Fix verifiers-rl API compatibility for v0.1.8+ #109
Merged
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
The verifiers package underwent breaking API changes in v0.1.8: - GenerateOutputs changed from a class to TypedDict, requiring bracket notation - rollout() now takes RolloutInput dict instead of individual parameters - score_rollout() signature changed to (state, score_sem) only Changes: - evaluate.py: Use bracket notation for GenerateOutputs fields - train.py: Update rollout() to use RolloutInput dict structure - train.py: Update score_rollout() to new signature with score_sem - train.py: Extract reward/metrics from state after scoring 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
Collaborator
Author
|
I wasn't able to test that it actually works due to other installation issues |
Collaborator
Author
|
OK I was able to get it running on reverse-text. I'm going to merge for now because this is breaking our CI, and if there are still issues, we can fix them based on @willccbb's input. |
jshanson7
approved these changes
Nov 23, 2025
Contributor
|
ah sorry yes feel free to merge! had started on a patch but got pulled away--will test tomorrow and put up any other changes needed |
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Outdated suggestions cannot be applied.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.
The verifiers package underwent breaking API changes in v0.1.8:
Changes:
🤖 Generated with Claude Code