code_explain

Instructions

Implementation Reference

• src/onion_mcp_server/tools/code.py:106-176 (handler)

  The handler function handle_code dispatches tool requests by name. For 'code_explain' (lines 109-117), it builds a prompt using detail level (brief/normal/detailed), language, and the user's code, then calls llm_call to get an explanation, and returns the result as TextContent.

  async def handle_code(name: str, arguments: dict) -> list[types.TextContent]:
      a = arguments
  
      if name == "code_explain":
          detail_map = {"brief": "用一两句话简短", "detailed": "非常详细地", "normal": ""}
          detail_str = detail_map.get(a.get("detail", "normal"), "")
          lang       = a.get("language", "") or "（自动检测）"
          prompt = (
              f"请{detail_str}解释以下 {lang} 代码的功能和逻辑，"
              f"包括：整体作用、关键步骤、重要变量/函数的含义。\n\n"
              f"```\n{a['code']}\n```"
          )
  
      elif name == "code_review":
          focus     = a.get("focus", ["all"])
          focus_str = "所有方面（Bug、安全、性能、代码风格）" if "all" in focus else "、".join(focus)
          lang      = a.get("language", "") or ""
          prompt = (
              f"请对以下 {lang} 代码进行代码审查，重点关注：{focus_str}。\n"
              f"请按以下格式输出：\n"
              f"1. 问题列表（严重程度 + 描述 + 修复建议）\n"
              f"2. 整体评分（1-10）\n"
              f"3. 改进后的代码（如有必要）\n\n"
              f"```\n{a['code']}\n```"
          )
  
      elif name == "code_generate":
          style_map = {
              "simple":     "简洁易读",
              "production": "生产级别（含完整错误处理、日志、类型注解）",
          }
          style_str = style_map.get(a.get("style", "simple"), "简洁易读")
          lang      = a.get("language", "Python")
          prompt = (
              f"请用 {lang} 编写以下功能的代码，风格要求：{style_str}。\n"
              f"只输出代码和必要的注释，不需要额外解释。\n\n"
              f"需求：{a['description']}"
          )
  
      elif name == "code_convert":
          prompt = (
              f"请将以下 {a['from_language']} 代码转换为 {a['to_language']}。\n"
              f"要求：保持逻辑完全一致，使用目标语言的惯用写法，只输出转换后的代码。\n\n"
              f"```{a['from_language'].lower()}\n{a['code']}\n```"
          )
  
      elif name == "code_fix":
          err_part = f"\n\n错误信息：\n```\n{a['error_message']}\n```" if a.get("error_message") else ""
          lang     = a.get("language", "") or ""
          prompt = (
              f"请修复以下 {lang} 代码中的错误。\n"
              f"要求：输出修复后的完整代码，并在代码前简要说明修复了什么问题。\n\n"
              f"```\n{a['code']}\n```{err_part}"
          )
  
      elif name == "code_docstring":
          style    = a.get("style", "google")
          language = a.get("language", "Python")
          prompt = (
              f"请为以下 {language} 代码生成 {style} 风格的文档注释（docstring）。\n"
              f"要求：为每个函数/类/方法添加完整的参数说明、返回值说明、异常说明（如有）。\n"
              f"只输出添加了文档注释的完整代码。\n\n"
              f"```\n{a['code']}\n```"
          )
  
      else:
          raise ValueError(f"未知 code 工具: {name}")
  
      reply = await llm_call(prompt)
      return [types.TextContent(type="text", text=reply)]

• src/onion_mcp_server/tools/code.py:8-25 (schema)

  The tool definition (input schema) for 'code_explain'. Declares name='code_explain', description='解释代码的功能和逻辑，支持所有主流编程语言。', and inputSchema with properties: code (required string), language (optional string), detail (optional enum: brief/normal/detailed).

  CODE_TOOLS: list[types.Tool] = [
      types.Tool(
          name="code_explain",
          description="解释代码的功能和逻辑，支持所有主流编程语言。",
          inputSchema={
              "type": "object",
              "properties": {
                  "code":     {"type": "string", "description": "要解释的代码"},
                  "language": {"type": "string", "description": "编程语言（可选，自动检测）", "default": ""},
                  "detail":   {
                      "type": "string",
                      "enum": ["brief", "normal", "detailed"],
                      "default": "normal",
                  },
              },
              "required": ["code"],
          },
      ),

• src/onion_mcp_server/server.py:52-53 (registration)

  Registration of the 'code_explain' tool: the _HANDLERS dict maps the tool's name to the handle_code handler function, so when a call_tool request comes in with name='code_explain', it dispatches to handle_code.

  for _t in CODE_TOOLS:   
      _HANDLERS[_t.name] = handle_code

• src/onion_mcp_server/server.py:39-46 (registration)

  ALL_TOOLS aggregates all tool definitions (including CODE_TOOLS) and is returned by the list_tools handler, making 'code_explain' discoverable by clients.

  ALL_TOOLS: list[types.Tool] = [
      *AI_TOOLS,
      *CODE_TOOLS,
      *TEXT_TOOLS,
      *DATA_TOOLS,
      *WEB_TOOLS,
      *SYSTEM_TOOLS,
  ]

• src/onion_mcp_server/tools/_llm.py:78-88 (helper)

  The llm_call helper function is called by handle_code to send the constructed prompt to an LLM (OpenAI-compatible API) and return the generated explanation text.

  async def llm_call(
      prompt: str,
      system: Optional[str] = None,
      temperature: float = 0.7,
  ) -> str:
      """单轮调用"""
      messages = []
      if system:
          messages.append({"role": "system", "content": system})
      messages.append({"role": "user", "content": prompt})
      return await llm_chat(messages, temperature=temperature)