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

# Reasoning Agent

> Expose an o4-mini reasoning agent with web search over the A2A protocol.

```python reasoning_agent.py theme={null}
"""
Reasoning Agent
===============

Demonstrates reasoning agent.
"""

from agno.agent.agent import Agent
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

reasoning_agent = Agent(
    name="reasoning-agent",
    id="reasoning_agent",
    model=OpenAIChat(id="o4-mini"),
    description="An advanced AI assistant with deep reasoning and analytical capabilities, enhanced with real-time web search to deliver thorough, well-thought-out responses with contextual awareness",
    instructions="You are a helpful AI assistant with reasoning capabilities.",
    add_datetime_to_context=True,
    add_history_to_context=True,
    add_location_to_context=True,
    timezone_identifier="Etc/UTC",
    markdown=True,
    tools=[WebSearchTools()],
)

# Setup your AgentOS app
agent_os = AgentOS(
    agents=[reasoning_agent],
    a2a_interface=True,
)
app = agent_os.get_app()


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    """Run your AgentOS with A2A interface.
    You can run the Agent via A2A protocol:
    POST http://localhost:7777/agents/{id}/v1/message:send
    For streaming responses:
    POST http://localhost:7777/agents/{id}/v1/message:stream
    Retrieve the agent card at:
    GET  http://localhost:7777/agents/{id}/.well-known/agent-card.json
    """
    agent_os.serve(app="reasoning_agent:app", reload=True, port=7777)
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[a2a,os]" ddgs openai requests
    ```
  </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="Run the example">
    Save the code above as `reasoning_agent.py`, then run:

    ```bash theme={null}
    python reasoning_agent.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/interfaces/a2a/reasoning\_agent.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/interfaces/a2a/reasoning_agent.py)