Description

Certain models executed under LiteLLM will return additional payloads inbetween the finish_reason message and the usage message. Here is an example of an inbetween payload:

ModelResponseStream(id='chatcmpl-3cdd4223-9c65-4ce0-9456-0a41d4a70b86', created=1747836095, model='gpt-4.1-mini-2025-04-14', object='chat.completion.chunk', system_fingerprint='fp_c8225066ea', choices=[StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, content=None, role=None, function_call=None, tool_calls=None, audio=None), logprobs=None)], provider_specific_fields=None, stream_options={'include_usage': True})

We don't have any use for these inbetween messages and so for now, we will skip over them so we can get to the final usage message for reporting.

Related Issues

#47

Type of Change

• Bug fix
• New feature
• Breaking change
• Documentation update
• Other (please describe):

Testing

• hatch fmt --linter
• hatch fmt --formatter
• hatch test --all: Relying on existing unit tests and integration tests. They still cover these changes.
• Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

Checklist

• I have read the CONTRIBUTING document
• I have added tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature
• My changes generate no new warnings
• Any dependent changes have been merged and published

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.