diff --git a/CLAUDE.md b/CLAUDE.md
new file mode 100644
index 00000000..fca25068
--- /dev/null
+++ b/CLAUDE.md
@@ -0,0 +1,147 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+This is a Retrieval-Augmented Generation (RAG) system for course materials that enables users to query educational content and receive AI-powered responses. The system uses ChromaDB for vector storage, Anthropic's Claude for AI generation, and provides a web interface for interaction.
+
+## Development Commands
+
+### Running the Application
+
+**Quick Start (Recommended):**
+```bash
+chmod +x run.sh
+./run.sh
+```
+
+**Manual Start:**
+```bash
+cd backend
+uv run uvicorn app:app --reload --port 8000
+```
+
+The application will be available at:
+- Web Interface: `http://localhost:8000`
+- API Documentation: `http://localhost:8000/docs`
+
+### Environment Setup
+
+1. **Install dependencies:**
+   ```bash
+   uv sync
+   ```
+
+2. **Set up environment variables:**
+   ```bash
+   cp .env.example .env
+   # Edit .env and add your ANTHROPIC_API_KEY
+   ```
+
+### Development Tools
+
+- **Python package management:** Uses `uv` instead of pip
+- **Python version:** Requires Python 3.13 or higher
+- **Live reload:** Enabled with `--reload` flag during development
+
+## Architecture Overview
+
+### Core Components
+
+The RAG system follows a modular architecture with clear separation of concerns:
+
+**Backend Layer (`backend/`):**
+- `app.py` - FastAPI web server and API endpoints
+- `rag_system.py` - Main orchestrator coordinating all components
+- `document_processor.py` - Handles parsing and chunking of course documents
+- `vector_store.py` - ChromaDB integration for semantic search
+- `ai_generator.py` - Claude API integration with tool calling
+- `search_tools.py` - Tool system for intelligent course content searching
+- `session_manager.py` - Conversation history and session management
+
+**Frontend Layer (`frontend/`):**
+- Vanilla JavaScript web interface
+- Real-time chat interface with loading states
+- Source attribution display
+
+**Data Layer:**
+- `docs/` - Course materials in structured text format
+- `chroma_db/` - Vector database storage (auto-created)
+
+### Key Architectural Patterns
+
+**RAG Flow:**
+1. User query → FastAPI endpoint
+2. RAG system constructs prompt with conversation history
+3. Claude AI determines if course content search is needed
+4. If needed: Vector search → Formatted results → Claude generates response
+5. Response + sources returned to frontend
+
+**Document Processing Pipeline:**
+- Documents follow structured format: Course metadata → Lesson markers → Content
+- Smart chunking with overlap for context preservation
+- Context enrichment: Each chunk gets course/lesson metadata
+
+**Tool System:**
+- Claude can call `search_course_content` tool with filters (course name, lesson number)
+- Tools managed through `ToolManager` with source tracking
+- Enables intelligent, context-aware course content retrieval
+
+**Session Management:**
+- Stateless API with session IDs for conversation continuity
+- Limited history (2 rounds) to manage context window
+- Automatic session creation on first interaction
+
+### Document Format Requirements
+
+Course documents must follow this structure:
+```
+Course Title: [title]
+Course Link: [url] (optional)
+Course Instructor: [name] (optional)
+
+Lesson 0: [lesson title]
+Lesson Link: [url] (optional)
+[lesson content...]
+
+Lesson 1: [next lesson title]
+[lesson content...]
+```
+
+### Configuration
+
+Key settings in `backend/config.py`:
+- `CHUNK_SIZE: 800` - Text chunk size for vector storage
+- `CHUNK_OVERLAP: 100` - Overlap between chunks for context
+- `MAX_RESULTS: 5` - Search results limit
+- `MAX_HISTORY: 2` - Conversation rounds to remember
+- `ANTHROPIC_MODEL: "claude-sonnet-4-20250514"` - AI model version
+
+## API Endpoints
+
+- `POST /api/query` - Main chat endpoint with session management
+- `GET /api/courses` - Course statistics and available titles
+- `GET /docs` - Interactive API documentation (Swagger UI)
+
+## Important Implementation Details
+
+**Tool Calling Integration:**
+- The system uses Anthropic's tool calling feature for intelligent search
+- Search results are automatically tracked for source attribution
+- Tools are designed to be stateless and composable
+
+**Vector Search Strategy:**
+- Semantic search with metadata filtering capabilities
+- Supports course name partial matching and lesson-specific filtering
+- Results include context headers for better AI understanding
+
+**Error Handling:**
+- Graceful degradation when documents are missing
+- Input validation with helpful error messages
+- Frontend loading states for better UX
+
+**Development Considerations:**
+- No test suite currently implemented
+- Uses SQLite-backed ChromaDB for development
+- Frontend uses marked.js for Markdown rendering
\ No newline at end of file
diff --git a/user_input_flow_diagram.md b/user_input_flow_diagram.md
new file mode 100644
index 00000000..ca702447
--- /dev/null
+++ b/user_input_flow_diagram.md
@@ -0,0 +1,241 @@
+# 用户输入处理流程图
+
+## 整体架构流程图
+
+```mermaid
+graph TD
+    A[用户输入问题] --> B{前端处理}
+    B --> C[验证输入 & 清空界面]
+    C --> D[显示用户消息]
+    D --> E[显示加载动画]
+    E --> F[发送API请求]
+
+    F --> G{后端FastAPI}
+    G --> H[验证请求格式]
+    H --> I[创建/获取会话ID]
+    I --> J[RAG系统处理]
+
+    J --> K[构造提示词]
+    K --> L[获取会话历史]
+    L --> M[调用AI生成器]
+
+    M --> N{Claude AI处理}
+    N --> O{是否需要搜索课程内容?}
+    O -->|是| P[调用搜索工具]
+    O -->|否| Q[直接生成回答]
+
+    P --> R[向量数据库搜索]
+    R --> S[格式化搜索结果]
+    S --> T[Claude基于搜索结果回答]
+    T --> U[更新会话历史]
+
+    Q --> U
+    U --> V[返回响应 & 来源信息]
+
+    V --> W{前端响应处理}
+    W --> X[移除加载动画]
+    X --> Y[显示AI回答]
+    Y --> Z[显示来源信息]
+    Z --> AA[重新启用输入]
+    AA --> BB[等待下次输入]
+
+    style A fill:#e1f5fe
+    style BB fill:#e8f5e8
+    style G fill:#fff3e0
+    style N fill:#f3e5f5
+    style R fill:#fce4ec
+```
+
+## 详细组件交互图
+
+```mermaid
+sequenceDiagram
+    participant U as 用户界面
+    participant F as 前端 (script.js)
+    participant API as FastAPI (app.py)
+    participant RAG as RAG系统 (rag_system.py)
+    participant AI as AI生成器 (ai_generator.py)
+    participant ST as 搜索工具 (search_tools.py)
+    participant VS as 向量存储 (vector_store.py)
+    participant SM as 会话管理 (session_manager.py)
+
+    U->>F: 输入问题并提交
+    F->>F: 验证输入 & 禁用界面
+    F->>F: 添加用户消息到界面
+    F->>F: 显示加载动画
+
+    F->>API: POST /api/query<br/>{query, session_id}
+    API->>API: 验证Pydantic模型
+    API->>SM: 创建或获取会话
+    SM-->>API: session_id
+
+    API->>RAG: query(query, session_id)
+    RAG->>SM: get_conversation_history()
+    SM-->>RAG: conversation_history
+
+    RAG->>AI: generate_response()<br/>(query, history, tools)
+    AI->>AI: 构造系统提示 + 历史上下文
+
+    AI->>AI: 调用Claude API
+    Note over AI: Claude分析问题类型
+
+    alt 需要搜索课程内容
+        AI->>ST: execute_tool("search_course_content")
+        ST->>VS: search(query, filters)
+        VS-->>ST: 搜索结果
+        ST->>ST: 格式化结果 & 记录来源
+        ST-->>AI: 格式化的搜索结果
+
+        AI->>AI: 第二次Claude调用<br/>(包含搜索结果)
+        AI-->>RAG: 最终回答
+    else 直接回答
+        AI-->>RAG: 直接生成的回答
+    end
+
+    RAG->>SM: add_exchange(user_msg, assistant_msg)
+    RAG-->>API: {answer, sources, session_id}
+    API-->>F: JSON响应
+
+    F->>F: 移除加载动画
+    F->>F: 渲染AI回答 (Markdown)
+    F->>F: 显示来源信息 (可折叠)
+    F->>F: 重新启用输入框
+
+    F-->>U: 显示完整回答
+```
+
+## 核心组件内部流程图
+
+### 1. 文档搜索工具流程
+
+```mermaid
+graph TD
+    A[Claude调用搜索工具] --> B[解析工具参数]
+    B --> C{参数验证}
+    C -->|有效| D[调用向量存储搜索]
+    C -->|无效| E[返回错误信息]
+
+    D --> F[语义向量搜索]
+    F --> G[应用过滤条件]
+    G --> H[课程名称匹配]
+    H --> I[课程编号过滤]
+    I --> J[排序结果]
+
+    J --> K{找到结果?}
+    K -->|是| L[格式化搜索结果]
+    K -->|否| M[返回无结果消息]
+
+    L --> N[添加上下文信息<br/>课程标题 + 课程编号]
+    N --> O[记录来源信息]
+    O --> P[返回格式化结果]
+
+    style A fill:#e3f2fd
+    style P fill:#e8f5e8
+    style E fill:#ffebee
+    style M fill:#fff3e0
+```
+
+### 2. 会话管理流程
+
+```mermaid
+stateDiagram-v2
+    [*] --> NewSession: 首次访问
+    NewSession --> ActiveSession: 创建session_1
+
+    ActiveSession --> AddMessage: 用户提问
+    AddMessage --> AddResponse: AI回答
+    AddResponse --> CheckHistory: 检查历史长度
+
+    CheckHistory --> HistoryOK: 历史在限制内
+    CheckHistory --> TrimHistory: 超过最大限制
+
+    HistoryOK --> ActiveSession: 继续对话
+    TrimHistory --> ActiveSession: 保留最近N轮
+
+    ActiveSession --> NewSession: 用户刷新页面
+    ActiveSession --> [*]: 会话结束
+
+    note right of CheckHistory
+        最大历史: 2轮对话
+        (4条消息: 2用户 + 2AI)
+    end note
+```
+
+### 3. 前端状态管理流程
+
+```mermaid
+graph LR
+    A[初始状态] --> B[输入就绪]
+    B --> C[用户输入中]
+    C --> D[提交请求]
+    D --> E[等待响应]
+    E --> F[显示结果]
+    F --> B
+
+    subgraph "UI状态变化"
+        G[输入框: 启用] --> H[输入框: 禁用]
+        H --> G
+        I[发送按钮: 可用] --> J[发送按钮: 禁用]
+        J --> I
+        K[加载动画: 隐藏] --> L[加载动画: 显示]
+        L --> K
+    end
+
+    subgraph "消息状态"
+        M[用户消息: 显示]
+        N[AI消息: 加载中] --> O[AI消息: 完整显示]
+        P[来源信息: 可折叠显示]
+    end
+
+    style A fill:#e1f5fe
+    style B fill:#e8f5e8
+    style E fill:#fff3e0
+    style F fill:#f3e5f5
+```
+
+## 技术栈组件图
+
+```mermaid
+graph TB
+    subgraph "前端层"
+        UI[HTML界面]
+        JS[JavaScript处理]
+        CSS[样式渲染]
+    end
+
+    subgraph "API层"
+        FastAPI[FastAPI服务器]
+        CORS[CORS中间件]
+        Static[静态文件服务]
+    end
+
+    subgraph "业务逻辑层"
+        RAG[RAG系统协调器]
+        AI[Claude AI集成]
+        Tools[搜索工具管理]
+        Session[会话管理器]
+    end
+
+    subgraph "数据层"
+        Chroma[ChromaDB向量存储]
+        Docs[文档处理器]
+        Config[配置管理]
+    end
+
+    UI --> FastAPI
+    JS --> FastAPI
+    FastAPI --> RAG
+    RAG --> AI
+    RAG --> Tools
+    RAG --> Session
+    Tools --> Chroma
+    Session --> Session
+    Docs --> Chroma
+
+    style UI fill:#e3f2fd
+    style FastAPI fill:#fff3e0
+    style RAG fill:#f3e5f5
+    style Chroma fill:#fce4ec
+```
+
+这些流程图详细展示了从用户输入到获得回答的完整处理过程，包括各个组件之间的交互、数据流向和状态变化。每个图都从不同角度展示了系统的工作机制。
\ No newline at end of file