Confirmation Required with Toolkit

This example demonstrates human-in-the-loop functionality using toolkit-based tools that require confirmation. It shows how to handle user confirmation when working with pre-built tool collections like DuckDuckGoTools.

1. Create a Python file

   Create a Python file and add the above code.

   touch confirmation_required_toolkit.py
   

2. Add the following code to your Python file

   confirmation_required_toolkit.py

   from agno.agent import Agent
   from agno.models.openai import OpenAIChat
   from agno.tools import tool
   from agno.tools.duckduckgo import DuckDuckGoTools
   from agno.utils import pprint
   from rich.console import Console
   from rich.prompt import Prompt
   
   console = Console()
   
   agent = Agent(
       model=OpenAIChat(id="gpt-5-mini"),
       tools=[DuckDuckGoTools(requires_confirmation_tools=["get_current_stock_price"])],
       markdown=True,
   )
   
   run_response = agent.run("What is the current stock price of Apple?")
   if run_response.is_paused:  # Or agent.run_response.is_paused
       for tool in run_response.tools_requiring_confirmation:  # type: ignore
           # 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
   
       run_response = agent.continue_run(run_response=run_response)
       pprint.pprint_run_response(run_response)
   

3. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   

4. Install libraries

   pip install -U agno openai ddgs rich
   

5. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   

6. Run Agent

   Mac

   python confirmation_required_toolkit.py
   

7. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub