Difftastic seems like a really cool tool. There are a few reasons, however, why it doesn't apply well to use cases I had in mind:

1. It's in JS and not Python. These days a common data (including data tooling) stack revolves around Python and fitting JS into this ecosystem is not straightforwad.

2. Limited dialect support. As far as I can see it only supports "PostgreSQL flavor" (not sure what exactly is meant by "flavor" here). Support for dialects like Spark, Trino, Hive, etc SQL was crucial.

Definitely a worthy mention, though, thank you!