Repository navigation
Conversation
Retain nonce-bound terminal measurements for each original benchmark attempt, including explicit zero-candidate results and unknown failed-attempt capture. Validate final successful capture before calibration recording or release comparison, with diagnostic transport isolated from existing retry decisions.
![postil-dev[bot]](https://avatars.githubusercontent.com/in/3455612?s=60&v=4){kind=small}
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Benchmark results omit review timing and correction outcomes, leaving deadline use unverified. Retain bounded, nonce-bound terminal measurements for each original attempt, distinguish explicit zero-candidate results (
notRequired) from missing failed-attempt evidence (unknown), and require complete final successful capture before calibration recording or release comparison.Keep diagnostic transport separate from retry classification: preserve unmatched diagnostic bytes and retain a newline boundary when removing matching capture. Offline tests cover short writes, malformed and replayed frames, retry decisions and accounting, and actual CLI children against a local mock endpoint. Genuine calibration and release qualification require fresh runs against the changed evaluator.