{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# CodeReviewAgent - 智能代码审查助手\n",
    "\n",
    "本项目演示如何使用HelloAgents框架构建一个智能代码审查助手。\n",
    "\n",
    "## 📖 使用说明\n",
    "\n",
    "- **快速体验**: 运行「第0部分」的快速演示\n",
    "- **完整功能**: 依次运行第1-7部分,体验完整的代码审查流程"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "## 第0部分：快速演示 ⚡\n",
    "\n",
    "如果你想快速了解项目功能,可以运行这个简化版本。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ 库导入和配置完成\n"
     ]
    }
   ],
   "source": [
    "# 快速演示 - 导入库和配置\n",
    "from hello_agents import SimpleAgent, HelloAgentsLLM\n",
    "from hello_agents.tools import Tool, ToolParameter\n",
    "from typing import Dict, Any, List\n",
    "import ast\n",
    "import os\n",
    "\n",
    "# 配置LLM参数\n",
    "os.environ[\"LLM_MODEL_ID\"] = \"Qwen/Qwen2.5-72B-Instruct\"\n",
    "os.environ[\"LLM_API_KEY\"] = \"your_api_key_here\"\n",
    "os.environ[\"LLM_BASE_URL\"] = \"https://api-inference.modelscope.cn/v1/\"\n",
    "os.environ[\"LLM_TIMEOUT\"] = \"60\"\n",
    "\n",
    "print(\"✅ 库导入和配置完成\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ 工具定义完成\n"
     ]
    }
   ],
   "source": [
    "# 快速演示 - 定义简单的代码分析工具\n",
    "class QuickAnalysisTool(Tool):\n",
    "    def __init__(self):\n",
    "        super().__init__(\n",
    "            name=\"quick_analysis\",\n",
    "            description=\"快速分析Python代码结构\"\n",
    "        )\n",
    "    \n",
    "    def run(self, parameters: Dict[str, Any]) -> str:\n",
    "        code = parameters.get(\"code\", \"\")\n",
    "        if not code:\n",
    "            return \"错误：代码不能为空\"\n",
    "        \n",
    "        try:\n",
    "            tree = ast.parse(code)\n",
    "            functions = [n.name for n in ast.walk(tree) if isinstance(n, ast.FunctionDef)]\n",
    "            classes = [n.name for n in ast.walk(tree) if isinstance(n, ast.ClassDef)]\n",
    "            return f\"发现{len(classes)}个类、{len(functions)}个函数: {', '.join(functions)}\"\n",
    "        except Exception as e:\n",
    "            return f\"代码解析失败: {str(e)}\"\n",
    "    \n",
    "    def get_parameters(self) -> List[ToolParameter]:\n",
    "        return [\n",
    "            ToolParameter(\n",
    "                name=\"code\",\n",
    "                type=\"string\",\n",
    "                description=\"要分析的Python代码\",\n",
    "                required=True\n",
    "            )\n",
    "        ]\n",
    "\n",
    "print(\"✅ 工具定义完成\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ 工具 'quick_analysis' 已注册。\n",
      "✅ 智能体创建完成\n",
      "✅ 可用工具: ['quick_analysis']\n"
     ]
    }
   ],
   "source": [
    "# 快速演示 - 创建工具注册表和智能体\n",
    "from hello_agents import ToolRegistry\n",
    "\n",
    "# 创建工具注册表\n",
    "quick_registry = ToolRegistry()\n",
    "quick_registry.register_tool(QuickAnalysisTool())\n",
    "\n",
    "# 创建智能体\n",
    "quick_agent = SimpleAgent(\n",
    "    name=\"快速审查助手\",\n",
    "    llm=HelloAgentsLLM(),\n",
    "    system_prompt=\"你是代码审查助手,使用工具分析代码并给出简要建议。\",\n",
    "    tool_registry=quick_registry\n",
    ")\n",
    "\n",
    "print(\"✅ 智能体创建完成\")\n",
    "print(f\"✅ 可用工具: {list(quick_registry._tools.keys())}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=== 快速演示：分析测试代码 ===\n",
      "看来我们遇到了一些技术问题，导致代码无法通过工具进行分析。不过，我可以直接为你提供一些建议和观察结果。\n",
      "\n",
      "### 代码分析\n",
      "\n",
      "#### 1. **函数定义**\n",
      "- `hello()` 和 `world()` 函数都很简单，分别打印 \"Hello\" 和 \"World\"。这部分代码是正确的，没有问题。\n",
      "\n",
      "#### 2. **类定义**\n",
      "- `Greeter` 类包含一个 `greet` 方法，该方法调用了 `hello()` 和 `world()` 函数。这也是正确的。\n",
      "\n",
      "### 建议\n",
      "\n",
      "1. **代码风格**\n",
      "   - 代码风格符合 PEP 8 规范，这是 Python 的官方编码风格指南。建议保持这种风格。\n",
      "   - 你可以考虑添加一些文档字符串（docstrings）来描述每个函数和类的作用。例如：\n",
      "     ```python\n",
      "     def hello():\n",
      "         \"\"\"Prints 'Hello'\"\"\"\n",
      "         print(\"Hello\")\n",
      "\n",
      "     def world():\n",
      "         \"\"\"Prints 'World'\"\"\"\n",
      "         print(\"World\")\n",
      "\n",
      "     class Greeter:\n",
      "         \"\"\"A class to greet the world\"\"\"\n",
      "\n",
      "         def greet(self):\n",
      "             \"\"\"Prints 'Hello World'\"\"\"\n",
      "             hello()\n",
      "             world()\n",
      "     ```\n",
      "\n",
      "2. **测试**\n",
      "   - 为了确保代码按预期工作，可以编写一些简单的测试用例。例如：\n",
      "     ```python\n",
      "     if __name__ == \"__main__\":\n",
      "         greeter = Greeter()\n",
      "         greeter.greet()\n",
      "     ```\n",
      "   - 这样可以在运行脚本时调用 `greet` 方法，验证输出是否正确。\n",
      "\n",
      "3. **扩展性**\n",
      "   - 如果未来需要扩展 `Greeter` 类的功能，可以考虑添加更多的方法或属性。例如，可以添加一个 `set_greeting` 方法来动态设置问候语。\n",
      "\n",
      "### 总结\n",
      "你的代码已经很简洁明了，但可以通过添加文档字符串和测试用例来提高可读性和可靠性。希望这些建议对你有帮助！如果还有其他问题或需要进一步的分析，请告诉我。\n",
      "\n",
      "✅ 快速演示完成！\n",
      "\n",
      "💡 提示：继续运行下面的单元格,体验完整功能\n"
     ]
    }
   ],
   "source": [
    "# 快速演示 - 测试代码\n",
    "test_code = \"\"\"\n",
    "def hello():\n",
    "    print(\"Hello\")\n",
    "\n",
    "def world():\n",
    "    print(\"World\")\n",
    "\n",
    "class Greeter:\n",
    "    def greet(self):\n",
    "        hello()\n",
    "        world()\n",
    "\"\"\"\n",
    "\n",
    "print(\"=== 快速演示：分析测试代码 ===\")\n",
    "result = quick_agent.run(f\"请分析这段代码:\\n{test_code}\")\n",
    "print(result)\n",
    "print(\"\\n✅ 快速演示完成！\")\n",
    "print(\"\\n💡 提示：继续运行下面的单元格,体验完整功能\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "# 完整版代码审查系统\n",
    "\n",
    "下面是完整的代码审查系统,包含更强大的分析功能。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第1部分：环境配置"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ 环境配置完成\n",
      "✅ 使用模型: Qwen/Qwen2.5-72B-Instruct\n",
      "✅ API地址: https://api-inference.modelscope.cn/v1/\n"
     ]
    }
   ],
   "source": [
    "# 导入必要的库\n",
    "from hello_agents import SimpleAgent, HelloAgentsLLM\n",
    "from hello_agents.tools import Tool, ToolParameter\n",
    "from typing import Dict, Any, List\n",
    "import ast\n",
    "import os\n",
    "\n",
    "# 配置LLM参数\n",
    "os.environ[\"LLM_MODEL_ID\"] = \"Qwen/Qwen2.5-72B-Instruct\"\n",
    "os.environ[\"LLM_API_KEY\"] = \"your_api_key_here\"\n",
    "os.environ[\"LLM_BASE_URL\"] = \"https://api-inference.modelscope.cn/v1/\"\n",
    "os.environ[\"LLM_TIMEOUT\"] = \"60\"\n",
    "\n",
    "print(\"✅ 环境配置完成\")\n",
    "print(f\"✅ 使用模型: {os.getenv('LLM_MODEL_ID')}\")\n",
    "print(f\"✅ API地址: {os.getenv('LLM_BASE_URL')}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第2部分：定义代码分析工具"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ CodeAnalysisTool定义完成\n"
     ]
    }
   ],
   "source": [
    "class CodeAnalysisTool(Tool):\n",
    "    \"\"\"代码静态分析工具\"\"\"\n",
    "\n",
    "    def __init__(self):\n",
    "        super().__init__(\n",
    "            name=\"code_analysis\",\n",
    "            description=\"分析Python代码的结构、复杂度和潜在问题\"\n",
    "        )\n",
    "\n",
    "    def run(self, parameters: Dict[str, Any]) -> str:\n",
    "        \"\"\"分析代码并返回结果\"\"\"\n",
    "        code = parameters.get(\"code\", \"\")\n",
    "        if not code:\n",
    "            return \"错误：代码不能为空\"\n",
    "        \n",
    "        try:\n",
    "            tree = ast.parse(code)\n",
    "\n",
    "            # 统计信息\n",
    "            functions = [node for node in ast.walk(tree) if isinstance(node, ast.FunctionDef)]\n",
    "            classes = [node for node in ast.walk(tree) if isinstance(node, ast.ClassDef)]\n",
    "\n",
    "            result = {\n",
    "                \"函数数量\": len(functions),\n",
    "                \"类数量\": len(classes),\n",
    "                \"代码行数\": len(code.split('\\n')),\n",
    "                \"函数列表\": [f.name for f in functions],\n",
    "                \"类列表\": [c.name for c in classes]\n",
    "            }\n",
    "\n",
    "            return str(result)\n",
    "        except SyntaxError as e:\n",
    "            return f\"语法错误：{str(e)}\"\n",
    "    \n",
    "    def get_parameters(self) -> List[ToolParameter]:\n",
    "        return [\n",
    "            ToolParameter(\n",
    "                name=\"code\",\n",
    "                type=\"string\",\n",
    "                description=\"要分析的Python代码\",\n",
    "                required=True\n",
    "            )\n",
    "        ]\n",
    "\n",
    "print(\"✅ CodeAnalysisTool定义完成\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ StyleCheckTool定义完成\n"
     ]
    }
   ],
   "source": [
    "class StyleCheckTool(Tool):\n",
    "    \"\"\"代码风格检查工具\"\"\"\n",
    "\n",
    "    def __init__(self):\n",
    "        super().__init__(\n",
    "            name=\"style_check\",\n",
    "            description=\"检查代码是否符合PEP 8规范\"\n",
    "        )\n",
    "\n",
    "    def run(self, parameters: Dict[str, Any]) -> str:\n",
    "        \"\"\"检查代码风格\"\"\"\n",
    "        code = parameters.get(\"code\", \"\")\n",
    "        if not code:\n",
    "            return \"错误：代码不能为空\"\n",
    "        \n",
    "        issues = []\n",
    "\n",
    "        lines = code.split('\\n')\n",
    "        for i, line in enumerate(lines, 1):\n",
    "            # 检查行长度\n",
    "            if len(line) > 79:\n",
    "                issues.append(f\"第{i}行：超过79个字符\")\n",
    "\n",
    "            # 检查缩进\n",
    "            if line.startswith(' ') and not line.startswith('    '):\n",
    "                if len(line) - len(line.lstrip()) not in [0, 4, 8, 12]:\n",
    "                    issues.append(f\"第{i}行：缩进不规范\")\n",
    "\n",
    "        if not issues:\n",
    "            return \"代码风格良好，符合PEP 8规范\"\n",
    "        return \"发现以下问题：\\n\" + \"\\n\".join(issues)\n",
    "    \n",
    "    def get_parameters(self) -> List[ToolParameter]:\n",
    "        return [\n",
    "            ToolParameter(\n",
    "                name=\"code\",\n",
    "                type=\"string\",\n",
    "                description=\"要检查的Python代码\",\n",
    "                required=True\n",
    "            )\n",
    "        ]\n",
    "\n",
    "print(\"✅ StyleCheckTool定义完成\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第3部分：创建智能体"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ 工具 'code_analysis' 已注册。\n",
      "✅ 工具 'style_check' 已注册。\n",
      "✅ 智能体创建完成\n",
      "智能体名称: 代码审查助手\n",
      "可用工具: ['code_analysis', 'style_check']\n"
     ]
    }
   ],
   "source": [
    "# 导入工具注册表\n",
    "from hello_agents import ToolRegistry\n",
    "\n",
    "# 创建工具注册表\n",
    "tool_registry = ToolRegistry()\n",
    "tool_registry.register_tool(CodeAnalysisTool())\n",
    "tool_registry.register_tool(StyleCheckTool())\n",
    "\n",
    "# 初始化LLM\n",
    "llm = HelloAgentsLLM()\n",
    "\n",
    "# 定义系统提示词\n",
    "system_prompt = \"\"\"你是一位经验丰富的代码审查专家。你的任务是：\n",
    "\n",
    "1. 使用code_analysis工具分析代码结构\n",
    "2. 使用style_check工具检查代码风格\n",
    "3. 基于分析结果，提供详细的审查报告\n",
    "\n",
    "审查报告应包括：\n",
    "- 代码结构分析\n",
    "- 风格问题\n",
    "- 潜在bug\n",
    "- 性能优化建议\n",
    "- 最佳实践建议\n",
    "\n",
    "请以Markdown格式输出报告。\"\"\"\n",
    "\n",
    "# 创建智能体\n",
    "agent = SimpleAgent(\n",
    "    name=\"代码审查助手\",\n",
    "    llm=llm,\n",
    "    system_prompt=system_prompt,\n",
    "    tool_registry=tool_registry\n",
    ")\n",
    "\n",
    "print(\"✅ 智能体创建完成\")\n",
    "print(f\"智能体名称: {agent.name}\")\n",
    "print(f\"可用工具: {list(tool_registry._tools.keys())}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第4部分：读取示例代码"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=== 待审查的代码 ===\n",
      "\"\"\"\n",
      "示例代码：一个简单的用户管理系统\n",
      "用于演示代码审查功能\n",
      "\"\"\"\n",
      "\n",
      "class UserManager:\n",
      "    \"\"\"用户管理类\"\"\"\n",
      "    \n",
      "    def __init__(self):\n",
      "        self.users = []\n",
      "    \n",
      "    def add_user(self, name, age, email):\n",
      "        \"\"\"添加用户\"\"\"\n",
      "        user = {\"name\": name, \"age\": age, \"email\": email}\n",
      "        self.users.append(user)\n",
      "        return True\n",
      "    \n",
      "    def get_user(self, name):\n",
      "        \"\"\"获取用户信息\"\"\"\n",
      "        for user in self.users:\n",
      "            if user[\"name\"] == name:\n",
      "                return user\n",
      "        return None\n",
      "    \n",
      "    def delete_user(self, name):\n",
      "        \"\"\"删除用户\"\"\"\n",
      "        for i, user in enumerate(self.users):\n",
      "            if user[\"name\"] == name:\n",
      "                del self.users[i]\n",
      "                return True\n",
      "        return False\n",
      "\n",
      "def calculate_average_age(users):\n",
      "    \"\"\"计算平均年龄\"\"\"\n",
      "    total = 0\n",
      "    for user in users:\n",
      "        total += user[\"age\"]\n",
      "    return total / len(users)\n",
      "\n",
      "def send_email(email, message):\n",
      "    \"\"\"发送邮件（模拟）\"\"\"\n",
      "    print(f\"发送邮件到 {email}: {message}\")\n",
      "    return True\n",
      "\n",
      "\n",
      "\n",
      "==================================================\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# 读取示例代码\n",
    "with open(\"data/sample_code.py\", \"r\", encoding=\"utf-8\") as f:\n",
    "    sample_code = f.read()\n",
    "\n",
    "print(\"=== 待审查的代码 ===\")\n",
    "print(sample_code)\n",
    "print(\"\\n\" + \"=\"*50 + \"\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第5部分：执行代码审查"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=== 开始代码审查 ===\n",
      "## 代码审查报告\n",
      "\n",
      "### 代码结构分析\n",
      "\n",
      "根据`code_analysis`工具的结果，代码中没有语法错误。以下是代码结构的详细分析：\n",
      "\n",
      "1. **类定义**：\n",
      "   - `UserManager` 类负责用户管理，包含三个方法：`add_user`, `get_user`, 和 `delete_user`。\n",
      "   - 类的初始化方法 `__init__` 创建了一个空的用户列表 `self.users`。\n",
      "\n",
      "2. **方法分析**：\n",
      "   - `add_user(name, age, email)`：将用户信息添加到用户列表中。返回 `True` 表示操作成功。\n",
      "   - `get_user(name)`：根据用户名查找并返回用户信息。如果找不到用户，返回 `None`。\n",
      "   - `delete_user(name)`：根据用户名从用户列表中删除用户。如果删除成功，返回 `True`，否则返回 `False`。\n",
      "\n",
      "3. **辅助函数**：\n",
      "   - `calculate_average_age(users)`：计算给定用户列表的平均年龄。\n",
      "   - `send_email(email, message)`：模拟发送邮件的功能，实际只是打印一条消息。\n",
      "\n",
      "### 风格问题\n",
      "\n",
      "根据`style_check`工具的结果，代码存在以下风格问题：\n",
      "\n",
      "1. **行长度**：\n",
      "   - 第1行超过了79个字符。建议将长行拆分成多行或减少注释的长度。\n",
      "\n",
      "### 潜在Bug\n",
      "\n",
      "1. **删除用户时的索引问题**：\n",
      "   - 在 `delete_user` 方法中，删除用户后，列表的索引会发生变化。虽然当前实现可以正常工作，但为了避免潜在的索引问题，建议使用列表推导或其他更安全的方法来删除元素。\n",
      "\n",
      "### 性能优化建议\n",
      "\n",
      "1. **查找用户**：\n",
      "   - `get_user` 方法在最坏情况下需要遍历整个用户列表。如果用户数量较多，可以考虑使用字典来存储用户信息，以提高查找效率。\n",
      "\n",
      "2. **计算平均年龄**：\n",
      "   - `calculate_average_age` 方法在每次调用时都需要遍历整个用户列表。如果用户列表非常大，可以考虑缓存计算结果或使用其他数据结构来优化性能。\n",
      "\n",
      "### 最佳实践建议\n",
      "\n",
      "1. **异常处理**：\n",
      "   - 在 `add_user` 和 `delete_user` 方法中，可以添加异常处理机制，以应对可能的输入错误或意外情况。\n",
      "\n",
      "2. **日志记录**：\n",
      "   - 使用日志记录库（如 `logging`）替代 `print` 函数，以便更好地管理和调试代码。\n",
      "\n",
      "3. **单元测试**：\n",
      "   - 编写单元测试来验证每个方法的正确性，确保代码的稳定性和可靠性。\n",
      "\n",
      "4. **文档字符串**：\n",
      "   - 虽然代码已经包含了文档字符串，但可以进一步细化和扩展，特别是对于复杂的逻辑和边缘情况。\n",
      "\n",
      "### 代码改进示例\n",
      "\n",
      "以下是改进后的代码示例：\n",
      "\n",
      "```python\n",
      "\"\"\"\n",
      "示例代码：一个简单的用户管理系统\n",
      "用于演示代码审查功能\n",
      "\"\"\"\n",
      "\n",
      "import logging\n",
      "\n",
      "# 配置日志记录\n",
      "logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')\n",
      "\n",
      "class UserManager:\n",
      "    \"\"\"用户管理类\"\"\"\n",
      "    \n",
      "    def __init__(self):\n",
      "        self.users = {}\n",
      "    \n",
      "    def add_user(self, name, age, email):\n",
      "        \"\"\"添加用户\"\"\"\n",
      "        if name in self.users:\n",
      "            logging.warning(f\"用户 {name} 已经存在\")\n",
      "            return False\n",
      "        self.users[name] = {\"name\": name, \"age\": age, \"email\": email}\n",
      "        return True\n",
      "    \n",
      "    def get_user(self, name):\n",
      "        \"\"\"获取用户信息\"\"\"\n",
      "        return self.users.get(name)\n",
      "    \n",
      "    def delete_user(self, name):\n",
      "        \"\"\"删除用户\"\"\"\n",
      "        if name in self.users:\n",
      "            del self.users[name]\n",
      "            return True\n",
      "        return False\n",
      "\n",
      "def calculate_average_age(users):\n",
      "    \"\"\"计算平均年龄\"\"\"\n",
      "    if not users:\n",
      "        return 0\n",
      "    total = sum(user[\"age\"] for user in users.values())\n",
      "    return total / len(users)\n",
      "\n",
      "def send_email(email, message):\n",
      "    \"\"\"发送邮件（模拟）\"\"\"\n",
      "    logging.info(f\"发送邮件到 {email}: {message}\")\n",
      "    return True\n",
      "\n",
      "# 示例用法\n",
      "if __name__ == \"__main__\":\n",
      "    user_manager = UserManager()\n",
      "    user_manager.add_user(\"Alice\", 30, \"alice@example.com\")\n",
      "    user_manager.add_user(\"Bob\", 25, \"bob@example.com\")\n",
      "    print(user_manager.get_user(\"Alice\"))\n",
      "    user_manager.delete_user(\"Alice\")\n",
      "    print(user_manager.get_user(\"Alice\"))\n",
      "    average_age = calculate_average_age(user_manager.users)\n",
      "    print(f\"平均年龄: {average_age}\")\n",
      "    send_email(\"admin@example.com\", \"用户管理系统的平均年龄已更新\")\n",
      "```\n",
      "\n",
      "### 总结\n",
      "\n",
      "通过这次代码审查，我们发现了几个风格问题和潜在的性能优化点。改进后的代码更加健壮、高效，并且易于维护。希望这些建议对您有所帮助。\n"
     ]
    }
   ],
   "source": [
    "# 执行代码审查\n",
    "print(\"=== 开始代码审查 ===\")\n",
    "review_result = agent.run(f\"请审查以下Python代码：\\n\\n```python\\n{sample_code}\\n```\")\n",
    "\n",
    "print(review_result)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第6部分：保存审查报告"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "✅ 审查报告已保存到 outputs/review_report.md\n"
     ]
    }
   ],
   "source": [
    "# 保存审查报告\n",
    "with open(\"outputs/review_report.md\", \"w\", encoding=\"utf-8\") as f:\n",
    "    f.write(review_result)\n",
    "\n",
    "print(\"\\n✅ 审查报告已保存到 outputs/review_report.md\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 第7部分：总结与展望\n",
    "\n",
    "### 实现的功能\n",
    "- ✅ 代码结构分析\n",
    "- ✅ PEP 8风格检查\n",
    "- ✅ 智能审查报告生成\n",
    "\n",
    "### 遇到的挑战\n",
    "- 如何准确解析Python代码结构\n",
    "- 如何设计合理的提示词让LLM生成高质量报告\n",
    "\n",
    "### 未来改进方向\n",
    "- 支持更多编程语言\n",
    "- 添加安全漏洞检测\n",
    "- 集成更多静态分析工具\n",
    "- 支持批量文件审查"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}