the hard part for coding is actually state engineering (e.g. getting your dependencies in context) - we haven't even tried it yet (because my philosophy is we should automate the easy tasks before the hard and we've been working on getting the model smart on the former)

we do think there's a lot of potential though and do want coding themed releases soon

I saw the CEO reply elsewhere in the comments to some other question. Maybe he can shed some light on it. My gut feeling is that this is non-trivial and they did not get this to work (yet?), otherwise I can’t come up with a good reason as to why they would not demo that as I assume half of the crowd here (myself included) would line up as customers.

I've implemented tree-sitter in pi before, and while it works, I have no real proof it saves me tokens, or is more accurate. I think a better implementation is a model that's trained for AST's, not just "use tool, see what happens".

I'd love to do research on this when I have the time.