Where does the bug appear (feature/product)? Cursor IDE Describe the Bug The agent calls a clone model, not the model specified in the card. The agent claims that he did not pass the model argument, which could override the value from the card. I checked the agent-transcripts and the agent indeed did not use model and called the correct subagent_type Steps to Reproduce Unknown. Operating System Windows 10/11 Version Information Version: 3.12.6 (system setup) VS Code Extension API: 1.128.0 Commit: 68ebb3d8033bceeb85416f924ff4bf5ea1220a20 Date: 2026-07-15T19:55:51.646Z 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.256 OS: Windows_NT x64 10.0.22631 For AI issues: which model did you use? GPT-5.6 Terra 1M Max MAX For AI issues: add Request ID with privacy disabled 9e2fe875-8b8d-4a6e-9141-5f462426f17e Does this stop you from using Cursor Sometimes - I can sometimes use Cursor

[2026-07-16_14-10-55] [2026-07-16_14-11-18]

[image] Artemonim: Steps to Reproduce Unknown. Subagent resume broken again

[image] Artemonim: Subagent resume broken again likely repaired Version: 3.12.10 (system setup) VS Code Extension API: 1.128.0 Commit: 24a12dbd9cabf48956ce5bb3dbd234e41385b3d0 Date: 2026-07-16T03:15:48.538Z 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.256 OS: Windows_NT x64 10.0.22631

This lines up with the subagent resume behavior you flagged here (“resume broken again”): when a subagent gets resumed, it can fall back to the parent agent’s model instead of the one it was originally spawned with. That’s the “sometimes” you’re seeing. Fresh spawns use the configured card model (your Grok 4.5 and Composer 2.5 rows look right), while the resumed ones clone the parent (the GPT-5.6 rows, which also drop to Medium effort). This is something we’ve seen reported before, and I’m adding your report to what we’re tracking. I’d hold off on calling 3.12.10 fixed, though. Even when the model label on the card looks correct, a resumed subagent can still run on the parent model underneath, so the label alone isn’t proof. Workaround for now: where the subagent’s model matters, spawn a fresh subagent instead of resuming it. Fresh spawns pick up the configured model correctly. If you want to confirm whether 3.12.10 genuinely fixed it (and not just the label): resume a subagent that’s set to a non-parent model, then check the model actually consumed on your Usage page, or drop a fresh Request ID from that resumed run with privacy disabled. That’ll tell us for sure.

[image] Mohit: If you want to confirm whether 3.12.10 genuinely fixed it (and not just the label): resume a subagent that’s set to a non-parent model, then check the model actually consumed on your Usage page, or drop a fresh Request ID from that resumed run with privacy disabled. That’ll tell us for sure. Yes, I checked the dashboard to check the called model, but I agree that you should pay attention to the problem, this bug has regressed for at least the third time. [image] Mohit: Workaround for now: where the subagent’s model matters, spawn a fresh subagent instead of resuming it. Fresh spawns pick up the configured model correctly. In one of my work flows, I might leave a team of agents working on a list of tasks for hours at a time. resume is a good time and usage saver; and it’s sad to return to the team and see how usage stops saving.

[image] Mohit: I’d hold off on calling 3.12.10 fixed, though. Even when the model label on the card looks correct, a resumed subagent can still run on the parent model underneath, so the label alone isn’t proof. Happened again in 3.12.17. Reasoning effort label incorrect ARID: 7e9773ae-8bab-4531-b64d-8199005e39ce SRID: 6cc9e4fb-5ac2-4084-8cd6-4824dad043c6 [2026-07-17_14-37-04]

Maybe I’m just lucky again, but Terra might resume agents correctly if the chat was initially started with Grok and then switched to Terra. Cursor 3.12.17

Sometimes a clone is called instead of the configured subagent

Support Bug Reports

Artemonim (Artemonim) July 23, 2026, 3:29pm 14

Fixed in 3.13.x Nightly, turned into another bug: Resume to First-Party non-fast models redirects to fast variants - #5 by Artemonim

Topic		Replies	Views
If there is an error in the model name, the Subagent is created as a clone of the Agent Bug Reports openai , subagents	3	116	April 21, 2026
Sub-Agent Model still not deterministic Bug Reports composer , subagents	2	83	September 25, 2026
Subagent configured model not honored Bug Reports anthropic , subagents	2	1105	February 10, 2026
Sub-agent model being ignored and premium models being erroniously used for subagents Bug Reports composer , subagents	1	351	May 16, 2026
Cursor-agent silently falls back to session model when an agent declares an unresolvable model: ID Bug Reports cli , subagents	3	128	August 27, 2026

Sometimes a clone is called instead of the configured subagent

Related topics