mirror of
https://github.com/stablyai/orca.git
synced 2026-09-30 00:03:15 +00:00
Jinwoo-H
5dc65a3820
The kernel claimed every unverifiable row reports a `none` nextAction, but projectFleetNextAction deliberately keeps `inspect` when input or approval is pending, because that is work a command can actually move. An agent following the guide literally would have treated a waiting question as another wait-only row. The guidance test asserted the sentence verbatim, so it agreed with the wrong text instead of the behavior; it now checks the rule's two halves as fragments, and the projection suite covers both pending flags directly.