docs: fix review findings — residual ordinals, hypothetical IPC row, citation-rule amendments

Purge the residual task/phase ordinals review caught ((T2), (queue cut 1)
×3, T6, P-I, 'this cut' ×6 including battery-expansion finds in two
untouched notes and a workflow JSDoc); drop the 'externally logged as
Decision 21' parenthetical and rename the remaining bare decision-21
mentions; mark the gui-layering IPC bridge row as a hypothetical example;
restore the GATE_NOTICE doc-typecheck clause and the py-types 'measured'
provenance; say subprocess-backed in filesystem.md; add the picker note
path. Amend the citations note: merged-PR evidence anchors in Agent Notes
are sanctioned, and the candidate gate patterns gain the four shapes the
sweep missed. All nine touched pairs re-recorded.

.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.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 .agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md
-2026-06-21-subagent-capability-seam.md: 82010b4d11d2de5fc00f892b05e73807530e9cbf
-2026-06-21-subagent-capability-seam.zh.md: dc4e35e9ca6de8790b26bda1aeca30af00db5e1d
+2026-06-21-subagent-capability-seam.md: 72f17d7566aa982a5710e466cb4f740906ef167b
+2026-06-21-subagent-capability-seam.zh.md: 8205a6e2eab3bdaddf25b582c590034e2cf2f8dd

.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md

@@ -62,7 +62,7 @@ Each in-process subagent runs in its **own `Session`** (own id, `parentSession`
 
 ### Provider selection is config, not model-facing
 
-`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — no provider/type parameter in the schema this cut.
+`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — the schema carries no provider/type parameter.
 
 ## Testing
 
@@ -72,5 +72,5 @@ Registry and tool tests replace only the nondeterministic child boundary with a
 
 - **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits.
 - **Blocking the parent turn.** Foreground collection holds the parent's step open for the child's full duration. Background delegation uses the shared `ctx.tasks` runtime and generic `task_*` tools, the same collection mechanism as background bash; the subagent seam itself remains task-agnostic.
-- **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
+- **Live progress.** Only lifecycle + the final result surface; a per-chunk child→parent update stream is deferred with the background redesign.
 - **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.

.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md

@@ -62,7 +62,7 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
 
 ### 提供方选择是配置，不面向模型
 
-`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——本版 schema 中没有提供方/type 参数。
+`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——schema 中没有提供方/type 参数。
 
 ## 测试
 
@@ -72,5 +72,5 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
 
 - **递归。** 如果不设限制，进程内子 agent 能看到委派工具并递归调用。进程内后端实现了可选的绝对深度限制和有作用域的实时全局 `toolFilter`；ACP 声明这两项能力为关闭状态，并拒绝此类请求。[subagent 组合控制 Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责定义它们的确切语义和安全边界。
 - **阻塞父轮次。** 前台收集在子 agent 的整个持续时间内保持父 agent 的步骤打开。后台委派使用共享的 `ctx.tasks` 运行时与通用 `task_*` 工具，与后台 bash 共用同一套收集机制；subagent seam 本身仍不感知任务。
-- **实时进度。** 本版仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
+- **实时进度。** 仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
 - **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent（共享工作区模式）是后续工作；首版不声明这两项能力，子 agent 在自己的进程中自行服务。

.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.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 .agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md
-2026-06-22-acp-subagent-backend.md: 211030a6ecc9b6f673174ba410415c7bd80818ef
-2026-06-22-acp-subagent-backend.zh.md: 2dde3d96329cc47d9c7cca08e1d25764c32f8ebe
+2026-06-22-acp-subagent-backend.md: 41a60bc8e73cbda1d382226acfbd9c0a4b146fa6
+2026-06-22-acp-subagent-backend.zh.md: 6aea991c2b4ab783b5f8c43ecb9529df07269d3f

.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md

@@ -18,7 +18,7 @@ Each `start` spawns a new child, runs exactly one ACP session (`initialize` →
 
 ### Minimal client stub
 
-The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards) in this cut, which surfaces only the child's final answer. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — the first cut surfaces no prompt to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
+The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards), so only the child's final answer surfaces. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — no prompt is surfaced to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
 
 ### No start-time capabilities
 

.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.zh.md

@@ -18,7 +18,7 @@ subagent seam（[seam Agent Note](2026-06-21-subagent-capability-seam.md)）的
 
 ### 最小化客户端桩
 
-客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，在本阶段忽略其余内容（思考、工具调用卡片），仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——本阶段不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
+客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，忽略其余内容（思考、工具调用卡片），因此仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
 
 ### 无启动时能力
 

.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.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 .agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md
-2026-07-05-dynamic-workflows.md: 4dc8744f7505aeb84a14dbf5ad0cc8cb5783d234
-2026-07-05-dynamic-workflows.zh.md: 5d3f5b014ff4532050bb0afd5464f7ec5e91a323
+2026-07-05-dynamic-workflows.md: 3e491478286eb77b56872fcbbdd5ebb6b62a5545
+2026-07-05-dynamic-workflows.zh.md: 7888d83f981a96ac5eb31d5ca6f1f8d0b4930ec7

.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md

@@ -52,7 +52,7 @@ An output schema makes a schema-valid committed capture mandatory for successful
 
 Worker-side logic runs through an in-process `MessageChannel` so V8 coverage measures it. Unit tests cover script helpers, fatal and nullable failures, JSON boundaries, caps, cancellation, child ownership, and structured output through real loops. A built-bin smoke runs the separately bundled `lib/worker.cjs` under plain Node, a with-key e2e drives real child agents, and model-facing workflow behavior is snapshot-covered through its owning example.
 
-## Deferred (documented non-goals of this cut)
+## Deferred (documented non-goals)
 
 - **Background collection** (start tool → run id → completion notice → collect), designed alongside bash/subagent background unification.
 - **Journaling + resume** (`resumeFromRunId`, cached agent() prefixes) — implementing it reintroduces CC's determinism bans as a script-contract tightening (scripts may read the clock today).

.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md

@@ -52,7 +52,7 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
 
 worker 侧逻辑通过进程内 `MessageChannel` 运行，使 V8 覆盖率能够度量它。单元测试覆盖脚本辅助函数、fatal 与 nullable 失败、JSON 边界、上限、取消、子 agent 所有权和通过真实循环的结构化输出。构建后二进制文件的冒烟测试在纯 Node 下运行单独打包的 `lib/worker.cjs`，带密钥的 e2e 驱动真实子 agent，面向模型的工作流行为通过其所属示例进行快照覆盖。
 
-## 延迟（本轮明确的非目标）
+## 延迟（明确的非目标）
 
 - **后台收集**（启动工具 → run id → 完成通知 → 收集），与 bash/subagent 后台统一一起设计。
 - **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本约定收紧的形式重新引入 CC 的确定性禁令（脚本目前可以读取时钟）。

.agents/notes/implemented/feature/2026-08-08-user-explicit-skill-invocation.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 .agents/notes/implemented/feature/2026-08-08-user-explicit-skill-invocation.md
-2026-08-08-user-explicit-skill-invocation.md: 55001ec2b352bba6f37dd937f64ec8b10853bffb
-2026-08-08-user-explicit-skill-invocation.zh.md: 5e9eb90502a178c4171899247ebac9bec965c89f
+2026-08-08-user-explicit-skill-invocation.md: 74d9f01f191005db6d3d283a3c56f5ee664447f8
+2026-08-08-user-explicit-skill-invocation.zh.md: 0f7c9e1261dda796d988c17ddf7199b74be4133e

.agents/notes/implemented/feature/2026-08-08-user-explicit-skill-invocation.md

@@ -6,7 +6,7 @@ English | [中文](2026-08-08-user-explicit-skill-invocation.zh.md)
 
 ## Problem
 
-A `disable-model-invocation: true` skill is user-only by design: it never enters the model-facing catalog and the `skill` tool refuses to load it. Its only legitimate entry point is an explicit user gesture — yet the web client had none. `skill.list` filtered to the model-and-user intersection (hiding user-only skills from the menu), an entered `/name` line rode into the default prompt sink as plain text, and the model it reached was forbidden to load the skill — so it degraded to `read`-ing the SKILL.md file or ignoring the gesture (issue #1470). Even for ordinary skills, the decision-21 plain-text reference made user invocation a collaboration cue the model could ignore, not a guarantee.
+A `disable-model-invocation: true` skill is user-only by design: it never enters the model-facing catalog and the `skill` tool refuses to load it. Its only legitimate entry point is an explicit user gesture — yet the web client had none. `skill.list` filtered to the model-and-user intersection (hiding user-only skills from the menu), an entered `/name` line rode into the default prompt sink as plain text, and the model it reached was forbidden to load the skill — so it degraded to `read`-ing the SKILL.md file or ignoring the gesture (issue #1470). Even for ordinary skills, the plain-text reference made user invocation a collaboration cue the model could ignore, not a guarantee.
 
 ## Decision
 
@@ -14,7 +14,7 @@ User-explicit invocation is a host-side pre-step injection, uniform for every us
 
 - `dsh-tool-skill` registers a second `agent/pre-step` listener (beside its catalog listener, the same seam `workspace-instructions` and the runtime-context snapshot ride): it scans the step's claimed messages for whitespace-bounded `/name` tokens — anywhere in the text, the same word-boundary shape the transcript chip decoration uses — collects first-seen-deduplicated names, loads each through `ctx.skills.get`, checks `isUserInvocable` on the loaded definition (the single lookup that produces what is injected), renders it with the shared `renderSkillContent`, and appends the injections after every other injection of the step: background first (workspace rules, runtime policy, catalog), the material the model must act on last, closest to its answer. Registration order pins the placement — the gesture listener registers before the catalog listener, so the waterfall hands it the catalog-bearing list to extend.
 - Precision is closed-set matching, exactly like slash commands: `/goal` resolves against the command registry, `/name` against the workspace's user-invocable skill directory; a miss stays ordinary prose, so nothing is ever guessed. Only `source.kind === 'user'` messages are scanned — external text cannot forge a gesture. Paths (`/usr/bin`), fractions (`5/8`), and prefixed tokens (`foo/name`) all break the boundary.
-- The client stays decision 21: a menu pick lands the literal `/name ` and the prompt ships it verbatim; ui-skill implements no adjudication hooks and no reference codec. `skill.list` (now the domain's only RPC) serves every user-invocable skill with `modelInvocable` so menus mark user-only entries. A name shared with a host command resolves to the command — adjudication claims the line client-side before it becomes a prompt.
+- The client keeps the [plain-text-reference decision](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md): a menu pick lands the literal `/name ` and the prompt ships it verbatim; ui-skill implements no adjudication hooks and no reference codec. `skill.list` (now the domain's only RPC) serves every user-invocable skill with `modelInvocable` so menus mark user-only entries. A name shared with a host command resolves to the command — adjudication claims the line client-side before it becomes a prompt.
 - The injection is a `user`-role message carrying the `skill-invocation` source (`{ name, form: 'instructions' }`), so `user/message` logging, the context-injection transcript row (labelled with the skill name), and replay all come free; `renderSkillContent` lives in the `dsh-skill` seam, shared verbatim with the `skill` tool result, and the catalog's closing sentence tells the model to follow an injected block instead of re-loading it.
 
 Peer-product survey (Pi, OpenCode, Claude Code, Kimi Code, Codex, DeepSeek-Reasonix — local checkouts) was unanimous that user-explicit triggering is programmatic injection with zero model participation; the final shape is closest to Codex's core-side `$name` mention scanning, which likewise frees every front end from implementing recognition.
@@ -30,7 +30,7 @@ Peer-product survey (Pi, OpenCode, Claude Code, Kimi Code, Codex, DeepSeek-Reaso
 
 ## Consequences
 
-- Decision 21's plain-text reference is now the whole client story: the draft carries plain text, chip visuals derive from the lexicon, and the sent text is judged by the host boundary — a hand-typed gesture, a menu pick, and a TUI prompt are indistinguishable and equally deterministic.
+- The plain-text reference is now the whole client story: the draft carries plain text, chip visuals derive from the lexicon, and the sent text is judged by the host boundary — a hand-typed gesture, a menu pick, and a TUI prompt are indistinguishable and equally deterministic.
 - Every user-invocable skill invocation costs its full rendered body unconditionally — the price of determinism the peer survey showed everyone pays. Mentioning a known skill name mid-sentence loads it; that is the Codex mention semantic, accepted deliberately.
 - The `skill-invocation` source rides `user/message`, so Model-visible ⟺ logged holds with no new event type, and replay/UI read metadata rather than text markers.
 - Accepted residual of dropping the per-injection preamble: the no-reload framing rides only the catalog, and a workspace whose skills are all user-only never publishes a first catalog — an injection can arrive with no framing at all, and the model may redundantly try the `skill` tool once (the replacement catalog's empty arm carries the sentence; the never-published case does not). Publishing a catalog for framing alone was judged worse than that one recoverable error.

.agents/notes/implemented/feature/2026-08-08-user-explicit-skill-invocation.zh.md

@@ -6,7 +6,7 @@ Status: implemented
 
 ## 问题
 
-`disable-model-invocation: true` 的 skill（技能）在设计上就是仅限用户的：它绝不进入面向模型的目录，`skill` 工具也拒绝加载它。它唯一正当的入口是一次显式的用户手势——而 web 客户端此前没有这个入口。`skill.list` 过滤到模型与用户的交集（把仅限用户的 skill 挡在菜单之外），回车提交的 `/name` 一行以纯文本落入默认提示词 sink，而这行文本到达的模型又被禁止加载该 skill——于是退化为模型去 `read` 那份 SKILL.md 文件，或者干脆无视这次手势（issue #1470）。即使对普通 skill，决策 21 的纯文本引用也让用户调用只是模型可以忽略的协作线索，而不是保证。
+`disable-model-invocation: true` 的 skill（技能）在设计上就是仅限用户的：它绝不进入面向模型的目录，`skill` 工具也拒绝加载它。它唯一正当的入口是一次显式的用户手势——而 web 客户端此前没有这个入口。`skill.list` 过滤到模型与用户的交集（把仅限用户的 skill 挡在菜单之外），回车提交的 `/name` 一行以纯文本落入默认提示词 sink，而这行文本到达的模型又被禁止加载该 skill——于是退化为模型去 `read` 那份 SKILL.md 文件，或者干脆无视这次手势（issue #1470）。即使对普通 skill，纯文本引用也让用户调用只是模型可以忽略的协作线索，而不是保证。
 
 ## 决策
 
@@ -14,7 +14,7 @@ Status: implemented
 
 - `dsh-tool-skill` 注册第二个 `agent/pre-step` 监听器（与其目录监听器并列，也是 `workspace-instructions` 与运行时上下文快照搭乘的同一 seam）：它在该步骤已认领的消息中扫描以空白为界的 `/name` token——文本中任意位置均可，与 transcript（文本记录）chip 装饰所用的词边界形状相同——收集按首见去重的名称，逐个经 `ctx.skills.get` 加载，在已加载定义上检查 `isUserInvocable`（产生注入内容的正是这同一次查找），用共享的 `renderSkillContent` 渲染，并把注入追加在该步骤所有其他注入之后：背景在前（工作区规则、运行时策略、目录），模型必须着手处理的材料在最后、最贴近它的回答。注册顺序钉住了这一位置——手势监听器先于目录监听器注册，因此 waterfall（瀑布式事件）会把携带目录的列表交给它来扩展。
 - 精确性来自封闭集合匹配，与斜杠命令完全一致：`/goal` 对照命令注册表解析，`/name` 对照工作区的用户可调用 skill 目录解析；未命中即保持为普通行文，因此绝不猜测。只扫描 `source.kind === 'user'` 的消息——外部文本无法伪造手势。路径（`/usr/bin`）、分数（`5/8`）与带前缀的 token（`foo/name`）都会破坏该边界。
-- 客户端停留在决策 21：菜单 pick 落下字面文本 `/name `，该文本随提示词原样提交；ui-skill 不实现任何裁决钩子，也没有引用 codec。`skill.list`（现在是该领域唯一的 RPC）提供每一个用户可调用的 skill 并携带 `modelInvocable`，供菜单标出仅限用户的条目。与宿主命令同名的名称解析为命令——客户端会在该行成为提示词之前完成裁决并将其认领。
+- 客户端沿用[纯文本引用决策](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md)：菜单 pick 落下字面文本 `/name `，该文本随提示词原样提交；ui-skill 不实现任何裁决钩子，也没有引用 codec。`skill.list`（现在是该领域唯一的 RPC）提供每一个用户可调用的 skill 并携带 `modelInvocable`，供菜单标出仅限用户的条目。与宿主命令同名的名称解析为命令——客户端会在该行成为提示词之前完成裁决并将其认领。
 - 注入是一条携带 `skill-invocation` 来源（`{ name, form: 'instructions' }`）的 `user` 角色消息，因此 `user/message` 落账、上下文注入的 transcript 行（以 skill 名称标注）与回放全部免费获得；`renderSkillContent` 位于 `dsh-skill` seam，由注入和 `skill` 工具结果共用，二者内容逐字相同，目录的结尾一句会告诉模型遵循注入块而不是重新加载。
 
 同类产品调研（Pi、OpenCode、Claude Code、Kimi Code、Codex、DeepSeek-Reasonix——本地检出）一致表明：用户显式触发都是模型零参与的程序化注入；最终形态最接近 Codex 核心侧的 `$name` mention 扫描——它同样让每一种前端免于自行实现识别。
@@ -30,7 +30,7 @@ Status: implemented
 
 ## 后果
 
-- 决策 21 的纯文本引用如今就是客户端的全部故事：草稿承载纯文本，chip 视觉由 lexicon 派生，发出的文本由宿主边界评判——手动键入的手势、菜单 pick 与 TUI 提示词无从区分，也同样具有确定性。
+- 纯文本引用如今就是客户端的全部故事：草稿承载纯文本，chip 视觉由 lexicon 派生，发出的文本由宿主边界评判——手动键入的手势、菜单 pick 与 TUI 提示词无从区分，也同样具有确定性。
 - 每一次用户可调用 skill 的调用都无条件付出其完整渲染正文的成本——这是确定性的代价，同类调研表明所有产品都在支付。在句子中间提到一个已知 skill 名称也会加载它；这就是 Codex 的 mention 语义，属于有意接受。
 - `skill-invocation` 来源搭乘 `user/message`，因此「模型可见 ⟺ 已记录」在不新增事件类型的情况下继续成立，回放与 UI 读取的是元数据而非文本标记。
 - 放弃逐次注入前导语后被接受的残余：no-reload framing 只搭乘目录，而 skill 全部为仅用户的工作区永远不会发布首个目录——注入可能在完全没有 framing 的情况下到达，模型可能多余地调用一次 `skill` 工具（替换目录的空分支携带该句；从未发布的情形没有）。仅为 framing 而发布目录被判定比这一次可恢复的错误更糟。