> each costs like 15 minutes

I've got a custom agent loop that will reuse unit testing results if no apply patch operations occurred since the last invoke.

Wall clock time isn't something I would put on the AI provider. That's entirely a consequence of the system that you've brought to the party.

Even better, use some kind of local-ci runner that does deterministic builds from a dependency graph. No changes, no build, massive parallelism if you want it