Agent turn ends after a tool result and never sends the reply

The agent loop stops after a tool result and never sends the reply. The answer is already in the tool output. A follow-up message such as “??” starts a new turn, and the reply comes back immediately from that same result.

What happens

  1. The agent runs a tool (read, search, shell, and so on).
  2. The tool returns the information needed to answer.
  3. The turn ends. No assistant message is shown.
  4. The user has to send another message. That new turn answers from the result that was already available.

Examples from one session

Project: a local Swift package (ChessCore), macOS, Cursor agent chat.

  • Asked whether en passant repetition had tests. The test files had already been read. The turn ended. “stuck?” produced the answer.
  • Asked how en passant state relates to FEN. The relevant source had already been read. The turn ended. Several pings (“do it now”, “R U THERE”) were required.
  • Asked to run the rewrap and reorder skills. The scripts finished, SwiftFormat and SwiftLint were clean, and all 41 tests passed. The turn ended on the git diff. “?” / “??” produced the summary.
  • Asked why BoardTests changed from a struct to an enum. SwiftFormat’s default enumNamespaces rule had already been identified. The turn ended. “??” produced the answer.

Expected

After every tool result, resume the agent until it writes a user-visible message. A project rule cannot fix this, because the model is not invoked again until the user sends another message.

Environment

  • macOS (darwin 25.5)
  • Cursor agent chat in the IDE
  • Model in that session: Grok 4.7
  • Reproduced across several turns in the same chat on 2026-10-14

Hey @IliasKarim,

This was an issue on our side with Grok 4.7 between roughly 06:20 and 07:50 UTC today. The model’s next step was stuck waiting, so the turn looked finished until your follow-up restarted it. It’s been back to normal since then, and we’ve let the team know.

If it happens again, switching to a different model in the model picker should get you moving. A Request ID (chat’s … menu, then Copy Request ID) would also help us check it.

Switching models did not help. The issue appears to be resolved now. However the agents chats have a similar problem that’s unresolved. They get stuck “Planning next moves” after pushing changes. On latest Cursor for Mac, 3.25.9

The Oct 14 stall is cleared. The Agents window in your screenshot is separate, and it’s already covered in Cursor for Mac gets stuck on Planning next moves.

Reload the window with Cmd+Shift+P, then Developer: Reload Window, and reopen the agent. It should show the finished result. You can also open it at cursor.com/agents, which shows the real state.