Package ai.acolite.agentsdk.core

Interface ToolOutputGuardrail<TContext>

All Superinterfaces:

ToolGuardrailBase

public interface ToolOutputGuardrail<TContext>
extends ToolGuardrailBase

ToolOutputGuardrail

Validates tool output after tool execution.

Tool guardrails execute sequentially (not in parallel) and can: - Allow the tool output to be used (ALLOW) - Reject and replace output with alternative content (REJECT_CONTENT) - Throw an exception to halt execution (THROW_EXCEPTION)

Use tool output guardrails to: - Filter sensitive information from tool results - Validate tool output format - Transform or sanitize tool responses - Log/audit tool outputs

Ported from TypeScript OpenAI Agents SDK Source: toolGuardrail.ts

Method Summary

Modifier and Type	Method	Description
CompletableFuture<ToolGuardrailFunctionOutput>	execute(ToolOutputGuardrailFunctionArgs<TContext> args)	Execute the guardrail validation on tool output.
String	getName()	Unique name for this guardrail.

Method Details

getName

String getName()

Unique name for this guardrail.

Returns:

The guardrail name

execute

CompletableFuture<ToolGuardrailFunctionOutput> execute(ToolOutputGuardrailFunctionArgs<TContext> args)

Execute the guardrail validation on tool output.

Parameters:

args - The tool output arguments

Returns:

A CompletableFuture with the guardrail result