> I think it's going to be another year or 2 before dropping CocoaPods entirely is a fair choice for libraries
For libraries this is probably true, but I would imagine that most apps could start on SPM from today and never need to introduce CocoaPods or Carthage (we did, ~1 year ago). There are certainly limitations, but they are disappearing fairly rapidly, and the advantage of simpler builds, no Ruby setup, simpler Xcode project structures, etc, are worthwhile.
For libraries this is probably true, but I would imagine that most apps could start on SPM from today and never need to introduce CocoaPods or Carthage (we did, ~1 year ago). There are certainly limitations, but they are disappearing fairly rapidly, and the advantage of simpler builds, no Ruby setup, simpler Xcode project structures, etc, are worthwhile.