fix(agent-loop): address review — quiet-item parking, meta, discard balance

Resolve six review findings on the unified-send change:
- quiet (wakeup:false) queued items no longer un-park the driver; the
  inbox distinguishes hasWakingQueued (drives the loop, idle/quiescence)
  from hasQueued (anything to dequeue), so a lone quiet item parks at idle
  and rides the next waking send. whenIdle/cancel settle off the waking
  signal, so cancelling a parked quiet item no longer hangs whenIdle.
- SendOptions.meta on queued/steering sends now reaches the durable
  user/message and steering/message (was dropped except on injection).
- a terminal agent/turn-stop that drops pending steering emits
  agent/inbox/discard so the enqueue-dequeue-or-discard ledger balances.
- the loop-authored continuation reason is snapshotted and frozen like a
  public send.
- gen-cordis-api collects exported classes (body-stripped) so the now-
  abstract-class Agent and its transitive shapes reappear in the API
  catalog.

Adds regression tests for each and re-records the affected snapshot.

.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml

@@ -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
-2026-07-22-unified-send-and-coalesced-user-messages.md: d88cd60f5c09f7961d7a59dbbd0703abdd26cc1a
-2026-07-22-unified-send-and-coalesced-user-messages.zh.md: d16ed9f763a350e61abc00d3971e4a7711e8f610
+2026-07-22-unified-send-and-coalesced-user-messages.md: e969012c8172bbba78f04943be46b7dc866ccb7f
+2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 35cc183a7c7bfd8a649557e50e6e7d379f8f8193

.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md

@@ -36,6 +36,8 @@ Separately, `context/message` and `user/message` had converged: the surface proj
 
 The delivery surface is now one primitive plus three self-documenting presets, and the (`target` × `wakeup`) matrix makes previously-unreachable combinations explicit. One durable message type serves prompts, injected context, and goal rounds, so the surface projection and every "human prompt?" check simplify to a `source` test. The cost: `Agent` became an abstract class, so object-literal test fakes must supply `followup` and cannot spread a class-typed value without re-casting (prototype methods are non-enumerable); the goal fold's channel split moved from event type to `source.round`; and every consumer that filtered `context/message` now filters `user/message` by source. The turn-enclosure and reconstruction invariants are unchanged — an idle injection still wraps a one-shot turn, now emitting `user/message` instead of `context/message`.
 
+`wakeup` is the "should the model run" signal, so the inbox distinguishes `hasWakingQueued` (drives the loop and idle/quiescence decisions) from `hasQueued` (anything to dequeue): a lone `next-turn`/no-wakeup item stays parked at idle and rides along the next waking send, and `whenIdle`/`cancel` settle quiescence off the waking signal. `SendOptions.meta` on a queued or steering send is carried onto the durable `user/message`/`steering/message`, matching injection. Every FIFO exit publishes exactly one lifecycle event: a terminal `agent/turn-stop` that drops pending steering now emits `agent/inbox/discard` for it, and a loop-authored continuation reason is snapshotted and frozen like a public send. `gen-cordis-api` collects exported classes (body-stripped) so the now-class `Agent` and its transitive shapes still appear in the model-facing API catalog.
+
 ## Related
 
 - [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md) — the one-claimed-message-per-turn rule this builds on.

.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md

@@ -36,6 +36,8 @@ agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`
 
 投递接口现在是一个原语加三个自解释的预设，(`target` × `wakeup`) 矩阵把此前无法表达的组合显式化。一种持久消息类型同时服务提示词、注入的上下文和 goal 轮次，因此对外接口的投影和每一处“是否人类提示词？”检查都简化为一次 `source` 判断。代价是：`Agent` 变成了抽象类，因此对象字面量形式的测试替身必须提供 `followup`，且无法在不重新做类型转换的情况下展开一个类类型的值（原型方法不可枚举）；goal 折叠的通道区分从事件类型改到了 `source.round`；此前过滤 `context/message` 的每个消费方现在改为按来源过滤 `user/message`。轮次封闭与重建的不变量保持不变——空闲状态下的一次注入仍然封装成一个一次性轮次，只是现在发出 `user/message` 而非 `context/message`。
 
+`wakeup` 是“模型是否应当运行”的信号，因此 inbox 区分 `hasWakingQueued`（驱动 loop 以及空闲/静默判定）与 `hasQueued`（是否有任何可 dequeue 的项）：一个孤立的 `next-turn`/no-wakeup 队列项会停泊在空闲状态，并随下一次唤醒 send 一同带出，而 `whenIdle`/`cancel` 依据唤醒信号来结算静默。排队 send 或 steering send 上的 `SendOptions.meta` 会被带到持久的 `user/message`/`steering/message` 上，与注入保持一致。每一次 FIFO 退出都恰好发布一个生命周期事件：一次会丢弃待处理 steering 项的终止性 `agent/turn-stop` 现在会为它发出 `agent/inbox/discard`，而由 loop 生成的继续原因会像一次对外 send 那样被快照并冻结。`gen-cordis-api` 收集导出的类（剥除方法体），因此如今已是类的 `Agent` 及其传递涉及的形状仍会出现在面向模型的 API 目录中。
+
 ## 相关
 
 - [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md)——本决策所依托的“每轮次只认领一条消息”规则。