Everything I could decide myself is decided. What's left needs
you. Each one carries the recommendation of the session that raised it — if you
agree, pick it and press Done. A model's opinion, where there is one, appears on the card
as a receipt line; cards with no receipt were never put to a model. "I'm not sure" is a real answer and becomes work for me.
You don't need to open the session — pressing Done sends your answer back and it picks up.
1The mini's desktop login closed 2026-09-25 04:04 local and every co.propflow LaunchAgent (~60 jobs: fleet-medic, operator-heartbeat, tracker-refresh, doctrine-pull, the decision sweeps, Smith's own worker with its KeepAlive) has been unloaded since; Smith was fully down ~47h until the worker was hand-started 09-27 03:10 local, and the whatsapp-doc-mirror is still down. How do we keep the fleet alive across a logout or reboot?
In plain terms. Should the mini log itself back in automatically after a reboot so Smith and its background jobs keep running?
The session raising this recommends: Enable auto-login on the mini LaunchAgents only exist inside a logged-in GUI session; auto-login restores that after any reboot with zero code change and keeps every plist as-is. LaunchDaemons need sudo for every edit and break the co.propflow.* self-serve rule. A dead-man only reports the death faster; it brings nothing back. Tried first, unsuccessfully: Tried from Smith's runtime: launchctl bootstrap/print into gui/501 (125: domain does not support), sudo and launchctl asuser, an osascript into Terminal (-10810) — four routes, all dead; the decider on the wa-mirror alert hit the same wall. Only a console login or an OS setting restores the domain, and that is a human/owner call.