Recover translation-bench checkpoints after interrupted writes - #2769
Merged
Dominic Nguyen (datduyng) merged 12 commits intoAug 21, 2026
Conversation
Treat determiner-only listName captures (the/my/list) as invalid via checked_wildcard validation so "add ham to the list" falls through to the LLM instead of creating a list named "the".
- Normalize: strip true determiners + trailing list(s) only (keep whole foods / active tasks / most wanted intact) - Reject bare closed-class, of-led junk, closed-class "… of them", lots/rest partial anaphora; accept open-class "photos of them" - Execute guards on all listName actions; removeItems throws if missing - Salvage key __recovered__; checked_wildcard on createList - Expand unit coverage for validator, coalesce, and edge names
…eal-pr-2769 # Conflicts: # ts/packages/agents/list/src/listSchema.agr # ts/packages/agents/list/src/listSchema.ts
Dominic Nguyen (datduyng)
changed the title
jebrans
reviewed
Aug 21, 2026
jebrans
approved these changes
Aug 21, 2026
Dominic Nguyen (datduyng)
marked this pull request as ready for review
August 21, 2026 18:41
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Makes single-writer translation-bench checkpoints recover from interrupted JSONL writes while preserving validated resume and merge behavior.