[bug] AsyncGuard().to_runnable() method fails cause GuardRunnable is not designed to be async

[XyAgent]

Describe the bug
A clear and concise description of what the bug is

To Reproduce
Steps to reproduce the behavior:

Guard call:

    from guardrails import AsyncGuard
    from guardrails.hub import EndpointIsReachable
    from guardrails.types.on_fail import OnFailAction

    guard = AsyncGuard().use_many(
        EndpointIsReachable(on_fail=OnFailAction.NOOP),
    ).to_runnable()    
    
    result = await guard.ainvoke("invalid url")
    print(result)

Code fails with AttributeError here: validated_output = response.validated_output

cause previous line (response: ValidationOutcome[OT] = self.guard.validate(input))
returns when using AsyncGuard

class GuardRunnable(BaseRunnable):
    guard: Guard

    def __init__(self, guard: Guard):
        self.name = guard.name
        self.guard = guard

    def _validate(self, input: str) -> OT:
        response: ValidationOutcome[OT] = self.guard.validate(input)
        validated_output = response.validated_output
        if validated_output is None or response.validation_passed is False:
            raise ValidationError(
                (
                    "The response from the LLM failed validation!"
                    "See `guard.history` for more details."
                )
            )
        return validated_output

Expected behavior
I guess a separate AsyncGuardRunnable should be implemented in this case to properly handle coroutines coming from validate method

Library version:
Version: 0.6.6

[CalebCourier]

Can repro.
@zsimjee This probably broke during the Guard/AsyncGuard split. We don't define ainvoke on the runnable so langchain will fallback to wrapping the invoke method. Before the split, this would always call the synchronous validate/parse method. Now that AsyncGuard exists, and all of its methods return Coroutines, the default behaviour is no longer appropriate.