Cursor TypeScript SDK: `run.steer()` on a cloud agent returns `revert_to_followup` instead of `complete_delivered` (expected for cloud; send a follow-up with `agent.send()`)

Context

Source(s): https://forum.cursor.com/t/cloud-agents-mid-run-steer-works-in-the-ts-sdk-locally-but-not-on-cloud/174463 Signal: 32 views; staff answer accepted (2026-10-14), confirming the original poster's local-versus-cloud test. Status: reported working by source, not reproduced by us (workaround only; root fix not confirmed).

Problem

With @cursor/sdk 1.0.37, calling run.steer() about 12 seconds into a long-running agent run delivers the message mid-turn on a local agent (complete_delivered, the same run keeps going), but on a cloud agent it returns revert_to_followup: the message is not delivered and you have to wait for the turn to finish. The Python SDK (cursor-sdk 1.0.37) has no Run.steer method at all, local or cloud.

Error (redacted / normalized)

Cloud: run.steer() → revert_to_followup

Applies when

Cursor TypeScript SDK @cursor/sdk and Python SDK cursor-sdk, both 1.0.37, model { id: "default" }, cloud agents, 2026-10-12.

Confirm it is this problem

1. Start a long-running cloud agent run with the TypeScript SDK and call run.steer() while it is still streaming. → expect: revert_to_followup.
2. Do the same on a local agent. → expect: complete_delivered.

Not this when / boundary

You are using the Python SDK, which has no steer method to call; only the follow-up route is left there (our inference).

Root cause

Per Cursor staff: this is the current behavior for cloud agents, as the TypeScript SDK docs describe, not something broken on your side. Mid-run steering for cloud agents over the SDK and REST API is a tracked feature request, and the missing Python steer is a separate gap passed to the team. Staff also agreed the launch post's wording reads as ambiguous for cloud.

Fix

1. When run.steer() returns revert_to_followup on a cloud agent, wait for the turn to finish and send your message as a follow-up with agent.send() (the original poster's workaround, consistent with the staff answer).
2. If feedback must land mid-run, run that agent locally, where run.steer() returned complete_delivered in the original poster's test (our inference that this suits your setup). → expect: the message lands in the same run.

How to verify

The follow-up sent with agent.send() is picked up after the turn ends; for local agents, run.steer() returns complete_delivered.

What did not work

None reported; there is no setting that makes cloud steer deliver mid-run.

Risks

Cancelling and restarting a run instead of waiting loses its progress and can repeat tool calls that aren't idempotent (the original poster's concern); prefer the follow-up (our inference).

Verified scope

Cursor SDK 1.0.37 (TypeScript and Python), cloud agents, October 2026.

Becomes obsolete when

Cursor's cloud agents accept mid-run steer through the SDK or REST API (staff: no ETA, updates go to the consolidated feature request thread).