claude a09aaadcbd fieldtest: trace-handle cycle — 5 examples, 3 bugs / 4 friction / 2 spec-gaps / 4 working ...

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

2026-07-26 23:43:39 +02:00

0 lines

0 B

Plaintext

Raw Blame History

The file is empty.