fix(preset): correct the composition-authoring skill and give it a real check

The `cordis` preset's `editing-cordis-compositions` skill is the only guidance
an agent has when it authors a preset, and four of its statements were false.

`tool-bash` was named as the worked example of a row that hides a service; it
provides nothing and injects `bashEnv` from the host's own `bash-env` row, so
following that advice strands the row behind its realm and the preset fails to
mount. The `isolate` example composed `tasks-local` with `tool-tasks`, which
the shipped compositions' own comments say breaks `run_in_background`. A string
realm label was described as pooling one instance; labels join realms and
`provide()` still throws on the second registration. Rows were to be checked
against a package README, which no harness package publishes.

Verification is now the agent's own: `standingKeyFor(id)` runs the same mount a
session start performs and rejects an unresolvable package, an invalid config, a
service in the root realm, and a row that never activated. The skill states that
`list()`'s `broken` field is a shape check that every one of those passes, ships
the `cordis_mount` plugin that reaches the roster service, and names `copy()` as
the authoring write. The prohibition on touching the shipped install is promoted
to its own section and extended to the host composition.

Fixes #2266

.agents/notes/implemented/bug-fix/2026-08-09-broken-preset-roster-rows.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/bug-fix/2026-08-09-broken-preset-roster-rows.md
-2026-08-09-broken-preset-roster-rows.md: fef6a183b10f98b8ae9d2b42701380c69bc83462
-2026-08-09-broken-preset-roster-rows.zh.md: 196bcf4ef16325a1d7692d2ea13d9fa683d500f4
+2026-08-09-broken-preset-roster-rows.md: 069585957d4d99598cc38e4a7c6bc8c8d82490ca
+2026-08-09-broken-preset-roster-rows.zh.md: d541292b59496464eb91bc03278e0800af16c4a3

.agents/notes/implemented/bug-fix/2026-08-09-broken-preset-roster-rows.md

@@ -26,7 +26,7 @@ Surfaces split by their job: the management section renders broken rows as marke
 - **`PRESET_ID` moved to `types.ts`** so discovery and authoring share one containment vocabulary; authoring re-exports it unchanged.
 - **The reason is one line.** js-yaml appends a multi-line code-frame snippet; the roster card is not a terminal, so `compositionProblem` keeps the first line.
 - **Two mount.spec races were left untouched deliberately**: `ensureStanding` is still reachable with a preset resolved just before deletion (the private-path tests), and its stamp/unstampable semantics are unchanged — the health check happens before, in the public route.
-- **Creator-mode guidance rides the same PR**: the `cordis` preset's persona now forbids editing the shipped install (corrupting `cordis` would disable the mode itself) and points authoring at `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`; its skill teaches `preset.yml` metadata, the copy-first workflow, the one-escalation sandbox reality (the preset root lies outside the session workspace), and honest verification (the agent cannot start sessions; the settings page's red marking is the user's check). Verified live: asked to edit the shipped `cordis` composition directly, the composed agent refuses citing both rules and offers the copy path; asked for a real preset, it lands it under `$DSH_HOME`, batches writes into one escalation, self-checks with the loader dialect, and hands verification to the user.
+- **Creator-mode guidance rides the same PR**: the `cordis` preset's persona forbids editing the shipped install (corrupting `cordis` would disable the mode itself) and points authoring at `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`; its skill teaches `preset.yml` metadata, the copy-first workflow, and the one-escalation sandbox reality (the preset root lies outside the session workspace). Verified live: asked to edit the shipped `cordis` composition directly, the composed agent refuses citing both rules and offers the copy path; asked for a real preset, it lands it under `$DSH_HOME` and batches writes into one escalation. The verification half of that guidance — that the agent cannot start sessions, so the settings page's red marking is the user's check — is superseded by [the authoring agent mount-validates its own composition](2026-08-11-preset-authoring-agent-validates-its-own-composition.md): the shape check below is not validation, and `standingKeyFor` gives the agent the real one. The health decision in this note is unchanged.
 
 ## Alternatives considered
 

.agents/notes/implemented/bug-fix/2026-08-09-broken-preset-roster-rows.zh.md

@@ -26,7 +26,7 @@ Status: implemented
 - **`PRESET_ID` 移到 `types.ts`**，让发现与创作共享同一份包含边界词汇；authoring 原样转发导出。
 - **原因只留一行。** js-yaml 会附上多行代码框摘录；名单卡片不是终端，`compositionProblem` 只保留首行。
 - **mount.spec 的两个竞态用例特意不动**：`ensureStanding` 仍可能拿到删除前一刻解析出的 preset（私有路径测试），其 stamp/unstampable 语义不变——健康检查发生在此之前的公开路径上。
-- **创造模式的引导随同一 PR 落地**：`cordis` preset 的 persona 现在禁止编辑随附安装（损坏 `cordis` 会禁用这一模式本身），并把创作指向 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`；其技能新教了 `preset.yml` 元信息、先复制再改的流程、一次升级的沙箱现实（preset 根目录在会话工作区之外）与诚实的验证方式（agent 无法自己启动会话；设置页的红色标记是用户的检查项）。已实测：被要求直接改随附 `cordis` 组装时，组装出的 agent 援引两条规则拒绝并给出复制路径；被要求真正创建 preset 时，它落在 `$DSH_HOME` 下、把写入合并为一次升级、用加载器方言自查、并把验证交还用户。
+- **创造模式的引导随同一 PR 落地**：`cordis` preset 的 persona 禁止编辑随附安装（损坏 `cordis` 会禁用这一模式本身），并把创作指向 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`；其技能教了 `preset.yml` 元信息、先复制再改的流程与一次升级的沙箱现实（preset 根目录在会话工作区之外）。已实测：被要求直接改随附 `cordis` 组装时，组装出的 agent 援引两条规则拒绝并给出复制路径；被要求真正创建 preset 时，它落在 `$DSH_HOME` 下并把写入合并为一次升级。该引导中关于验证的那一半——agent 无法自己启动会话，因而设置页的红色标记是用户的检查项——已由[创作 preset 的 agent 自行挂载校验其组装](2026-08-11-preset-authoring-agent-validates-its-own-composition.md)取代：下文的结构检查不是校验，而 `standingKeyFor` 才给了 agent 真正的校验手段。本篇的健康检查决策不变。
 
 ## 曾考虑的替代方案
 

.agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.md
+2026-08-11-preset-authoring-agent-validates-its-own-composition.md: 77bd30d4c8f6599ccde50b4d814f55d065266763
+2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: cdc0d30bcd769e1a17ddcce364002f0136a26242

.agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.md

@@ -0,0 +1,68 @@
+# Agent Note: The preset-authoring agent mount-validates its own composition
+
+Status: implemented
+
+English | [中文](2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md)
+
+## Problem
+
+The `cordis` preset ships `editing-cordis-compositions`, the only guidance an agent has when it authors a preset. Four of its statements were false, and the two that carried the most weight pointed at the rule the skill itself calls "the rule that catches people".
+
+It named `tool-bash` as the worked example of a row whose name hides a service — "reads like a tool but provides `bashEnv`". `tool-bash` provides nothing; it declares `inject: ['tools', 'bash', 'systemPrompt', 'bashEnv']`, and `bashEnv` comes from the host composition's own `bash-env` row. An agent wrapping `tool-bash` in an `isolate` realm on that advice strands the row waiting for a service its realm hides, and the whole preset fails to mount.
+
+Its `isolate` example composed `tasks-local` with `tool-tasks`. `tasks-local` is host-plane, and the shipped compositions say in their own comments that an entry-local realm around `tool-tasks` makes `run_in_background` answer "background tasks unavailable". The example contradicted the file next to it.
+
+It described a string realm label as pooling one instance across subtrees. Labels join realms; `provide()` still throws on the second registration under the same realm symbol, which `standard`'s header comment already stated.
+
+It sent the agent to a package's README to learn whether a row publishes a service. Outside `apps/cli` (`files: ["lib/*.js", "config"]`), every harness package publishes only `lib/index.js`, `lib/invariant.js`, and `lib/types/**/*.d.ts` — no README, no `src/`, no `docs/`. In an installed deployment that instruction cannot be followed at all.
+
+Underneath all four sat a capability claim: the agent "cannot start one \[a session\] yourself", so verification was hand-reading YAML fields and handing the result to the user through the settings page's red marking. That marking is discovery's shape check, which is far weaker than the sentence implied.
+
+## Decision
+
+The skill teaches the agent to mount-validate its own composition through `ctx.agentPresets`, and every remaining example is taken from a shipped composition in the same repository.
+
+`standingKeyFor(id)` is the check. It runs `ensureStanding()` — the same real mount a session start performs, minus the agent — so it rejects a row whose package does not resolve, a row whose config is invalid, a service published into the root realm, and a row that never activated. A failed mount deletes the standing entry and disposes its scope, leaving nothing behind; a successful one installs the standing generation the first real session would have installed anyway. The skill therefore places it as the final check on a finished edit rather than a per-line loop.
+
+The skill states plainly that `list()`'s `broken` field is **not** validation. Discovery's health check proves the file parses in the loader's dialect and holds named rows, and every one of the four failures above passes it.
+
+The agent reaches the roster service the way `cordis_mount` documents: a temporary plugin declaring `inject: ['agentPresets', 'tools']` that registers a tool for itself, because a mount returns only its own acknowledgement and a registered tool is how a service answer reaches the model on the next step. The skill ships that plugin verbatim. `agentPresets` is in the generated `cordis_inspect what:"api"` catalog with full JSDoc, and the sandbox façade gates services on `fiber.inject` alone rather than an allowlist, so nothing about this path is special-cased for the skill.
+
+`copy(from, id, name)` is named as the authoring write, in place of a shell copy: it validates the id, refuses one any root supplies, rolls a failed copy back, rewrites the copy's `preset.yml`, and runs host-side without sandbox escalation. The escalation guidance stays, moved to where it applies — editing `agent.cordis.yml` afterwards still writes outside the session workspace.
+
+"Whether a row publishes a service" resolves through `cordis_inspect what:"services"`, which names the owning fiber of every live service.
+
+The prohibition on touching the shipped install is promoted from a paragraph inside the authoring steps to a top `## Off-limits` section, extended to cover editing the host composition as a workaround. The new self-validation calls do not weaken it: `copy()` refuses an id any root supplies, and `remove()` refuses a preset that ships with the deployment.
+
+## Measured behavior
+
+Each row was produced by booting the shipped Web composition and calling the tools through `ctx.tools.execute` on an agent composed from `cordis` — no model in the loop.
+
+| Composition under test | `list()` `broken` | `standingKeyFor()` |
+|---|---|---|
+| row names an absent package | empty | `Cannot find package '@deepseek-ai/dsh-does-not-exist'` |
+| service row with no realm | empty | `service "tasks" has been registered at <LocalTaskService>` |
+| same row inside `isolate` | empty | mounts |
+| consumer row with no provider | empty | `1 row(s) did not activate: … waiting for workflows` |
+| row missing a required config field | empty | `invalid config: $.allowParallelInProgress missing required value` |
+
+The skill's own `cordis_mount` snippet was executed verbatim through the tool registry: it mounts, its `preset_check` tool appears in the composing agent's catalog on the next read, and it answers `mounted OK` for a valid preset and the mount rejection for an invalid one.
+
+## Alternatives considered
+
+**Leaving verification with the user and only fixing the four errors.** The errors and the capability claim share a cause — the guidance was written from the preset layer's public surface rather than from what the composed agent can reach — and an agent that cannot check its work hands over compositions whose defects the settings page cannot see either.
+
+**Teaching `list()`'s `broken` field as the check.** It is the one the settings page shows, so it reads like the intended answer. It passes every failure that matters, and presenting it as validation is what made the original guidance feel complete.
+
+**Adding a first-class preset-validation tool to the preset.** The composed path already exists and is documented by `cordis_mount`'s own schema; a dedicated tool would add a model-facing row to a preset whose point is that the runtime is reachable without one.
+
+## Consequences
+
+- A successful validation leaves a standing generation that is never reclaimed, which is the [standing-mount](../architecture/2026-08-08-per-preset-standing-mounts.md) cost the roster already carries per generation — the agent pays it once at the end of an edit instead of the user paying it at the first session.
+- The skill now depends on `cordis_inspect`'s generated API catalog staying current for `agentPresets`; `verify-cordis-api` in `doc-sync` is what holds that.
+- Two examples are now quotations of `standard`'s composition. They drift if that file's `delegation` group changes, which the `web-agent-presets` e2e does not catch.
+- The four corrected statements were the skill's only concrete illustrations of the realm rule. Replacing rather than deleting them keeps the rule teachable; the replacements are verifiable by reading one shipped file.
+
+## Related
+
+Supersedes the creator-guidance bullet in [broken presets are roster rows](2026-08-09-broken-preset-roster-rows.md), whose health-check decision remains current — this note reverses only its "the agent cannot start sessions; the settings page's red marking is the user's check" conclusion. Authoring's copy-only shape is owned by [copy-only preset authoring](../simplification/2026-08-08-copy-only-preset-authoring.md).

.agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md

@@ -0,0 +1,68 @@
+# Agent Note: 创作 preset 的 agent 自行挂载校验其组装
+
+Status: implemented
+
+[English](2026-08-11-preset-authoring-agent-validates-its-own-composition.md) | 中文
+
+## Problem
+
+`cordis` preset 随包发布 `editing-cordis-compositions`，它是 agent 创作 preset 时唯一的指导来源。其中四条陈述与事实不符，而分量最重的两条恰好指向该 skill 自称「最容易让人栽跟头的规则」。
+
+它把 `tool-bash` 当作「行名看不出发布服务」的示例——「看着像工具，其实 provides `bashEnv`」。`tool-bash` 不发布任何服务，它声明 `inject: ['tools', 'bash', 'systemPrompt', 'bashEnv']`，`bashEnv` 来自宿主组装自己的 `bash-env` 行。agent 照此给 `tool-bash` 套上 `isolate` realm，该行会永远等待被自己的 realm 挡住的服务，整个 preset 挂载失败。
+
+它的 `isolate` 示例把 `tasks-local` 与 `tool-tasks` 组在一起。`tasks-local` 位于宿主平面，而已发布组装在自己的注释里写明：给 `tool-tasks` 套 entry-local realm 会让 `run_in_background` 回答「background tasks unavailable」。示例与紧挨着它的文件互相矛盾。
+
+它把字符串 realm label 描述为跨子树共享一个实例。label 只是加入同一 realm，`provide()` 在同一 realm symbol 下第二次注册仍然抛错——`standard` 的头部注释早已如此说明。
+
+它让 agent 去读包的 README 判断某行是否发布服务。除 `apps/cli`（`files: ["lib/*.js", "config"]`）外，所有 harness 包只发布 `lib/index.js`、`lib/invariant.js` 与 `lib/types/**/*.d.ts`，没有 README、没有 `src/`、没有 `docs/`。在装机部署中该指令根本无法执行。
+
+四条之下还压着一个能力断言：agent「自己起不了会话」，于是校验退化成肉眼核对 YAML 字段，再把结果经设置页的红色标记交给用户。那个标记是发现阶段的结构检查，远弱于这句话给人的印象。
+
+## Decision
+
+skill 教 agent 通过 `ctx.agentPresets` 自行挂载校验其组装，其余每个示例都取自同一仓库中已发布的组装。
+
+`standingKeyFor(id)` 是校验手段。它走 `ensureStanding()`——与会话启动完全相同的真实挂载，只是不创建 agent——因此能拒绝包无法解析的行、配置非法的行、把服务发布进根 realm 的行，以及始终未激活的行。挂载失败会删除常驻条目并 dispose 其 scope，不留残留；挂载成功则装上首次真实会话本来也会装上的那个常驻代际。因此 skill 把它安排为完成编辑后的最终检查，而不是逐行循环。
+
+skill 明确写出：`list()` 的 `broken` 字段**不是**校验。发现阶段的健康检查只证明文件能被 Loader 的方言解析且行带 `name`，上述四类失败全部能通过它。
+
+agent 按 `cordis_mount` 自身文档所述的方式够到 roster 服务：挂一个声明 `inject: ['agentPresets', 'tools']` 的临时插件，并为自己注册一个工具——因为挂载只返回自身的确认信息，而已注册的工具才是服务结果在下一步抵达模型的途径。skill 逐字附上该插件。`agentPresets` 位于生成的 `cordis_inspect what:"api"` 目录中并带完整 JSDoc，沙箱 façade 仅凭 `fiber.inject` 而非白名单放行服务，因此这条路径没有为该 skill 做任何特例。
+
+`copy(from, id, name)` 被指定为创作写入手段，取代 shell 复制：它校验 id、拒绝任何根已提供的 id、失败时回滚、重写副本的 `preset.yml`，并在宿主侧运行而无需沙箱升级。沙箱升级的说明保留，移到真正适用之处——其后编辑 `agent.cordis.yml` 仍然写在会话工作区之外。
+
+「某行是否发布服务」改由 `cordis_inspect what:"services"` 回答，它会给出每个存活服务的持有 fiber。
+
+禁止改动随发布安装的约束，从创作步骤中的一段提升为顶部的 `## Off-limits` 一节，并扩展到禁止改宿主组装绕行。新增的自校验调用不削弱它：`copy()` 拒绝任何根已提供的 id，`remove()` 拒绝随部署发布的 preset。
+
+## Measured behavior
+
+下表每一行都由启动已发布的 Web 组装、并在由 `cordis` 组装出的 agent 上经 `ctx.tools.execute` 调用工具得出——全程无模型参与。
+
+| 被测组装 | `list()` 的 `broken` | `standingKeyFor()` |
+|---|---|---|
+| 行指向不存在的包 | 空 | `Cannot find package '@deepseek-ai/dsh-does-not-exist'` |
+| 服务行未套 realm | 空 | `service "tasks" has been registered at <LocalTaskService>` |
+| 同一行置于 `isolate` 内 | 空 | 挂载成功 |
+| 消费者行无人提供服务 | 空 | `1 row(s) did not activate: … waiting for workflows` |
+| 行缺少必填配置字段 | 空 | `invalid config: $.allowParallelInProgress missing required value` |
+
+skill 自带的 `cordis_mount` 代码片段经工具注册表逐字执行：它成功挂载，其 `preset_check` 工具在下一次读取时出现在组装该 agent 的目录中，对有效 preset 回答 `mounted OK`，对无效 preset 回答挂载拒绝原因。
+
+## Alternatives considered
+
+**把校验留给用户，只修四处错误。** 这些错误与那句能力断言同源——指导是按 preset 层的公开面写的，而不是按被组装出的 agent 实际够得到的东西写的——而无法自查的 agent 交出的组装，其缺陷设置页同样看不见。
+
+**把 `list()` 的 `broken` 字段教成校验手段。** 它正是设置页展示的字段，看起来像是预期答案。它对所有要紧的失败一律放行，而把它当成校验，正是原指导显得完整的原因。
+
+**给 preset 加一个一等的 preset 校验工具。** 组合出的路径已经存在，且由 `cordis_mount` 自己的 schema 记载；专用工具会给一个「无需专用工具即可够到运行时」的 preset 再添一个面向模型的行。
+
+## Consequences
+
+- 校验成功会留下一个永不回收的常驻代际，这是 roster 按代际本就承担的[常驻挂载](../architecture/2026-08-08-per-preset-standing-mounts.md)代价——由 agent 在编辑收尾时付一次，而不是由用户在首次会话时付。
+- skill 现在依赖 `cordis_inspect` 生成的 API 目录对 `agentPresets` 保持最新；`doc-sync` 中的 `verify-cordis-api` 是守住这一点的门禁。
+- 有两个示例现在是对 `standard` 组装的引用。若该文件的 `delegation` 组发生变化它们会漂移，而 `web-agent-presets` e2e 捕捉不到。
+- 被修正的四条陈述原本是该 skill 对 realm 规则仅有的具体图示。选择替换而非删除，规则才仍然可教；替换后的示例读一个已发布文件即可核验。
+
+## Related
+
+取代[破损 preset 是 roster 行](2026-08-09-broken-preset-roster-rows.md)中关于创作模式指导的那一条，其健康检查决策依然有效——本篇只推翻它「agent 起不了会话；设置页的红色标记是用户的检查手段」这一结论。创作的 copy-only 形态由[copy-only preset 创作](../simplification/2026-08-08-copy-only-preset-authoring.md)负责。