Spring AI should allow function calling to be proxied for a remove invocation by OpenAI clients

[csterwa]

Expected Behavior

OpenAI python client application calls a Spring AI application. The Spring AI Server is configured so that functional calling does not invoke a local (JVM) Java function, but calls back to to the python client application. Consider the case of how this solution looks for the case where there are advisors that would be invoked after the assistant message is returned and function calling is complete.

Current Behavior

Not sure if the current interfaces accommodate this use case.

Related Issues

#1177, #1032, #656, #652, #368