This is why I love Hetzner. It has billing alerts. What was so difficult about it that fly had to rebuild their system?
Also, do everything except databases inside kubernetes. Deploy kubernetes across multiple clouds via wireguard. Label your instances properly on each provider. Prefer bare metal instances where available. Migrate your workloads accordingly. Force cloud providers to earn your money. Don’t however have both workloads running at the same time in multiple providers as you will eat insane data costs.
I can't read the tone, but perhaps you haven't seen much technical debt. It's possible to have a fairly good codebase, full of good decisions, yet you still can't "get there from here".
Also, do everything except databases inside kubernetes. Deploy kubernetes across multiple clouds via wireguard. Label your instances properly on each provider. Prefer bare metal instances where available. Migrate your workloads accordingly. Force cloud providers to earn your money. Don’t however have both workloads running at the same time in multiple providers as you will eat insane data costs.