Repository navigation
feat: customize output guardrail blocked messages - #4594
Merged
Merged
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request adds configurable, data-free placeholder messages for terminal tool output rejected by an output guardrail.
RunConfig.output_guardrail_blocked_messageaccepts either a non-empty fixed string or a synchronous formatter receiving the default message, guardrail name, current agent, and run context. This allows applications to localize or otherwise adjust the retained message based on context.The selected placeholder is applied consistently to the caller-visible tripwire, Session history, serialized
RunState, streamed results, tool-output guardrail metadata, and subsequent model replay. Formatter failures and invalid return values fail closed to the existing SDK default, and rejected output or guardrailoutput_infois never passed to the formatter.Async formatters are intentionally rejected. Awaiting application code between the terminal tripwire and retained-owner redaction can leave rejected output reachable through cancellation traceback locals or partially sanitized state, so async support requires a redesign of that redaction boundary rather than simply awaiting the formatter result.