Record server-side Prometheus metric for spent ZKAPs

also rename and clarify the read_bucket `size` parameter

The test demonstrates this now by depending on part of the successful result
from the underlying storage server object.

It's more specific and less powerful, therefore more expressive and safe.

Co-authored-by: Tom Prince <tom.prince@private.storage>

Make the lease duration config reader respect the lease crawler config

This means you can make estimates about storage-time remaining based on the
results of the calculator endpoint and they'll at least match your local
configuration.

also, move the function to the config module.

Also make the metrics path's parent directory if necessary

Let's see how far we get with just this simpler version.  We now have a
histogram for number of zkaps spent, bucketed by the size of individual spend
operations.

Also implement it for mutables

Add configuration for lease maintenance behavior