This worked for me, huge thanks!!
Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
These couple days the IDE is virtually unusable - always “planning next move” and waiting and waiting and waiting. So what’s the point of keep rolling out features? They are useless since Cursor is now unusable. Wonder what happen. I am an ultra - no other people have similar issue?
Steps to Reproduce
No step needed, just send anything to any model - always “planning next move”
Operating System
MacOS
Current Cursor Version (Menu → About Cursor → Copy)
Version: 2.2.14
VSCode Version: 1.105.1
Commit: 1685afce45886aa5579025ac7e077fc3d4369c50
Date: 2025-12-11T01:12:35.790Z
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
Does this stop you from using Cursor
Yes - Cursor is unusable
I’m also experiencing the same issue persistently. Even if I go back to a story point and retry, it doesn’t execute. I must restart the session. This is a serious problem.
same here, this is hapening for me for a quite of days already 
There is a top thread that post the same issue, it still not fixed for couple of days. I’m affected too
Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
Stuck on ‘planning next moves…’
Steps to Reproduce
Open Cursor, start chat, nothing happens & Stuck on ‘planning next moves…’
Indexing always says loading. (NO OPTION TO DELETE & NO PROGRESS BAR FOR INDEXING)
Tried all trouble shooting methods e.g. privacy toggle, restarting, uninstalling, deleting cache, no VPN etc…
Interesting old chats work sometimes, the odd chat works in about 1 in 100.
I had this issue about a week and a bit ago and now its back.
Need a hard delete of all prior indexes…
Expected Behavior
Agent plans next moves and begins implementing changes
Operating System
Windows 10/11
Current Cursor Version (Menu → About Cursor → Copy)
Version: 2.1.50 (system setup)
VSCode Version: 1.105.1
Commit: 56f0a83df8e9eb48585fcc4858a9440db4cc7770
Date: 2025-12-06T23:39:52.834Z
Electron: 37.7.0
Chromium: 138.0.7204.251
Node.js: 22.20.0
V8: 13.8.258.32-electron.0
OS: Windows_NT x64 10.0.26200
For AI issues: which model did you use?
ALL MODELS
For AI issues: add Request ID with privacy disabled
n/a
Additional Information
Indexing, .cursorignore etc are all set up properly.
Sometimes if you wait long enough the chat stops and I see ‘no files’ underneath the chat name…
Does this stop you from using Cursor
Yes - Cursor is unusable
I love Cursor, but where is the team on this? I see over 5,000 people have commented on this issue, yet there hasn’t been a single response from the big dog devs (except make a bug report). It’s been reported for over a month with no patch, and the editor has been unusable for me for a week. Really losing time over this and less important but its eating into me Xmas break! lol
Hi @TutukakaCoder,
I saw your post in the other thread:
Glad to hear you got it sorted. The team is continuing to work on this, and confirmation of workarounds helps us get closer to a real solution.
I’ve got the same bug, but it’s only with Anthropic and google models. It implements the code really quickly, but then goes to planning next moves for about 5-10 minutes at a time
Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
The AI agent (in Agent Mode or Composer) gets permanently stuck at the “Planning next moves” (or “Planning next actions”) stage, with the animation running forever, without proceeding, throwing an error, or completing the request. This happens on simple or complex prompts (e.g., “2+2” or code tasks like “generate a FastAPI endpoint”). No Request ID is generated because it never finishes – it just spins the loader indefinitely.
This started about 3 days ago and persists across all models tested . It’s not specific to one provider.
What I’ve Already Tried (without success):
Switched networks/internet (WiFi > 4G > Ethernet, DNS to 8.8.8.8).
Restarted the app, cleared cache (Settings > Advanced > Clear Cache), killed processes in task manager.
Reinstalled Cursor from scratch (uninstalled + fresh download).
Ran Network Diagnostics (Settings > Network): All OK (low ping, no connection/VPN errors).
Disabled Privacy Mode, switched models/providers multiple times.
Checked API/sub limits (Pro+ active, no rate limits hit).
No VPN, firewall temporarily disabled, OS updated.
This is killing my workflow – can’t code without the agent. Anyone else hitting this? Team, this seems like server overload or a bug in the planning logic? Please prioritize!
Steps to Reproduce
Open Cursor.
Go to Chat/Composer/Agent Mode.
Type any prompt (e.g., “Explain how an inclined plane works in Physics”).
Submit – the agent shows “Planning next moves” and animates, but hangs forever (tested for >10min).
Try canceling/restarting: It sometimes responds once, but hangs again on the next prompt.
Operating System
Windows 10/11
Current Cursor Version (Menu → About Cursor → Copy)
VS Code Version: 1.105.1
Commit: 6042bed27e57543e04a8dc53c4e5be260
Date: 2025-11-27T03:49:28Z (6 hrs ago)
Chromium: 137.0.7204.251
Node.js: 22.20.0
V8: 13.8.258.32-electron.0
OS: Windows_NT x64 10.0.26100
Version: 2.139 (system setup)
VSCode Version: 1.105.1
For AI issues: which model did you use?
All models doesn’t work.
Does this stop you from using Cursor
Yes - Cursor is unusable
Hey, thanks for the report. This looks very similar to a recently solved case where extensions were causing the same infinite “Planning next moves” delay, even though network diagnostics suggested otherwise.
Try this first:
- Run
cursor --disable-extensionsin CMD or terminal - In the new window that opens, don’t open a project - instead open Agent chat directly
- Check if the agent responds
- If it works, go to the Extensions panel and remove extensions one by one to find the culprit
Full solution here: SLOW or NO response from the agent
If that doesn’t help, also try:
- Fully close Cursor → open a different project → then reopen your original project (this fixed a similar case)
- Check if you have MCP servers configured (Settings → search “MCP”) and temporarily disable them
If still stuck, please share:
- Which extensions you have installed (if any)
- Console errors:
CMD+Shift+P→ “Developer: Toggle Developer Tools” → Console tab (screenshot any red errors) - Try creating a brand new empty folder project and test there
Let me know what happens!
It still doesn’t work and I don’t have any MCP servers configured and I’ve already tried to open different projects. Locally the AI Agents is working normally, the problem is when i connect to SSH the agents starts to slow down, planning next moves forever and when it works it comes to connection error.
Update: Post-clean install, only on remote SSH/VPS, see console errors attached
1. Erros de Segurança/Trusted Types (Não Críticos, mas Recorrentes)
-
This document requires ‘TrustedScript’ assignment. Stack:
-
workbench.desktop.main.js:542 (get value)
-
workbench.desktop.main.js:542 (anonymous)
-
workbench.desktop.main.js:562 (n)
-
workbench.desktop.main.js:542 (anonymous)
-
workbench.desktop.main.js:564 (n)
-
workbench.desktop.main.js:542 (ZodObject)
-
workbench.desktop.main.js:542 (Xrh)
-
out-build/vs/platform/experiments/common/experimentConfig.gen.js
-
workbench.desktop.main.js:564 (anonymous)
-
out-build/vs/workbench/services/experiment/browser/experimentService.js
-
workbench.desktop.main.js:564 (anonymous)
-
out-build/vs/workbench/contrib/composer/browser/composerDataService.js
-
workbench.desktop.main.js:564 (anonymous)
-
out-build/vs/workbench/services/aiSettings/browser/aiSettingsService.js
-
workbench.desktop.main.js:565 (anonymous)
-
out-build/vs/workbench/contrib/aiReactiveContextKeys/browser/aiReactiveContextKeys.contribution.js
-
workbench.desktop.main.js:565 (anonymous)
-
workbench.desktop.main.js:6120 (anonymous)
-
-
The JavaScript Function constructor does not accept TrustedString arguments. Link: https://github.com/w3c/webappsec-trusted-types/wiki/Trusted-Types-for-function-constructor-for-more-information. (Repetido em workbench.desktop.main.js:542)
2. Warnings de Configuração/Migração (Baixa Prioridade)
-
WARN Missing property “rpcFileLoggerFolder” in oldValue. Filling with value from initValue. Please add a migration if necessary. Stack:
-
workbench.desktop.main.js:55 (warn)
-
workbench.desktop.main.js:55 (hydrateOldValue)
-
workbench.desktop.main.js:7325 (getOldValue)
-
workbench.desktop.main.js:7325 (loadPersistentStorage)
-
workbench.desktop.main.js:7325 (zzt)
-
workbench.desktop.main.js:7325 (_createInstance)
-
workbench.desktop.main.js:7392 (anonymous)
-
workbench.desktop.main.js:50 (_executor)
-
workbench.desktop.main.js:7392 (get value)
-
workbench.desktop.main.js:50 (get)
-
workbench.desktop.main.js:7392 (migrateIfNecessary)
-
workbench.desktop.main.js:541 (fYn)
-
workbench.desktop.main.js:7392 (_createInstance)
-
workbench.desktop.main.js:7392 (anonymous)
-
workbench.desktop.main.js:50 (_executor)
-
workbench.desktop.main.js:7392 (get value)
-
workbench.desktop.main.js:50 (get)
-
workbench.desktop.main.js:536 (Yeh)
-
workbench.desktop.main.js:541 (EYn)
-
workbench.desktop.main.js:7392 (_createInstance)
-
workbench.desktop.main.js:7392 (anonymous)
-
workbench.desktop.main.js:50 (_executor)
-
workbench.desktop.main.js:7392 (get value)
-
workbench.desktop.main.js:50 (get)
-
workbench.desktop.main.js:6995 (too)
-
workbench.desktop.main.js:7392 (_createInstance)
-
workbench.desktop.main.js:7392 (anonymous)
-
workbench.desktop.main.js:50 (_executor)
-
workbench.desktop.main.js:7392 (get value)
-
workbench.desktop.main.js:50 (get)
-
workbench.desktop.main.js:564 (_initializeStatsigClient)
-
workbench.desktop.main.js:564 (_hydrateStatsigClient)
-
workbench.desktop.main.js:564 (_initFromCachedBootstrap)
-
workbench.desktop.main.js:564 (eZn)
-
workbench.desktop.main.js:7392 (_createInstance)
-
workbench.desktop.main.js:7392 (_createServiceInstance)
-
workbench.desktop.main.js:7392 (_createServiceInstanceWithOwner)
-
workbench.desktop.main.js:7392 (_createAndCacheServiceInstance)
-
workbench.desktop.main.js:7392 (_safeCreateAndCacheServiceInstance)
-
workbench.desktop.main.js:7392 (_getOrCreateServiceInstance)
-
workbench.desktop.main.js:7392 (get)
-
workbench.desktop.main.js:8929 (_setupTracing)
-
workbench.desktop.main.js:8929 (anonymous)
-
workbench.desktop.main.js:7392 (invokeFunction)
-
workbench.desktop.main.js:8929 (initServices)
-
workbench.desktop.main.js:8929 (startup)
-
workbench.desktop.main.js:8933 (open)
-
-
WARN [ms-python.python]: Cannot register ‘python.venvPath’. This property is already registered. (workbench.desktop.main.js:55)
3. Warnings de Extensões (API Proposals Ausentes – Comum em Beta)
-
Via ‘product.json#extensionEnabledApiProposals’ extension ‘ms-toolsai.datawrangler’ wants API proposal ‘debugFocus’ but that proposal DOES NOT EXIST. (Repetido para: ms-vscode.vscode-copilot-data-analysis (‘chatVariableResolver’), ms-python.python (‘terminalShellType’), ms-python.vscode-python-envs (‘terminalShellType’), github.copilot-chat (‘chatReadonlyPromptReference’), ms-azuretools.vscode-azure-github-copilot (‘lmTools’), vscjava.vscode-java-pack (‘lmTools’), apidev.azure-api-center (‘chatParticipant’ e ‘languageModels’)) Stack comum:
-
workbench.desktop.main.js:55 (warn)
-
workbench.desktop.main.js:8932 (anonymous)
-
workbench.desktop.main.js:8973 (Uxo)
-
workbench.desktop.main.js:7392 (_createInstance)
-
workbench.desktop.main.js:7392 (createInstance)
-
workbench.desktop.main.js:8977 (qxo)
-
workbench.desktop.main.js:7392 (_createInstance)
-
workbench.desktop.main.js:7392 (_createServiceInstance)
-
workbench.desktop.main.js:7392 (_createServiceInstanceWithOwner)
-
workbench.desktop.main.js:7392 (_createAndCacheServiceInstance)
-
workbench.desktop.main.js:7392 (_safeCreateAndCacheServiceInstance)
-
workbench.desktop.main.js:7392 (_getOrCreateServiceInstance)
-
workbench.desktop.main.js:7392 (get)
-
workbench.desktop.main.js:8929 (_setupTracing)
-
workbench.desktop.main.js:8929 (anonymous)
-
workbench.desktop.main.js:7392 (invokeFunction)
-
workbench.desktop.main.js:8929 (initServices)
-
workbench.desktop.main.js:8929 (startup)
-
workbench.desktop.main.js:8933 (open)
-
4. Erros de Lock e Inicialização
- The customer named _initialize has been holding on to the lock for 30s. This might be a problem. (workbench.desktop.main.js:8971)
5. Erros de Terminal e Remote Host (Relacionado ao VPS)
-
[TerminalExecutionServiceProxy] v3 health check failed (took 205ms/177ms/233ms)
- Staying with current version / Cannot switch to v3. (workbench.desktop.main.js:9303)
-
ERR The remote extension host took longer than 60s to send its ready message. Stack:
-
workbench.desktop.main.js:55 (ERR Error received from starting extension host (kind: Remote))
-
workbench.desktop.main.js:55 (ERR)
-
workbench.desktop.main.js:8932 (error)
-
workbench.desktop.main.js:6948 (anonymous)
-
-
WARN No search provider registered for scheme: vscode-remote, waiting (workbench.desktop.main.js:55, stack com searchWithProviders em 8971)
-
ERR Error received from starting extension host (kind: Remote) (workbench.desktop.main.js:55)
6. Timeouts de Requests (Direto no Planning/AI)
-
ERR Request 1/13/25/37 timed out (15000ms) Stack comum:
-
workbench.desktop.main.js:55 (ERR)
-
workbench.desktop.main.js:55 (error)
-
workbench.desktop.main.js:8932 (error)
-
workbench.desktop.main.js:8929 (handleUnexpectedError)
-
workbench.desktop.main.js:8929 (anonymous)
-
workbench.desktop.main.js:27 (onUnexpectedError)
-
workbench.desktop.main.js:22 (Wa)
-
workbench.desktop.main.js:22 (anonymous)
-
workbench.desktop.main.js:8929 (anonymous)
-
7. Erros de Conexão AI/Transport (Vilão Principal – DNS/Outage?)
-
[transport] Connect error in unary AI connect ConnectError: [deadline_exceeded] the operation timed out Stack:
-
workbench.desktop.main.js:6995 (error)
-
workbench.desktop.main.js:6331 (t)
-
workbench.desktop.main.js:565 (async Object.checkNumberConfig)
-
workbench.desktop.main.js:7025:6196 (async)
-
workbench.desktop.main.js:7025:5955 (async n)
-
workbench.desktop.main.js:7025:6179 (async aoo.maybeRefreshConfigInner)
-
workbench.desktop.main.js:7025:5568 (async aoo.getLatestConfig)
-
-
[transport] Connect error in unary AI connect ConnectError: [unauthenticated] Error Stack:
-
workbench.desktop.main.js:6995 (error)
-
workbench.desktop.main.js:6331 (t)
-
workbench.desktop.main.js:565 (async Object.getTeamCommands)
-
workbench.desktop.main.js:8979:2992 (async Zxo.loadTeamCommands)
-
-
Failed to load team commands: ConnectError: [unauthenticated] Error (workbench.desktop.main.js:8979)
-
[transport] Connect error in unary AI connect ConnectError: [unavailable] getaddrinfo ENOTFOUND api2.cursor.sh (NOVO – Erro de DNS/Resolução!) Stack repetida várias vezes:
-
workbench.desktop.main.js:6995 (error)
-
workbench.desktop.main.js:6331 (t)
-
Variações: reportClientNumericMetrics (6948:14240, flush Qro), getTeams (8903:35130, refreshMembership h0o), markPrivacy (8903:21001, initialRetryTimeMs vct)
-
Extension Host rejected promise: workbench.desktop.main.js:6299 (vXh)
-
[anysphere.cursor-always-local][unavailable] getaddrinfo ENOTFOUND api2.cursor.sh
-
Stack completa: o.from (c:\Program Files\cursor\resources\app\extensions\cursor-always-local\dist\main.js:2:810432), B (2:3169699), ClientHttp2Session.a (2:3178631), emit (node:events:519:28), emitClose (node:internal/http2/core:1164:10), processTicksAndRejections (node:internal/process/task_queues:90:21)
-
-
ERR [unavailable] getaddrinfo ENOTFOUND api2.cursor.sh: ConnectError (workbench.desktop.main.js:55)
-
ERR An unknown error occurred. Please consult the log for more details. (Repetido, ligado aos de cima)
8. Erros de Git e KnowledgeBase
-
[KnowledgeBaseService] Error fetching git upstream URL: Error: No full commit provider registered Stack:
-
workbench.desktop.main.js:2876 (getGitUpstreamUrl)
-
workbench.desktop.main.js:542:320323 (nXn.getGitUpstreamURL)
-
workbench.desktop.main.js:2876:35921 (Qgs.getGitUpstreamUrl)
-
workbench.desktop.main.js:2876:36243 (Qgs.refresh)
-
-
WARN Failed to get current repository URL: Error: No full commit provider registered Stack similar, com h0o.getCurrentRepoUrl (8903:35478), getSlackInstallUrl (8903:35676), async u (2806:146577)
9. Erros de Composer (Direto no Planning)
- [composer] Error in getPopulatedContext: EntryNotFound (FileSystemError): Error: ENOENT: no such file or directory, stat ‘/root/.cursor/projects/root/terminals/2.txt’ (workbench.desktop.main.js:4075, anonymous)
10. Outros Warnings/Erros Menores
-
Automatic fallback to software WebGL has been deprecated. Link: about:flags#enable-unsafe-swiftshader (workbench.html:1)
-
GL Driver Message (OpenGL, Performance, GL_CLOSE_PATH_NV, High): GPU stall due to ReadPixels (Repetido, workbench.html:1)
-
ERR CloseEvent (Repetido, workbench.desktop.main.js:55)
Thanks for the detailed console logs - they clearly show the issue! Your VPS can’t resolve api2.cursor.sh (DNS lookup failing with ENOTFOUND). This explains why it works locally but not on your remote server.
Could you run these commands on your VPS to confirm?
nslookup api2.cursor.sh
or
dig api2.cursor.sh
If DNS lookup fails:
- Check if your VPS has firewall rules blocking certain domains
- Try changing VPS DNS to
8.8.8.8or1.1.1.1(Google/Cloudflare DNS) - Contact your VPS provider - some hosting providers restrict DNS resolution or have network policies blocking certain domains
If DNS lookup succeeds (domain resolves but Cursor still fails):
- Share the output of the DNS commands above
- Let me know your VPS provider and location
Troubleshooting the extension won’t help here since your local Cursor works fine - this is specifically a network connectivity issue from your VPS to Cursor’s servers.
Since yesturday before i update to latest version 2.1.46 i experience the same issue.
- I’ve disable all extensions with the command –disable-extensions;
- I’ve disable all MCP servers
- I’ve switch from HTTP1 to HTTP2
- I’ve started a new context with a new folder opened
- Flushed “ipconfig /flushdns” from Windows
- Added 1.1.1.1 into Primary DNS (even if All Network Diagnostics is 100% fine)
Cursor v 2.1.46 with VSCode 1.105.1
Confirmation that all extensions are disabled:
API ‘nslookup’ api2.cursor.sh is working:
Network Diagnostics:
Note: The only difference is i worked with a Network Share Folder that is opened into Cursor, but never get an issue and don’t think it’s related to this.
Updates:
I’ve installed a previous version 2.0 and same issue but.. opening a working folder on a network shared folder and working from it seem’s to be the issue.
I’ve opened the same folder into my own PC which is on a local HDD into Laragon\www\ is working fine.
See the context chat, the header resume that the AI are generated the title of the chat resume, but not been able to working further (in Green the resume of the chat request) and (in Red the error stucked “Planning next moves”).
It could be that the AI can’t read the files? But the folder opened fine in workspace and same with VSCode with Gemini CLI.
Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
First (and subsequent messages on previous chats) when submitted are stuck at “planning next moves” (or steps or actions or whatever, I already downgraded).
Codebase indexing stuck at “Loading”.
Reverting to 2.1.50 restored normal behavior.
Steps to Reproduce
Send any agent chat.
Operating System
MacOS
Current Cursor Version (Menu → About Cursor → Copy)
2.2.9
SSH connection to Ubuntu
For AI issues: which model did you use?
Opus 4.5
Does this stop you from using Cursor
Yes - Cursor is unusable
Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
Whenever the models go to planning next moves they get stuck for about 5-10 minutes at a time
Steps to Reproduce
Use Gemini or Anthropic models.
Expected Behavior
Only go to planning next moves for 1 minute max.
Operating System
MacOS
Current Cursor Version (Menu → About Cursor → Copy)
Version: 2.1.50
VSCode Version: 1.105.1
Commit: 56f0a83df8e9eb48585fcc4858a9440db4cc7770
Date: 2025-12-06T23:39:52.834Z
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?
All of the Anthropic and Google models. Composer 1 is fine.
Additional Information
It will implement the code quickly, but the "planning next moves"part between code implementations is just incredibly slow.
I’ve tried disabling all my mcp’s, creating a new project. Disabling all my rules. My network diagnostics look completely fine. There’s something going on between Cursor and the model providers.
Does this stop you from using Cursor
Yes - Cursor is unusable
Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
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)
Version: 2.1.39 (Universal)
VSCode Version: 1.105.1
Commit: 60d42bed27e5775c43ec0428d8c653c49e58e260
Date: 2025-11-27T02:30:49.286Z (2 days ago)
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?
Same for all
Does this stop you from using Cursor
Yes - Cursor is unusable
I’ve got the same issue, but only with the Anthropic models.