Docs: Fix Guardrail definition to include both input and output validations #756
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…rrect Output guardrail first step. Enhanced the documentation for input and output guardrails by specifying that input guardrails apply only to the first agent in a sequence, while output guardrails apply only to the last agent. This clarification improves understanding of how guardrails function in agent chains.
Updated the documentation for output guardrails to specify that the guardrail receives the output produced by the agent, enhancing clarity in the guardrail process.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
This PR updates the description of Guardrails in the OpenAI Agents SDK documentation to reflect that they apply to both input and output validations.
Original Text:
Proposed Update:
Why this change is necessary:
The original statement is incomplete and potentially misleading, as it only mentions input validations. However, the [Agents SDK Guardrail Documentation] defines two distinct types of guardrails:
InputGuardrail: Validates user input before it reaches the agent.OutputGuardrail: Validates the agent’s final output before it is returned to the user.Both types of guardrails are critical for ensuring the safety and reliability of agent behavior. Additionally, both can trigger a
Tripwire(e.g.,InputGuardrailTripwireTriggered,OutputGuardrailTripwireTriggered) to halt execution when a validation fails—hence, the phrase “breaking early” applies to both.Impact:
This correction improves clarity and accuracy, helping developers better understand the full lifecycle of guardrail checks in the SDK.