chore: persona-smoke fence-stripping + baseline refresh (ILO-534) - #787
Merged
Conversation
Every fenced generation died at ILO-L001 on the backtick, which is how the whole smoke set read failed once the API key was restored. Port _strip_fences from closed-loop-bench.py. Baseline re-recorded on post-#785/#786 main. Still weak - the -- out: regex only captures one line so multi-line expectations can never match, and Haiku is nondeterministic across attempts - but it reflects what main actually does today. Gate redesign tracked in ILO-534.
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
First half of ILO-534. The API key is restored (repo secret reset earlier today); this fixes the next failure down: model output wrapped in markdown fences died at ILO-L001 on the backtick before anything ran, so all personas read failed.
Ports _strip_fences from closed-loop-bench.py and re-records the baseline against current main (post #785/#786).
Known remaining weaknesses, deliberately out of scope here and tracked in ILO-534: the -- out: regex captures a single line so multi-line expected outputs can never classify working, and generation nondeterminism makes exact-output baselines rot. Gate is honest now, not yet strong.