claude
9add426a93
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
11 lines
407 B
JSON
11 lines
407 B
JSON
{
|
|
"format_version": 1,
|
|
"kind": "process",
|
|
"name": "p277-sweep-gate",
|
|
"description": "Fieldtest process: rank the axis grid by sqn (deflated), then keep only members with positive expectancy_r.",
|
|
"pipeline": [
|
|
{ "block": "std::sweep", "metric": "sqn", "select": "argmax", "deflate": true },
|
|
{ "block": "std::gate", "all": [ { "metric": "expectancy_r", "cmp": "gt", "value": 0.0 } ] }
|
|
]
|
|
}
|