feat: add word-count scorer - #57
Merged
royalpinto007 merged 3 commits intoSep 17, 2026
Merged
Conversation
Scores output length against minWords/maxWords (and/or chars) bounds: full credit inside, linear falloff outside, mirroring the latency scorer's curve so one-word answers and rambling output both get caught. Closes AgentPostmortem#38
|
Nice work @sharadvc, this is merged. Genuinely helpful change for Evalgate. If this project helps you out, a star helps others find it too. Happy to see more from you whenever you have the time. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #38
Verbosity control is a core eval need: one-word answers slip through
contains, rambling breaks UX budgets. No scorer covered length.Change
src/scorers/word-count.ts(sibling tolatency.ts's budget + linear-falloff pattern).word-counttype inregistry.tsbuiltinScorers.minWords/maxWords(and/orminChars/maxChars); full credit inside the bounds, linear falloff outside, mirroring the latency scorer's curve.[Unreleased].Acceptance
ctx("Paris")withminWords: 5scores <1 and fails.minWords: 5, maxWords: 100passes with score 1.Full suite: 112/112 pass (
npm test— 107 baseline + 5 new);tsc --noEmitandeslintclean.This contribution was made with AI assistance (Claude).