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
2 lines
315 B
Plaintext
2 lines
315 B
Plaintext
aura: no recorded run or family 'deadbeef-0-GER40-w0-r0-s0-0' under runs/traces — that looks like a family id, not a trace handle. The handle is the `trace_name` the campaign run printed; this id's second segment counts strategies while the handle's counts runs, so cutting the id down is not a way to derive it.
|