Collect RSS groups, top processes, and loadavg from inside each podman
container (not host /proc), merge into performance.memory, show compact
labels with cgroup limits and byte tooltips, and cover this in the test suite.
Add a host-side Python collector that lists every bank account, pages
through all ledger rows, and emits stats.json with amount_alt fields
(Kilo/Mega/Peta-GOA) so large ladder withdrawals fit on the landing tiles.