launch-kit evals: frozen scenarios with a deterministic count, S6 and S7, the 2026-09-02 run - #16
Merged
Merged
Conversation
…re screenshots, S7 the poster's shot; the 2026-09-02 run
hblee12294
marked this pull request as ready for review
September 2, 2026 15:22
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The scenarios are declared frozen so runs compare, and every run now records one deterministic number beside the judged pass/fail: the problems
vos validate <kit>/kit.jsonreports across the run's kits (plugin ≥0.20.0 reads each asset's bytes against the channel specs). Two scenarios join from two real runs (Harper v2.9, Karakeep v0.33): S6, store screenshots are the real page, full bleed, no zoom, no chrome; S7, the poster's shot is a named zoom apex, never the cold open, and every card is a real PNG. The 2026-09-02 results file scores both runs and records the two findings that became plugin fixes.