test(fixtures): expand rewrite-quality corpus to 10 KO + 10 EN (enable A/B measurement)#501
Merged
Merged
Conversation
The live-quality corpus had only 1 fixture per language, too small to measure rewrite-pipeline A/B (single vs ouroboros) meaningfully. Adds 10 KO + 10 EN synthetic, redistributable (repo-ok) AI-sounding fixtures across registers (blog, academic-summary, product-doc, chat-update, technical-how-to, marketing, news, email, instructional, social), each with meaning anchors (numbers/entities that must survive a rewrite) for MPS/fidelity grading. No version bump: test data only, no schema/behavior change. Enables `npm run quality:rewrite-ab` and `quality:live` to run at n>=10 per language.
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Expands the rewrite-quality (live) fixture corpus from 1 → 11 fixtures per language so the
quality:rewrite-abandquality:liveharnesses can measure rewrite-pipeline A/B (single vs ouroboros) at a meaningful sample size. No version bump — test data only, no schema/behavior change.Adds 10 KO + 10 EN synthetic, redistributable (
repo-ok) AI-sounding fixtures across registers: blog, academic-summary, product-doc, chat-update, technical-how-to, marketing, news, email, instructional, social. Each carries meaning anchors (numbers/entities that must survive a rewrite) for MPS/fidelity grading.Why
The earlier measurement attempt found the real blocker:
tests/fixtures/live-quality/ko/had only 1 fixture, so single-vs-ouroboros (and the multi-agent--strictquestion) couldn't be measured (n=1). This unblocks the measurement phase.Verification
npm test— 797 pass / 0 fail (live-quality fixture-shape test green)npm run release:check— OK for 5.4.0 (unchanged)npm run check:no-private-assets— OK (332 packed; all fixturesrepo-ok)Next phase: run
quality:rewrite-ab --configs single,ouroborosacross the corpus with a backend, then decide keep/cut the multi-agent surface from data.