Keep harness metrics merge inside experimental composable env#1201
Merged
Keep harness metrics merge inside experimental composable env#1201
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Previous PR touched core verifiers logic (in non-harmful ways, but still); this undoes those changes and solves the problem they were meant to address fully inside experimental
Type of Change
Testing
uv run pytestlocally.Checklist
Additional Notes
Note
Medium Risk
Changes how rewards are aggregated in
RubricGroupby no longer coercingNonerewards to0.0, which could surface type errors if any rubric returnsNone. The new harness-metrics merge runs during rubric cleanup in the experimental env and should be low impact outside that path.Overview
Moves harness metrics merging fully into the experimental
ComposableEnvby replacing the standaloneHarnessMetricsRubric(and its@cleanupdecorator) with aHarnessMetricsRubricGroupthat runs child rubric cleanup then folds_harness_metricsintostate["metrics"].When
harness.metrics_pathis set,ComposableEnvnow wraps the existing rubric (or existingRubricGroup) inside this new group so metrics are merged without touching core scoring flow.Separately,
RubricGroupno longer normalizesNonerewards to0.0duringscore_rollout/score_group, relying on rubrics to always set numeric rewards.Reviewed by Cursor Bugbot for commit 1ae31b4. Bugbot is set up for automated code reviews on this repo. Configure here.