Repository navigation
fix(sleep): retain gate trials in per-skill reports - #334
Open
Langning Zhang (Boulea7) wants to merge 1 commit into
Open
Langning Zhang (Boulea7) wants to merge 1 commit into
Langning Zhang (Boulea7) wants to merge 1 commit into
Conversation
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Multi-skill fanout evaluates each skill against its own held-out tasks, but the group report drops those gate trials. Keep the existing trials on each group row and show the task changes in Markdown and diagnostics, including why a regression blocks one group while another passes.
The new nested report data uses the existing secret redaction and strict JSON handling. JSON and CLI output retain each group’s own trials in order.
Validation:
run_sleep_cycleregression: fails on currentmainafter both groups consolidate, then passes with this change. It also checks group isolation, call counts, switches, failed/skipped groups, redaction, Markdown controls and non-finite values.python -m pytest -q: 1993 passed, 24 skipped, 4 xfailed; 383 subtests passed.git diff --checkpasses. Ruff reports the existingI001incycle.pyimports, with identical output on the unmodified base.