Multi-Repo Workspace Causes Agent turns to terminate early

[Eliott_Williams]

Same problem here move_agent_to_root aborts the in-flight turn and never resumes (“Switching workspace root”, then silence)

Repro

1. Open a multi-root .code-workspace (or any workspace whose environment.id is not the single-folder id of repo A).

2. Start a local Agent chat. Give it a task in repo A.

3. Let the agent call MCP cursor-app-control / move_agent_to_root with rootPath = repo A (even if A is already in the workspace).

4. Observe: “Switching workspace root” → generation ends cancelled → new workbench may open on repo A → no agent.turn.start on the new composer.

   Worktree on a local-only feat/* (never pushed) → git fetch origin <branch> → Remote branch not found on origin.

5. Calling the tool mid-turn (the common case: the tool itself is the in-flight MCP call).

I made another issue with the full detail of the bug and some analysis of the underlying code causing it so that cursor devs can fix this

Move_agent_to_root aborts the in-flight turn and never resumes (“Switching workspace root”, then silence)

Where does the bug appear (feature/product)? Cursor IDE Describe the Bug When a local agent calls move_agent_to_root (UI: “Switching workspace root”), Cursor aborts the current chat, opens a new workspace/composer, restores history as status: “aborted”, then fails to continue the turn. The source conversation is archived. The user sees the spinner, then nothing. This is not just “remote branch not found”. It also happens when the destination folder already exists, is already a workspace folder…