output_guardrail.py
Run the Example
1
Set up your virtual environment
2
Install dependencies
3
Export your OpenAI API key
4
Run the example
Save the code above as
output_guardrail.py, then run:Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Reject responses under 20 characters with a post-hook that raises OutputCheckError.
"""
Output Guardrail
=============================
Output Guardrail.
"""
from agno.agent import Agent
from agno.exceptions import CheckTrigger, OutputCheckError
from agno.models.openai import OpenAIResponses
from agno.run.agent import RunOutput
def enforce_non_empty_output(run_output: RunOutput) -> None:
"""Reject empty or very short responses."""
content = (run_output.content or "").strip()
if len(content) < 20:
raise OutputCheckError(
"Output is too short to be useful.",
check_trigger=CheckTrigger.OUTPUT_NOT_ALLOWED,
)
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
name="Output-Checked Agent",
model=OpenAIResponses(id="gpt-5.2"),
post_hooks=[enforce_non_empty_output],
)
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
agent.print_response("Summarize the key ideas in clean architecture.", stream=True)
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
Install dependencies
uv pip install -U agno openai
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
Run the example
output_guardrail.py, then run:python output_guardrail.py
Was this page helpful?