feat: [Orchestration] Convenience for response format

[Jonas-Isr]

Context

AI/ai-sdk-java-backlog#195.

This PR adds convenience methods to set the response format in Orchestration. A JSON schema can be created from a class and then used as a response schema as follows:

var schema =
        ResponseJsonSchema.from(Translation.class)
            .withDescription("Output schema for language translation.")
            .withStrict(true);
val configWithResponseSchema = config.withJsonSchemaResponse(schema);

If only any JSON response is wanted, without strict adherence to a given schema, the user can use
var configWithJsonResponse = config.withJsonResponse().

Feature scope:

• Add a way to generate schema conveniently
  • Add new class ResponseJsonSchema
  • Add methods to create such schema from class or from a map
• convenience methods to add response format (JSON schema or JSON object) to config
  • had to overwrite OrchestrationModulConfig.withTemplateConfig() to make it work conveniently

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

[CharlesDuboisSAP]

Minor comments

[CharlesDuboisSAP]

Should the overwriting behaviours throw?
It could avoid customers asking why their response format is broken

[Jonas-Isr]

I think if the users set a response format in their new template config they will expect it to change, right? So I don't think we should throw here.