Describe the Bug
Kimi K3, acting as the leader throughout the session, invokes the preconfigured subagent model: grok-4.5[effort=high,fast=false] exclusively in fast mode.
Steps to Reproduce
Just using broken again Cursor?
Screenshots / Screen Recordings
Operating System
Windows 10/11
Version Information
Version: 3.15.1 (system setup)
VS Code Extension API: 1.128.0
Commit: 41c5e281845de0ce890a8053a3874064bfbdb8b0
Date: 2026-08-04T06:41:23.990Z
Layout: IDE
Build Type: Stable
Release Track: Nightly
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.291
OS: Windows_NT x64 10.0.22631
For AI issues: which model did you use?
Kimi-K3-Max, Grok-4.5-High
For AI issues: add Request ID with privacy disabled
938f31c1-6ef8-4326-9f34-90156e61815e Privacy On
Additional Information
See also:
- The chat with the subagent won't load until the subagent is finished
- Resume to First-Party non-fast models redirects to fast variants
- Subagent `resume` runs an incorrect model
Does this stop you from using Cursor
Sometimes - I can sometimes use Cursor
