Conversation
charlesmeng18
approved these changes
Dec 7, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Notion ticket: https://www.notion.so/cleanlab/Mutative-tool-fallback-responses-2c0c7fee85be80b19645df046150bc08?source=copy_link
This PR re-introduces mutative tools by fixing the issue of guardrailed responses after mutative tools => user doesn't know that mutative action was done.
Example of issue:

Fix is to have the develop provide a template fallback for each mutative tool. If final response is guardrailed, collate the fallbacks for each tool into one response e.g.
TODO: Codex backend needs to be updated to take the developer's fallback response and show that instead of the Cleanlab fallback to maintain visibility. That will be fixed by this ticket: https://www.notion.so/cleanlab/Mutative-tool-fallback-responses-2c0c7fee85be80b19645df046150bc08?source=copy_link