Reasoning Agent Events Handling

This example demonstrates how to handle and monitor reasoning events when using an agent with reasoning capabilities, including reasoning steps and content generation.

Code

reasoning_agent_events.py

import asyncio

from agno.agent import RunEvent
from agno.agent.agent import Agent
from agno.models.openai import OpenAIChat

finance_agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    reasoning=True,
)


async def run_agent_with_events(prompt: str):
    content_started = False
    async for run_output_event in finance_agent.arun(
        prompt,
        stream=True,
        stream_events=True,
    ):
        if run_output_event.event in [RunEvent.run_started, RunEvent.run_completed]:
            print(f"\nEVENT: {run_output_event.event}")

        if run_output_event.event in [RunEvent.reasoning_started]:
            print(f"\nEVENT: {run_output_event.event}")

        if run_output_event.event in [RunEvent.reasoning_step]:
            print(f"\nEVENT: {run_output_event.event}")
            print(f"REASONING CONTENT: {run_output_event.reasoning_content}")  # type: ignore

        if run_output_event.event in [RunEvent.reasoning_completed]:
            print(f"\nEVENT: {run_output_event.event}")

        if run_output_event.event in [RunEvent.run_content]:
            if not content_started:
                print("\nCONTENT:")
                content_started = True
            else:
                print(run_output_event.content, end="")


if __name__ == "__main__":
    task = (
        "Analyze the key factors that led to the signing of the Treaty of Versailles in 1919. "
        "Discuss the political, economic, and social impacts of the treaty on Germany and how it "
        "contributed to the onset of World War II. Provide a nuanced assessment that includes "
        "multiple historical perspectives."
    )
    asyncio.run(
        run_agent_with_events(
            task,
        )
    )

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install libraries

   pip install -U agno openai
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch reasoning_agent_events.py
   
5. Run Agent

   Mac

   python reasoning_agent_events.py
   
6. 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