fix: support unconstrained array item schemas - #2378
Open
tuanzirwar wants to merge 2 commits into
Open
tuanzirwar wants to merge 2 commits into
tuanzirwar wants to merge 2 commits into
Conversation
This branch has not been 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
LlamaGrammar.from_json_schema()raisesKeyErrorfor{"type": "array", "items": {}}, including the schema generated by Pydantic forlist[Any]. Empty schemas in other positions are also incorrectly restricted to objects.Preserve empty
itemswhen there is noprefixItemsfallback and compile an empty schema as the existing unrestricted JSON value rule. Keep typed arrays and closed tuples usingprefixItemswithitems: falseworking. Add regression and compatibility tests and an Unreleased changelog entry.Validation: 8 grammar tests pass; all Python source/tests pass Ruff and formatting checks. Three new regressions fail on the original code. With the same-version official 0.3.36 CPU library and a tiny GGUF model, the native grammar sampler accepts number/string/boolean/null/object/array elements, and real grammar-constrained CPU inference returns
[]. Large models, GPU backends, and the full server suite were not exercised.AI-assisted implementation. The Unreleased changelog entry references #2378.