test(sdk): add evals for llm judge, tool selection, followup quality, and multi-turn memory#1838
Open
Mason Daugherty (mdrxy) wants to merge 7 commits intomainfrom
Open
test(sdk): add evals for llm judge, tool selection, followup quality, and multi-turn memory#1838Mason Daugherty (mdrxy) wants to merge 7 commits intomainfrom
Mason Daugherty (mdrxy) wants to merge 7 commits intomainfrom
Conversation
github-actions
bot
added
deepagents
Collaborator
Eugene Yurtsev (eyurtsev)
left a comment
Eugene Yurtsev (eyurtsev)
left a comment
There was a problem hiding this comment.
very nice! do you think you could run the evals against this branch to just get a sense of what it looks like?
Mason Daugherty (mdrxy)
changed the title
This comment was marked as outdated.
This comment was marked as outdated.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Port from Agent Builder: LLM-as-judge assertion (
LLMJudge) and three new eval suites — tool selection, followup question quality, and multi-turn memory behavior.The judge assertion fills a gap where substring matching can't evaluate semantic correctness, using a second LLM to grade agent responses against human-readable criteria with per-criterion pass/fail granularity.