Repository navigation
terminal-bench-2@1.0, and each dataset numbers its own versions from 1.0 - #19
Merged
Merged
Conversation
A dataset's version is now this repository's own, starting at 1.0: a new upstream release or commit bumps the first component, a change of ours the last. Upstream's 2.0 names Terminal-Bench 2 rather than a revision of it, so the dataset becomes terminal-bench-2@1.0, with 2.0.1's tasks byte for byte, and superseded.yaml maps both terminal-bench versions to it. Its images stay in hbench-envs/terminal-bench: environment.mirror names the package when it is not the dataset's name, so nothing is mirrored again and no task byte changes. dataset_index.py leaves a superseded version out only once its successor is in the index, so terminal-bench stays listed until terminal-bench-2@1.0 is published.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
terminal-bench-2@1.0has 2.0.1's tasks, byte for byte.superseded.yamlmapsterminal-bench@2.0and@2.0.1to it.environment.mirror: the images stay inhbench-envs/terminal-bench, so nothing is mirrored again.dataset_index.pyleaves a superseded version out only once its successor is in the index. terminal-bench stays listed untilterminal-bench-2@1.0is published.terminal-bench-21.0. It runs Index at the end.Tests: 356 OK (5 new) and
validate_sources.py, run locally.