[Feat]: RequestContext supports distinguishing between message/send and message/stream

[ThinkMo]

Is your feature request related to a problem? Please describe.

No response

Describe the solution you'd like

In some cases, the a2a task needs to be executed in the background. When the background is executed, the underlying non-streaming seems to return faster than the streaming.

If RequestContext supports distinguishing between message/send and message/stream，llm invoke() seem faster than stream()

Describe alternatives you've considered

No response

Additional context

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[ovidiutaralesca]

@ThinkMo if I understand correctly, you'd expect the JSON-RPC method to be present in the ServerCallContext such that you can distinguish between message/stream and message/send. And that is because LLM APIs have different methods for streaming/non-streaming, like you've mentioned.

I think it makes sense, it's a valid point. It would also be helpful for me.

@holtskinner if you think it's a good idea, I can open a PR for this.

[ThinkMo]

Yes, your understanding is absolutely correct.