I don't think patch theory is untyped in principle. But all developments I've seen are untyped. And it's probably good this way, for typically you don't want to tie a version control system to a specific programming language / typing system. There is recent work on patch theory using category theory [2] and homotopy type theory [3], maybe that introduces a types angle (I have only skimmed these papers).

I think Unison is based on [1] quoted above, but I'm not sure.

[2] S. Mimram, C. Di Giusto, A Categorical Theory of Patches.

[3] C. Angiuli, E. Morehouse, D. R. Licata, R. Harper, Homotopical Patch Theory.

It seems wasteful not to use insights from one domain (untyped, textual) in another (typed, contextual).

I knew about (not that I understand it) the connection homotopy...mostly just worried there's work happening that isn't informed by research.