Downstream-consumer fieldtest over the public surface at the close of the
maximize-throughput complex: a 4-instrument campaign authored, validated,
run and read back through the normal verbs; determinism probed across
--parallel-instruments 1/2/4/10 and a same-K repeat (byte-identical modulo
the run-counter suffix); duplicate-instrument refusal and faulted-cell
isolation (exit 3, healthy cells persist) confirmed under the parallel
loop. 5 working, 0 bugs, 1 friction (the zero-bound diagnostic leaks
clap's NonZeroUsize wording), 1 spec_gap (gate-emptied cell exit semantics
undocumented) — both resolved in the follow-up tidy.
refs #277
claude
9add426a93