Repository navigation
feat(mcp): search_attributes full tool and subagent evals - #2244
Open
nikkikapadia wants to merge 3 commits into
Open
nikkikapadia wants to merge 3 commits into
nikkikapadia wants to merge 3 commits into
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub. 1 Skipped Deployment
|
nikkikapadia
had a problem deploying
to
Actions
November 13, 2026 17:02 — with 
GitHub Actions
Failure
Contributor
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 6ce2ce6. Configure here.
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes EXP-1352
This PR adds a bunch of evals for the new
search_attributestool. There's a file for entire tool evals and then another file to test the subagent behaviour.In the full tool eval we test multiple cases like what the tool will do if there's no query, query that results in no results, choosing between two close attributes, choosing between attributes with no descriptions, testing if it hits specific tools, etc.
In the subagent evals we test the outputs of the hint and the attribute shortlist agents. So whether it gets the hint key words we expect and whether it ranks attributes properly (based on factors such as deprecation).
The rest of the file changes are adjustments to existing tests/logic, adding mocks or exporting all of the tools so we can test them.