All AI models are completely unusable

Support Bug Reports
,
4

Hey, this is a known issue where the backend generates the response, but the client fails to render it. A few things to try:

  1. Resync your project index: Cursor Settings > Indexing > Resync Index. This has fixed it for several users.

  2. Disable HTTP/2: Add "cursor.general.disableHttp2": true to your settings.json via Cmd+Shift+P > Preferences: Open User Settings (JSON), then restart Cursor.

  3. Run network diagnostics: Cursor Settings > Network > Run Diagnostics, then share a screenshot of the results.

  4. Test in an empty folder: File > Open Folder > pick an empty directory, start a new chat, type “hello”. Does the same thing happen?

  5. Update to 2.6.20. You’re on 2.6.19, and the latest stable is 2.6.20.

Are you using a VPN or proxy? If yes, try without it.

The team is aware of this issue. Related mega-thread for reference: Taking longer than expected

Let me know how it goes.