Running a remote crew on an AWS Lambda MicroVM

A crew on this lane runs inside a MicroVM that the platform terminates at a maximum lifetime it will not extend. That clock is the whole shape of the lane, and almost every surprise on it comes from the one fact below.

The crew's home lives on the VM's disk and goes away with the VM. Nothing on this lane copies it anywhere: no suspend, no archive, no reopen. When the VM goes, the conversations go. Say that plainly to anyone who asks what a crew here keeps, and say it BEFORE they put work into one.

Before anything else: the lane is offered only when its block is complete.

An incomplete microvm block publishes no provisioner row at all, which is the deliberate choice: a row whose every launch is refused is worse than no row. So the first thing to do is READ the provisioner list, not assume. If the microvm row is absent, the block is incomplete and the missing field is the thing to find -- most often activation_role_arn, which the AWS call that enrols the crew refuses to run without, or bundle_dir, which a block that will build an image also requires.

Completeness is judged on every request, so a correct edit shows up immediately with no restart.

Two numbers that decide everything.

1 hour	the lifetime a launch asks for when the operator sets none. Raisable through wall_seconds; it is this short because the home is not kept past it
28,800 seconds	the platform's own maximum, and the ceiling on wall_seconds. Not adjustable and nothing extends it

First: is the lane even configured?

Do this before anything else, and do not infer it from the presence of an AWS profile. The lane is offered only when its configuration is complete; an incomplete block leaves it unregistered rather than registered and refusing.

GET /api/cloud/provisioners

Look for a row with "id": "microvm". Three outcomes, and they mean different things: