GLM 5.2 don't think all the time

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Using the cursor-built-in GLM 5.2 MAX, the model never thinks all the time during a session.

Steps to Reproduce

just use build-in GLM 5.2 max and start a job, you will find it doesn’t think.

Expected Behavior

It should think.

Operating System

MacOS

Version Information

Version: 3.8.23
VS Code Extension API: 1.105.1
Commit: 7cf19b7482706625cdb70db3211b7dd035b7aa30
Date: 2026-06-23T14:57:42.334Z
Layout: glass
Build Type: Stable
Release Track: Default
Electron: 40.10.3
Chromium: 144.0.7559.236
Node.js: 24.15.0
V8: 14.4.258.32-electron.0
xterm.js: 6.1.0-beta.256
OS: Darwin arm64 25.5.0

Does this stop you from using Cursor

No - Cursor works, but with this issue

indeed, I had 1 conversation in which glm max didn’t show thinking trace and seemed to answer directly, sharing a request id for tracing purpose, would love to get the whys :

63977e07-729a-41d0-abe8-c690f3fdc12f

btw @Li_Chuyang it would be useful if you share the request ID too, so that team will be able to look into it!

I have the same issue.

Version: 3.8.11 (system setup)
VS Code Extension API: 1.105.1
Commit: e56ad3440df06d22ca7501e65fd518e905486ef0
Date: 2026-06-18T01:40:18.333Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 40.10.3
Chromium: 144.0.7559.236
Node.js: 24.15.0
V8: 14.4.258.32-electron.0
xterm.js: 6.1.0-beta.256
OS: Windows_NT x64 10.0.26200

Tried both high and max reasoning effort, none of them showed thinking blocks.

request ID: 6c644f6e-4d1f-4fbc-b663-83c74c5c699c

Hey all!

Thanks for reporting this.

The thinking is happening, but a UI bug means that it’s not being displayed in chat. We’re working on a fix.