Fix enum schema flattening #600
Open
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Outdated suggestions cannot be applied.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.
Description
This PR fixes a JSON schema validation error that occurs when using enum types in tool function parameters with certain model providers (e.g., Bedrock via LiteLLM).
The issue was that Pydantic generates JSON schemas with
$ref
references and$defs
sections for enum types, but some model providers don't support JSON Schema$ref
references. This caused "JSON schema is invalid" errors when calling tools with enum parameters.The fix adds a
_resolve_json_schema_references()
function to the decorator.py file that flattens the schema by replacing all$ref
occurrences with their actual definitions from the$defs
section. This ensures compatibility with all model providers while maintaining the same functionality.Related Issues
Fixes #565
Documentation PR
N/A - No documentation changes required as this is an internal implementation fix that doesn't change the API.
Type of Change
Bug fix
Testing
How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli
hatch run prepare
Checklist
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.