fix(grammar): decode JSON Pointer escapes in schema references - #2368
Open
YaoxinHuang wants to merge 4 commits into
Open
YaoxinHuang wants to merge 4 commits into
YaoxinHuang wants to merge 4 commits into
Conversation
Added parameterized test for grammar JSON pointer escapes.
Record the pull request number required by the contribution guidelines.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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()raisesAssertionErrorfor valid references to definition names containing/or~. For example,{"$defs": {"a/b": {"const": 42}}, "$ref": "#/$defs/a~1b"}fails because the resolver looks up the literal keya~1b.Decode each JSON Pointer token before looking it up, replacing
~1before~0as required by RFC 6901 section 4. The regression cases cover slash, tilde, combined escapes, and~01to catch an incorrect decoding order.Validation: the new cases fail on the original code; all 10 grammar, chat-format, and speculative tests pass after the fix. Ruff lint and formatting checks pass for
llama_cppandtests. Tested on Windows/Python 3.12 using the current Python source and the official v0.3.35 CPU wheel's native library; the model-dependent inference suite was not run.Prepared with AI assistance (Codex).