fix(agent-loop): preserve deferred message boundaries

This commit is contained in:
_Kerman
2026-07-27 18:58:27 +08:00
parent 7c2cf5f0b3
commit 9152858fd7
17 changed files with 253 additions and 76 deletions

View File

@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md
2026-07-22-unified-send-and-coalesced-user-messages.md: 63af2a34a331e0008009457d5dbc5b9381795ace
2026-07-22-unified-send-and-coalesced-user-messages.zh.md: baf81b064899a58ac3d370187135ac99afbbdec7
2026-07-22-unified-send-and-coalesced-user-messages.md: 6936fbfa04c0fdaf1a8786c0465c193e9c285243
2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 3af14359fa01e92f63ae3b3e51dced9a97f6419f

View File

@@ -24,9 +24,11 @@ Separately, `context/message` and `user/message` had converged: the surface proj
**Three inbox events replace agent/queued.** `agent/inbox/enqueue` (an item entered a FIFO), `agent/inbox/dequeue` (the driver claimed one), and `agent/inbox/discard` (`cancel()` dropped pending items) type their `AgentMessage` payload with only the accepted message's returned `id`, content, and source. Enqueue separately carries the resolved `queued | steering` placement captured by the producer at acceptance time, so observers and reconnect mirrors never reconstruct routing from later status or session history. Injection never touches a FIFO and emits none of these. Every FIFO entry publishes an enqueue, including steering submitted by an `agent/turn-stopping` listener, so the ledger stays balanced with its later dequeue or discard. The `dsh-agent` invariant companion asserts FIFO conservation: a per-agent outstanding count that dequeue and discard can never drive negative.
**Admission accepts next-step input without becoming a turn.** The loop opens a private next-step acceptance window before `agent/prompt-submit`, keeps it open through the turn, and closes it before `turn/end`. Steering and injection received during admission therefore remain together in the outbox and join an allowed turn. If admission blocks or fails, a context-only caller batch takes idle injection's immediate append, while steering and context staged beside it remain available to retry; neither path writes the rejected prompt or hook-produced context. Closing the window before `turn/end` preserves the rule that reentrant late steering becomes an independent queued turn. `Agent.acceptsNextStep` exposes whether a `next-step` send would currently join this window; `status` remains the broader activity signal rather than a routing predicate.
**Admission accepts next-step input without becoming a turn.** The loop opens a private next-step acceptance window before `agent/prompt-submit`, keeps it open through the turn, and closes it before `turn/end`. Steering and injection received during admission therefore remain together in the outbox and join an allowed turn. If admission blocks or fails, a context-only caller batch takes idle injection's immediate append, while steering and context staged beside it remain available to retry; neither path writes the rejected prompt. When a later prompt is admitted, retained outbox input enters its turn before that prompt, while input accepted during the current admission remains after the prompt. Closing the window before `turn/end` preserves the rule that reentrant late steering becomes an independent queued turn. `Agent.acceptsNextStep` exposes whether a `next-step` send would currently join this window; `status` remains the broader activity signal rather than a routing predicate.
**One accepted message keeps one representation.** Durable user-role input and additional model-facing context both use `UserMessageData { content, source }` directly; public `AgentMessage` extends it with the correlation `id`, and the loop-private `PendingMessage` extends that with `wakeup`. A queued message that becomes steering enters the outbox as the same `PendingMessage` object, while injected and tool-produced context enters as plain `UserMessageData`. The outbox therefore stores their union directly instead of wrapping steering beside a duplicate copy of its content and source. Provider-native assistant messages remain adapter-owned output types and do not participate in this input hierarchy.
**One accepted message keeps one representation.** Durable user-role input and additional model-facing context both use `UserMessageData { content, source }` directly; public `AgentMessage` extends it with the correlation `id`, and the loop-private `PendingMessage` extends that with `wakeup`. The loop clones and freezes `UserMessageData` before publication, queueing, or immediate append, so later caller or observer mutation cannot change the accepted value. A queued message that becomes steering enters the outbox as the same `PendingMessage` object, while injected and tool-produced context enters as plain `UserMessageData`. The outbox therefore stores their union directly instead of wrapping steering beside a duplicate copy of its content and source. Provider-native assistant messages remain adapter-owned output types and do not participate in this input hierarchy.
**Idle wakeup follows acceptance.** Before publishing enqueue, a waking queued send installs quiescence ownership and schedules driver admission for a microtask that runs after the id returns. Every send in one synchronous caller stack therefore resolves placement against the same pre-admission state, while reentrant cancellation or teardown cannot retire before the scheduled admission settles. Two idle `steer()` calls remain two FIFO turns instead of the first opening an admission window that captures the second.
**cancel gains keepInbox.** `cancel(cause, { keepInbox? })`; callers choose the cause explicitly, and `keepInbox: true` aborts the active turn while preserving queued and steering items (no discard event, and un-started work is not dropped).

View File

@@ -24,9 +24,11 @@ agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`
**三个 inbox 事件取代 agent/queued。** `agent/inbox/enqueue`(一个队列项进入某个 FIFO`agent/inbox/dequeue`(驱动器认领了一个)和 `agent/inbox/discard``cancel()` 丢弃了待处理项)都将各自的 `AgentMessage` 载荷类型限定为仅包含被接受消息所返回的 `id`、内容和来源。enqueue 还会单独携带生产方在接受消息时捕获的已解析 `queued | steering` 放置方式,因此观察方和重连镜像永远不必根据后续状态或会话历史重建路由。注入从不触及 FIFO也不发出这些事件中的任何一个。每一次 FIFO 入队都会发布一个 enqueue 事件,包括 `agent/turn-stopping` 监听器提交的 steering因此账目会与其后的 dequeue 或 discard 保持平衡。`dsh-agent` 的不变量配套断言 FIFO 守恒:一个按 agent 计的未结算计数dequeue 和 discard 永远无法把它压到负数。
**准入接受 next-step 输入,但不会因此成为一个轮次。** 循环会在 `agent/prompt-submit` 前打开一个私有的 next-step 接受窗口,使其贯穿整个轮次,并在 `turn/end` 前关闭。因此,在准入期间收到的 steering 和注入会一起留在 outbox 中并加入获准轮次。如果准入被阻止或失败,仅含调用方上下文的批次会采用空闲注入的立即追加行为,而 steering 及与其一同暂存的上下文仍可重试;两种路径都不会写入被拒绝的提示词或钩子产生的上下文。在 `turn/end` 前关闭窗口,可以保留这样的规则:可重入的晚到 steering 会成为一个独立的排队轮次。`Agent.acceptsNextStep` 会公开一次 `next-step` 发送当前是否会加入该窗口;`status` 仍是更宽泛的活动信号,而非路由判据。
**准入接受 next-step 输入,但不会因此成为一个轮次。** 循环会在 `agent/prompt-submit` 前打开一个私有的 next-step 接受窗口,使其贯穿整个轮次,并在 `turn/end` 前关闭。因此,在准入期间收到的 steering 和注入会一起留在 outbox 中并加入获准轮次。如果准入被阻止或失败,仅含调用方上下文的批次会采用空闲注入的立即追加行为,而 steering 及与其一同暂存的上下文仍可重试;两种路径都不会写入被拒绝的提示词。后续提示词获准时,保留在 outbox 中的输入会先于该提示词进入其轮次,而当前准入期间接受的输入则留在提示词之后。在 `turn/end` 前关闭窗口,可以保留这样的规则:可重入的晚到 steering 会成为一个独立的排队轮次。`Agent.acceptsNextStep` 会公开一次 `next-step` 发送当前是否会加入该窗口;`status` 仍是更宽泛的活动信号,而非路由判据。
**一条已接受消息只保留一种表示。** 持久的用户角色输入和附加的模型可见上下文都直接使用 `UserMessageData { content, source }`;公开的 `AgentMessage` 在此基础上增加用于关联的 `id`,循环私有的 `PendingMessage` 再增加 `wakeup`。一条成为 steering 的排队消息会以同一个 `PendingMessage` 对象进入 outbox而注入和工具产生的上下文则以普通 `UserMessageData` 进入。因此outbox 直接存储这两种类型的联合,而不再把 steering 与一份重复的内容和来源副本包装在一起。提供方原生的助手消息仍是适配器拥有的输出类型,不参与这套输入层级。
**一条已接受消息只保留一种表示。** 持久的用户角色输入和附加的模型可见上下文都直接使用 `UserMessageData { content, source }`;公开的 `AgentMessage` 在此基础上增加用于关联的 `id`,循环私有的 `PendingMessage` 再增加 `wakeup`循环会在发布、入队或立即追加前克隆并冻结 `UserMessageData`,因此调用方或观察方后续的修改无法改变已接受的值。一条成为 steering 的排队消息会以同一个 `PendingMessage` 对象进入 outbox而注入和工具产生的上下文则以普通 `UserMessageData` 进入。因此outbox 直接存储这两种类型的联合,而不再把 steering 与一份重复的内容和来源副本包装在一起。提供方原生的助手消息仍是适配器拥有的输出类型,不参与这套输入层级。
**空闲唤醒在接受之后发生。** 在发布 enqueue 前,一次会唤醒驱动器的排队发送会先取得完全停稳所有权,并把驱动器准入调度到一个会在该次发送返回 id 后运行的微任务中。因此,同一同步调用栈中的每次发送都会基于同一份准入前状态解析放置方式,而可重入的取消或拆除在已调度的准入结算前无法完成退役。空闲时的两次 `steer()` 调用会保留为两个 FIFO 轮次,而不会因第一次调用打开准入窗口而把第二次吸纳进去。
**cancel 新增 keepInbox。** `cancel(cause, { keepInbox? })`;调用方显式选择 cause`keepInbox: true` 会中止活跃轮次,同时保留排队项和 steering 项(不发出 discard 事件,尚未启动的工作也不会被丢弃)。