Series of bugs in 0.47.8 that drive me nuts

[ruz]

The new feature “suggest candidates to LLM” in “read file” operation is bogus and may result in out of control endless loop. LLM tried to open “■■■/yyy/service.go”, no such file exists. Local cursor code tries to suggest candidates. “■■■/yyy/” exists and has the only file “entrypoint.go”. Instead cursor offered two alternative paths to LLM (don’t remember names), but those variants were awful. LLM read one and said, ok, it’s not what I need. Returned back to step “read ■■■/yyy/service.go”. Two ended up in a loop.

There is no button “Stop” anymore or it’s masked. May be it only happens when you have “not accepted” changes and decides to continue conversation. In a such conversation agent went rogue, I saw it, but had to click “Accept” in order for “Stop” button to show up.

Context in the compose is switching to the current file in the following case and it’s wrong. Opened a file, started a new compose, wrote some instructions, realized that I don’t have pre-reqs in other file and it’s way easier to write them manually. Switched to editor, opened other file, wrote pre-reqs and switched back to compose/agent sidebar. Didn’t notice that cursor changed context to this second file with pre-req as the only context. I believe that if the input with instructions is not empty then compose shouldn’t be changed in any way without my explicit action.

Previous case ended in another bug manifesting. Sure I hit enter and got weirdest results generated in a wrong place. Scrolled to the top. Clicked “restore checkpoint”. Corrected context and hit “Send” to see another bogus generation. Looks like “restore checkpoint” on the very first message didn’t restore state, it kept all those code changes in the wrong file.

All of the above doesn’t seems like LLM’s culprit, but rather sloppy code in the cursor itself.

[ruz]

Above may be a bit over the edge. However, I still find the following behavior so annoying and frustrating.

I started a new “compose”, started typing instructions and by default the current file opened in the editor is the only context. As soon as I wrote a one symbol manually (may be besides spaces), at very that moment I want all auto-context switching to the current editor disabled. It’s annoying. To get as much as possible out of AI assistant you want to provide as much as possible relevant context. This means that sometimes you start typing instructions, then want to browse code, copy and paste context and so on. Each time I do that I end up with some random file in the context and no file where I started. It’s so frustrating.

Just checked again on the latest version.

It seems that there is already such concept in the code. When you add a second file to the context then switching between files in the editor doesn’t change the context. I just want this concept activated when I start typing my request.