You'd have to do the join on the client. This is a problem in general for scaling SQL - its not impossible, but with sharded SQL servers you have to be very deliberate in how you do joins so as to coincide as much as possible with your sharing strategy.

It would be similar here. According to the author each sqlite DB belongs to a single microservice, which will naturally group together the most common of joins. Anything else will indeed have to be manually joined.

Part of the reason nosql became popular for a bit. That's reversed, and sharded SQL is pretty common now, but it definitely adds more cognitive load to schema design.