Reject aborted runs and incomplete classification evidence

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0e76f-be98-7ae3-965d-e0b31290a4c4
This commit is contained in:
tegwick 2026-09-28 12:17:13 +02:00
parent 081fb8c73c
commit 7779768058
7 changed files with 311 additions and 3 deletions

View file

@ -299,3 +299,19 @@ Then state a verdict, including the verdict "not yet, and here is what is missin
A readiness review that cannot conclude *not ready* is not a review.
**2026-09-28 closeout — done.** Published explicit real-system gates and a NOT READY verdict for autonomous application, including D-07 cost, provenance from real backlogs, ambiguity, engagement-specific false-adaptation harm, custody/timing/cleanup and economics. The audit-core contract remains intent plus fixture calibration, not a runnable production engagement.
**2026-09-28 safety follow-up — done.** Fixed two reproduced readiness defects
under this existing task. Forbidden-surface aborts now retain all unreached
scheduled claims/invariants as INCONCLUSIVE, prevent a passing-prefix run verdict,
and preserve failures already observed. Evidence packs record scheduled steps
and expected judgments before execution; classification rejects incomplete
baseline or candidate evidence, including missing S1/S2/S3 records, missing or
duplicate verdicts, and identical truncation of both packs. Historical packs
without the input manifest require a rerun before automatic acceptance.
Validation: the new regression module produced 55 failures before the fix; all
**299 tests pass** after it, including existing classification matrices and
intentional partial scenarios. `git diff --check` is clean. Decision:
`afb38ade-893b-48a2-b1b3-c55e49cc40ee`. No new task or workplan was created;
T01/T06/T07 and the blocked workplan state are unchanged.