Support audited checkpoint-reader upgrades for existing runs - #168
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Allow existing benchmark checkpoints to resume with bounded parallel reads without accepting arbitrary evaluator changes.
The compatibility registry permits only an audited pair of exact evaluator source hashes. Resumes retain the original manifest identity; model, runtime, settings, input and batch-integrity checks remain enforced. New runs retain their actual evaluator identity.
This recovery build applies the reader optimization to the evaluator currently used by in-flight production checkpoints. It intentionally retains its package version so the runtime contract is unchanged.
Validation: 105 tests passed, 4 skipped; lint passed. Resume tests cover the approved upgrade, rejection of unapproved evaluator changes, and rejection of changed models. Built-wheel source identity and registry packaging verified.