feat: rank exact definition sites and release v0.7.0#64
Merged
Conversation
aryamthecodebreaker
marked this pull request as ready for review
July 22, 2026 11:06
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Why
The frozen Zod #5944 case named
cidrv6and included the start of the faulty regex, but token overlap ranked JSON-schema consumers above the file that defined the pattern. The ranker had no punctuation-preserving literal evidence and no explicit definition-site signal.The new signal is general and explainable: code-shaped identifiers can support their definition, and a distinctive exact fragment receives an additional boost only when it occurs at a nearby definition/assignment. Generic short names such as
levelare deliberately excluded from identifier evidence.Measured impact
The unchanged six-repository benchmark moves from:
Zod #5944 moves from outside Top-5 to Top-1. No task text, expected path, case, or selection rule changed. The checked-in per-case output remains public, and the docs explicitly avoid turning six cases into a general accuracy claim.
Validation
npm run cinode scripts/evaluate-external.mjs --gate --check-recordedCloses #59