I've been using Windsurf for a few weeks. I'm a novice programmer trying to build a web app using React and NextJS.
The "context-in-the-codebase" thing for AI-based IDEsis overrated IMO. To extract the most from it, you have to remember to @mention the files.
If you don't remember to @mention specific files, the agent simply tries to perform searches (i.e., it has access to that tool) on the files and folders until it gets some results... and will usually keep broadening the search until it does.
It works well enough I suppose. But I still find myself beginning new chats (for example, per feature) because the model still loses its place, and with all the code/lint fixes it does, it starts to lose context.
Then you're right back having to @mention more files to ensure the model knows how to structure your front end, back end, etc.
(Please excuse any misnamed development terms.) :-)
In VS Code, you automatically get the current file context and you can add all open files, specific files, etc. just before you hit send.
I don't think you're quite right about this, as I've noticed (at least in Cursor) that appropriate context tends to be pulled in automatically.
What I do notice is that the AI systems seem to forget to pull in a lot of context as the project size grows. It's almost as if there's something of a limit to the amount of input data, either to manage costs or compute cycles or something like that.
When I start "vibecoding" it goes really well in the beginning but then when the project grows in complexity, asking it to do something relatively simple falls apart as the AI "forgets" to do that really simple thing in every applicable place (e.g., removing a feature that is no longer needed).