when update to pydantic 1.3.0 stream model run error cause UnexpectedModelBehavior

[JuneLeGency]

Initial Checks

• I confirm that I'm using the latest version of Pydantic AI
• I confirm that I searched for my issue in https://github.com/pydantic/pydantic-ai/issues before opening this issue

Description

if isinstance(first_chunk, _utils.Unset):
raise UnexpectedModelBehavior( # pragma: no cover
'Streamed response ended without content or tool calls'
)

Example Code

    async def _process_streamed_response(
            self, response: AsyncStream[ChatCompletionChunk], model_request_parameters: ModelRequestParameters
    ) -> OpenAIStreamedResponse:
        """Process a streamed response, and prepare a streaming response to return."""
        peekable_response = _utils.PeekableAsyncStream(response)
        first_chunk = await peekable_response.peek()
        if isinstance(first_chunk, _utils.Unset):
            raise UnexpectedModelBehavior(  # pragma: no cover
                'Streamed response ended without content or tool calls'
            )

        # When using Azure OpenAI and a content filter is enabled, the first chunk will contain a `''` model name,
        # so we set it from a later chunk in `OpenAIChatStreamedResponse`.
        model_name = first_chunk.model or self._model_name
        if not first_chunk.created:
            # patch time
            first_chunk.created = int(time.time())
        return OpenAIStreamedResponse(
            model_request_parameters=model_request_parameters,
            _model_name=model_name,
            _model_profile=self.profile,
            _response=peekable_response,
            _timestamp=number_to_datetime(first_chunk.created),
            _provider_name=self._provider.name,
            _provider_url=self._provider.base_url,
        )

Python, Pydantic AI & LLM client version

python 3.10 
pydantic-ai 1.3.0
llm dashscope qwen3-coder-plus

[DouweM]

@JuneLeGency Thanks for the report. I can't reproduce this with the following code that also uses `OpenAIChatModel':

from pydantic_ai import Agent

agent = Agent('openai:gpt-5')


async def main():
    async for event in agent.run_stream_events('Hello, how are you?'):
        print(event)


if __name__ == '__main__':
    import asyncio

    asyncio.run(main())

Are you only seeing this issue with qwen3-coder-plus on dashscope or also other models/providers?

What was the latest Pydantic AI version on which it was working?