first_mes": "嘿嘿！我是测试角色3，让我们来玩吧！",
+  "mes_example": "",
+  "categories": ["测试", "娱乐"],
+  "tags": ["test", "demo", "fun"],
+  "worldInfoId": null,
+  "outputSchema": null,
+  "avatarPath": null,
+  "alternate_greetings": [
+    "哟呼！"
+  ],
+  "createdAt": 1700000200,
+  "updatedAt": 1700000200,
+  "lastChatAt": null,
+  "isFavorite": false,
+  "version": 1
+}
--- a/data/characters/测试角色3/chats/默认聊天.jsonl
+++ b/data/characters/测试角色3/chats/默认聊天.jsonl
@@ -0,0 +1,2 @@
+{"user_name": "User", "character_name": "测试角色3", "integrity": "dc677e4e-dd79-43ad-bbf9-ca886d176a0d", "chat_id_hash": "2fa6e72e-dce1-4f70-9e2d-0bc0ebce3bc1", "note_prompt": "", "note_interval": 0, "note_position": 0, "note_depth": 0, "note_role": 0, "extensions": {}, "timedWorldInfo": {}, "variables": {}, "tainted": false, "lastInContextMessageId": -1}
+{"name": "测试角色3", "is_user": false, "is_system": false, "floor": 1, "send_date": "1777569143944", "mes": "嘿嘿！我是测试角色3，让我们来玩吧！", "extra": {}, "swipes": [], "swipe_id": 0}
--- a/data/chat/testRole1/12331212.jsonl
+++ b/data/chat/testRole1/12331212.jsonl
@@ -1,4 +0,0 @@
-{"integrity": "test-uuid-2", "chat_id_hash": "hash2", "note_prompt": "探索神秘森林", "note_interval": 5, "note_position": 0, "note_depth": 2, "note_role": 1, "extensions": {}, "timedWorldInfo": {}, "variables": {"location": "forest"}, "tainted": false, "lastInContextMessageId": -1}
-{"name": "System", "is_user": false, "is_system": true, "send_date": "1700000002000", "mes": "你进入了一片神秘的森林，周围充满了未知的危险。", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
-{"name": "User", "is_user": true, "is_system": false, "send_date": "1700000003000", "mes": "我该往哪个方向走？", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
-{"name": "Ranger", "is_user": false, "is_system": false, "send_date": "1700000004000", "mes": "东边有一条小路，但西边似乎有奇怪的声音。", "extra": {}, "swipes": ["东边有一条小路，但西边似乎有奇怪的声音。", "建议往东走，那边比较安全。", "小心西边，可能有野兽。"], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
--- a/data/chat/testRole1/33211.jsonl
+++ b/data/chat/testRole1/33211.jsonl
@@ -1,3 +0,0 @@
-{"integrity": "test-uuid-1", "chat_id_hash": "hash1", "note_prompt": "", "note_interval": 0, "note_position": 0, "note_depth": 0, "note_role": 0, "extensions": {}, "timedWorldInfo": {}, "variables": {}, "tainted": false, "lastInContextMessageId": -1}
-{"name": "User", "is_user": true, "is_system": false, "send_date": "1700000000000", "mes": "你好，我是新来的冒险者。", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
-{"name": "Guide", "is_user": false, "is_system": false, "send_date": "1700000001000", "mes": "欢迎来到我们的世界！你需要什么帮助？", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
--- a/data/chat/testRole2/222.jsonl
+++ b/data/chat/testRole2/222.jsonl
@@ -1,4 +0,0 @@
-{"integrity": "test-uuid-3", "chat_id_hash": "hash3", "note_prompt": "酒馆闲聊", "note_interval": 0, "note_position": 0, "note_depth": 0, "note_role": 0, "extensions": {}, "timedWorldInfo": {}, "variables": {}, "tainted": false, "lastInContextMessageId": -1}
-{"name": "User", "is_user": true, "is_system": false, "send_date": "1700000005000", "mes": "有人知道关于龙的消息吗？", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
-{"name": "Bard", "is_user": false, "is_system": false, "send_date": "1700000006000", "mes": "听说北边的山脉里有一条红龙，它守护着巨大的宝藏。", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejs_processed": [], "gen_started": null, "gen_finished": null}
-{"name": "Warrior", "is_user": false, "is_system": false, "send_date": "1700000007000", "mes": "别信那些谣言，我上周去过那里，什么都没发现。", "extra": {}, "swipes": [], "swipe_id": 0, "swipe_info": [], "title": "", "force_avatar": null, "variables": [], "variables_initialized": [], "is_ejsprocessed": [], "gen_started": null, "gen_finished": null}
--- a/data/imports/导入测试角色.json
+++ b/data/imports/导入测试角色.json
@@ -0,0 +1,16 @@
+{
+  "name": "导入测试角色",
+  "description": "这是一个用于测试导入功能的角色",
+  "personality": "温和、耐心、善于倾听",
+  "scenario": "心理咨询场景",
+  "first_mes": "你好，我是你的倾听者。有什么想和我分享的吗？",
+  "mes_example": "",
+  "categories": ["测试", "心理"],
+  "tags": ["import-test", "counselor", "listener"],
+  "worldInfoId": null,
+  "outputSchema": null,
+  "alternate_greetings": [
+    "欢迎到来，我在这里听你说。"
+  ],
+  "isFavorite": false
+}
--- a/data/preset/Default.json
+++ b/data/preset/Default.json
@@ -0,0 +1,218 @@
+{
+    "temperature": 1,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "top_p": 1,
+    "top_k": 0,
+    "top_a": 0,
+    "min_p": 0,
+    "repetition_penalty": 1,
+    "openai_max_context": 4095,
+    "openai_max_tokens": 300,
+    "names_behavior": 0,
+    "send_if_empty": "",
+    "impersonation_prompt": "[Write your next reply from the point of view of {{user}}, using the chat history so far as a guideline for the writing style of {{user}}. Don't write as {{char}} or system. Don't describe actions of {{char}}.]",
+    "new_chat_prompt": "[Start a new Chat]",
+    "new_group_chat_prompt": "[Start a new group chat. Group members: {{group}}]",
+    "new_example_chat_prompt": "[Example Chat]",
+    "continue_nudge_prompt": "[Continue your last message without repeating its original content.]",
+    "bias_preset_selected": "Default (none)",
+    "max_context_unlocked": false,
+    "wi_format": "{0}",
+    "scenario_format": "{{scenario}}",
+    "personality_format": "{{personality}}",
+    "group_nudge_prompt": "[Write the next reply only as {{char}}.]",
+    "stream_openai": true,
+    "prompts": [
+        {
+            "name": "Main Prompt",
+            "system_prompt": true,
+            "role": "system",
+            "content": "Write {{char}}'s next reply in a fictional chat between {{char}} and {{user}}.",
+            "identifier": "main"
+        },
+        {
+            "name": "Auxiliary Prompt",
+            "system_prompt": true,
+            "role": "system",
+            "content": "",
+            "identifier": "nsfw"
+        },
+        {
+            "identifier": "dialogueExamples",
+            "name": "Chat Examples",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "name": "Post-History Instructions",
+            "system_prompt": true,
+            "role": "system",
+            "content": "",
+            "identifier": "jailbreak"
+        },
+        {
+            "identifier": "chatHistory",
+            "name": "Chat History",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "identifier": "worldInfoAfter",
+            "name": "World Info (after)",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "identifier": "worldInfoBefore",
+            "name": "World Info (before)",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "identifier": "enhanceDefinitions",
+            "role": "system",
+            "name": "Enhance Definitions",
+            "content": "If you have more knowledge of {{char}}, add to the character's lore and personality to enhance them but keep the Character Sheet's definitions absolute.",
+            "system_prompt": true,
+            "marker": false
+        },
+        {
+            "identifier": "charDescription",
+            "name": "Char Description",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "identifier": "charPersonality",
+            "name": "Char Personality",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "identifier": "scenario",
+            "name": "Scenario",
+            "system_prompt": true,
+            "marker": true
+        },
+        {
+            "identifier": "personaDescription",
+            "name": "Persona Description",
+            "system_prompt": true,
+            "marker": true
+        }
+    ],
+    "prompt_order": [
+        {
+            "character_id": 100000,
+            "order": [
+                {
+                    "identifier": "main",
+                    "enabled": true
+                },
+                {
+                    "identifier": "worldInfoBefore",
+                    "enabled": true
+                },
+                {
+                    "identifier": "charDescription",
+                    "enabled": true
+                },
+                {
+                    "identifier": "charPersonality",
+                    "enabled": true
+                },
+                {
+                    "identifier": "scenario",
+                    "enabled": true
+                },
+                {
+                    "identifier": "enhanceDefinitions",
+                    "enabled": false
+                },
+                {
+                    "identifier": "nsfw",
+                    "enabled": true
+                },
+                {
+                    "identifier": "worldInfoAfter",
+                    "enabled": true
+                },
+                {
+                    "identifier": "dialogueExamples",
+                    "enabled": true
+                },
+                {
+                    "identifier": "chatHistory",
+                    "enabled": true
+                },
+                {
+                    "identifier": "jailbreak",
+                    "enabled": true
+                }
+            ]
+        },
+        {
+            "character_id": 100001,
+            "order": [
+                {
+                    "identifier": "main",
+                    "enabled": true
+                },
+                {
+                    "identifier": "worldInfoBefore",
+                    "enabled": true
+                },
+                {
+                    "identifier": "personaDescription",
+                    "enabled": true
+                },
+                {
+                    "identifier": "charDescription",
+                    "enabled": true
+                },
+                {
+                    "identifier": "charPersonality",
+                    "enabled": true
+                },
+                {
+                    "identifier": "scenario",
+                    "enabled": true
+                },
+                {
+                    "identifier": "enhanceDefinitions",
+                    "enabled": false
+                },
+                {
+                    "identifier": "nsfw",
+                    "enabled": true
+                },
+                {
+                    "identifier": "worldInfoAfter",
+                    "enabled": true
+                },
+                {
+                    "identifier": "dialogueExamples",
+                    "enabled": true
+                },
+                {
+                    "identifier": "chatHistory",
+                    "enabled": true
+                },
+                {
+                    "identifier": "jailbreak",
+                    "enabled": true
+                }
+            ]
+        }
+    ],
+    "assistant_prefill": "",
+    "assistant_impersonation": "",
+    "use_sysprompt": false,
+    "squash_system_messages": false,
+    "media_inlining": true,
+    "continue_prefill": false,
+    "continue_postfix": " ",
+    "seed": -1,
+    "n": 1
+}
--- a/data/worldbooks/卡立创-v5.json
+++ b/data/worldbooks/卡立创-v5.json
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -2,33 +2,56 @@ version: '3.8'

 services:
  backend:
-    build: ./backend
-    command: uvicorn backend.main:app --host 0.0.0.0 --port 8000 --reload
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: llm-backend
+    command: uvicorn main:app --host 0.0.0.0 --port 8000 --reload
    ports:
-      - "3001:8000"
+      - "23337:8000"
    volumes:
-      - ./backend:/app/backend
+      - ./backend:/app
      - ./data:/app/data
-      - ./outputs:/outputs
+      - ./outputs:/app/outputs
    environment:
      - PYTHONUNBUFFERED=1
+      - PYTHONDONTWRITEBYTECODE=1
    restart: unless-stopped
+    networks:
+      - llm-network
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s

  frontend:
    build:
-      context: ./frontend-react
+      context: ./frontend
      dockerfile: Dockerfile
+      target: development
+    container_name: llm-frontend
    ports:
-      - "3000:5173"
+      - "23338:5173"
    volumes:
-      - ./frontend-react:/app
+      - ./frontend:/app
      - /app/node_modules
    environment:
-      # 如果不需要特定环境变量，可以完全移除 environment 部分
-      # 或者添加有效的环境变量，例如：
      - NODE_ENV=development
-      - VITE_BACKEND_URL=http://backend:8000
+      - VITE_API_URL=http://backend:8000
+      - VITE_WS_URL=ws://backend:8000
    command: sh -c "npm install && npm run dev -- --host 0.0.0.0"
    depends_on:
-      - backend
+      backend:
+        condition: service_healthy
    restart: unless-stopped
+    networks:
+      - llm-network
+
+networks:
+  llm-network:
+    driver: bridge
+
+volumes:
+  node_modules:
--- a/frontend-react/Dockerfile
+++ b/frontend-react/Dockerfile
@@ -1,26 +0,0 @@
-# 使用 Node.js 18 Alpine 镜像作为基础
-# 必须明确指定 node 版本，否则可能默认为空或 python 镜像
-FROM node:18-alpine
-
-# 设置工作目录
-WORKDIR /app
-
-# 设置 npm 镜像源（可选，国内推荐使用，加速依赖下载）
- RUN npm config set registry https://registry.npmmirror.com/
-
-# 复制 package.json 和 package-lock.json
-# 利用 Docker 缓存层，只有依赖变更时才重新安装
-COPY package.json package-lock.json* ./
-
-# 安装依赖
-RUN npm install
-
-# 复制源代码到容器
-COPY . .
-
-# 暴露 Vite 默认端口 5173
-EXPOSE 5173
-
-# 启动 Vite 开发服务器
-# --host 0.0.0.0 允许外部访问（Docker 容器外）
-CMD ["npm", "run", "dev", "--", "--host", "0.0.0.0"]
--- a/frontend-react/src/App.jsx
+++ b/frontend-react/src/App.jsx
@@ -1,40 +0,0 @@
-import React from 'react';
-import Toolbar from './components/ToolBar/ToolBar';
-import ChatBox from './components/ChatBox/ChatBox';
-import DicePanel from './components/DicePanel/DicePanel';
-import ImageDisplay from './components/ImageDisplay/ImageDisplay';
-import PresetPanel from './components/PresetPanel/PresetPanel';
-import './index.css';
-
-function App() {
-  return (
-    <div className="app">
-      <Toolbar />
-
-      {/* 主内容容器 */}
-      <div className="main-container">
-        {/* 左侧栏 - 预设面板 */}
-        <div className="sidebar-left">
-          <PresetPanel />
-        </div>
-
-        {/* 中间栏：聊天框 */}
-        <div className="chat-area">
-          <ChatBox />
-        </div>
-
-        {/* 右侧栏 */}
-        <div className="sidebar-right">
-          <div className="right-top">
-            <ImageDisplay />  {/* 图片展示放在顶部 */}
-          </div>
-          <div className="right-bottom">
-            <DicePanel />  {/* 骰子面板放在底部 */}
-          </div>
-        </div>
-      </div>
-    </div>
-  );
-}
-
-export default App;
--- a/frontend-react/src/Store/Slices/ChatBoxSlice.jsx
+++ b/frontend-react/src/Store/Slices/ChatBoxSlice.jsx
@@ -1,95 +0,0 @@
-import { create } from 'zustand';
-import { subscribeWithSelector } from 'zustand/middleware';
-
-const useChatBoxStore = create(
-  subscribeWithSelector((set, get) => ({
-    // 聊天历史消息列表
-    messages: [],
-
-    // 用户名称
-    userName: '',
-
-    // 角色名称
-    characterName: '',
-
-    // 当前选中的角色
-    currentRole: null,
-
-    // 当前选中的聊天
-    currentChat: null,
-
-    // 是否正在加载
-    isLoading: false,
-
-    // 错误信息
-    error: null,
-
-    // 设置消息列表
-    setMessages: (messages) => set({ messages }),
-
-    // 设置用户名称
-    setUserName: (userName) => set({ userName }),
-
-    // 设置角色名称
-    setCharacterName: (characterName) => set({ characterName }),
-
-    // 设置当前角色
-    setCurrentRole: (role) => set({ currentRole: role }),
-
-    // 设置当前聊天
-    setCurrentChat: (chat) => set({ currentChat: chat }),
-
-    // 加载聊天历史
-    fetchChatHistory: async (roleName, chatName) => {
-      set({ isLoading: true, error: null });
-      try {
-        const response = await fetch(`/api/chat_box/get_chat_history?role_name=${encodeURIComponent(roleName)}&chat_name=${encodeURIComponent(chatName)}`);
-        if (!response.ok) {
-          throw new Error('Failed to fetch chat history');
-        }
-        const data = await response.json();
-        set({
-          messages: data.messages || [],
-          userName: data.userName || 'User',
-          characterName: data.characterName || 'Assistant',
-          isLoading: false
-        });
-      } catch (error) {
-        set({
-          error: error.message,
-          isLoading: false
-        });
-      }
-    },
-
-    // 清空聊天历史
-    clearChatHistory: () => set({
-      messages: [],
-      userName: '',
-      characterName: '',
-      error: null
-    }),
-
-    // 更新特定消息的内容
-    updateMessage: (id, content) => set((state) => ({
-      messages: state.messages.map((msg) =>
-        msg.id === id ? { ...msg, content } : msg
-      )
-    })),
-  }))
-);
-
-// 监听角色和聊天变化，自动加载聊天历史
-useChatBoxStore.subscribe(
-  (state) => ({ role: state.currentRole, chat: state.currentChat }),
-  ({ role, chat }) => {
-    if (role && chat) {
-      useChatBoxStore.getState().fetchChatHistory(role, chat);
-    } else {
-      useChatBoxStore.getState().clearChatHistory();
-    }
-  },
-  { equalityFn: (a, b) => a.role === b.role && a.chat === b.chat }
-);
-
-export default useChatBoxStore;
--- a/frontend-react/src/Store/Slices/RoleSelectorSlice.jsx
+++ b/frontend-react/src/Store/Slices/RoleSelectorSlice.jsx
@@ -1,202 +0,0 @@
-import { create } from 'zustand';
-
-// 异步获取角色数据
-const fetchRoleData = async () => {
-  try {
-    const response = await fetch('/api/tool_bar/get_all_role_and_chat', {
-      method: 'GET',
-      headers: {
-        'Cache-Control': 'no-cache',
-        'Pragma': 'no-cache',
-        'Expires': '0'
-      }
-    });
-    const data = await response.json();
-    return data;
-  } catch (error) {
-    console.error('获取角色数据失败:', error);
-    throw error;
-  }
-};
-
-const useRoleSelectorStore = create((set, get) => ({
-  // 状态
-  roleData: {},
-  selectedRole: null,
-  selectedChat: null,
-  hoveredRole: null,
-  clickedRole: null,
-  isLoading: false,
-  searchTerm: '',
-  editingRole: null,
-  editingChat: null,
-  showDeleteConfirm: null,
-  deleteType: null,
-
-  // 操作
-  fetchRoleData: async () => {
-    set({ isLoading: true });
-    try {
-      const data = await fetchRoleData();
-      set({ roleData: data, isLoading: false });
-    } catch (error) {
-      set({ isLoading: false });
-      console.error('获取角色数据失败:', error);
-    }
-  },
-
-  setSelectedRole: (role) => set({ selectedRole: role }),
-
-  setSelectedChat: (chat) => set({ selectedChat: chat }),
-
-  setHoveredRole: (role) => set({ hoveredRole: role }),
-
-  setClickedRole: (role) => set({ clickedRole: role }),
-
-  setSearchTerm: (term) => set({ searchTerm: term }),
-
-  setEditingRole: (role) => set({ editingRole: role }),
-
-  setEditingChat: (chat) => set({ editingChat: chat }),
-
-  setShowDeleteConfirm: (name) => set({ showDeleteConfirm: name }),
-
-  setDeleteType: (type) => set({ deleteType: type }),
-
-  handleRenameRole: (oldName, newName) => {
-    const { roleData, selectedRole } = get();
-    if (newName && newName !== oldName) {
-      const newRoleData = { ...roleData };
-      const chats = newRoleData[oldName];
-      delete newRoleData[oldName];
-      newRoleData[newName] = chats;
-
-      if (selectedRole === oldName) {
-        set({
-          roleData: newRoleData,
-          selectedRole: newName,
-          editingRole: null
-        });
-      } else {
-        set({
-          roleData: newRoleData,
-          editingRole: null
-        });
-      }
-    } else {
-      set({ editingRole: null });
-    }
-  },
-
-  handleRenameChat: (oldName, newName) => {
-    const { roleData, selectedRole, selectedChat } = get();
-    if (newName && newName !== oldName) {
-      const newRoleData = { ...roleData };
-      const chatIndex = newRoleData[selectedRole].indexOf(oldName);
-      if (chatIndex !== -1) {
-        newRoleData[selectedRole][chatIndex] = newName;
-
-        if (selectedChat === oldName) {
-          set({
-            roleData: newRoleData,
-            selectedChat: newName,
-            editingChat: null
-          });
-        } else {
-          set({
-            roleData: newRoleData,
-            editingChat: null
-          });
-        }
-      } else {
-        set({ editingChat: null });
-      }
-    } else {
-      set({ editingChat: null });
-    }
-  },
-
-  confirmDelete: () => {
-    const { roleData, selectedRole, selectedChat, showDeleteConfirm, deleteType } = get();
-    const newRoleData = { ...roleData };
-
-    if (deleteType === 'role') {
-      delete newRoleData[showDeleteConfirm];
-      if (selectedRole === showDeleteConfirm) {
-        set({
-          roleData: newRoleData,
-          selectedRole: null,
-          selectedChat: null,
-          showDeleteConfirm: null,
-          deleteType: null
-        });
-      } else {
-        set({
-          roleData: newRoleData,
-          showDeleteConfirm: null,
-          deleteType: null
-        });
-      }
-    } else if (deleteType === 'chat') {
-      const chatIndex = newRoleData[selectedRole].indexOf(showDeleteConfirm);
-      if (chatIndex !== -1) {
-        newRoleData[selectedRole].splice(chatIndex, 1);
-        if (selectedChat === showDeleteConfirm) {
-          set({
-            roleData: newRoleData,
-            selectedChat: null,
-            showDeleteConfirm: null,
-            deleteType: null
-          });
-        } else {
-          set({
-            roleData: newRoleData,
-            showDeleteConfirm: null,
-            deleteType: null
-          });
-        }
-      } else {
-        set({
-          showDeleteConfirm: null,
-          deleteType: null
-        });
-      }
-    }
-  },
-
-  cancelDelete: () => set({ showDeleteConfirm: null, deleteType: null }),
-
-  handleAddRole: () => {
-    const { roleData } = get();
-    const newRole = '新角色';
-    const newRoleData = { ...roleData };
-    newRoleData[newRole] = [];
-    set({
-      roleData: newRoleData,
-      editingRole: newRole
-    });
-  },
-
-  handleAddChat: () => {
-    const { roleData, selectedRole } = get();
-    if (!selectedRole) return;
-
-    const newChat = '新聊天';
-    const newRoleData = { ...roleData };
-    newRoleData[selectedRole].push(newChat);
-    set({
-      roleData: newRoleData,
-      editingChat: newChat
-    });
-  },
-
-  resetPanel: () => set({
-    hoveredRole: null,
-    clickedRole: null,
-    editingRole: null,
-    editingChat: null,
-    showDeleteConfirm: null
-  })
-}));
-
-export default useRoleSelectorStore;
--- a/frontend-react/src/Store/indexStore.jsx
+++ b/frontend-react/src/Store/indexStore.jsx
@@ -1,2 +0,0 @@
-// frontend-react/src/store/index.js
-export { default as useRoleSelectorStore } from './roleSelectorStore';
--- a/frontend-react/src/components/ChatBox/ChatBox.css
+++ b/frontend-react/src/components/ChatBox/ChatBox.css
@@ -1,429 +0,0 @@
-/* ==================== 聊天框区域 ==================== */
-
-/* React 组件根容器 */
-.chat-box {
-  height: 100%; /* 修改为100%，填满父容器 */
-  width: 100%;
-  display: flex;
-  flex-direction: column;
-  background-color: #fafafa;
-  overflow: hidden; /* 防止内容溢出 */
-}
-
-/* 消息列表容器 */
-.chat-messages {
-  flex: 1;
-  min-height: 0;
-  max-height: calc(95vh - 62px); /* 减去输入区域的高度 */
-  overflow-y: auto;
-  padding: 20px;
-  padding-top: 60px;
-  display: flex;
-  flex-direction: column;
-  gap: 15px;
-}
-
-/* 设置面板 */
-.settings-panel {
-  position: absolute;
-  top: 0;
-  right: 0;
-  z-index: 20;
-  background-color: #fff;
-  border-bottom-left-radius: 8px;
-  box-shadow: 0 2px 8px rgba(0,0,0,0.1);
-  overflow: hidden;
-  transition: all 0.3s ease;
-  max-width: 200px;
-}
-
-.settings-panel.collapsed {
-  width: 40px;
-  height: 40px;
-  cursor: pointer;
-}
-
-.settings-panel.expanded {
-  width: auto;
-  min-width: 150px;
-  padding: 10px;
-  border: 1px solid #eee;
-  border-top: none;
-  border-right: none;
-}
-
-.settings-header {
-  height: 40px;
-  width: 100%;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  background-color: #f0f0f0;
-  cursor: pointer;
-  font-size: 18px;
-  color: #666;
-}
-
-.settings-panel.collapsed .settings-header:hover {
-  background-color: #e0e0e0;
-}
-
-.settings-options {
-  display: none;
-  flex-direction: column;
-  gap: 10px;
-  padding-top: 10px;
-}
-
-.settings-panel.expanded .settings-options {
-  display: flex;
-}
-
-.setting-item {
-  display: flex;
-  align-items: center;
-  justify-content: space-between;
-  font-size: 14px;
-  color: #333;
-}
-
-.setting-item input[type="checkbox"] {
-  margin-right: 8px;
-  cursor: pointer;
-}
-
-/* ==================== 聊天气泡样式 ==================== */
-
-/* 消息行容器 */
-.message {
-  display: flex;
-  width: 100%;
-  margin-bottom: 10px;
-}
-
-/* 区分左右布局 */
-.message.user {
-  justify-content: flex-end; /* 用户消息靠右 */
-}
-
-.message.ai {
-  justify-content: flex-start; /* AI 消息靠左 */
-}
-
-/* 消息容器 - 调整为垂直排列 */
-.message-container {
-  display: flex;
-  flex-direction: column;
-  max-width: 70%;
-}
-
-/* 消息头部 - 包含名称和工具栏 */
-.message-header {
-  display: flex;
-  align-items: center;
-  margin-bottom: 5px;
-  order: 1; /* 确保头部显示在第一个位置 */
-}
-
-/* 消息名称 */
-.message-name {
-  font-size: 14px;
-  font-weight: 500;
-  color: #333;
-  padding: 2px 8px;
-  border-radius: 12px;
-  background-color: rgba(0, 0, 0, 0.05);
-  display: inline-block;
-}
-
-/* 用户消息名称 */
-.message.user .message-name {
-  background-color: rgba(24, 144, 255, 0.1);
-  color: #1890ff;
-}
-
-/* AI消息名称 */
-.message.ai .message-name {
-  background-color: rgba(0, 0, 0, 0.05);
-  color: #333;
-}
-
-/* 消息工具栏 - 优化布局使图标更紧凑 */
-.message-toolbar {
-  display: flex;
-  align-items: center;
-  padding: 0 5px;
-  opacity: 0;
-  transition: opacity 0.2s ease;
-}
-
-.message:hover .message-toolbar {
-  opacity: 1;
-}
-
-.message-id {
-  font-size: 12px;
-  color: #888;
-  padding: 2px 6px;
-  border-radius: 4px;
-  background-color: rgba(0, 0, 0, 0.05);
-  display: flex;
-  align-items: center;
-}
-
-.toolbar-buttons {
-  display: flex;
-  gap: 3px; /* 减少图标之间的间距 */
-  margin: 0 5px;
-}
-
-.toolbar-button {
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  width: 24px;
-  height: 24px;
-  border: none;
-  background-color: rgba(0, 0, 0, 0.05);
-  border-radius: 4px;
-  cursor: pointer;
-  color: #555;
-  transition: all 0.2s ease;
-}
-
-.toolbar-button:hover {
-  background-color: rgba(0, 0, 0, 0.1);
-  color: #333;
-}
-
-/* AI消息头部布局：AI助手 - ID - 编辑 - 更多 */
-.message.ai .message-header {
-  flex-direction: row;
-  justify-content: flex-start;
-}
-
-.message.ai .message-name {
-  order: 1;
-}
-
-.message.ai .message-id {
-  order: 2;
-  margin-left: 5px;
-}
-
-.message.ai .toolbar-buttons {
-  order: 3;
-  margin-left: 5px;
-}
-
-/* 用户消息头部布局：更多 - 编辑 - ID - 我 */
-.message.user .message-header {
-  flex-direction: row;
-  justify-content: flex-end;
-}
-
-.message.user .message-name {
-  order: 4;
-}
-
-.message.user .message-id {
-  order: 3;
-  margin-right: 5px;
-}
-
-.message.user .toolbar-buttons {
-  order: 1;
-  margin-right: 5px;
-}
-
-/* 消息内容 - 确保显示在名称下方 */
-.message-content {
-  display: flex;
-  flex-direction: column;
-  max-width: 100%;
-  order: 2; /* 确保内容显示在第二个位置 */
-}
-
-/* 气泡本体 */
-.message .bubble {
-  max-width: 100%;
-  padding: 10px 15px;
-  border-radius: 12px;
-  position: relative;
-  font-size: 14px;
-  line-height: 1.6;
-  word-wrap: break-word;
-  box-shadow: 0 1px 2px rgba(0, 0, 0, 0.05);
-}
-
-/* AI 气泡样式 */
-.message.ai .bubble {
-  background-color: #fff;
-  color: #333;
-  border-top-left-radius: 2px;
-  border-bottom-left-radius: 2px;
-  border: 1px solid #eee;
-}
-
-/* 用户气泡样式 */
-.message.user .bubble {
-  background-color: #1890ff;
-  color: #fff;
-  border-top-right-radius: 2px;
-  border-bottom-right-radius: 2px;
-}
-
-/* 针对 AI 消息中的 HTML 内容进行简单的样式重置 */
-.message.ai .bubble p {
-  margin: 0 0 8px 0;
-}
-.message.ai .bubble p:last-child {
-  margin-bottom: 0;
-}
-.message.ai .bubble ul, .message.ai .bubble ol {
-  margin: 0 0 8px 0;
-  padding-left: 20px;
-}
-.message.ai .bubble b {
-  font-weight: 600;
-  color: #000;
-}
-
-/* 编辑模式 */
-.edit-container {
-  display: flex;
-  flex-direction: column;
-  gap: 10px;
-}
-
-.edit-textarea {
-  width: 100%;
-  min-height: 80px;
-  padding: 10px;
-  border: 1px solid #ddd;
-  border-radius: 8px;
-  resize: vertical;
-  font-family: inherit;
-  font-size: 14px;
-  line-height: 1.5;
-}
-
-.edit-textarea:focus {
-  outline: none;
-  border-color: #1890ff;
-  box-shadow: 0 0 0 2px rgba(24, 144, 255, 0.2);
-}
-
-.edit-buttons {
-  display: flex;
-  justify-content: flex-end;
-  gap: 8px;
-}
-
-.save-button, .cancel-button {
-  display: flex;
-  align-items: center;
-  gap: 4px;
-  padding: 6px 12px;
-  border: none;
-  border-radius: 4px;
-  font-size: 14px;
-  cursor: pointer;
-  transition: all 0.2s ease;
-}
-
-.save-button {
-  background-color: #1890ff;
-  color: white;
-}
-
-.save-button:hover {
-  background-color: #40a9ff;
-}
-
-.cancel-button {
-  background-color: #f0f0f0;
-  color: #333;
-}
-
-.cancel-button:hover {
-  background-color: #e6e6e6;
-}
-
-/* ==================== 输入区域 ==================== */
-
-.chat-input-wrapper {
-  background-color: #fff;
-  border-top: 1px solid #ddd;
-  padding: 10px 20px;
-  height: 62px; /* 明确设置高度 */
-  flex-shrink: 0; /* 防止被压缩 */
-  display: flex;
-  align-items: flex-end;
-  gap: 10px;
-  width: 100%;
-  position: relative;
-  z-index: 10;
-}
-
-
-.chat-input-area {
-  flex: 1;
-  display: flex;
-}
-
-.chat-input-area textarea {
-  width: 100%;
-  height: 42px;
-  min-height: 42px;
-  max-height: 300px;
-  padding: 10px;
-  border: 1px solid #ddd;
-  border-radius: 4px;
-  resize: none;
-  outline: none;
-  font-family: inherit;
-  line-height: 1.5;
-  overflow-y: auto;
-  display: block;
-}
-
-.send-button {
-  height: 42px;
-  padding: 0 20px;
-  background-color: #1890ff;
-  color: white;
-  border: none;
-  border-radius: 4px;
-  cursor: pointer;
-  white-space: nowrap;
-  flex-shrink: 0;
-}
-
-.send-button:hover {
-  background-color: #40a9ff;
-}
-
-/* 加载状态样式 */
-.loading {
-  display: flex;
-  justify-content: center;
-  align-items: center;
-  padding: 20px;
-  color: #888;
-  font-size: 14px;
-}
-
-/* 错误信息样式 */
-.error {
-  display: flex;
-  justify-content: center;
-  align-items: center;
-  padding: 20px;
-  color: #f5222d;
-  font-size: 14px;
-  background-color: rgba(245, 34, 45, 0.05);
-  border-radius: 4px;
-  margin: 10px 0;
-}
-
--- a/frontend-react/src/components/ChatBox/ChatBox.jsx
+++ b/frontend-react/src/components/ChatBox/ChatBox.jsx
@@ -1,156 +0,0 @@
-import React, { useState, useRef } from 'react';
-import useChatBoxStore from '../../Store/Slices/ChatBoxSlice';
-import './ChatBox.css';
-
-const ChatBox = () => {
-  const [isHtmlRender, setIsHtmlRender] = useState(false);
-  const [isImageGen, setIsImageGen] = useState(false);
-  const [isDynamicTable, setIsDynamicTable] = useState(false);
-  const [editingId, setEditingId] = useState(null);
-  const [editContent, setEditContent] = useState('');
-
-  const textareaRef = useRef(null);
-
-  // 从 store 获取状态
-  const { messages, userName, characterName, isLoading, error } = useChatBoxStore();
-
-  // 自动调整 Textarea 高度
-  const adjustHeight = () => {
-    const textarea = textareaRef.current;
-    const wrapper = textarea?.closest('.chat-input-wrapper');
-
-    if (textarea && wrapper) {
-      textarea.style.height = '42px';
-      wrapper.style.height = 'auto';
-      const newHeight = textarea.scrollHeight;
-
-      if (newHeight > 42) {
-        textarea.style.height = newHeight + 'px';
-      } else {
-        textarea.style.height = '42px';
-      }
-    }
-  };
-
-  const handleInput = () => {
-    adjustHeight();
-  };
-
-  // 开始编辑消息
-  const startEdit = (id, content) => {
-    setEditingId(id);
-    setEditContent(content);
-  };
-
-  // 保存编辑的消息
-  const saveEdit = (id) => {
-    // 这里可以添加向后端发送请求的代码
-    console.log(`保存消息 ${id} 的编辑内容: ${editContent}`);
-
-    // 更新前端显示
-    const messageIndex = messages.findIndex(msg => msg.id === id);
-    if (messageIndex !== -1) {
-      messages[messageIndex].content = editContent;
-    }
-
-    // 退出编辑模式
-    setEditingId(null);
-    setEditContent('');
-  };
-
-  // 取消编辑
-  const cancelEdit = () => {
-    setEditingId(null);
-    setEditContent('');
-  };
-
-  return (
-    <div className="chat-box">
-      {/* 上方：消息列表区域 */}
-      <div className="chat-messages">
-        {/* 加载状态和错误信息 */}
-        {isLoading && <div className="loading">加载中...</div>}
-        {error && <div className="error">{error}</div>}
-
-        {/* 消息列表 */}
-        {messages.map((msg) => (
-          <div key={msg.id} className={`message ${msg.role}`}>
-            <div className="message-container">
-              {/* 消息名称和工具栏在同一行 */}
-              <div className="message-header">
-                <div className="message-name">{msg.role === 'user' ? userName : characterName}</div>
-
-                {/* 消息工具栏 */}
-                <div className="message-toolbar">
-                  <span className="message-id">ID: {msg.id}</span>
-                  <div className="toolbar-buttons">
-                    <button
-                      className="toolbar-button edit-button"
-                      onClick={() => startEdit(msg.id, msg.content)}
-                    >
-                      编辑
-                    </button>
-                    <button className="toolbar-button expand-button">
-                      ⋮
-                    </button>
-                  </div>
-                </div>
-              </div>
-
-              {/* 消息内容 */}
-              <div className="message-content">
-                <div className="bubble">
-                  {editingId === msg.id ? (
-                    <div className="edit-container">
-                      <textarea
-                        value={editContent}
-                        onChange={(e) => setEditContent(e.target.value)}
-                        className="edit-textarea"
-                      />
-                      <div className="edit-buttons">
-                        <button
-                          className="save-button"
-                          onClick={() => saveEdit(msg.id)}
-                        >
-                          保存
-                        </button>
-                        <button
-                          className="cancel-button"
-                          onClick={cancelEdit}
-                        >
-                          取消
-                        </button>
-                      </div>
-                    </div>
-                  ) : (
-                    isHtmlRender ? (
-                      <div dangerouslySetInnerHTML={{ __html: msg.content }} />
-                    ) : (
-                      <div>{msg.content}</div>
-                    )
-                  )}
-                </div>
-              </div>
-            </div>
-          </div>
-        ))}
-      </div>
-
-      {/* 下方：输入框区域 */}
-      <div className="chat-input-wrapper">
-        <div className="chat-input-area">
-          <textarea
-            ref={textareaRef}
-            placeholder="输入消息..."
-            onInput={handleInput}
-            rows="1"
-            style={{ height: '42px' }}
-          />
-        </div>
-        <button className="send-button">发送</button>
-      </div>
-    </div>
-  );
-};
-
-export default ChatBox;
--- a/frontend-react/src/components/DicePanel/DicePanel.jsx
+++ b/frontend-react/src/components/DicePanel/DicePanel.jsx
@@ -1,11 +0,0 @@
-import React from 'react';
-
-const DicePanel = () => {
-  return (
-    <div className="dice-panel">
-      <div>骰子区</div>
-    </div>
-  );
-};
-
-export default DicePanel;
--- a/frontend-react/src/components/ImageDisplay/ImageDisplay.jsx
+++ b/frontend-react/src/components/ImageDisplay/ImageDisplay.jsx
@@ -1,11 +0,0 @@
-import React from 'react';
-
-const ImageDisplay = () => {
-  return (
-    <div className="image-display">
-      <div>图片展示区</div>
-    </div>
-  );
-};
-
-export default ImageDisplay;
--- a/frontend-react/src/components/Markdown2Html/Markdown2Html.jsx
+++ b/frontend-react/src/components/Markdown2Html/Markdown2Html.jsx
@@ -1,146 +0,0 @@
-// npm install react react-dom react-markdown react-syntax-highlighter remark-math rehype-katex react-copy-to-clipboard mermaid katex
-import React, { useState, useCallback, useEffect } from "react";
-import ReactMarkdown from "react-markdown";
-import { Prism as SyntaxHighlighter } from "react-syntax-highlighter";
-import { materialLight } from "react-syntax-highlighter/dist/cjs/styles/prism";
-import remarkMath from "remark-math";
-import rehypeKatex from "rehype-katex";
-import { CopyToClipboard } from "react-copy-to-clipboard";
-import mermaid from "mermaid";
-import "katex/dist/katex.min.css";
-
-// Mermaid 初始化配置
-// Mermaid是一个画图的语言
-mermaid.initialize({
-  startOnLoad: false,
-  theme: "default",
-  securityLevel: "loose",
-});
-
-const DownSvg = () => (
-  <svg width="12" height="12" viewBox="0 0 24 24">
-    <path d="M7 10l5 5 5-5z" fill="currentColor" />
-  </svg>
-);
-
-const CopySvg = () => (
-  <svg width="14" height="14" viewBox="0 0 24 24">
-    <path d="M16 1H4c-1.1 0-2 .9-2 2v14h2V3h12V1zm3 4H8c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h11c1.1 0 2-.9 2-2V7c0-1.1-.9-2-2-2zm0 16H8V7h11v14z" fill="currentColor" />
-  </svg>
-);
-
-
-const MermaidChart= ({ code }) => {
-  const [svg, setSvg] = useState("");
-  const [id] = useState(() => `mermaid-${Math.random().toString(36).substr(2, 9)}`);
-
-  useEffect(() => {
-    try {
-      mermaid.parse(code);
-      mermaid.render(id, code).then(({ svg }) => setSvg(svg));
-    } catch (err) {
-      setSvg(`<pre>Error rendering mermaid: ${err}</pre>`);
-    }
-  }, [code, id]);
-
-  return <div dangerouslySetInnerHTML={{ __html: svg }} />;
-};
-
-const MarkdownToHTML= ({ markdownRAW, className }) => {
-  const [isMermaidLoaded] = useState(true);
-  // 渲染代码块的方法
-  const CodeBlock = useCallback(
-    ({ node, inline, className, children, ...props } ) => {
-      const [isShowCode, setIsShowCode] = useState(true); // 添加展开与收起代码块状态
-      const [isShowCopy, setIsShowCopy] = useState(false);// 添加点击复制的状态
-      const match = /language-(\w+)/.exec(className || ""); // 这是用来匹配代码块对应语言的方法
-      const codeContent = String(children).replace(/\n$/, "");
-      // 处理复制成功提示
-      const handleCopy = () => {
-        setIsShowCopy(true);
-        setTimeout(() => setIsShowCopy(false), 1500);
-      };
-      //处理单行代码
-      if (inline) {
-        return <code className={className} {...props}>{children}</code>;
-      }
-
-      // 处理 Mermaid 图表代码
-      if (match?.[1] === "mermaid" && isMermaidLoaded) {
-        return (
-          <div style={{ position: "relative", margin: "20px 0" }}>
-            <div className="code-header">
-              <div
-                style={{ cursor: "pointer", marginRight: "10px", transformOrigin: "8px" }}
-                className={isShowCode ? "code-rotate-down" : "code-rotate-right"}
-                onClick={() => setIsShowCode(!isShowCode)}
-              >
-                <DownSvg />
-              </div>
-              <div>{match[1]}</div>
-              <CopyToClipboard text={codeContent} onCopy={handleCopy}>
-                <div className="preview-code-copy" style={{ cursor: "pointer" }}>
-                  {isShowCopy && <span className="copy-success">✓ 复制成功</span>}
-                  <CopySvg />
-                </div>
-              </CopyToClipboard>
-            </div>
-            {isShowCode && <MermaidChart code={codeContent} />}
-          </div>
-        );
-      }
-
-      return (
-        <div style={{ position: "relative", padding:"0"}}>
-          <div className="code-header">
-            <div
-              style={{ cursor: "pointer", marginRight: "10px", transformOrigin: "8px" }}
-              className={isShowCode ? "code-rotate-down" : "code-rotate-right"}
-              onClick={() => setIsShowCode(!isShowCode)}
-            >
-              <DownSvg style={{ 
-                transform: isShowCode ? "rotate(0deg)" : "rotate(-90deg)",
-                transition: "transform 0.2s"
-              }} />
-            </div>
-            <div>{match?.[1] || "code"}</div>
-            <CopyToClipboard text={codeContent} onCopy={handleCopy}>
-              <div className="preview-code-copy" style={{ cursor: "pointer" }}>
-                {isShowCopy && <span className="copy-success">✓ 复制成功</span>}
-                <CopySvg />
-              </div>
-            </CopyToClipboard>
-          </div>
-          {isShowCode && (
-            <SyntaxHighlighter
-              style={materialLight}
-              language={match?.[1] || "text"}
-              PreTag="div"
-              showLineNumbers
-              {...props}
-            >
-              {codeContent}
-            </SyntaxHighlighter>
-          )}
-        </div>
-      );
-    },
-    [isMermaidLoaded]
-  );
-
-  return (
-    <div
-      className={className} >
-    <ReactMarkdown
-      remarkPlugins={[remarkMath]}
-      rehypePlugins={[rehypeKatex]}
-      components={{ code: CodeBlock }}
-    >
-      {markdownRAW}
-    </ReactMarkdown>
-
-    </div>
-  );
-};
-
-export default MarkdownToHTML;
--- a/frontend-react/src/components/PresetPanel/PresetPanel.css
+++ b/frontend-react/src/components/PresetPanel/PresetPanel.css
@@ -1,57 +0,0 @@
-/* ==================== 顶部工具栏区域 ==================== */
-
-.toolbar {
-  position: absolute;
-  top: 0;
-  left: 0;
-  right: 0;
-  height: 50px;
-  background-color: #fff;
-  border-bottom: 1px solid #ddd;
-  padding: 0;
-  display: flex;
-  align-items: center;
-  justify-content: flex-end;
-  z-index: 100;
-  box-shadow: 0 2px 4px rgba(0,0,0,0.05);
-  transition: height 0.3s ease;
-}
-
-.toolbar.expanded {
-  height: auto;
-  max-height: 300px;
-  overflow-y: auto;
-  padding-bottom: 10px;
-}
-
-.toolbar-content {
-  display: none;
-  width: 100%;
-  padding: 10px 20px;
-}
-
-.toolbar.expanded .toolbar-content {
-  display: block;
-}
-
-.toolbar-toggle-btn {
-  position: absolute;
-  right: 0;
-  top: 0;
-  height: 50px;
-  width: 50px;
-  background: none;
-  border: none;
-  border-left: 1px solid #ddd;
-  cursor: pointer;
-  font-size: 0.8rem;
-  color: #666;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  z-index: 101;
-}
-
-.toolbar-toggle-btn:hover {
-  background-color: #f5f5f5;
-}
--- a/frontend-react/src/components/PresetPanel/PresetPanel.jsx
+++ b/frontend-react/src/components/PresetPanel/PresetPanel.jsx
@@ -1,30 +0,0 @@
-import React from 'react';
-import './PresetPanel.css';
-
-const PresetPanel = () => {
-  return (
-    <div className="preset-panel">
-      {/* 顶部：预设选择与输入 */}
-      <div className="preset-header">
-        {/* 下拉框 */}
-        <select className="preset-select">
-          <option>选择预设...</option>
-        </select>
-        {/* 输入框组（待定） */}
-        <div className="preset-inputs">
-          {/* inputs here */}
-        </div>
-      </div>
-
-      {/* 下方：大槽位区域 */}
-      <div className="preset-slots">
-        {/* 槽位列表 */}
-        <div className="slot-item">槽位 1</div>
-        <div className="slot-item">槽位 2</div>
-        {/* ... */}
-      </div>
-    </div>
-  );
-};
-
-export default PresetPanel;
--- a/frontend-react/src/components/RoleSelector/RoleSelector.css
+++ b/frontend-react/src/components/RoleSelector/RoleSelector.css
@@ -1,533 +0,0 @@
-/* ==================== 角色选择器容器 ==================== */
-
-.role-selector {
-  width: 100%;
-  height: 100%;
-  padding: 24px;
-  box-sizing: border-box;
-  display: flex;
-  flex-direction: column;
-  background-color: #f8fafc;
-  font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
-  /* 添加微妙的背景纹理 */
-  background-image: radial-gradient(#e5e7eb 1px, transparent 1px);
-  background-size: 20px 20px;
-  /* 添加平滑滚动 */
-  scroll-behavior: smooth;
-  /* 优化移动端体验 */
-  -webkit-overflow-scrolling: touch;
-}
-
-/* ==================== 当前选中角色显示 ==================== */
-
-.selected-role-display {
-  padding: 16px 24px;
-  border-radius: 12px;
-  /* 更丰富的渐变效果 */
-  background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
-  margin-bottom: 24px;
-  /* 增强阴影效果 */
-  box-shadow: 0 4px 12px rgba(102, 126, 234, 0.25), 0 0 0 1px rgba(255, 255, 255, 0.1) inset;
-  display: flex;
-  align-items: center;
-  justify-content: space-between;
-  /* 添加微妙的动画效果 */
-  transition: all 0.3s ease;
-}
-
-/* 悬停效果 */
-.selected-role-display:hover {
-  transform: translateY(-2px);
-  box-shadow: 0 6px 16px rgba(102, 126, 234, 0.3), 0 0 0 1px rgba(255, 255, 255, 0.2) inset;
-}
-
-.role-badge {
-  display: flex;
-  align-items: center;
-  font-size: 15px;
-}
-
-.role-badge.empty {
-  color: rgba(255, 255, 255, 0.8);
-}
-
-.role-label {
-  font-weight: 600;
-  margin-right: 8px;
-  color: rgba(255, 255, 255, 0.9);
-}
-
-.role-name {
-  color: #fff;
-  font-weight: 600;
-}
-
-.chat-name {
-  color: rgba(255, 255, 255, 0.85);
-  margin-left: 8px;
-}
-
-/* ==================== 搜索栏样式 ==================== */
-
-.search-bar {
-  margin-bottom: 20px;
-  position: relative;
-}
-
-.search-bar input {
-  width: 100%;
-  padding: 12px 16px 12px 40px; /* 为搜索图标留出空间 */
-  border: 2px solid transparent;
-  border-radius: 10px;
-  font-size: 14px;
-  transition: all 0.3s ease;
-  box-sizing: border-box;
-  background-color: #fff;
-  box-shadow: 0 2px 8px rgba(0, 0, 0, 0.05);
-}
-
-/* 添加搜索图标 */
-.search-bar::before {
-  content: '🔍';
-  position: absolute;
-  left: 14px;
-  top: 50%;
-  transform: translateY(-50%);
-  font-size: 16px;
-  opacity: 0.5;
-}
-
-.search-bar input:focus {
-  outline: none;
-  border-color: #667eea;
-  box-shadow: 0 4px 12px rgba(102, 126, 234, 0.2);
-}
-
-.search-bar input::placeholder {
-  color: #a0a0a0;
-}
-
-/* ==================== 角色列表样式 ==================== */
-
-.role-list {
-  flex: 1;
-  overflow-y: auto;
-  display: grid;
-  grid-template-columns: repeat(auto-fill, minmax(200px, 1fr)); /* 响应式网格布局 */
-  gap: 16px;
-  padding-right: 8px;
-  padding-bottom: 8px;
-  /* 自定义滚动条样式 */
-  scrollbar-width: thin;
-  scrollbar-color: #cbd5e1 transparent;
-}
-
-/* Webkit浏览器滚动条样式 */
-.role-list::-webkit-scrollbar {
-  width: 6px;
-}
-
-.role-list::-webkit-scrollbar-track {
-  background: transparent;
-}
-
-.role-list::-webkit-scrollbar-thumb {
-  background-color: #cbd5e1;
-  border-radius: 3px;
-}
-
-.role-item {
-  border: none;
-  border-radius: 14px;
-  background-color: #fff;
-  transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
-  display: flex;
-  flex-direction: column;
-  box-shadow: 0 2px 8px rgba(0, 0, 0, 0.04);
-  overflow: hidden;
-  min-height: 140px;
-  position: relative;
-  /* 添加微妙的边框效果 */
-  border: 1px solid rgba(0, 0, 0, 0.05);
-}
-
-.role-item:hover {
-  transform: translateY(-4px);
-  box-shadow: 0 8px 16px rgba(102, 126, 234, 0.15);
-}
-
-.role-item.active {
-  border: 2px solid #667eea;
-  background-color: #f5f7ff;
-  box-shadow: 0 4px 12px rgba(102, 126, 234, 0.2);
-}
-
-.role-header {
-  padding: 16px;
-  display: flex;
-  justify-content: space-between;
-  align-items: center;
-  flex: 1;
-}
-
-.role-header .role-name {
-  font-size: 15px;
-  font-weight: 600;
-  color: #1f2937;
-  overflow: hidden;
-  text-overflow: ellipsis;
-  white-space: nowrap;
-}
-
-.role-item.active .role-header .role-name {
-  color: #667eea;
-}
-
-.role-actions {
-  display: flex;
-  gap: 4px;
-  position: absolute;
-  top: 12px;
-  right: 12px;
-  opacity: 0;
-  transition: opacity 0.2s ease;
-}
-
-.role-item:hover .role-actions {
-  opacity: 1;
-}
-
-.icon-btn {
-  background: rgba(255, 255, 255, 0.95);
-  border: none;
-  cursor: pointer;
-  font-size: 14px;
-  padding: 6px;
-  border-radius: 8px;
-  transition: all 0.2s ease;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
-}
-
-.icon-btn:hover {
-  background-color: #fff;
-  transform: scale(1.1);
-}
-
-.icon-btn.delete:hover {
-  background-color: #fff1f0;
-  color: #ff4d4f;
-}
-
-/* ==================== 聊天列表样式 ==================== */
-
-.chat-list {
-  border-top: 1px solid #f0f0f0;
-  padding: 8px 0;
-  background-color: #fafbfc;
-  max-height: 140px;
-  overflow-y: auto;
-  /* 自定义滚动条样式 */
-  scrollbar-width: thin;
-  scrollbar-color: #cbd5e1 transparent;
-}
-
-/* Webkit浏览器滚动条样式 */
-.chat-list::-webkit-scrollbar {
-  width: 4px;
-}
-
-.chat-list::-webkit-scrollbar-track {
-  background: transparent;
-}
-
-.chat-list::-webkit-scrollbar-thumb {
-  background-color: #cbd5e1;
-  border-radius: 2px;
-}
-
-.chat-item {
-  padding: 10px 16px 10px 20px;
-  cursor: pointer;
-  display: flex;
-  justify-content: space-between;
-  align-items: center;
-  transition: all 0.2s ease;
-  /* 添加微妙的左边框指示器 */
-  border-left: 3px solid transparent;
-}
-
-.chat-item:hover {
-  background-color: #f0f2f5;
-}
-
-.chat-item.active {
-  background-color: #eef1ff;
-  color: #667eea;
-  /* 激活状态添加左边框指示器 */
-  border-left-color: #667eea;
-}
-
-.chat-item .chat-name {
-  font-size: 13px;
-  font-weight: 500;
-  color: #4b5563;
-  overflow: hidden;
-  text-overflow: ellipsis;
-  white-space: nowrap;
-}
-
-.chat-item.active .chat-name {
-  font-weight: 600;
-  color: #667eea;
-}
-
-/* ==================== 加载和空状态 ==================== */
-
-.loading,
-.empty-state {
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  padding: 48px;
-  color: #9ca3af;
-  font-size: 14px;
-  grid-column: 1 / -1;
-  flex-direction: column;
-  gap: 16px;
-}
-
-/* 添加加载动画 */
-.loading::before {
-  content: '';
-  width: 32px;
-  height: 32px;
-  border: 3px solid #e5e7eb;
-  border-top-color: #667eea;
-  border-radius: 50%;
-  animation: spin 0.8s linear infinite;
-}
-
-@keyframes spin {
-  to {
-    transform: rotate(360deg);
-  }
-}
-
-/* 添加空状态图标 */
-.empty-state::before {
-  content: '📭';
-  font-size: 48px;
-  opacity: 0.5;
-}
-
-/* ==================== 模态框样式 ==================== */
-
-.delete-confirm-modal {
-  position: fixed;
-  top: 0;
-  left: 0;
-  right: 0;
-  bottom: 0;
-  background-color: rgba(0, 0, 0, 0.5);
-  backdrop-filter: blur(4px);
-  z-index: 1000;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  animation: fadeIn 0.2s ease-out;
-  /* 添加微妙的背景动画 */
-  background-image: radial-gradient(circle at center, rgba(0, 0, 0, 0.6) 0%, rgba(0, 0, 0, 0.4) 100%);
-}
-
-@keyframes fadeIn {
-  from {
-    opacity: 0;
-  }
-  to {
-    opacity: 1;
-  }
-}
-
-.modal-content {
-  background-color: #fff;
-  border-radius: 16px;
-  padding: 28px;
-  width: 90%;
-  max-width: 420px;
-  box-shadow: 0 12px 28px rgba(0, 0, 0, 0.15);
-  animation: slideUp 0.3s cubic-bezier(0.4, 0, 0.2, 1);
-  /* 添加微妙的边框效果 */
-  border: 1px solid rgba(255, 255, 255, 0.2);
-}
-
-@keyframes slideUp {
-  from {
-    transform: translateY(24px);
-    opacity: 0;
-  }
-  to {
-    transform: translateY(0);
-    opacity: 1;
-  }
-}
-
-.modal-content h3 {
-  margin: 0 0 12px 0;
-  font-size: 18px;
-  font-weight: 600;
-  color: #1f2937;
-}
-
-.modal-content p {
-  margin-bottom: 28px;
-  color: #6b7280;
-  font-size: 15px;
-  line-height: 1.6;
-}
-
-.modal-actions {
-  display: flex;
-  justify-content: flex-end;
-  gap: 12px;
-}
-
-.modal-actions button {
-  padding: 11px 24px;
-  border-radius: 10px;
-  border: none;
-  cursor: pointer;
-  font-size: 14px;
-  font-weight: 500;
-  transition: all 0.2s ease;
-  /* 添加微妙的阴影效果 */
-  box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
-}
-
-.modal-actions button:first-child {
-  background-color: #f3f4f6;
-  color: #4b5563;
-}
-
-.modal-actions button:first-child:hover {
-  background-color: #e5e7eb;
-  transform: translateY(-1px);
-}
-
-.modal-actions button.danger {
-  background-color: #ef4444;
-  color: white;
-  box-shadow: 0 2px 8px rgba(239, 68, 68, 0.3);
-}
-
-.modal-actions button.danger:hover {
-  background-color: #f87171;
-  box-shadow: 0 4px 12px rgba(239, 68, 68, 0.4);
-  transform: translateY(-1px);
-}
-
-/* ==================== 响应式设计 ==================== */
-
-@media (max-width: 768px) {
-  .role-selector {
-    padding: 16px;
-  }
-
-  .role-list {
-    grid-template-columns: repeat(auto-fill, minmax(150px, 1fr));
-    gap: 12px;
-  }
-
-  .role-item {
-      border: none;
-      border-radius: 14px;
-      background-color: #fff;
-      transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
-      display: flex;
-      flex-direction: column;
-      box-shadow: 0 2px 8px rgba(0, 0, 0, 0.04);
-      overflow: hidden;
-      min-height: 160px; /* 修改：增加最小高度，使其更适配宽度 */
-      position: relative;
-      /* 添加微妙的边框效果 */
-      border: 1px solid rgba(0, 0, 0, 0.05);
-  }
-
-  .modal-content {
-    width: 95%;
-    padding: 20px;
-  }
-}
-
-@media (max-width: 480px) {
-  .role-list {
-    grid-template-columns: 1fr;
-  }
-
-  .selected-role-display {
-    padding: 12px 16px;
-  }
-
-  .modal-actions {
-    flex-direction: column;
-  }
-
-  .modal-actions button {
-    width: 100%;
-  }
-}
-
-/* ==================== 暗色模式支持 ==================== */
-
-@media (prefers-color-scheme: dark) {
-  .role-selector {
-    background-color: #1f2937;
-    background-image: radial-gradient(#374151 1px, transparent 1px);
-  }
-
-  .role-item {
-    background-color: #374151;
-    border-color: rgba(255, 255, 255, 0.1);
-  }
-
-  .role-item:hover {
-    box-shadow: 0 8px 16px rgba(0, 0, 0, 0.3);
-  }
-
-  .role-header .role-name {
-    color: #f9fafb;
-  }
-
-  .chat-list {
-    background-color: #374151;
-    border-top-color: #4b5563;
-  }
-
-  .chat-item:hover {
-    background-color: #4b5563;
-  }
-
-  .chat-item .chat-name {
-    color: #d1d5db;
-  }
-
-  .search-bar input {
-    background-color: #374151;
-    color: #f9fafb;
-  }
-
-  .modal-content {
-    background-color: #374151;
-    border-color: rgba(255, 255, 255, 0.1);
-  }
-
-  .modal-content h3 {
-    color: #f9fafb;
-  }
-
-  .modal-content p {
-    color: #d1d5db;
-  }
-}
--- a/frontend-react/src/components/RoleSelector/RoleSelector.jsx
+++ b/frontend-react/src/components/RoleSelector/RoleSelector.jsx
@@ -1,339 +0,0 @@
-import React, { useEffect, useRef } from 'react';
-import useRoleSelectorStore from '../../store/Slices/RoleSelectorSlice';
-import useChatBoxStore from '../../Store/Slices/ChatBoxSlice';
-import './RoleSelector.css';
-
-const RoleSelector = () => {
-  const panelRef = useRef(null);
-
-  // 从 Zustand store 中获取状态和操作
-  const {
-    roleData,
-    selectedRole,
-    selectedChat,
-    hoveredRole,
-    clickedRole,
-    isLoading,
-    searchTerm,
-    editingRole,
-    editingChat,
-    showDeleteConfirm,
-    deleteType,
-    fetchRoleData,
-    setSelectedRole,
-    setSelectedChat,
-    setHoveredRole,
-    setClickedRole,
-    setSearchTerm,
-    setEditingRole,
-    setEditingChat,
-    setShowDeleteConfirm,
-    setDeleteType,
-    handleRenameRole,
-    handleRenameChat,
-    confirmDelete,
-    cancelDelete,
-    handleAddRole,
-    handleAddChat,
-    resetPanel
-  } = useRoleSelectorStore();
-
-  // 从 ChatBoxStore 获取状态更新方法
-  const { setCurrentRole, setCurrentChat } = useChatBoxStore();
-
-  // 组件挂载时获取数据
-  useEffect(() => {
-    fetchRoleData();
-  }, [fetchRoleData]);
-
-  // 点击外部关闭面板
-  useEffect(() => {
-    const handleClickOutside = (event) => {
-      if (panelRef.current && !panelRef.current.contains(event.target)) {
-        resetPanel();
-      }
-    };
-
-    document.addEventListener('mousedown', handleClickOutside);
-    return () => {
-      document.removeEventListener('mousedown', handleClickOutside);
-    };
-  }, [resetPanel]);
-
-  // 处理角色选择
-  const handleRoleSelect = (role) => {
-    setSelectedRole(role);
-    // 更新 ChatBoxStore 中的当前角色
-    setCurrentRole(role);
-
-    // 如果该角色有聊天记录，默认选择第一个
-    if (roleData[role] && roleData[role].length > 0) {
-      const firstChat = roleData[role][0];
-      setSelectedChat(firstChat);
-      // 更新 ChatBoxStore 中的当前聊天
-      setCurrentChat(firstChat);
-    } else {
-      setSelectedChat(null);
-      // 清除 ChatBoxStore 中的当前聊天
-      setCurrentChat(null);
-    }
-  };
-
-  // 处理聊天选择
-  const handleChatSelect = (chat) => {
-      // 获取当前展开的角色（聊天所属的角色）
-      const currentRole = hoveredRole || clickedRole;
-
-      setSelectedChat(chat);
-      setSelectedRole(currentRole); // 使用当前展开的角色
-      setHoveredRole(null);
-      setClickedRole(null);
-      // 更新 ChatBoxStore 中的当前聊天和角色
-      setCurrentChat(chat);
-      setCurrentRole(currentRole);
-  };
-
-  // 处理角色卡片点击
-    const handleRoleCardClick = (role) => {
-      if (clickedRole === role) {
-        setClickedRole(null);
-        // 取消选择角色时，更新 selectedRole 和 selectedChat
-        setSelectedRole(null);
-        setSelectedChat(null);
-        // 同步更新 ChatBoxStore 中的状态
-        setCurrentRole(null);
-        setCurrentChat(null);
-      } else {
-        setClickedRole(role);
-        handleRoleSelect(role);
-        setSelectedRole(role);
-        setSelectedChat(chat);
-        // 同步更新 ChatBoxStore 中的状态
-        setSele
-      }
-    };
-
-
-  // 处理搜索
-  const handleSearchChange = (e) => {
-    setSearchTerm(e.target.value);
-  };
-
-  // 处理角色编辑
-  const handleEditRole = (e, role) => {
-    e.stopPropagation();
-    setEditingRole(role);
-  };
-
-  // 处理角色重命名
-  const handleRenameRoleWrapper = (e, oldName) => {
-    e.stopPropagation();
-    const newName = e.target.value;
-    handleRenameRole(oldName, newName);
-    if (selectedRole === oldName && newName && newName !== oldName) {
-      // 更新 ChatBoxStore 中的当前角色
-      setCurrentRole(newName);
-    }
-  };
-
-  // 处理聊天编辑
-  const handleEditChat = (e, chat) => {
-    e.stopPropagation();
-    setEditingChat(chat);
-  };
-
-  // 处理聊天重命名
-  const handleRenameChatWrapper = (e, oldName) => {
-    e.stopPropagation();
-    const newName = e.target.value;
-    handleRenameChat(oldName, newName);
-    if (selectedChat === oldName && newName && newName !== oldName) {
-      // 更新 ChatBoxStore 中的当前聊天
-      setCurrentChat(selectedRole, newName);
-    }
-  };
-
-  // 处理删除确认
-  const handleDeleteClick = (e, type, name) => {
-    e.stopPropagation();
-    setDeleteType(type);
-    setShowDeleteConfirm(name);
-  };
-
-  // 确认删除
-  const confirmDeleteWrapper = () => {
-    confirmDelete();
-    if (deleteType === 'role' && selectedRole === showDeleteConfirm) {
-      // 清除 ChatBoxStore 中的当前角色和聊天
-      setCurrentRole(null);
-      setCurrentChat(null);
-    } else if (deleteType === 'chat' && selectedChat === showDeleteConfirm) {
-      // 清除 ChatBoxStore 中的当前聊天
-      setCurrentChat(null);
-    }
-  };
-
-  // 过滤角色
-  const filteredRoles = Object.keys(roleData).filter(role =>
-    role.toLowerCase().includes(searchTerm.toLowerCase())
-  );
-
-  return (
-    <div className="role-selector" ref={panelRef}>
-      <div className="selected-role-display">
-        {selectedRole ? (
-          <div className="role-badge">
-            <span className="role-label">当前角色/聊天:</span>
-            <span className="role-name">{selectedRole}</span>
-            {selectedChat && <span className="chat-name">/ {selectedChat}</span>}
-          </div>
-        ) : (
-          <div className="role-badge empty">
-            <span>未选择角色</span>
-          </div>
-        )}
-      </div>
-
-      <div className="search-bar">
-        <input
-          type="text"
-          placeholder="搜索角色..."
-          value={searchTerm}
-          onChange={handleSearchChange}
-        />
-      </div>
-
-      <div className="role-list">
-        {isLoading ? (
-          <div className="loading">加载中...</div>
-        ) : filteredRoles.length === 0 ? (
-          <div className="empty-state">
-            <p>没有找到匹配的角色</p>
-          </div>
-        ) : (
-          filteredRoles.map(role => (
-            <div
-              key={role}
-              className={`role-item ${selectedRole === role ? 'active' : ''}`}
-              onClick={() => handleRoleCardClick(role)}
-              onMouseEnter={() => setHoveredRole(role)}
-              onMouseLeave={() => setHoveredRole(null)}
-            >
-              <div className="role-header">
-                {editingRole === role ? (
-                  <input
-                    type="text"
-                    defaultValue={role}
-                    autoFocus
-                    onBlur={(e) => handleRenameRoleWrapper(e, role)}
-                    onKeyDown={(e) => {
-                      if (e.key === 'Enter') {
-                        handleRenameRoleWrapper(e, role);
-                      }
-                    }}
-                    onClick={(e) => e.stopPropagation()}
-                  />
-                ) : (
-                  <div className="role-name">{role}</div>
-                )}
-
-                <div className="role-actions">
-                  <button
-                    className="icon-btn"
-                    title="编辑"
-                    onClick={(e) => handleEditRole(e, role)}
-                  >
-                    ✏️
-                  </button>
-                  <button
-                    className="icon-btn delete"
-                    title="删除"
-                    onClick={(e) => handleDeleteClick(e, 'role', role)}
-                  >
-                    🗑️
-                  </button>
-                </div>
-              </div>
-
-              {/* 聊天列表 */}
-              {(hoveredRole === role || clickedRole === role) && roleData[role] && roleData[role].length > 0 && (
-                <div className="chat-list">
-                  {roleData[role].map(chat => (
-                    <div
-                      key={chat}
-                      className={`chat-item ${selectedChat === chat ? 'active' : ''}`}
-                      onClick={(e) => {
-                        e.stopPropagation();
-                        handleChatSelect(chat);
-                      }}
-                    >
-                      <div className="chat-content">
-                        {editingChat === chat ? (
-                          <input
-                            type="text"
-                            defaultValue={chat}
-                            autoFocus
-                            onBlur={(e) => handleRenameChatWrapper(e, chat)}
-                            onKeyDown={(e) => {
-                              if (e.key === 'Enter') {
-                                handleRenameChatWrapper(e, chat);
-                              }
-                            }}
-                            onClick={(e) => e.stopPropagation()}
-                          />
-                        ) : (
-                          <div className="chat-name">{chat}</div>
-                        )}
-                      </div>
-
-                      <div className="chat-actions">
-                        {editingChat !== chat && (
-                          <>
-                            <button
-                              className="icon-btn"
-                              title="编辑"
-                              onClick={(e) => handleEditChat(e, chat)}
-                            >
-                              ✏️
-                            </button>
-                            <button
-                              className="icon-btn delete"
-                              title="删除"
-                              onClick={(e) => handleDeleteClick(e, 'chat', chat)}
-                            >
-                              🗑️
-                            </button>
-                          </>
-                        )}
-                      </div>
-                    </div>
-                  ))}
-                </div>
-              )}
-            </div>
-          ))
-        )}
-      </div>
-
-      {/* 删除确认对话框 */}
-      {showDeleteConfirm && (
-        <div className="delete-confirm-modal">
-          <div className="modal-content">
-            <h3>确认删除</h3>
-            <p>确定要删除{deleteType === 'role' ? '角色' : '聊天'} "{showDeleteConfirm}" 吗？</p>
-            <div className="modal-actions">
-              <button className="modal-button cancel-button" onClick={cancelDelete}>
-                取消
-              </button>
-              <button className="modal-button danger" onClick={confirmDeleteWrapper}>
-                确认删除
-              </button>
-            </div>
-          </div>
-        </div>
-      )}
-    </div>
-  );
-};
-
-export default RoleSelector;
--- a/frontend-react/src/components/ToolBar/ToolBar.css
+++ b/frontend-react/src/components/ToolBar/ToolBar.css
@@ -1,154 +0,0 @@
-/* ==================== 顶部工具栏区域 ==================== */
-
-.toolbar {
-  position: fixed;
-  top: 0;
-  left: 0;
-  right: 0;
-  height: 50px;
-  background-color: #fff;
-  box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1);
-  z-index: 1000;
-  display: flex;
-  align-items: center;
-  padding: 0 20px;
-  justify-content: space-between;
-  transition: all 0.3s ease;
-}
-
-/* 工具栏主要部分容器 */
-.toolbar-section {
-  display: flex;
-  align-items: center;
-  gap: 15px;
-  flex: 1;
-}
-
-/* 工具栏图标容器 */
-.toolbar-icons {
-  display: flex;
-  align-items: center;
-  gap: 15px;
-  flex: 1;
-}
-
-/* 工具栏图标 */
-.toolbar-icon {
-  width: 36px;
-  height: 36px;
-  border-radius: 6px;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  cursor: pointer;
-  transition: all 0.2s ease;
-  font-size: 18px;
-  color: #555;
-  background-color: #f5f5f5;
-}
-
-.toolbar-icon:hover {
-  background-color: #e6f7ff;
-  color: #1890ff;
-  transform: translateY(-2px);
-  box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
-}
-
-.toolbar-icon.active {
-  background-color: #1890ff;
-  color: #fff;
-}
-
-/* ==================== 弹出面板通用样式 ==================== */
-
-.close-panel-button {
-  background: none;
-  border: none;
-  font-size: 20px;
-  cursor: pointer;
-  color: #666;
-  padding: 5px 10px;
-  margin-left: auto;
-  transition: color 0.2s;
-}
-
-.close-panel-button:hover {
-  color: #333;
-}
-
-.panel-overlay {
-  position: fixed;
-  top: 50px;
-  left: 0;
-  right: 0;
-  bottom: 0;
-  background-color: rgba(0, 0, 0, 0.3);
-  z-index: 999;
-  display: flex;
-  justify-content: center;
-  padding-top: 20px;
-  animation: fadeIn 0.2s ease;
-}
-
-@keyframes fadeIn {
-  from {
-    opacity: 0;
-  }
-  to {
-    opacity: 1;
-  }
-}
-
-.panel-content {
-  background-color: #fff;
-  border-radius: 8px;
-  box-shadow: 0 4px 16px rgba(0, 0, 0, 0.15);
-  width: 90%;
-  max-width: 1200px;
-  max-height: calc(100vh - 80px);
-  overflow: hidden;
-  display: flex;
-  flex-direction: column;
-  animation: slideDown 0.3s ease;
-}
-
-@keyframes slideDown {
-  from {
-    transform: translateY(-20px);
-    opacity: 0;
-  }
-  to {
-    transform: translateY(0);
-    opacity: 1;
-  }
-}
-
-.panel-header {
-  padding: 16px 20px;
-  border-bottom: 1px solid #e0e0e0;
-  display: flex;
-  justify-content: space-between;
-  align-items: center;
-  background-color: #fafafa;
-}
-
-.panel-header h3 {
-  margin: 0;
-  font-size: 16px;
-  font-weight: 500;
-  color: #333;
-}
-
-.panel-body {
-  padding: 20px;
-  overflow-y: auto;
-  flex: 1;
-}
-
-/* 主内容区域 */
-.main-container {
-  margin-top: 50px;
-  height: calc(100vh - 50px);
-  display: flex;
-  overflow: hidden;
-}
--- a/frontend-react/src/components/ToolBar/ToolBar.jsx
+++ b/frontend-react/src/components/ToolBar/ToolBar.jsx
@@ -1,141 +0,0 @@
-import React, { useState, useRef } from 'react';
-import RoleSelector from '../RoleSelector/RoleSelector';
-import './ToolBar.css';
-
-const Toolbar = () => {
-  const [activePanel, setActivePanel] = useState(null);
-  const panelRef = useRef(null);
-
-  // 点击外部关闭面板
-  React.useEffect(() => {
-    const handleClickOutside = (event) => {
-      if (panelRef.current && !panelRef.current.contains(event.target)) {
-        setActivePanel(null);
-      }
-    };
-
-    document.addEventListener('mousedown', handleClickOutside);
-    return () => {
-      document.removeEventListener('mousedown', handleClickOutside);
-    };
-  }, []);
-
-  // 处理面板切换
-  const handlePanelToggle = (panelName) => {
-    if (activePanel === panelName) {
-      setActivePanel(null);
-    } else {
-      setActivePanel(panelName);
-    }
-  };
-
-  // 关闭面板
-  const handleClosePanel = () => {
-    setActivePanel(null);
-  };
-
-  return (
-    <>
-      <div className="toolbar">
-        {/* 左侧工具栏图标 */}
-        <div className="toolbar-section">
-          <div className="toolbar-icons">
-            {/* Logo图标 */}
-            <div
-              className="toolbar-icon"
-              title="首页"
-              onClick={() => handlePanelToggle(null)}
-            >
-              🤖
-            </div>
-          </div>
-        </div>
-
-        {/* 中间操作图标 */}
-        <div className="toolbar-section">
-          <div className="toolbar-icons">
-            {/* 角色选择图标 */}
-            <div
-              className={`toolbar-icon ${activePanel === 'role' ? 'active' : ''}`}
-              title="角色管理"
-              onClick={() => handlePanelToggle('role')}
-            >
-              👤
-            </div>
-          </div>
-        </div>
-
-        {/* 右侧工具栏图标 */}
-        <div className="toolbar-section">
-          <div className="toolbar-icons" style={{ justifyContent: 'flex-end' }}>
-            <div
-              className="toolbar-icon"
-              title="设置"
-              onClick={() => handlePanelToggle('settings')}
-            >
-              ⚙️
-            </div>
-            <div
-              className="toolbar-icon"
-              title="帮助"
-              onClick={() => handlePanelToggle('help')}
-            >
-              ❓
-            </div>
-          </div>
-        </div>
-      </div>
-
-      {/* 角色管理面板 */}
-      {activePanel === 'role' && (
-        <div className="panel-overlay" ref={panelRef}>
-          <div className="panel-content">
-            <div className="panel-header">
-              <h3>角色管理</h3>
-              <button className="close-panel-button" onClick={handleClosePanel} title="关闭">
-                ✕
-              </button>
-            </div>
-            <div className="panel-body">
-              <RoleSelector />
-            </div>
-          </div>
-        </div>
-      )}
-
-      {activePanel === 'settings' && (
-        <div className="panel-overlay" ref={panelRef}>
-          <div className="panel-content">
-            <div className="panel-header">
-              <h3>设置</h3>
-              <button className="close-panel-button" onClick={handleClosePanel} title="关闭">
-                ✕
-              </button>
-            </div>
-            <div className="panel-body">
-              <p>设置内容...</p>
-            </div>
-          </div>
-        </div>
-      )}
-
-      {activePanel === 'help' && (
-        <div className="panel-overlay" ref={panelRef}>
-          <div className="panel-content">
-            <div className="panel-header">
-              <h3>帮助</h3>
-              <button className="close-panel-button" onClick={handleClosePanel} title="关闭">
-                ✕
-              </button>
-            </div>
-            <div className="panel-body">
-              <p>帮助内容...</p>
-            </div>
-          </div>
-        </div>
-      )}
-    </>
-  );
-};
-
-export default Toolbar;
--- a/frontend-react/src/index.css
+++ b/frontend-react/src/index.css
@@ -1,61 +0,0 @@
-/* 重置样式 */
-* {
-  margin: 0;
-  padding: 0;
-  box-sizing: border-box;
-}
-
-html, body, .app {
-  height: 100%;
-  width: 100%;
-  overflow: hidden; /* 防止出现滚动条 */
-}
-
-.app {
-  display: flex;
-  flex-direction: column;
-}
-
-/* 主内容区域 */
-.main-container {
-  flex: 1; /* 这会让主容器占据剩余的所有空间 */
-  display: flex;
-  overflow: hidden; /* 防止内容溢出 */
-  height: 100%; /* 确保高度填满 */
-}
-
-/* 左侧栏 */
-.sidebar-left {
-  width: 250px; /* 或者你想要的宽度 */
-  height:  继承父元素高度; /* 确保高度填满 */
-  overflow-y: auto; /* 内容过多时显示滚动条 */
-}
-
-/* 中间聊天区域 */
-.chat-area {
-  flex: 1; /* 占据剩余空间 */
-  height: 100%; /* 确保高度填满 */
-  display: flex;
-  flex-direction: column;
-  overflow: hidden; /* 防止内容溢出 */
-}
-
-/* 右侧栏 */
-.sidebar-right {
-  width: 300px; /* 或者你想要的宽度 */
-  height: 100%; /* 确保高度填满 */
-  display: flex;
-  flex-direction: column;
-}
-
-/* 右侧栏顶部 */
-.right-top {
-  flex: 1; /* 占据剩余空间 */
-  overflow-y: auto;
-}
-
-/* 右侧栏底部 */
-.right-bottom {
-  height: 200px; /* 或者你想要的高度 */
-  overflow-y: auto;
-}
--- a/frontend-react/vite.config.js
+++ b/frontend-react/vite.config.js
@@ -1,14 +0,0 @@
-import { defineConfig } from 'vite'
-import react from '@vitejs/plugin-react'
-
-export default defineConfig({
-  plugins: [react()],
-  server: {
-    proxy: {
-      '/api': {
-        target: 'http://backend:8000',
-        changeOrigin: true,
-      }
-    }
-  }
-})
--- a/frontend/.env.development
+++ b/frontend/.env.development
@@ -0,0 +1,3 @@
+# 开发环境配置
+VITE_API_URL=http://localhost:23337/api
+VITE_WS_URL=ws://localhost:23337/api
--- a/frontend/.env.example
+++ b/frontend/.env.example
@@ -0,0 +1,3 @@
+# 环境变量示例
+VITE_API_URL=http://localhost:23337/api
+VITE_WS_URL=ws://localhost:23337/api
--- a/frontend/.env.production
+++ b/frontend/.env.production
@@ -0,0 +1,3 @@
+# 生产环境配置
+VITE_API_URL=/api
+VITE_WS_URL=ws://backend:8000/api
--- a/frontend/COMPONENT_STRUCTURE.txt
+++ b/frontend/COMPONENT_STRUCTURE.txt
--- a/frontend/Dockerfile
+++ b/frontend/Dockerfile
@@ -1,5 +1,5 @@
-# 使用 Node.js 18 Alpine 镜像作为基础
-FROM node:18-alpine
+# 多阶段构建 - 开发环境
+FROM node:20-alpine AS development

 # 设置工作目录
 WORKDIR /app
@@ -8,15 +8,55 @@ WORKDIR /app
 RUN npm config set registry https://registry.npmmirror.com/

 # 复制 package.json 和 package-lock.json
-# 利用 Docker 缓存层，只有依赖变更时才重新安装
 COPY package.json package-lock.json* ./

 # 安装依赖
 RUN npm install

+# 复制源代码到容器
+COPY . .
+
 # 暴露 Vite 默认端口 5173
 EXPOSE 5173

-# 启动命令由 docker-compose.yml 中的 command 覆盖，
-# 这里保留默认的 dev 命令作为 fallback
+# 设置环境变量
+ENV NODE_ENV=development
+ENV VITE_API_URL=http://backend:8000/api
+
+# 启动 Vite 开发服务器
 CMD ["npm", "run", "dev", "--", "--host", "0.0.0.0"]
+
+# 多阶段构建 - 生产环境
+FROM node:20-alpine AS build
+
+WORKDIR /app
+
+# 设置 npm 镜像源
+RUN npm config set registry https://registry.npmmirror.com/
+
+# 复制依赖文件
+COPY package.json package-lock.json* ./
+
+# 安装依赖
+RUN npm install
+
+# 复制源代码
+COPY . .
+
+# 构建生产版本
+RUN npm run build
+
+# 生产环境镜像
+FROM nginx:alpine AS production
+
+# 复制构建产物到 Nginx
+COPY --from=build /app/dist /usr/share/nginx/html
+
+# 复制 Nginx 配置文件
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+
+# 暴露端口
+EXPOSE 80
+
+# 启动 Nginx
+CMD ["nginx", "-g", "daemon off;"]
--- a/frontend/pycache/app.cpython-39.pyc
+++ b/frontend/pycache/app.cpython-39.pyc
--- a/frontend/app.py
+++ b/frontend/app.py
@@ -1,608 +0,0 @@
-import requests
-import streamlit as st
-import os
-from pathlib import Path
-import time
-import random
-
-# --- 页面配置 ---
-st.set_page_config(
-    page_title="AI WorkFlow Engine",
-    page_icon="🤖",
-    layout="wide",
-    initial_sidebar_state="expanded"
-)
-BACKEND_URL = os.getenv("BACKEND_URL", "http://127.0.0.1:8000")
-print(f"DEBUG BACKEND_URL: {BACKEND_URL}", flush=True)  # 看 docker logs
-
-# --- 自定义 CSS (蓝白清晰风格) ---
-st.markdown("""
-<style>
-    /* 全局背景与字体 */
-    .stApp {
-        background-color: #F0F4F8; /* 浅蓝灰背景，护眼且清晰 */
-        color: #1A1A1A; /* 深黑色字体 */
-        font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, sans-serif;
-    }
-
-    /* 隐藏默认菜单 */
-    #MainMenu {visibility: hidden;}
-    footer {visibility: hidden;}
-    header {visibility: hidden;} /* 隐藏顶部默认栏，使用自定义工具栏 */
-
-    /* 侧边栏样式 */
-    section[data-testid="stSidebar"] {
-        background-color: #FFFFFF;
-        border-right: 1px solid #D1D9E6;
-        color: #1A1A1A;
-    }
-    section[data-testid="stSidebar"] .stMarkdown, 
-    section[data-testid="stSidebar"] .stNumberInput, 
-    section[data-testid="stSidebar"] .stSlider {
-        color: #1A1A1A;
-    }
-
-    /* 聊天容器背景 (白色卡片感) */
-    .stChatMessage {
-        background-color: #FFFFFF;
-        border: 1px solid #E1E8F0;
-        border-radius: 8px;
-        padding: 10px;
-        margin-bottom: 10px;
-        box-shadow: 0 2px 4px rgba(0,0,0,0.05);
-    }
-
-    /* 用户消息特殊样式 */
-    .stChatMessage[data-testid="stChatMessage"]:has(.stMarkdown p) {
-        /* 这里很难直接针对 user/assistant 做不同背景，通过 JS 或特定类名较难，
-           Streamlit 原生 chat_message 会自动处理头像，我们主要靠边框和布局区分 */
-    }
-
-    /* 输入框样式 */
-    .stTextInput > div > div > input, 
-    .stTextArea > div > div > textarea {
-        background-color: #FFFFFF;
-        color: #1A1A1A;
-        border: 1px solid #0056B3; /* 蓝色边框 */
-        border-radius: 6px;
-    }
-    .stTextInput > div > div > input:focus, 
-    .stTextArea > div > div > textarea:focus {
-        border-color: #003D80;
-        box-shadow: 0 0 0 2px rgba(0, 86, 179, 0.2);
-    }
-
-    /* 按钮样式 */
-    .stButton > button {
-        background-color: #FFFFFF;
-        color: #0056B3;
-        border: 1px solid #0056B3;
-        border-radius: 6px;
-        font-weight: 600;
-    }
-    .stButton > button:hover {
-        background-color: #0056B3;
-        color: #FFFFFF;
-    }
-    .stButton > button[kind="primary"] {
-        background-color: #0056B3;
-        color: #FFFFFF;
-        border: 1px solid #0056B3;
-    }
-    .stButton > button[kind="primary"]:hover {
-        background-color: #003D80;
-        border-color: #003D80;
-    }
-
-    /* 拼接块列表样式优化 */
-    .splice-item {
-        background-color: #FFFFFF;
-        border: 1px solid #D1D9E6;
-        border-radius: 6px;
-        padding: 8px;
-        margin-bottom: 6px;
-        display: flex;
-        align-items: center;
-    }
-    .splice-name-active { color: #1A1A1A; font-weight: 500; }
-    .splice-name-inactive { color: #8898AA; text-decoration: line-through; }
-
-    /* 顶部工具栏 */
-    .top-bar {
-        background-color: #FFFFFF;
-        padding: 10px 20px;
-        border-bottom: 1px solid #D1D9E6;
-        margin: -10px -10px 10px -10px; /* 抵消默认 padding */
-        display: flex;
-        justify-content: space-between;
-        align-items: center;
-    }
-
-    /* 可折叠工具栏 */
-    .collapsible-toolbar {
-        background-color: #FFFFFF;
-        border-bottom: 1px solid #D1D9E6;
-        padding: 10px;
-        margin-bottom: 10px;
-    }
-
-    /* 隐藏工具栏时的样式 */
-    .toolbar-hidden {
-        display: none;
-    }
-
-    /* 工具栏切换按钮 */
-    .toolbar-toggle {
-        position: fixed;
-        top: 10px;
-        right: 10px;
-        z-index: 999;
-        background-color: #FFFFFF;
-        border: 1px solid #D1D9E6;
-        border-radius: 50%;
-        width: 40px;
-        height: 40px;
-        display: flex;
-        align-items: center;
-        justify-content: center;
-        cursor: pointer;
-        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
-    }
-
-    /* 三栏布局 - 修改部分 */
-    .main-container {
-        display: flex;
-        flex-direction: column;
-        height: calc(100vh - 60px);
-    }
-
-    .three-column-layout {
-        display: flex;
-        flex-direction: row;
-        height: 100%;
-        overflow: hidden;
-    }
-
-    .left-column, .middle-column, .right-column {
-        padding: 10px;
-        overflow-y: auto;
-        height: 100%;
-    }
-
-    .left-column {
-        flex: 1;
-        border-right: 1px solid #D1D9E6;
-    }
-
-    .middle-column {
-        flex: 3;
-        border-right: 1px solid #D1D9E6;
-        display: flex;
-        flex-direction: column;
-        overflow: hidden;
-    }
-
-    .right-column {
-        flex: 1;
-    }
-
-    /* 中间列的聊天区域 */
-    .chat-area {
-        flex: 1;
-        overflow-y: auto;
-        padding: 10px;
-        height: calc(100% - 80px); /* 减去输入区域的高度 */
-    }
-
-    /* 中间列的输入区域 */
-    .input-area {
-        flex: 0 0 auto;
-        padding: 10px;
-        border-top: 1px solid #D1D9E6;
-        background-color: #F0F4F8;
-        height: 80px; /* 固定高度 */
-    }
-
-    /* 隐藏Streamlit默认的滚动条样式 */
-    ::-webkit-scrollbar {
-        width: 8px;
-        height: 8px;
-    }
-    ::-webkit-scrollbar-track {
-        background: #f1f1f1;
-    }
-    ::-webkit-scrollbar-thumb {
-        background: #888;
-        border-radius: 4px;
-    }
-    ::-webkit-scrollbar-thumb:hover {
-        background: #555;
-    }
-</style>
-
-<script>
-    // 动态调整布局高度
-    function adjustLayout() {
-        // 获取三个列容器
-        const leftColumn = document.querySelector('.left-column');
-        const middleColumn = document.querySelector('.middle-column');
-        const rightColumn = document.querySelector('.right-column');
-
-        // 设置高度为视口高度减去顶部工具栏高度
-        const height = window.innerHeight - 60; // 减去顶部工具栏的高度
-
-        if (leftColumn) leftColumn.style.height = `${height}px`;
-        if (middleColumn) middleColumn.style.height = `${height}px`;
-        if (rightColumn) rightColumn.style.height = `${height}px`;
-
-        // 调整聊天区域高度
-        const chatArea = document.querySelector('.chat-area');
-        if (chatArea) {
-            const inputArea = document.querySelector('.input-area');
-            const inputHeight = inputArea ? inputArea.offsetHeight : 80;
-            chatArea.style.height = `${height - inputHeight}px`;
-        }
-    }
-
-    // 页面加载时调整布局
-    window.addEventListener('load', adjustLayout);
-
-    // 窗口大小改变时重新调整布局
-    window.addEventListener('resize', adjustLayout);
-
-    // 每次Streamlit重新渲染后调整布局
-    document.addEventListener('newElementRendered', adjustLayout);
-</script>
-""", unsafe_allow_html=True)
-
-# --- 状态初始化 ---
-if "messages" not in st.session_state:
-    # 初始化一些示例数据，方便查看效果
-    st.session_state.messages = [
-        {"role": "assistant", "content": "你好！我是你的 AI 工作流助手。系统已就绪，请开始对话。"},
-        {"role": "user", "content": "帮我生成一个角色卡，需要包含姓名、年龄和背景故事。"},
-        {"role": "assistant",
-         "content": "好的，这是一个示例角色卡：<br><b>姓名</b>: 艾莉娅<br><b>年龄</b>: 24<br><b>背景</b>: 一位来自北方边境的流浪法师。<br><i>(这是 HTML 渲染测试)</i>"}
-    ]
-if "render_html" not in st.session_state:
-    st.session_state.render_html = True  # 默认开启 HTML 渲染以展示效果
-if "image_folder" not in st.session_state:
-    st.session_state.image_folder = "./assets/images"
-if "splice_blocks" not in st.session_state:
-    st.session_state.splice_blocks = [
-        {"id": 1, "name": "[必看] 系统指令", "active": True, "type": "system"},
-        {"id": 2, "name": "A.U.T.O. 预设设置", "active": True, "type": "system"},
-        {"id": 3, "name": "世界书：人物关系", "active": False, "type": "world"},
-        {"id": 4, "name": "Chat History (自动)", "active": True, "type": "history", "editable": False},
-    ]
-if "toolbar_visible" not in st.session_state:
-    st.session_state.toolbar_visible = True
-
-# --- 顶部工具栏 ---
-# 工具栏切换按钮
-st.markdown("""
-<div class="toolbar-toggle" onclick="toggleToolbar()">
-    <span id="toolbar-icon">▼</span>
-</div>
-<script>
-    function toggleToolbar() {
-        var toolbar = document.querySelector('.collapsible-toolbar');
-        var icon = document.getElementById('toolbar-icon');
-        if (toolbar.style.display === 'none') {
-            toolbar.style.display = 'block';
-            icon.textContent = '▼';
-        } else {
-            toolbar.style.display = 'none';
-            icon.textContent = '▲';
-        }
-    }
-</script>
-""", unsafe_allow_html=True)
-
-# 工具栏内容
-if st.session_state.toolbar_visible:
-    with st.container():
-        c_top1, c_top2, c_top3 = st.columns([1, 6, 1])
-        with c_top1:
-            if st.button("📂 打开", key="btn_open"):
-                st.toast("打开会话功能预留")
-            if st.button("💾 保存", key="btn_save"):
-                st.toast("会话已保存")
-        with c_top2:
-            st.markdown("<h3 style='margin:0; color:#0056B3;'>AI WorkFlow Engine</h3>", unsafe_allow_html=True)
-        with c_top3:
-            if st.button("⚙️ 设置", key="btn_settings"):
-                st.toast("全局设置预留")
-
-st.divider()
-
-# --- 三栏布局 ---
-col_left, col_mid, col_right = st.columns([1, 3, 1], gap="small")
-
-# =======================
-# 1. 左侧：预设与拼接管理 (蓝白风格适配)
-# =======================
-with col_left:
-    # 使用自定义容器类
-    st.markdown('<div class="left-column">', unsafe_allow_html=True)
-
-    st.markdown("#### 📜 全局预设")
-    c_pre1, c_pre2 = st.columns([4, 1])
-    with c_pre1:
-        preset_options = ["Default", "A.U.T.O. v1.47", "Roleplay Pro"]
-        st.selectbox("选择预设", preset_options, label_visibility="collapsed")
-    with c_pre2:
-        if st.button("📥", key="btn_import", help="导入预设"):
-            st.toast("导入功能预留")
-
-    st.markdown("#### ⚙️ 生成参数")
-    c_p1, c_p2 = st.columns(2)
-    with c_p1:
-        st.slider("温度", 0.0, 2.0, 1.0, key="slider_temp")
-        st.slider("Top P", 0.0, 1.0, 0.9, key="slider_top_p")
-    with c_p2:
-        st.slider("频率惩罚", 0.0, 2.0, 1.0, key="slider_freq")
-        st.slider("存在惩罚", 0.0, 2.0, 0.0, key="slider_pres")
-
-    c_l1, c_l2 = st.columns(2)
-    with c_l1:
-        st.number_input("上下文长度", value=30000, key="input_ctx")
-    with c_l2:
-        st.number_input("最大回复", value=500, key="input_max")
-
-    st.checkbox("✅ 流式传输", value=True, key="chk_stream")
-
-    st.markdown("#### 🧩 内容拼接块")
-    st.caption("控制发送至后端的上下文组成")
-
-    # 渲染拼接块列表
-    for block in st.session_state.splice_blocks:
-        with st.container():
-            # 自定义行布局模拟列表项
-            cols = st.columns([0.5, 3, 0.5, 0.5])
-            with cols[0]:
-                icon = "🌍" if block['type'] == 'world' else ("💬" if block['type'] == 'history' else "📄")
-                st.write(icon)
-            with cols[1]:
-                name_class = "splice-name-active" if block['active'] else "splice-name-inactive"
-                st.markdown(f"<div class='{name_class}' style='font-size:0.85em;'>{block['name']}</div>",
-                            unsafe_allow_html=True)
-            with cols[2]:
-                disabled = not block.get('editable', True)
-                if st.button("✏️", key=f"edit_{block['id']}", disabled=disabled):
-                    st.toast(f"编辑：{block['name']}")
-            with cols[3]:
-                is_active = st.checkbox("✓", value=block['active'], key=f"act_{block['id']}",
-                                        label_visibility="collapsed")
-                if is_active != block['active']:
-                    block['active'] = is_active
-                    st.rerun()
-            st.markdown("<div style='height:1px; background:#E1E8F0; margin:4px 0;'></div>", unsafe_allow_html=True)
-
-    if st.button("+ 添加拼接块", use_container_width=True):
-        st.toast("添加新功能预留")
-
-    st.markdown('</div>', unsafe_allow_html=True)
-
-# =======================
-# 2. 中间：流式对话区 (动态读取历史)
-# =======================
-with col_mid:
-    # 使用自定义容器类
-    st.markdown('<div class="middle-column">', unsafe_allow_html=True)
-
-    # --- 控制区域 ---
-    c_ctrl1, c_ctrl2, c_ctrl3 = st.columns([3, 2, 1])
-
-    with c_ctrl1:
-        # --- 数据集选择下拉框 ---
-        try:
-            response = requests.get(f"{BACKEND_URL}/get_all_role_and_chat")
-            if response.status_code == 200:
-                datasets = response.json()
-                dataset_options = list(datasets.keys())
-            else:
-                st.error(f"获取数据集失败: {response.status_code}")
-                dataset_options = []
-        except requests.exceptions.RequestException as e:
-            st.error(f"请求数据集时出错: {e}")
-            dataset_options = []
-
-        selected_dataset = st.selectbox(
-            "选择数据集",
-            dataset_options,
-            index=0 if dataset_options else None,
-            key="dataset_selector"
-        )
-
-    with c_ctrl2:
-        # --- 文件路径选择下拉框 ---
-        # 初始化两层下拉框的数据结构
-        chat_history_options = {}
-        file_options = []
-
-        if selected_dataset:
-            # 使用已经获取的数据集数据
-            chat_history_options = datasets
-            # 获取当前选中数据集对应的文件列表
-            file_options = chat_history_options.get(selected_dataset, [])
-
-        # 第一层下拉框：选择聊天会话（这里应该直接使用selected_dataset）
-        # 不需要再创建一个selectbox，因为已经选择了数据集
-        selected_chat_session = selected_dataset
-
-        # 第二层下拉框：选择文件路径（value列表）
-        if selected_chat_session:
-            file_options = chat_history_options.get(selected_chat_session, [])
-            if file_options:
-                # 提取文件名并去除.jsonl后缀，用于显示
-                display_names = [os.path.basename(f).replace('.jsonl', '') for f in file_options]
-
-                # 创建文件名到完整路径的映射
-                file_name_to_path = {os.path.basename(f).replace('.jsonl', ''): f for f in file_options}
-
-                selected_file_display = st.selectbox(
-                    "选择聊天",
-                    display_names,
-                    index=0 if display_names else None,
-                    key="file_selector"
-                )
-
-                if selected_file_display:
-                    # 保存完整路径到session_state
-                    st.session_state.selected_file_path = file_name_to_path[selected_file_display]
-            else:
-                # 如果没有文件路径，清空选择
-                if "file_selector" in st.session_state:
-                    del st.session_state["file_selector"]
-        else:
-            # 如果没有选择会话，清空选择
-            if "file_selector" in st.session_state:
-                del st.session_state["file_selector"]
-
-    with c_ctrl3:
-        # HTML 渲染切换
-        toggle_html = st.toggle("HTML 渲染", value=st.session_state.render_html, key="html_toggle")
-        if toggle_html != st.session_state.render_html:
-            st.session_state.render_html = toggle_html
-            st.rerun()
-
-        # 显示当前会话信息
-        if selected_dataset and 'selected_file_path' in st.session_state:
-            file_name = os.path.basename(st.session_state.selected_file_path).replace('.jsonl', '')
-            st.caption(f"当前会话：{selected_dataset} - {file_name}")
-        else:
-            st.caption("当前会话：Active_Session_01")
-
-    # --- 核心：动态渲染历史记录 ---
-    # 使用自定义容器类包裹聊天区域
-    st.markdown('<div class="chat-area">', unsafe_allow_html=True)
-
-    # 如果选择了聊天记录，则显示该记录
-    if hasattr(st.session_state, 'selected_chat_data') and st.session_state.selected_chat_data:
-        # 显示选中的聊天记录
-        msg = st.session_state.selected_chat_data
-        with st.chat_message(msg["role"]):
-            content = msg["content"]
-
-            # 根据开关决定是否解析 HTML
-            if st.session_state.render_html and msg["role"] == "assistant":
-                st.markdown(content, unsafe_allow_html=True)
-            else:
-                st.markdown(content)
-
-            # 显示其他信息
-            with st.expander("详细信息", expanded=False):
-                st.json(msg)
-    else:
-        # 否则显示session_state中的消息历史
-        for i, msg in enumerate(st.session_state.messages):
-            with st.chat_message(msg["role"]):
-                content = msg["content"]
-
-                if st.session_state.render_html and msg["role"] == "assistant":
-                    st.markdown(content, unsafe_allow_html=True)
-                else:
-                    st.markdown(content)
-
-    st.markdown('</div>', unsafe_allow_html=True)
-
-    # --- 输入区域 ---
-    # 使用自定义容器类包裹输入区域
-    st.markdown('<div class="input-area">', unsafe_allow_html=True)
-
-    # 聊天输入框
-    user_input = st.chat_input("输入消息... (支持 /命令)")
-
-    if user_input:
-        # 1. 将用户输入加入历史
-        st.session_state.messages.append({"role": "user", "content": user_input})
-
-        # 2. 触发重新渲染
-        with st.chat_message("assistant"):
-            message_placeholder = st.empty()
-            message_placeholder.markdown("*思考中...*")
-
-            # === 模拟后端流式响应 ===
-            full_response = ""
-            simulated_text = f"收到您的指令：**{user_input}**。\n\n这是一个测试回复，如果您开启了 **HTML 渲染**，下方将显示彩色文本和表格：<br><span style='color:#0056B3; font-weight:bold;'>蓝色高亮文本</span><br><table border='1' style='border-collapse:collapse; width:100%;'><tr><th>属性</th><th>值</th></tr><tr><td>状态</td><td>正常</td></tr></table>"
-
-            chunks = simulated_text.split(" ")
-            for chunk in chunks:
-                full_response += chunk + " "
-                time.sleep(0.1)
-
-                if st.session_state.render_html:
-                    message_placeholder.markdown(full_response, unsafe_allow_html=True)
-                else:
-                    message_placeholder.markdown(full_response)
-
-            # 3. 将完整的助手回复存入历史
-            st.session_state.messages.append({"role": "assistant", "content": full_response})
-
-        # 强制刷新以确保持久化显示
-        st.rerun()
-
-    st.markdown('</div>', unsafe_allow_html=True)
-
-    st.markdown('</div>', unsafe_allow_html=True)
-
-# =======================
-# 3. 右侧：图片与骰子 (蓝白风格)
-# =======================
-with col_right:
-    # 使用自定义容器类
-    st.markdown('<div class="right-column">', unsafe_allow_html=True)
-
-    st.markdown("#### 🖼️ 本地图库")
-    img_path = Path(st.session_state.image_folder)
-    img_path.mkdir(parents=True, exist_ok=True)
-
-    try:
-        images = [f for f in os.listdir(img_path) if f.endswith(('.png', '.jpg', '.jpeg', '.webp'))]
-        if images:
-            cols = st.columns(2)
-            for idx, img_name in enumerate(images[:8]):
-                with cols[idx % 2]:
-                    # 增加白色背景和边框，使图片在浅灰底上更突出
-                    st.markdown(
-                        f"<div style='background:white; padding:5px; border-radius:4px; border:1px solid #ddd;'>",
-                        unsafe_allow_html=True)
-                    st.image(str(img_path / img_name), use_container_width=True)
-                    st.caption(img_name)
-                    st.markdown("</div>", unsafe_allow_html=True)
-        else:
-            st.info("图片文件夹为空")
-    except Exception as e:
-        st.error(f"读取错误：{e}")
-
-    st.divider()
-
-    st.markdown("#### 🎲 检定工具")
-    tab_table, tab_dice = st.tabs(["📊 表格", "🎲 骰子"])
-
-    with tab_table:
-        st.markdown("**动态数据表**")
-        st.dataframe(
-            {"属性": ["力量", "敏捷", "智力"], "数值": [50, 60, 70]},
-            hide_index=True,
-            use_container_width=True
-        )
-
-    with tab_dice:
-        roll_type = st.radio("类型", ["难度检定", "对抗骰"], horizontal=True)
-        diff_opts = ["极难 (95)", "困难 (75)", "普通 (50)"]
-        selected_diff = st.selectbox("难度", diff_opts)
-
-        c_r1, c_r2 = st.columns(2)
-        with c_r1:
-            if st.button("🎲 投掷", type="primary", use_container_width=True):
-                res = random.randint(1, 100)
-                color = "#d9534f" if res > int(selected_diff.split('(')[1].strip(')')) else "#5cb85c"
-                st.markdown(
-                    f"<div style='text-align:center; font-size:1.5em; color:{color}; font-weight:bold;'>{res}</div>",
-                    unsafe_allow_html=True)
-        with c_r2:
-            st.caption(f"目标：{selected_diff.split('(')[1].strip(')')}")
-
-    st.markdown('</div>', unsafe_allow_html=True)
--- a/frontend/assets/images/ceaa019ee659f86fc8e2a22217df30f7.jpg
+++ b/frontend/assets/images/ceaa019ee659f86fc8e2a22217df30f7.jpg
--- a/frontend/components/pycache/chat_window.cpython-39.pyc
+++ b/frontend/components/pycache/chat_window.cpython-39.pyc
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
moranzhi	f0e7e75ffb	完成大量美化	2026-05-01 15:44:14 +08:00
moranzhi	6b65b24b0f	完成大量美化	2026-05-01 14:44:18 +08:00
moranzhi	1d0f0ae0ef	feat: sync latest local code	2026-04-30 01:38:53 +08:00
moranzhi	ba9b925c32	完成世界书、骰子、apiconfig页面处理	2026-04-30 01:35:10 +08:00
moranzhi	a3e3711b2b	重构前端完成	2026-04-29 00:19:46 +08:00
moranzhi	8b10ef5828	重构后端成功	2026-04-28 00:45:18 +08:00
shen893514322@126.com	dd17206e1f	世界书部分基本完成,剩余编辑条目部分，可以推进到下一步	2026-04-07 05:40:27 +08:00
shen893514322@126.com	4f9cf4b725	世界书部分基本完成	2026-04-07 01:56:13 +08:00
shen893514322@126.com	e8dedb5ec4	重构路由架构,修复导致的前端出错	2026-04-06 00:52:04 +08:00
shen893514322@126.com	7a62139683	重构路由架构	2026-04-05 12:04:18 +08:00
shen893514322@126.com	01ca2bd0f9	暂时完成预设部分、开始世界书部分	2026-04-04 15:42:43 +08:00
shen893514322@126.com	1fc0c43689	预设拖拽实现	2026-04-04 15:19:37 +08:00
shen893514322@126.com	1abfaeda9d	后端预设列表读取完成	2026-04-04 12:36:27 +08:00
shen893514322@126.com	0ae53c4b81	后端预设、世界书部分补充	2026-04-04 10:41:38 +08:00
shen893514322@126.com	f90ad8dc13	补充css修改	2026-04-03 13:44:35 +08:00
shen893514322@126.com	6375f9759c	完成前端初步重构、实现显示选中角色功能	2026-04-03 12:09:08 +08:00
shen893514322@126.com	33188a345e	完成后端chatmessage格式修改，可以在前端完成swipe切换显示	2026-04-01 19:15:10 +08:00
shen893514322@126.com	6fa1fd6e7f	修补输入框	2026-04-01 12:50:16 +08:00
shen893514322@126.com	80237463ef	完成聊天框功能开发	2026-03-30 20:28:50 +08:00