Feature/probinso/fast completion detection

[robinson96]

SUMMARY

Refactor completion handling behind a CompletionDetector interface so
machine launch/cleanup code can select between detector strategies instead
of hard-coding one polling path.

Adds 2 queue-based completion detection modes alongside the legacy polling behavior. completion_queue (or reap) uses a reaper thread to notice when subprocesses end and mark the corresponding test for later processing. (Lower overhead, but not technically safe, but reasonably safe in practice). completion_queue_simple launches 1 thread per test to notice when that test is finished, marking it for later processing. Higher thread count and memory overhead, but safer threading model. Does not scale past a few hundred concurrent tests.

Add detector configuration plumbing, completion stats/spans hooks, updated
scheduler-extension documentation, and focused detector tests.

Record and summarize warnings when the queue-mode reaper observes child
exits that do not belong to registered ATS tests, so the known
waitpid(-1) race is visible in final reporting.

Restore Flux processor-capacity reporting through the normal ATS summary
path and keep unsupported queue-mode paths explicitly rejected where needed.