Last two days have been crazy with “Planning next moves” can wait for 5-10 minutes, and yet it believe it thought for 5-11 seconds. Then it often returns with me being on VPN. I am on a very strong internet connection without VPN. Only Cursor complain about this.
It did not happen after the last cursor update, that worked fine for some days and now it’s just unusable, it also makes code you then cannot redo sometimes so I had twice to fully load a backup from the day before.
Please give people some clarification. Your status page shows as all system are good, they are surely not.
Steps to Reproduce
Just try to use Cursor self … It’s for all Models.
Operating System
MacOS
Current Cursor Version (Menu → About Cursor → Copy)
Hey, thanks for the report. Let’s quickly check the most common causes of “Planning next moves”:
Run without extensions: in the Mac terminal run: cursor --disable-extensions. In the new window don’t open a project, just open the agent chat and send a simple message. If it works, disable or remove your extensions one by one.
Disable MCP servers (Settings → search for “MCP”) and test again.
Turn on “Disable HTTP/2”: Settings Cmd+, → search for “HTTP/2” → turn it on → restart Cursor.
Full restart: close Cursor → open a different project → then go back to the original one. Try a new chat.
If it doesn’t help, please share:
A screenshot of Settings → Network → Run Diagnostics
A list of extensions and info about VPN/proxy/corporate network (Zscaler, etc.)
Console errors: Cmd+Shift+P → “Developer: Toggle Developer Tools” → Console tab (screenshots of red errors)
Hey none of that had an effect. But now it seems like things are working again. Hope it stays stable now. But why don’t you just be honest and tell people when there are problems? It save us, customers a lot of time and when things goes wrong it’s fine - just say it.
Glad it worked! I understand the frustration - when the problem resolves itself, it’s hard to understand the cause.
Usually, “Planning next moves” followed by recovery indicates temporary network issues between the client and the API (api2.cursor.sh), which can happen anywhere along the route, not necessarily on our servers. The status page monitors main services availability but can’t catch all local network fluctuations or provider issues.
If it happens again:
Save the Request ID (chat menu > Copy Request ID) - this lets engineers check server logs
Take a screenshot of Settings > Network > Run Diagnostics during the issue
Try running curl -v https://api2.cursor.sh in your terminal - this shows if there are network-level delays
This will help to understand if the problem was on our side or with the provider. Thanks for your patience!
