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
5 lines
156 B
TOML
5 lines
156 B
TOML
# Static project context only (C17); paths only.
|
|
[paths]
|
|
runs = "runs"
|
|
# data = "/path/to/archive" # the recorded-data root; defaults to the built-in path
|