feat: Orchestration image support

[Jonas-Isr]

Context

AI/ai-sdk-java-backlog#152.

We want to support using images and prompts with multiple text messages as input for Orchestration.

Feature scope:

• Added possibility of using image and multiple text messages in prompts
• Added Convenience layer

Definition of Done

• Functionality scope stated & covered
• Tests cover the scope above
• Error handling created / updated & covered by the tests above
• Aligned changes with the JavaScript SDK
• Documentation updated
• Release notes updated

[newtork]

(Minor/Opinion)

I think it's a mistake to have this method on public API.
Maybe we could address this in another PR.

[newtork]

I want to explain my assumptions for convenience API behavior / contract.

• For request:

  • the user will only use public constructors and factory methods for easy instantiation.
  • low API hierarchy requirement; we'll try to avoid users to define helper classes.
  • strict value checking on design time; only allow what's aligned in spec.

• For responses:

  • developer uses public accessors.
  • while casting may be necessary, let's try to minimalize the effort.
  • hierarchy can be high as long as it's reasonable.
  • loose value checking; whatever is sent back from server can be read with our API.