What I've been doing when I want to avoid this "unexpected leading", is to tell the LLM to "Ask me 3 rounds of 5 clarifying questions each, first.". The first round usually exposes the main assumptions it's making, and from there we narrow down and clarify things.
I've read you comment about all the things you tried, and it seems you have much broader experience with LLMs than I do. But I didn't see this technique mentioned, so leaving this here in case it helps someone else :).
I also tried Zed on Linux a few months back, and had GPU/driver issues, so it was either slow or didn't run. Tried it just now and it worked right out of the box, and it's incredibly fast.
I will keep playing around with it to see if it's worth switching (from JetBrains WebStorm).