Conversation
This change updates Qwen3 Coder’s tool-call argument parser, which converts argument text generated by the model into Python values such as strings, dictionaries, and lists. When the top-level `type` is missing, the parser first attempts to parse the text as JSON. - If the parsed value is an object or array, it returns a dictionary or list. - If parsing fails, or the parsed value is a number, boolean, or string, it preserves the original text. Only objects and arrays are converted to avoid accidentally turning text such as `"123"` into a number. The handling of explicitly specified types is unchanged, and the existing `null` handling is preserved.
zmylol
marked this pull request as ready for review
September 21, 2026 16:49
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This change updates Qwen3 Coder’s tool-call argument parser, which converts argument text generated by the model into Python values such as strings, dictionaries, and lists. When the top-level
typeis missing, the parser first attempts to parse the text as JSON.Only objects and arrays are converted to avoid accidentally turning text such as
"123"into a number. The handling of explicitly specified types is unchanged, and the existingnullhandling is preserved.I reviewed the root cause and chose to limit automatic JSON conversion to objects and arrays to avoid unintended conversion of string values.I wrote the description myself and used Codex only to polish the English wording. Codex assisted with implementation, regression tests, code review. I also ran the tool-parsing tests locally to verify the changes.