Repository navigation
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Member
Author
|
Consolidated into #2029. Its measurement-file changes match the eval commit in that PR. Keeping this branch as the original off-arm comparison record. |
This branch was successfully 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
Measure the same long two-Turn task on Junior before the Hex and handoff changes in draft PR #2024. This branch starts at a6d8d0d and adds the identical eval and numeric-usage observer used at b2d3b32 in #2024. It also includes the earlier handoff reply-quality eval, so shared integration cases match.
The fixture records per-call cache reads, cache writes, and estimated Messages costs without storing model or tool content in usage metadata. Compare completed-task cost, answer quality, and duration only after both runs finish. The existing reporting job may fail on the unrelated history.eval.ts path; use the selected shard artifacts for case results.
Validation
Eval fixture typecheck and four focused tests passed on this branch. Full CI is pending. This is a draft comparison branch, not a product change.