> ## Documentation Index
> Fetch the complete documentation index at: https://ikun.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 用户确认要求

> 此示例演示了如何在执行工具调用前要求用户确认，以实现人为干预（human-in-the-loop）功能。

## 代码

```python cookbook/agent_concepts/user_control_flows/confirmation_required.py theme={null}
import json

import httpx
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools import tool
from agno.utils import pprint
from rich.console import Console
from rich.prompt import Prompt

console = Console()

@tool(requires_confirmation=True)
def get_top_hackernews_stories(num_stories: int) -> str:
    """获取 Hacker News 的热门故事。

    Args:
        num_stories (int): 要检索的故事数量

    Returns:
        str: 包含故事详情的 JSON 字符串
    """
    # 获取热门故事 IDs
    response = httpx.get("https://hacker-news.firebaseio.com/v0/topstories.json")
    story_ids = response.json()

    # yield 故事详情
    all_stories = []
    for story_id in story_ids[:num_stories]:
        story_response = httpx.get(
            f"https://hacker-news.firebaseio.com/v0/item/{story_id}.json"
        )
        story = story_response.json()
        if "text" in story:
            story.pop("text", None)
        all_stories.append(story)
    return json.dumps(all_stories)

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[get_top_hackernews_stories],
    markdown=True,
)

agent.run("Fetch the top 2 hackernews stories.")
if agent.is_paused:
    for tool in agent.run_response.tools_requiring_confirmation:
        # 请求确认
        console.print(
            f"Tool name [bold blue]{tool.tool_name}({tool.tool_args})[/] requires confirmation."
        )
        message = (
            Prompt.ask("Do you want to continue?", choices=["y", "n"], default="y")
            .strip()
            .lower()
        )

        if message == "n":
            tool.confirmed = False
        else:
            tool.confirmed = True

run_response = agent.continue_run()
pprint.pprint_run_response(run_response)
```

## 用法

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="设置您的 API 密钥">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

  <Step title="安装库">
    ```bash theme={null}
    pip install -U agno httpx rich openai
    ```
  </Step>

  <Step title="运行示例">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/agent_concepts/user_control_flows/confirmation_required.py
      ```

      ```bash Windows theme={null}
      python cookbook/agent_concepts/user_control_flows/confirmation_required.py
      ```
    </CodeGroup>
  </Step>
</Steps>

## 主要特点

* 使用 `@tool(requires_confirmation=True)` 标记需要用户确认的工具
* 演示了如何在用户输入后继续代理执行

## 用途

* 在执行敏感操作前进行确认