fix(subagent): make strict steering atomic

packages/core/agent/README.md

@@ -65,6 +65,7 @@ The handle every plugin programs against:
 - `agent.updateInbox(itemId, action)` — synchronously edits or removes one still-pending queued occurrence. Edit keeps its `MessageId`, `InboxItemId`, source, and FIFO position while replacing frozen content; remove emits the occurrence's terminal discard. Steering and claimed occurrences return `not-found`.
 - `agent.followup(input)` — the `next-turn`/wakeup preset of `send()`: queue an ordinary follow-up turn and wake the driver.
 - `agent.steer(input)` — the `next-step`/wakeup preset: during prompt admission or an open turn, stage steering for the next safe boundary without dispatching `agent/prompt-submit`; outside that acceptance window, delegate to a woken follow-up. Admission failure leaves staged steering for retry or a later admitted prompt, while cancellation or disposal may discard it.
+- `agent.trySteer?(input)` — an optional strict-steering capability implemented by the default loop. It atomically submits an identified message only while the current step still owns its final drain, returning `false` without accepting input during admission, between steps, or after that drain begins; cancellation and disposal can still discard accepted steering.
 - `agent.inject(input)` — the `next-step`/no-wakeup preset: append model-facing context without running the model; the next request sees a verbatim user-role message whose provenance is carried by the required `input.source`. During prompt admission or an open turn, injection waits in the outbox for the next safe boundary. Outside that acceptance window, it appends immediately without opening a turn; a context-only admission batch takes this fallback if admission closes without a turn, while context staged beside steering remains pending with it. Persistence reacts to `session/event` independently. Injection emits no `agent/inbox/*` event.
 - `agent.acceptsNextStep` — whether a `next-step` send would currently join prompt admission or the open turn. Use this narrower routing predicate when a caller must choose between steering and a fresh admitted prompt; `status === 'running'` also covers admission exit and turn settlement.
 - `agent.cancel(cause, options?)` — cancel the active turn and, unless `options.keepInbox`, ALL pending work. Callers must choose the `user | parent` cause explicitly; an active holder copies its discriminant into a detached frozen signal reason before aborting. An effective call emits `agent/cancel-requested` with the cause before clearing queued and steering work; dropped items are reported on `agent/inbox/discard`, and observers may synchronize state but cannot veto cancellation. `keepInbox: true` aborts the turn but preserves queued and steering items (no discard, and un-started work is not dropped). The same-process typed seam adds no runtime validation or compatibility fallback for untyped callers. Repeated active-turn cancellation is first-wins for the signal, and idle cancellation is a safe no-op with no notification. ACP maps to `user`, while in-process parent propagation maps to `parent`. The cause is runtime-only; durable `turn/end` stays coarse `aborted`.

packages/core/agent/src/types.ts

@@ -236,6 +236,16 @@ export interface Agent {
    */
   steer(message: UserMessage): void
 
+  /**
+   * Atomically submit steering only while the current step still owns its final
+   * drain. Returns `false` without accepting the message during admission,
+   * between steps, or after the final per-step drain has begun. Cancellation or
+   * disposal may still discard previously accepted steering.
+   * @param message - identified steering content and its producer provenance.
+   * @returns whether the message entered the current step.
+   */
+  trySteer?(message: UserMessage): boolean
+
   /**
    * Append model-facing context without running the model — the
    * `next-step`/no-wakeup preset of {@link send}. Admission or an open turn