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

# Confirmation Required with Mixed Tools

This example demonstrates human-in-the-loop functionality where only some tools require user confirmation. The agent executes tools that don't require confirmation automatically and pauses only for tools that need approval.

## Code

```python confirmation_required_mixed_tools.py theme={null}
"""🤝 Human-in-the-Loop: Adding User Confirmation to Tool Calls

This example shows how to implement human-in-the-loop functionality in your Agno tools.

In this case we have multiple tools and only one of them requires confirmation.

The agent should execute the tool that doesn't require confirmation and then pause for user confirmation.

The user can then either approve or reject the tool call and the agent should continue from where it left off.
"""

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()


def get_top_hackernews_stories(num_stories: int) -> str:
    """Fetch top stories from Hacker News.

    Args:
        num_stories (int): Number of stories to retrieve

    Returns:
        str: JSON string containing story details
    """
    # Fetch top story IDs
    response = httpx.get("https://hacker-news.firebaseio.com/v0/topstories.json")
    story_ids = response.json()

    # Yield story details
    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)


@tool(requires_confirmation=True)
def send_email(to: str, subject: str, body: str) -> str:
    """Send an email.

    Args:
        to (str): Email address to send to
        subject (str): Subject of the email
        body (str): Body of the email
    """
    return f"Email sent to {to} with subject {subject} and body {body}"


agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[get_top_hackernews_stories, send_email],
    markdown=True,
)

run_response = agent.run(
    "Fetch the top 2 hackernews stories and email them to john@doe.com."
)
if run_response.is_paused:
    for tool in run_response.tools:  # type: ignore
        if tool.requires_confirmation:
            # Ask for confirmation
            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:
                # We update the tools in place
                tool.confirmed = True
        else:
            console.print(
                f"Tool name [bold blue]{tool.tool_name}({tool.tool_args})[/] was completed in [bold green]{tool.metrics.duration:.2f}[/] seconds."  # type: ignore
            )

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

# Or for simple debug flow
# agent.print_response("Fetch the top 2 hackernews stories")
```

## Usage

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

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

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
        export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Create a Python file">
    Create a Python file and add the above code.

    ```bash theme={null}
    touch confirmation_required_mixed_tools.py
    ```
  </Step>

  <Step title="Run Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python confirmation_required_mixed_tools.py
      ```

      ```bash Windows   theme={null}
      python confirmation_required_mixed_tools.py
      ```
    </CodeGroup>
  </Step>

  <Step title="Find All Cookbooks">
    Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

    <Link href="https://github.com/agno-agi/agno/tree/main/cookbook/agents/human_in_the_loop" target="_blank">
      Agno Cookbooks on GitHub
    </Link>
  </Step>
</Steps>