Add integration tests for AI stack setup in GDK

Problem Statement

When AI Gateway or Duo Workflow Service update, we don't know if GDK can still set them up. We find out when engineers try to configure their environment and it fails.

Impact

Engineers spend hours debugging setup failures. We have no CI coverage for AI stack setup, so problems appear during onboarding instead of being caught early.

Proposal

Add tests that verify GDK can set up AI services. Test installing AI Gateway, starting Duo Workflow Service, and checking that services connect.

Run tests when setup scripts change, otherwise every 4 hours or nightly. Alert teams when setup breaks.

Expected Outcome

• Integration tests run in GDK CI when setup scripts change
• Tests run every 4 hours or nightly when no changes
• Test failures alert relevant teams showing which component failed

Impacted categories

The following categories relate to this issue:

• gdk-reliability - e.g. When a GDK action fails to complete.
• gdk-usability - e.g. Improvements or suggestions around how the GDK functions.
• gdk-performance - e.g. When a GDK action is slow or times out.