Keeping it in shell instead of rewriting in Python was probably the right call. Once you add a language runtime dependency you lose the “just drop this file in and use it” simplicity.
The transitive dependency case is what makes this painful in practice. You’re not even choosing that library it’s three levels deep in your dependency tree, and suddenly CI fails because some maintainer ran `go get go@latest` on a Saturday.
Interesting approach. How does it handle monorepos or repos with unconventional structure? The multi-pass analysis sounds nice, but I’d be curious how consistent the output is across runs if you run it twice on the same repo, do you get basically the same diagram?
Nice structure — separating the Grafana client from the TUI layer should make it easier to extend. Also cool to see testcontainers for integration tests.