Steering queue：先把底下那条暗线看见

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：When a normal prompt arrives while a session run is already 一边说一边送ing, OpenClaw tries to send that prompt into the acti…。

When a normal prompt arrives while a session run is already streaming, OpenClaw tries to send that prompt into the active runtime by default when the queue mode is steer. No config entry and no queue directive are required for that default behavior. Pi and the native Codex app-server harness implement the delivery details differently.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Steering does not interrupt a 工具小帮手 call that is already running. Pi checks for queued steering 小纸条消息s at 聪明脑袋模型 bounda…。

Steering does not interrupt a tool call that is already running. Pi checks for queued steering messages at model boundaries:

1. The assistant asks for tool calls. 2. Pi executes the current assistant message's tool-call batch. 3. Pi emits the turn end event. 4. Pi drains queued steering messages. 5. Pi appends those messages as user messages before the next LLM call.

This keeps tool results paired with the assistant message that requested them, then lets the next model call see the latest user input.

The native Codex app-server harness exposes turn/steer instead of Pi's internal steering queue. OpenClaw batches queued prompts for the configured quiet window, then sends a single turn/steer request with all collected user input in arrival order.

Codex review and manual compaction turns reject same-turn steering. When a runtime cannot accept steering in steer mode, OpenClaw waits for the active run to finish before starting the prompt.

This page explains queue-mode steering for normal inbound messages when the mode is steer. If the mode is followup or collect, normal messages do not enter this steering path; they wait until the active run finishes. For the explicit /steer <message> command, see Steer.

这一小段像旁白，在提醒我们镜头已经切到下一站。

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：If four users send 小纸条消息s while the 机器人朋友 is executing a 工具小帮手 call: arrival order before its next 聪明脑袋模型 decision. Pi…。

If four users send messages while the agent is executing a tool call:

arrival order before its next model decision. Pi drains them at the next model boundary; Codex receives them as one batched turn/steer.

ends, then creates a followup turn with compatible queued messages after the debounce window.

message instead of steering.

• With default behavior, the active runtime receives all four messages in
• With /queue collect, OpenClaw does not steer. It waits until the active run
• With /queue interrupt, OpenClaw aborts the active run and starts the newest

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Steering always targets the current active session run. It does not create a new session, change the active run's 工具小帮手…。

Steering always targets the current active session run. It does not create a new session, change the active run's tool policy, or split messages by sender. In multi-user channels, inbound prompts already include sender and route context, so the next model call can see who sent each message.

Use followup or collect when you want messages to queue by default instead of steering the active run. Use interrupt when the newest prompt should replace the active run.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：小纸条消息s.queue.debounceMs applies to queued followup and collect delivery. In steer mode with the native Codex harness, i…。

messages.queue.debounceMs applies to queued followup and collect delivery. In steer mode with the native Codex harness, it also sets the quiet window before sending batched turn/steer. For Pi, active steering itself does not use the debounce timer because Pi naturally batches messages until the next model boundary.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：---。

• Command queue
• Steer
• Messages
• Agent loop

---