docs: add tool guardrails documentation #2218
Open
+139
−1
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
Add comprehensive documentation for tool input and output guardrails: - Explain difference between tool and agent-level guardrails - Document @tool_input_guardrail decorator with examples - Document @tool_output_guardrail decorator with examples - Add behavior types table (allow, reject_content, raise_exception) - Include exception handling examples Closes openai#1830
seratch
reviewed
Dec 23, 2025
Member
seratch
left a comment
seratch
left a comment
There was a problem hiding this comment.
Thanks for sending this improvement! The changes look good to me, but as mentioned in my comments, I'd like to make the dev experience more intuitive before publishing these document sections. I will update you once the feature enhancement is available.
|
|
||
|
|
||
| # Attach the guardrail to the tool | ||
| send_email.tool_input_guardrails = [validate_email_args] |
Member
There was a problem hiding this comment.
Indeed, this is the only way to pass tool guardrails but thinking of better developer experience, enabling to pass the same to the decorator would be better. I will come up with a pull request enhancing this.
|
|
||
|
|
||
| # Attach the guardrail to the tool | ||
| get_user_data.tool_output_guardrails = [block_sensitive_data] |
seratch
added a commit
that referenced
this pull request
Dec 23, 2025
Contributor
|
This PR is stale because it has been open for 10 days with no activity. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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
Add comprehensive documentation for tool input and output guardrails to
docs/guardrails.md. This addresses the gap identified in #1830 where tool guardrails (implemented in PR #1792) were not documented in the main guides.The new documentation explains:
@tool_input_guardrailand@tool_output_guardraildecoratorsallow,reject_content, andraise_exceptionTest plan
uv run mkdocs buildIssue number
Closes #1830
Checks
make lintandmake format