Add readiness check to HTTP server

[kylemclaren]

This differs from the /health-check endpoint in that it only returns 200 if the health status is READY — i.e. ready to make a prediction.

In my particular use-case, this will be useful when running Cog on Fly.io GPUs (see here, here and here) with cold start requests; in my testing, I would regularly hit 409 - Conflict ("Already running a prediction") when sending an HTTP request to Cog and starting the VM. This occurs even with the idempotent endpoint. I am not sure if I this is intended behaviour — but it's not working for my use-case.

A readiness endpoint would allow me to set a health check to only forward the request to the Machine when it's ready to make a prediction:

  [[http_service.checks]]
    grace_period = "60s"
    interval = "30s"
    method = "GET"
    timeout = "5s"
    path = "/ready"

Happy to elaborate further!