DottaandPaperclip fa25178f36 test(evals): accept genuine descriptive pending secret proposal cards ...

Do not misclassify absent duplicate prose as a false completion claim. Require the actual visible human-only source-run-bound proposal card, exact secret/consumer/reference identity, and independent absent binding before either human decision. Contradictory prose, missing authority or wrong-card evidence still fail.

Co-Authored-By: Paperclip <noreply@paperclip.ing>

2026-10-27 08:27:38 -05:00

..

aggregator-accounts

…

ai-connections-app

…

ai-connections-review

…

canary-onboarding

fix(release): retry verified canary tarball 404s (#15768)

2026-10-10 16:49:15 -07:00

e2e

feat(evals): package a portable Runner controller runtime (#17506)

2026-10-26 14:32:46 -05:00

fixtures

…

helpers

feat(cases): add persistent workflows with same-task agent handoffs (#16959)

2026-10-20 12:46:14 -05:00

hiring-ai-connections

…

html-preview

…

lifecycle-baseline

…

perf

perf(ui): defer hidden task rendering until history is ready (#16878)

2026-10-19 14:01:37 -05:00

release-smoke

…

runner-acceptance

…

runner-e2e

test(evals): accept genuine descriptive pending secret proposal cards

2026-10-27 08:27:38 -05:00

runner-recovery

…

speko-native

test(voice): qualify Speko task conversations and Storybook surfaces (#15729)

2026-10-13 16:54:41 -05:00

speko-voice-proof

test(voice): qualify Speko task conversations and Storybook surfaces (#15729)

2026-10-13 16:54:41 -05:00

storybook-visual

feat: offer existing Claude and Codex agents a runner upgrade (#17122)

2026-10-21 15:13:42 -05:00

acpx-qualification-models.ts

feat: integrate Pi 1.0 into the experimental Runner (#14921)

2026-10-09 08:56:41 -05:00