Too many wrap lines

[tangjun]

Describe the Bug

there are too many wrap line in chat response.

Steps to Reproduce

when chat with AI, use kimi-k2 mode, it shows too many text wrap, difficult to read.

Screenshots / Screen Recordings

Operating System

Windows 10/11

Current Cursor Version (Menu → About Cursor → Copy)

Version: 1.2.4 (user setup)
VSCode Version: 1.99.3
Commit: a8e95743c5268be73767c46944a71f4465d05c90
Date: 2025-07-10T17:09:01.383Z
Electron: 34.5.1
Chromium: 132.0.6834.210
Node.js: 20.19.0
V8: 13.2.152.41-electron.0
OS: Windows_NT x64 10.0.22631

Additional Information

Request id:
0da5fcb1-95d6-4a99-9395-1f477554c69a

Does this stop you from using Cursor

No - Cursor works, but with this issue

[tangjun]

same to this:

Kimi K2 is now on Cursor - Consider Provider

there is currently a bug with kimi after some time in its answer it breaks request id if it helps a8848a3b-9f19-4e05-a18e-eba0138f446d [obraz]

[condor]

Thanks @tangjun this is a know issue and Cursor Team is looking into it.

Please avoid creating duplicate posts as this requires more threads to be processed and makes it harder to reach all user requests.

[tangjun]

sorry, I don’t know it is a duplicate post, before I create this new post. You can delete this topic later.

[condor]

No worries appreciate your detailed post!

[Ksneu]

Hi, would like to follow up with this

[condor]

hi @Ksneu we are still looking into this, though it does not occur on all Kimi K2 requests.

Could you post a Request ID with privacy disabled so we can look into the details? Cursor – Getting a Request ID

[Ksneu]

Hi, no, my company doesn’t allow non-privacy mode.

Would like to follow up, cuz it’s been 1 month (30 days) since this is opened. Wondering if this is a model limitation (Kimi couldn’t call tools correctly), or libraries issues, or provider issues?

[condor]

For now it is a model limitation which we have not yet resolved from our side. Some users reported that closing the chat and reopening the chat fixes the output formatting.