A save made while the connection blips for a few seconds is retried rather
than reverted: the request layer keeps trying a network failure for a
fifteen-second window, waking the instant the OS reports a link again, and
only falls back to the existing error path if the drop outlasts it. A quiet
"reconnecting" pill appears if the wait passes about a second, and leaves
the moment it heals — so a two-second blip is felt as nothing at all.
This is deliberately not offline mode: the app is a live view of a shared
list, so there is no cache to work in with no server and no write log to
reconcile. It is only the blip, ridden out. A server error (4xx/5xx) is the
server answering and is not retried; an aborted request (a superseded
search) is left to propagate.
Kristian: an offline function for when the net drops for short periods,
seconds. Shared items stay server-authoritative — nothing is edited against
a stale copy for longer than the blip.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
