[Frontend] request.tool_choice is not completely exhausted in non-stream mode

[MatheMatrix]

request.tool_choice could be "auto" or others, in that cases message would not be defined.

In chat_completion_stream_generator, request.tool_choice is completely exhausted:

if request.tool_choice and type(
        request.tool_choice
) is ChatCompletionNamedToolChoiceParam:
    delta_message = DeltaMessage(tool_calls=[
        ToolCall(function=FunctionCall(
            name=request.tool_choice.function.name,
            arguments=delta_text))
    ])
else:
    delta_message = DeltaMessage(content=delta_text)

so this pr just follow the approach in chat_completion_stream_generator

[MatheMatrix]

@simon-mo This is a small fix avoid message would be not defined since the if-else is not completely exhausted

[github-actions]

This pull request has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this pull request should remain open. Thank you!

[DarkLight1337]

Closing as superseded by #5649