Background Mode

Run GPT-5.4 in background mode with automatic polling and a 600-second default maximum wait.

Background mode submits a Responses request and polls automatically for completion. Agno stops after background_max_wait, which defaults to 600 seconds.

The source docstring overstates background-mode resilience. Polling requires connectivity, stops after background_max_wait, and surfaces polling failures.

background.py

"""
Background Mode
===============

Background mode enables long-running tasks on reasoning models like GPT-5.4
without worrying about timeouts or connectivity issues. The API returns
immediately and Agno polls for the result automatically.

Requires: openai>=2.0.0
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create Agent with background mode enabled
# ---------------------------------------------------------------------------

agent = Agent(
    model=OpenAIResponses(
        id="gpt-5.4",
        background=True,
        background_poll_interval=2.0,  # seconds between polls (default)
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("Explain the history of quantum computing in detail")

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Install dependencies

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

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

   Save the code above as background.py, then run:

   python background.py
   

Full source: cookbook/90_models/openai/responses/background.py