claude
a09aaadcbd
Source-blind field test of the handle echo and the rewritten chart refusal (range 9636b00..9f87e5a), driven from the public interface only: the built binary's help and refusals, the authoring guide, the glossary, the ledger. Replayable via c309_0_run_all.sh, which rebuilds its lab from scratch and captures stdout/stderr per step. The chain the cycle promised holds: take trace_name off a run's stdout, feed it to chart and to measure ic, never once list the trace directory. Both legs report the handle identically — including the measurement leg the audit caught shipping without a pin — and a tap-free run emits no key at all, consistently across stdout and the stored record. The family-id arm proved its worth: the intuitive cut of a family id yields a REAL but wrong handle (another run's data), and the arm refuses to make it. Findings routed: the three bugs fixed in-cycle RED-first (51ac155 and its successor); the friction and spec-gap items filed as a collective issue. refs #309
8 lines
204 B
JSON
8 lines
204 B
JSON
{
|
|
"format_version": 1,
|
|
"kind": "process",
|
|
"name": "c309-explore-only-sweep",
|
|
"description": "Selection-free sweep: the family itself is the result.",
|
|
"pipeline": [ { "block": "std::sweep" } ]
|
|
}
|