feat(luce-bench): multi-turn agent_recorded redesign + LLM-judge grading#333
Closed
easel wants to merge 1 commit into
Closed
feat(luce-bench): multi-turn agent_recorded redesign + LLM-judge grading#333easel wants to merge 1 commit into
easel wants to merge 1 commit into
Conversation
Replaces the single-shot recorded harness with a multi-turn replay, adds the grading/ subpackage with the llm_judge, multi_turn_cases fixture, agent_recorded test + extract-agentic-fixture test, and touches normalize/regrade/cli to support new turn-level metrics. Also carries the two qwen3.6 and two gemma4 coding-agent-loop sweep writeups that consume this area. Depends on: lucebench-harness (edits files introduced there). Part of the PR Luce-Org#285 split (Luce-Org#285) into tightly-scoped PRs. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
Collaborator
Author
|
Merged into PR #337 (lucebench-harness branch) via cherry-pick 🤖 Generated with Claude Code |
4 tasks
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Multi-turn
agent_recordedarea: replaces the single-shot recorded harness with a multi-turn replay, adds thegrading/subpackage with thellm_judge,multi_turn_casesfixture,agent_recordedtest + extract-agentic-fixture test, and touches normalize/regrade/cli to support new turn-level metrics. Carries the two qwen3.6 and two gemma4 coding-agent-loop sweep writeups that consume this area.Part of the PR #285 split
This PR is part of splitting the omnibus PR #285 into tightly-scoped reviewable PRs.
Dependencies
lucebench-harness— this PR edits files introduced there and must land first.Risk
medium