Commit graph

5 commits

Author SHA1 Message Date
Anton Razzhigaev
f05bf94362 feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying
Six reviewed phases land as one release.

Admission is the outer boundary: every migrated launcher records a manifest before
it can touch the filesystem, and finalizes a typed outcome on every path — success,
refusal, crash, and the real exit status. A structural audit enforces that boundary
across all fourteen launchers, together with confinement computed from the active
checkout and a single manifest publisher, judging by effect rather than by callee
name and failing closed on any write form it cannot resolve.

Harness exit codes are no longer trusted as run status: inspect returns zero for an
eval that raised and harbor returns zero for a job whose trials all errored, so the
launchers now read the harness's own artefact and keep "the harness failed", "it
scored nothing" and "it scored honest zeros" distinguishable.

The acceptance dialogue reconciles receipts through one typed identity that is an
equivalence by construction, so a passing check can no longer clear a red it never
addressed. Prompt caching is normalized at every send site and cached calls stop
under-reporting their input. The owner's context mode becomes explicit and
fail-closed, with one enforcement point for every writer of a disk-authored setting.

Deliberate limits are disclosed in each bench's METHODOLOGY.md rather than implied
by silence. Isolated benchmark egress and the multi-lane script generator are
deferred to a later release with restoration patches and carry-forward notes.
2026-07-26 03:40:44 +00:00
Ouroboros
7eb96f355f release: v5.30.0-rc.1 reasoning continuity cache support 2026-05-21 18:10:14 +03:00
Ouroboros
58ad2bf8b6 v5.25.0-rc.4: shrink review and skills UI surfaces 2026-05-17 21:37:56 +03:00
Ouroboros
c5ccfd4815 v5.2.2: marketplace and mobile stability wave 2026-04-27 21:03:22 +03:00
Ouroboros
6700358a41 Initial commit from app bundle 2026-04-22 01:04:48 +03:00