User Aborted Request in the middle of flow

Support Bug Reports
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

I’ve noticed this happen in agent flow and in plan mode. It will be running some task I’ve given it, and I will not be touching the IDE at all (or even sometimes navigate away and come back) and it will randomly break saying I aborted the request even though I wasn’t even active in the IDE (or when I am and it happens I’m just sitting there watching). Maybe some network disrupt issue that needs to be better retried? I have pretty good wifi though. ITs annoying because when it happens in the middle of a long process like a long agent thread with many commands or a long plan request it kind of breaks the flow and I sometimes have to just start all over again

Steps to Reproduce

Not sure, it happens intermittently

Operating System

MacOS

Current Cursor Version (Menu → About Cursor → Copy)

Version: 2.2.20
VSCode Version: 1.105.1
Commit: b3573281c4775bfc6bba466bf6563d3d498d1070
Date: 2025-12-12T06:29:26.017Z
Electron: 37.7.0
Chromium: 138.0.7204.251
Node.js: 22.20.0
V8: 13.8.258.32-electron.0
OS: Darwin arm64 25.1.0

For AI issues: which model did you use?

Auto

For AI issues: add Request ID with privacy disabled

Request ID: 2b16ef2e-eb04-4b78-ab57-6d52f45fbf8f
{“error”:“ERROR_USER_ABORTED_REQUEST”,“details”:{“title”:“User aborted request.”,“detail”:“Tool call ended before result was received”,“isRetryable”:false,“additionalInfo”:{},“buttons”:,“planChoices”:},“isExpected”:true}

Does this stop you from using Cursor

Sometimes - I can sometimes use Cursor

2

Hey, thanks for the report. This issue has come up before, so let’s try a few fixes:

  1. Settings > search for “HTTP/2” > enable “Disable HTTP/2”, then restart Cursor.
  2. Run this in a terminal: cursor --disable-extensions. A new window will open, then test Agent. If this helps, remove extensions one by one to find the problematic one. More details: SLOW or NO response from the agent
  3. Settings > Network > Run Diagnostics, then share a screenshot of the results.
  4. Create a new chat and try the request again.
  5. If you use MCP servers, a VPN/proxy, or Zscaler/CrowdStrike, disable them and test again.

If the issue still happens, please send:

  • 2 to 3 new Request IDs right after the error
  • Which tool fails and the exact steps to reproduce
  • Pick a specific model instead of Auto, and tell us which models reproduce the issue
  • Output from Help > Toggle Developer Tools > Console, especially any red errors
  • Your list of installed extensions

Let me know if disabling HTTP/2 or running without extensions helped.