Ensure that input_guardrails can block tools from running

[rm-openai]

Resolves #889

[github-actions]

This PR is stale because it has been open for 10 days with no activity.

[github-actions]

This PR was closed because it has been inactive for 7 days since being marked as stale.

[seratch]

@rm-openai do you think this approach is still good to go? If not, we may want to think of a solution for #889 and #991

[github-actions]

This PR is stale because it has been open for 10 days with no activity.

[lionelchg]

Hi @seratch, just checked out on the PR and tried the following script (a shorter version of the quickstart script) - it still does not block the call.

• this is the script:

from agents import Agent, InputGuardrail, GuardrailFunctionOutput, Runner
from agents.exceptions import InputGuardrailTripwireTriggered
from pydantic import BaseModel
import asyncio

class HomeworkOutput(BaseModel):
    is_homework: bool
    reasoning: str

guardrail_agent = Agent(
    name="Guardrail check",
    instructions="Check if the user is asking about homework.",
    output_type=HomeworkOutput,
)

math_tutor_agent = Agent(
    name="Math Tutor",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your reasoning at each step and include examples",
)

async def homework_guardrail(ctx, agent, input_data):
    result = await Runner.run(guardrail_agent, input_data, context=ctx.context)
    final_output = result.final_output_as(HomeworkOutput)
    return GuardrailFunctionOutput(
        output_info=final_output,
        tripwire_triggered=not final_output.is_homework,
    )

triage_agent = Agent(
    name="Triage Agent",
    instructions="You determine which agent to use based on the user's homework question",
    handoffs=[math_tutor_agent],
    input_guardrails=[
        InputGuardrail(guardrail_function=homework_guardrail),
    ],
)

async def main():
    # Example: General/philosophical question
    try:
        result = await Runner.run(triage_agent, "What is the meaning of life?")
        print(result.final_output)
    except InputGuardrailTripwireTriggered as e:
        print("Guardrail blocked this input:", e)

if __name__ == "__main__":
    asyncio.run(main())

• this is my screenshot of the logs (you can see that the second call passes even though is_homework is False):

I might try a fix this week-end will keep you posted!

[github-actions]

This PR is stale because it has been open for 10 days with no activity.

[github-actions]

This PR was closed because it has been inactive for 7 days since being marked as stale.

[illia-botscrew]

@rm-openai do you plan to finish this support of blocking tools from running when input_guardrail is processing the input?

This PR and the other PR that was trying to add support for this: #1622 are closed.