The sub-agent will select "Additional Model" when performing the task

Support Bug Reports
, ,
1

In the process of a large task being assigned to different sub-agents, why does the sub-agent choose a model that I have not defined? I clearly defined the Grok model, but it will choose the Sonnet model for me.

2

Hi there!

We detected that this may be a bug report, so we’ve moved your post to the Bug Reports category.

To help us investigate and fix this faster, could you edit your original post to include the details from the template below?

Bug Report Template - Click to expand

Where does the bug appear (feature/product)?

  • Editor, Tab & Chat (autocomplete, Composer, in-editor agent)
  • Terminal & commands
  • Models, pricing & API keys (availability, Auto/Max, BYOK/Bedrock)
  • MCP & tools
  • Cloud Agents & Automations (cursor.com/agents, scheduled/event)
  • BugBot & Code Review
  • Cursor CLI
  • Cursor Mobile
  • Remote (SSH / Dev Containers / WSL)
  • Account, billing & login
  • Something else…

Describe the Bug
A clear and concise description of what the bug is.

Steps to Reproduce
How can you reproduce this bug? We have a much better chance at fixing issues if we can reproduce them!

  1. …
  2. …
  3. …

Expected Behavior
What is meant to happen here that isn’t working correctly?

Screenshots / Screen Recordings
If applicable, attach images or videos (.jpg, .png, .gif, .mp4, .mov)

Operating System

  • Windows 10/11
  • MacOS
  • Linux

Version Information

  • For Cursor IDE: Menu → About Cursor → Copy
  • For Cursor CLI: Run agent about in your terminal
IDE:
Version: 2.xx.x
VSCode Version: 1.105.1
Commit: ......

CLI:
CLI Version 2026.01.17-d239e66

For AI issues: which model did you use?
Model name (e.g., Sonnet 4, Tab…)

For AI issues: add Request ID with privacy disabled
Request ID: f9a7046a-279b-47e5-ab48-6e8dc12daba1
For Background Agent issues, also post the ID: bc-…

Additional Information
Add any other context about the problem here.

Does this stop you from using Cursor?

  • Yes - Cursor is unusable
  • Sometimes - I can sometimes use Cursor
  • No - Cursor works, but with this issue

The more details you provide, the easier it is for us to reproduce and fix the issue. Thanks!

8

Hey there!

Here’s what’s going on: the model you pick in the dropdown sets your main (parent) agent’s model. When that agent delegates work to subagents (via the Task tool), it picks each subagent’s model itself, and right now it can choose a different one (like Sonnet) even while you’re running Grok. So the subagent model isn’t strictly locked to your selection. The orchestrating agent can override it, which is the known behavior here.

A few things that help in the meantime:

  1. Tell the agent to keep subagents on your model. Add a User Rule (Cursor Settings → Rules), or start your prompt with something like: “Always run subagents on the same model as me, and never pass a different model to the Task tool.” It’s a nudge rather than a hard guarantee, but it noticeably cuts down the wrong-model spawns.
  2. Set model: inherit on any custom subagents you’ve defined in .cursor/agents/ so they follow the parent by default. (The orchestrating agent can still request a model per Task call, so pair this with #1.)
  3. Keep an eye on the subagent cards while a task runs. If one starts on a model you didn’t pick, you can cancel it early before it uses much.

More on subagent model config here: Subagents | Cursor Docs

Let me know if that helps!