fix(ChatAdapter): None/True/False parsing in Dict[str, Any] fields (#8820) #9018
+78
−7
Conversation
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
When LLMs output Python-style dicts with None values, json_repair.loads was converting None to the string "None" instead of null. This caused high tool call failure rates for Dict[str, Any] fields. Changes: - Update ChatAdapter to instruct "valid JSON" instead of "valid Python dict" - Reorder parse_value to try ast.literal_eval before json_repair.loads - Preserve ast.literal_eval results as fallback when json_repair fails - Add comprehensive tests for None, True, False, and null handling This maintains backward compatibility by accepting both Python and JSON syntax while correctly parsing None/True/False/null values. Fixes #8820
isaacbmiller
changed the title
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Outdated suggestions cannot be applied.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.
When LLMs output Python-style dicts with None values, json_repair.loads was converting None to the string "None" instead of null. This caused high tool call failure rates for Dict[str, Any] fields.
Changes:
This maintains backward compatibility by accepting both Python and JSON syntax while correctly parsing None/True/False/null values.
Fixes #8820