alt Hacker NewsNice project. For the agent loop, the two UX pieces I'd make impossible to miss are: 1) a plan/checkpoint before file writes, and 2) a diff/revert view after each tool run.
WebContainer is great for "run it and see", but state can get fuzzy fast. The more the UI shows exactly what changed and why, the safer it feels to trust the agent.
This is very helpful feedback. You're totally right, when WebContainers run a real environment, the state gets fuzzy fast. A diff/revert view before the agent executes would be a good idea to implement into the UI to build trust. I'm going to open a github issue for this right now so hopefully someone in the community can pick it up while I'm revising!