Code Review: Adds OpenAI handoff support to the Cadence Python client. Consider removing the unused `Awaitable` import, fixing the `noop_invoke` return type annotation (async def should return `Coroutine` not `Awaitable`), and deferring the `OpenAIActivities` instantiation to avoid module-level side effects at import time.

1. 💡 Bug: Incorrect return type on async noop_invoke callback
   Files: cadence/contrib/openai/cadence_handoff.py:33, cadence/contrib/openai/cadence_handoff.py:6

   The `noop_invoke` function is declared as `async def` with return type `-> Awaitable[Any]`. Since `async def` functions implicitly wrap their return value in a coroutine (which is an `Awaitable`), this annotation means the actual type at the call site would be `Awaitable[Awaitable[Any]]`, which is incorrect. The `# type: ignore[return]` comment is masking this issue. The return type should be `-> Any` (or `-> None` since it only raises).

   Suggested fix:
   async def noop_invoke(_ctx: RunContextWrapper[Any], _json: str) -> Any:
       raise RuntimeError("Handoff invocation is handled by the runner, not the model")

2. 💡 Quality: Module-level side effect in cadence_registry.py
   Files: cadence/contrib/openai/cadence_registry.py:5-6

   cadence_registry.py instantiates `OpenAIActivities()` and registers it at import time. This means merely importing the module triggers side effects (object creation, registration). Consider using a factory function or lazy initialization pattern so consumers have explicit control over when registration happens.