Persistent Provider Error

Support Bug Reports
,
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

For the past 3 hours, I keep getting the following issue:

{“error”:“ERROR_PROVIDER_ERROR”,“details”:{“title”:“Provider Error”,“detail”:“We’re having trouble connecting to the model provider. This might be temporary - please try again in a moment.”,“isRetryable”:false,“additionalInfo”:{},“buttons”:,“planChoices”:},“isExpected”:true}
Provider Error We’re having trouble connecting to the model provider. This might be temporary - please try again in a moment.
Svs: Provider Error We’re having trouble connecting to the model provider. This might be temporary - please try again in a moment.
at mg_ (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29432:24260)
at dg_ (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29432:23144)
at wg_ (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29433:6490)
at nCh.run (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29433:11307)
at async lQi.runAgentLoop (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41749:12418)
at async mim.streamFromAgentBackend (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41817:12344)
at async mim.getAgentStreamResponse (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41817:19567)
at async hCt.submitChatMaybeAbortCurrent (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29548:16906)
at async Object.Xa [as onSubmit] (vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:40804:4244)
at async vscode-file://vscode-app/c:/Users/expan/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:40803:102189

Steps to Reproduce

Whenever I write a prompt.

Expected Behavior

the agent start implementing the request.

Operating System

Windows 10/11

Version Information

Version: 3.2.16 (user setup)
VSCode Version: 1.105.1
Commit: 3e548838cf824b70851dd3ef27d0c6aae371b3f0
Date: 2026-04-28T21:07:47.682Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Windows_NT x64 10.0.26200

For AI issues: which model did you use?

Sonner 4.5

For AI issues: add Request ID with privacy disabled

Request ID: 111d78cb-5ba2-4e81-b666-273380c2a8a7

Additional Information

The issue has been persistent for the past 3 hours.

Does this stop you from using Cursor

No - Cursor works, but with this issue

5

Hey, thanks for the detailed report and the Request ID, it helped us track it down fast.

What’s happening: this chat has built up over 200K tokens of context, and the provider that routes claude-sonnet-4-5 cuts off at that limit. Because of that, any next prompt in this same thread fails with a Provider Error, retry won’t help while the conversation is this long.

Workaround: start a new chat and pull context from the old one via @Past Chats. That way the model can see the previous session, but it starts with a clean context window. If you need even more context, you can enable Max mode.

On the inference side, we have open alerts for this routing, I’ll flag to the team that error handling still doesn’t always trigger auto-summarization. For now, @Past Chats in a new thread is the most reliable option.