What happened?

The SendMessageConfiguration of the spec says for blocking calls:

The operation MUST wait until the task reaches a terminal state (completed, failed, cancelled, rejected) before returning. The response MUST include the final task state with all artifacts and status information.

However, I think we need some clarification that if the state is INPUT_REQUIRED or AUTH_REQUIRED that we need to return? Or if that is not the case, and explanation of how this is meant to work.

Relevant log output

Code of Conduct

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