It's a spectrum, isn't it? I wouldn't want to waste my time reviewing a bunch of repetitive code generated from some script or do something like review every generated template instantiation in a C++ code base. I would want to review the script/template definition/etc., but what's the equivalent for AI? Should the review just be the prompt(s)?

Edit: Also, it's always good to provide maximal context to reviewers. For example, when I use code from StackOverflow I link the relevant answer in a comment so the reviewer doesn't have to re-tread the same ground I covered looking for that solution. It also gives reviewers some clues about my understanding of the problem. How is AI different in this regard?

No, it explicitly says that you don't need to disclose tab completion.

If you're not sure, it's probably safer to just mention it.