# Move\_agent\_to\_root AgentMigration clones one chat into two live auto-resumed sessions **URL:** \ **Category:** Bug Reports\ **Tags:** mcp, worktrees, chat\ **Created:** [September 1, 2026, 5:51pm UTC](https://forum.cursor.com/t/move-agent-to-root-agentmigration-clones-one-chat-into-two-live-auto-resumed-sessions/170245 "2026-09-01T17:51:42Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Klaas\_Hulder](https://avatars.discourse-cdn.com/v4/letter/k/c6cbf5/32.png) [@Klaas\_Hulder](https://forum.cursor.com/u/Klaas_Hulder)\ **Post date:** [September 1, 2026, 5:51pm UTC](https://forum.cursor.com/t/move-agent-to-root-agentmigration-clones-one-chat-into-two-live-auto-resumed-sessions/170245/1 "2026-09-01T17:51:42Z")
### Where does the bug appear (feature/product)? Cursor IDE ### Describe the Bug When an agent calls cursor-app-control → move\_agent\_to\_root to switch into a git worktree, Cursor runs [AgentMigration] and copies the conversation into a new composer ID in a new workbench. The source chat is aborted with abortReasonMessage: “migration” but is not torn down. If move\_agent\_to\_root is invoked twice in the same turn (the first call is cancelled by the migration abort, then the agent retries), AgentMigration runs twice about 8 seconds apart. Both clones restore the same history and auto-resume with no user message (isResume: true, textLength: 0). Two same-title agent sessions then keep editing the same worktree in parallel. This is not the documented Fork chat action. Docs say a worktree move continues the same chat. ### Steps to Reproduce 1. Open a long Agent chat in a git repo. 2. Have the agent create a git worktree and call move\_agent\_to\_root to that path (the using-git-worktrees skill does this). 3. Repeat for a second worktree in the same chat. 4. On a later move, if the first move\_agent\_to\_root is cancelled (Tool call was cancelled / abort\_chat\_and\_wait\_for\_finish from beginMigration) and the agent retries the same tool in the same turn, logs show two [AgentMigration] Starting worktree→local migration events with two different composerIds. 5. Both new composers auto-resume. The source composer in the previous workbench can also keep running. ### Expected Behavior One conversation continues in the new worktree. The source composer is stopped. Concurrent or retried move\_agent\_to\_root calls for the same chat must not create a second live clone that auto-resumes. ### Operating System MacOS ### Version Information 3.18.9 (client\_version from Composer structured logs, 2026-09-01) ### For AI issues: which model did you use? grok-4.6 ### For AI issues: add Request ID with privacy disabled 3bcaef47-efb6-481f-92a7-be9b7d7ddc73 5be36c30-90d2-4d4c-aadd-03fac7bcc41c 44b7780a-de6d-48cb-9ca5-f0278f59d7dd ### Additional Information Observed 2026-09-01 ~17:06 local (Europe/Amsterdam) in Cursor structured logs: - 17:06:36 abort source composer ab4537e9 (migration). MCP move\_agent\_to\_root cancelled. - 17:06:37 [AgentMigration] Starting worktree→local migration for composer 17059208. New workbench created (isNewWorkspace: true). - 17:06:45 second abort + second cancelled move\_agent\_to\_root. Second migration starts for composer ee9a9889. - 17:06:46 17059208 migration complete, auto-resume. - 17:06:53 ee9a9889 migration complete, auto-resume. Those two transcripts were identical for the first 294 lines, then both agents kept working on the same branch. Related (same tool, different failure modes): - [Move\_agent\_to\_root MCP fails in git worktrees](https://forum.cursor.com/t/move-agent-to-root-mcp-fails-in-git-worktrees/159576) - [Move\_agent\_to\_root aborts the in-flight turn and never resumes (“Switching workspace root”, then silence)](https://forum.cursor.com/t/move-agent-to-root-aborts-the-in-flight-turn-and-never-resumes-switching-workspace-root-then-silence/169527) Expected fix: continue the same composer (do not mint a new ID), stop the source, and de-dupe in-flight AgentMigration for one conversation. ### Does this stop you from using Cursor Sometimes - I can sometimes use Cursor ---
**Author:** ![mohitjain](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/mohitjain/32/100229_2.png) [@mohitjain](https://forum.cursor.com/u/mohitjain)\ **Post date:** [September 2, 2026, 6:31am UTC](https://forum.cursor.com/t/move-agent-to-root-agentmigration-clones-one-chat-into-two-live-auto-resumed-sessions/170245/7 "2026-09-02T06:31:45Z")
Hey @Klaas_Hulder, We’ve let the team know; it’s an issue we’re tracking. Until it’s sorted, two things help: - Stop the agent before it moves into a worktree. - If extra copies do appear after a move, stop them right away so they don’t keep editing the same worktree in parallel. I’ll post here when there’s an update.