Problem

When using streaming responses, some models or API endpoints may returnusage fields (prompt_tokens,completion_tokens,total_tokens) asNone or omit them entirely. The current implementation passes these values directly to theResponseUsage Pydantic model, which expects integers. This causes a validation error:

3 validation errors for ResponseUsage
input_tokens
Input should be a valid integer [type=int_type, input_value=None, input_type=NoneType]
output_tokens
Input should be a valid integer [type=int_type, input_value=None, input_type=NoneType]
total_tokens
Input should be a valid integer [type=int_type, input_value=None, input_type=NoneType]

Solution

This PR ensures that all token fields passed toResponseUsage are always integers. If any of the fields areNone or missing, they default to0. This is achieved by usingor 0 and explicitis not None checks for nested fields.

Key changes:

• Allinput_tokens,output_tokens,total_tokens fields useor 0 fallback.

Impact

• Fixes Pydantic validation errors for streaming responses with missing/None usage fields.
• Improves compatibility with OpenAI and third-party models.
• No breaking changes; only adds robustness.

fixes#1179