Merge remote-tracking branch 'origin/master' into worktree/sidebar-subagent-activity

# Conflicts: # packages/client/runtime/README.i18n.yaml
2026-08-08 16:37:29 +08:00
parent fb1d230518 bd518cb684
commit 3b10120d60
361 changed files with 3950 additions and 3337 deletions
@@ -376,6 +376,9 @@
    "simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.i18n.yaml": "sha256:531c446f0e95054f8ced17be9a180f8b0a823f7e9d5ce466c94c2f9cff90a111",
    "simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md": "sha256:a35a6372aabdf7cbc211f1bd5820d85d3467c9ed50f84e05caa3339382379ce7",
    "simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md": "sha256:a6ed9530289a783c3d7a1ddb038fba6b7daf7feb773298a57e811791e354d438",
+    "simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml": "sha256:5466161f3fb8f2e8117fe8ff242675cc9fe9ef264d1e29b9bc586891c73c051a",
+    "simplification/2026-08-03-explicit-config-dsh-entrypoint.md": "sha256:f23accae7d05c2e75cb73ec69b492307f1ce7526ecfa9f6b12a621e02fd1a0c3",
+    "simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md": "sha256:a32d2c6ecf748a16a2c35b59cd2da2fda75769e3ab24be6a2e026d8655466db4",
    "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml": "sha256:4177012c0821a8c22499852ecdf096af56d7263cb91c5d9d1bcd552cc26a3e00",
    "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md": "sha256:45234e7cc04b6010c6141f8d5924c04547300098f96262d423c50108e7c7011a",
    "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md": "sha256:15e5a4ad3dee0bb711480cabe45cd97ec37bbdba19c2c2b47d1e9c203b07a48b",
@@ -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/simplification/2026-08-03-explicit-config-dsh-entrypoint.md
-2026-08-03-explicit-config-dsh-entrypoint.md: e0d1e954d9cef472ea59345a3d2ef5a67bd03ae8
-2026-08-03-explicit-config-dsh-entrypoint.zh.md: b5b464e3b45a6f3909bbf087f7005ad3f819424a
+2026-08-03-explicit-config-dsh-entrypoint.md: 4474e786b3a99ff0ee81ac54fcb6eb5aaff5ee04
+2026-08-03-explicit-config-dsh-entrypoint.zh.md: 11b7b27c7560aaa43a9fdcfb12a9a17f9433e619
@@ -1,6 +1,7 @@
 # Agent Note: Explicit-config dsh entrypoint

 Status: implemented
+Archived: 2026-08-08

 English | [中文](2026-08-03-explicit-config-dsh-entrypoint.zh.md)

@@ -1,6 +1,7 @@
-# Agent Note：显式配置的 dsh 入口
+# Agent Note: 显式配置的 dsh 入口

 Status: implemented
+Archived: 2026-08-08

 [English](2026-08-03-explicit-config-dsh-entrypoint.md) | 中文

@@ -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/2026-07-19-gui-layering-and-rpc-protocol.md
-2026-07-19-gui-layering-and-rpc-protocol.md: 34077302c53081f6ee9171d64dce9af342710d71
-2026-07-19-gui-layering-and-rpc-protocol.zh.md: bc51542ac8159ee7cba234b4ee8b4db47a7f9b58
+2026-07-19-gui-layering-and-rpc-protocol.md: 8e020e4fe9b60100671c0cf0e98e28532d850f94
+2026-07-19-gui-layering-and-rpc-protocol.zh.md: 55fa8084083aa83fbb4a38f8e41d2e5624b6e58e
@@ -10,7 +10,7 @@ English | [中文](2026-07-19-gui-layering-and-rpc-protocol.zh.md)

 We need a UI integration layer. Beyond the existing ACP/stdio baseline, more product UI shapes are coming — Web (server), Electron, and others. We call these shapes Clients, uniformly, and want the following capabilities:

- One `dsh` process supporting both `dsh web` (serve) and `dsh -p` (headless) — one process, two modes (a design reservation)
+- One `dsh` process supporting both `dsh web` (serve) and `dsh run` (headless) — one process, two modes (a design reservation)
 - Launching inside Electron with the same Web technology shape as `dsh web`

 That demands a stable layered responsibility model in the engineering codebase, so future client shapes plug in cleanly.
@@ -31,7 +31,7 @@ Directories layer as follows:
    - **Fetch-arrival plugin packages** (`ui-layout`, `ui-sidebar`, `ui-conversation`, `ui-trajectory`): dual-entry — the root index is the node half (an empty `apply`, existing so the host Loader governs lifecycle and the web plugin registry discovers the package.json `dshClient` declaration); the implementation lives under `src/client/`, shipped as the `./client` subpath (a tsdown closure-factory bundle). Cross-plugin consumption of `/client` is type-only; value cooperation goes through cordis services.
 - `apps/` holds the externally exported application shapes, assembled from Client / Host mixtures.
    - `apps/web` (`dsh-frontend`) is the vite application: a thin `main.ts` over the shell surface exported by `dsh-client-web`.
-    - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = startHost + webserver + the built `dsh-frontend` dist; `dsh -p` = headless in-process calls, zero HTTP.
+    - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = startHost + webserver + the built `dsh-frontend` dist; `dsh run` = headless in-process calls, zero HTTP.
    - A future Electron shape reuses the same web client packages over an IPC fetch carrier.

 ```
@@ -215,7 +215,7 @@ All four quadrant full forms pass through `onEnvelope`; the base implementation

 | Subclass | Package | doFetch | Purpose |
 |---|---|---|---|
-| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing — `dsh -p` headless is the protocol's second real consumer |
+| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing — `dsh run` headless is the protocol's second real consumer |
 | `WebApiClient` | dsh-client-connection | `globalThis.fetch` uplink + one same-origin WebSocket downlink per logical stream | the browser shape; physical boundary in the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md) |
 | `FixtureApiClient` | dsh-client-connection | unused (protocol-layer override) | serverless UI development (`?fixture`): overrides the `callUnary`/`openMux`/`openHost`/`respond` virtuals and is itself the fake server (frame rpcIds minted by it, semantics self-consistent) |
 | (future) IPC bridge subclass | apps/electron | IPC serialization round trip | swaps only doFetch; contract and base class unchanged |
@@ -9,7 +9,7 @@ Status: implemented
 ## Problem

 需要提供 UI 对接层，除已有 ACP/stdio基础版本外，还需要 Web(server) 、 Electron 、等其他产品 UI 形态。我们把这些形态统一称为 Client。希望有如下能力支持:
- 以 `dsh` 进程，同时支持 `dsh web`(启动) 和 `dsh -p`(headless) ，一个进程两种模式（设计预留）
+- 以 `dsh` 进程，同时支持 `dsh web`(启动) 和 `dsh run`(headless) ，一个进程两种模式（设计预留）
 - 以与 `dsh web` 同构的 Web 技术形态，在 Electron 中启动

 那么当前的工程代码需要稳定的分层职责模型，便于以后接入各类 client 形态。
@@ -29,7 +29,7 @@ Status: implemented
    - **fetch 到达插件包**（`ui-layout`、`ui-sidebar`、`ui-conversation`、`ui-trajectory`）：双入口——根入口是 node 半边（空 `apply`，其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dshClient` 声明）；实现住在 `src/client/` 下，经 `./client` 子路径发布（tsdown 闭包工厂 bundle）。跨插件消费 `/client` 只限类型；值层面的协作走 cordis 服务。
 - `apps/` 作为对外导出的应用形态入口，可以由 Client / Host 混合组装。
    - `apps/web`（`dsh-frontend`）是 vite 应用：`dsh-client-web` 导出的壳表面之上的一层薄 `main.ts`。
-    - `apps/cli`（`@deepseek-ai/dsh`）做形态分发：`dsh web` = startHost + webserver + 构建出的 `dsh-frontend` dist；`dsh -p` = headless 进程内直调，零 HTTP。
+    - `apps/cli`（`@deepseek-ai/dsh`）做形态分发：`dsh web` = startHost + webserver + 构建出的 `dsh-frontend` dist；`dsh run` = headless 进程内直调，零 HTTP。
    - 将来的 Electron 形态经由 IPC fetch 载体复用同一套 web client 包。

 ```
@@ -213,7 +213,7 @@ export type ResponseValue<K> =

 | 子类 | 所在包 | doFetch | 用途 |
 |---|---|---|---|
-| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**：`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧——`dsh -p` headless 即协议第二真实消费者 |
+| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**：`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧——`dsh run` headless 即协议第二真实消费者 |
 | `WebApiClient` | dsh-client-connection | `globalThis.fetch` 上行 + 每逻辑流一条同源 WebSocket 下行 | 浏览器形态；物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md) |
 | `FixtureApiClient` | dsh-client-connection | 不用（协议层覆写） | 无 server 的 UI 开发（`?fixture`）：覆写 `callUnary`/`openMux`/`openHost`/`respond` 虚方法，自己就是假 server（帧 rpcId 由它 mint，语义自洽） |
 | （将来）IPC 桥子类 | apps/electron | IPC 序列化往返 | 仅换 doFetch，契约/基类零改 |
@@ -1,6 +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
-2026-07-27-compiler-independent-typert-model.md: 338476924dfb5d9832d0b64bf01b8d3c297cd6d6
-2026-07-27-compiler-independent-typert-model.zh.md: a88f4dbba50696071552ea12a63b69ecac202418
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-27-compiler-independent-typert-model.md
+2026-07-27-compiler-independent-typert-model.md: 15641e5f785c5d2daecbfc2d5cffedd64d8384a7
+2026-07-27-compiler-independent-typert-model.zh.md: 7bddd3ffde343346c163f55ef493c32bad1e8314
@@ -22,7 +22,7 @@ PackageModel recognizes Cordis services, events, `@typert object` reference obje

 [`dsh-typert-registry`](../../../../packages/typert/registry/README.md) provides `ctx.typert` and handles runtime registration only: one contribution atomically carries package-face reflection and an optional Zod schema, and Cordis effect disposal revokes it. The registry neither analyzes TypeScript nor merges the two faces. JSON Schema is an on-demand projection of registered Zod schemas.

-Package artifact publication is explicit opt-in. When invoked, `WorkspaceTypertGenerator` validates that each requested host face exposes the user-facing subpath `package/typert` from the root artifact `package/lib/typert.host.{js,d.ts}`, or that each requested client face exposes `package/client/typert` from `package/lib/typert.client.{js,d.ts}`. It neither edits exports nor runs as part of the ordinary root build or typecheck, so those commands do not generate whole-workspace Typert artifacts. Generated declarations keep `TYPERT` typed as `unknown`, so business packages do not depend on the registry.
+Package artifact publication remains explicit opt-in through package exports. When invoked, `WorkspaceTypertGenerator` validates that each requested host face exposes the user-facing subpath `package/typert` from the root artifact `package/lib/typert.host.{js,d.ts}`, or that each requested client face exposes `package/client/typert` from `package/lib/typert.client.{js,d.ts}`; it never edits those exports. The later [TypeRT Remote design](2026-08-02-typert-remote-method-calls.md) adds a whole-workspace Host contract pass to root build, typecheck, lint, and documentation typecheck. For opted-in Host packages, that pass emits both local reflection and strict Host-for-Client `/remote` contracts before consumers resolve them. Generated local declarations keep `TYPERT` typed as `unknown`, so business packages do not depend on the registry.

 At build time, `CordisCatalogProjector` consumes the analyzed `FaceModel` and `TypeGraph` once to generate `docs/cordis-catalog/events.md`, `docs/cordis-catalog/services.md`, and the static `SERVICE_API`, `EVENT_API`, and `TYPE_API` catalog committed for `tool-cordis`. `tool-cordis` reads that static catalog and has no runtime dependency on `ctx.typert`. [`dsh-typert-loader`](../../../../packages/typert/loader/README.md) and the registry remain an independent runtime path: the loader follows Cordis Loader entry lifecycle events, imports an explicitly published `./typert` host artifact, and registers it through `ctx.typert`; neither component supplies the current `cordis_inspect` catalog.

@@ -50,4 +50,4 @@ For each supported node kind and literal category, Zod emitter tests run both su

 New generation targets and static checks can reuse the same TypeGraph, and business categories can extend PackageModel without parsing the AST again. Preserving pre-evaluation types and independent faces makes the model more complex than a flattened schema; emitters must explicitly declare their supported scope and fail on missing capabilities.

-Explicit opt-in keeps artifact publication and package exports under package ownership, while ordinary root builds and typechecks incur no whole-workspace Typert generation phase. The static Cordis catalogs remain reproducible from the canonical model without coupling `tool-cordis` to runtime registry state. `ctx.typert` reflects only artifacts mounted in the current runtime, and unloading does not control Zod instances that consumers retain after importing them directly.
+Explicit package opt-in keeps artifact publication and exports under package ownership. Repository orchestration may still run the whole-workspace Host contract pass for every opted-in package; that pass remains owned by the later Remote Gateway Agent Note. The static Cordis catalogs remain reproducible from the canonical model without coupling `tool-cordis` to runtime registry state. `ctx.typert` reflects only artifacts mounted in the current runtime, and unloading does not control Zod instances that consumers retain after importing them directly.
@@ -22,7 +22,7 @@ PackageModel 识别 Cordis service、event、`@typert object` 引用对象和 `@

 [`dsh-typert-registry`](../../../../packages/typert/registry/README.md) 提供 `ctx.typert`，且只负责运行时注册：一个 contribution 原子携带 package-face reflection 与可选 Zod schema，并随 Cordis effect 撤销。注册表不分析 TypeScript，也不合并两个 face。JSON Schema 是对已注册 Zod schema 的按需投影。

-包产物发布采用显式 opt-in。`WorkspaceTypertGenerator` 仅在被调用时校验所请求 face 的根目录产物协议：host face 必须通过面向用户的 subpath `package/typert` 暴露 `package/lib/typert.host.{js,d.ts}`，client face 必须通过 `package/client/typert` 暴露 `package/lib/typert.client.{js,d.ts}`。它既不修改 exports，也不作为根目录普通 build 或 typecheck 的一部分运行，因此这些命令不会生成全仓 Typert 产物。生成的声明将 `TYPERT` 类型保持为 `unknown`，因此业务包不依赖注册表。
+包产物发布仍通过 package exports 采用显式 opt-in。`WorkspaceTypertGenerator` 仅在被调用时校验所请求 face 的根目录产物协议：host face 必须通过面向用户的 subpath `package/typert` 暴露 `package/lib/typert.host.{js,d.ts}`，client face 必须通过 `package/client/typert` 暴露 `package/lib/typert.client.{js,d.ts}`；它不会修改这些 exports。后续的 [TypeRT Remote 设计](2026-08-02-typert-remote-method-calls.md) 为根目录 build、typecheck、lint 与文档类型检查增加了全仓 Host 契约 pass。对于已 opt-in 的 Host 包，该 pass 会在消费方解析两者之前生成本地反射产物与严格的 Host-for-Client `/remote` 契约。生成的本地声明将 `TYPERT` 类型保持为 `unknown`，因此业务包不依赖注册表。

 构建期的 `CordisCatalogProjector` 一次消费分析后的 `FaceModel` 与 `TypeGraph`，生成 `docs/cordis-catalog/events.md`、`docs/cordis-catalog/services.md`，以及为 `tool-cordis` 提交的静态 `SERVICE_API`、`EVENT_API` 和 `TYPE_API` catalog。`tool-cordis` 读取该静态 catalog，运行时不依赖 `ctx.typert`。[`dsh-typert-loader`](../../../../packages/typert/loader/README.md) 与注册表仍是独立的运行时路径：loader 监听 Cordis Loader 配置项生命周期事件，导入显式发布的 `./typert` host 产物，并通过 `ctx.typert` 注册；两者都不是当前 `cordis_inspect` catalog 的数据源。

@@ -50,4 +50,4 @@ Zod emitter 对支持的节点和各类 literal 逐类执行成功与失败 pars

 新增生成目标或静态检查可复用同一 TypeGraph，业务类目也可在 PackageModel 上扩展，而无需再次解析 AST。保留计算前类型和独立 face 的代价是模型比打平后的 schema 更复杂，emitter 必须显式声明支持范围并对缺失能力失败。

-显式 opt-in 使产物发布与 package exports 由各包自行管理，根目录普通 build 和 typecheck 不会引入全仓 Typert 生成阶段。静态 Cordis catalog 可从标准模型复现，同时不把 `tool-cordis` 与运行时注册表状态耦合。`ctx.typert` 只反映当前运行时中已挂载的产物；对于消费方直接导入后仍持有的 Zod 实例，卸载流程无法控制。
+包级显式 opt-in 使产物发布与 exports 由各包自行管理。仓库编排仍可为每个已 opt-in 的包运行全仓 Host 契约 pass；该 pass 仍由后续 Remote Gateway Agent Note 负责说明。静态 Cordis catalog 可从标准模型复现，同时不把 `tool-cordis` 与运行时注册表状态耦合。`ctx.typert` 只反映当前运行时中已挂载的产物；对于消费方直接导入后仍持有的 Zod 实例，卸载流程无法控制。
@@ -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/2026-07-29-dsh-source-launch-tsx-esm.md
-2026-07-29-dsh-source-launch-tsx-esm.md: 21e912c7c7bbdd70142c202105d9a3035442884a
-2026-07-29-dsh-source-launch-tsx-esm.zh.md: dc6150b7017777eea99778cc9813e17402354462
+2026-07-29-dsh-source-launch-tsx-esm.md: aabe6c2d6a92b5cc6568eee1d42df3a6998cf0ca
+2026-07-29-dsh-source-launch-tsx-esm.zh.md: fdeb8a976e02bb9311a6ec9d097d09151a998a04
@@ -35,4 +35,4 @@ The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`
 - One launch vector across the whole engines range, including future Node lines that change native TypeScript support; the smoke gate enforces it per matrix line.
 - TypeScript transformation is delegated to tsx/esbuild again, reversing the prior note's goal of proving Node-native transformation; that goal is unreachable while vendored sources use non-erasable syntax and Node ships no transform mode.
 - The runtime declared-dependency enforcement in source launches is gone; undeclared workspace imports now surface only through static gates or built-mode resolution failures.
- Startup improves ~0.4s over the full tsx default (`demo:headless` and ACP keep `--import tsx`; their graphs were not audited for CJS-hook dependence and their launch latency is not on the interactive path).
+- Startup improves ~0.4s over the full tsx default (`demo:headless` now aliases the same `dsh run` source launch; ACP keeps `--import tsx` because its graph was not audited for CJS-hook dependence and its launch latency is not on the interactive path).
@@ -35,4 +35,4 @@ node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`
 - 整个 engines 范围（包括未来改变原生 TypeScript 支持的 Node 版本线）只有一个启动向量；冒烟门禁按矩阵行强制执行。
 - TypeScript 转换重新委托给 tsx/esbuild，逆转了前一篇 Agent Note「证明 Node 原生转换可用」的目标；在 vendor 源码使用不可擦除语法且 Node 不再提供 transform 模式的情况下，该目标不可达。
 - 源码启动中的运行时依赖声明强制不复存在；未声明的 workspace import 现在只能通过静态门禁或构建模式的解析失败暴露。
- 启动相比完整 tsx 默认形态快约 0.4s（`demo:headless` 与 ACP 保持 `--import tsx`：其依赖图未就 CJS 钩子依赖性做审计，且其启动延迟不在交互路径上）。
+- 启动相比完整 tsx 默认形态快约 0.4s（`demo:headless` 现为同一条 `dsh run` 源码启动命令的别名；ACP 保留 `--import tsx`，因为它的依赖图尚未就 CJS 钩子依赖性做审计，且其启动延迟不在交互路径上）。
@@ -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/2026-08-02-typert-remote-method-calls.md
-2026-08-02-typert-remote-method-calls.md: 215c647bcd7413b92625ee670022dc7316e3045a
-2026-08-02-typert-remote-method-calls.zh.md: 0ce431b7cbc948e937f722f2769b15a1d26dcec9
+2026-08-02-typert-remote-method-calls.md: f3db8b9eec5eb8fb610fc58edad9313e4f715326
+2026-08-02-typert-remote-method-calls.zh.md: da4459432e8c9e08821bcded2921cbd33fc5e8c8
@@ -217,6 +217,8 @@ Host lib build

 The existing top-level `build` still runs `build:lib` before `build:web`, but `build:lib` must complete the Host and Remote artifacts before starting Client TypeScript compilation. A clean build must not depend on stale `.d.ts` files from an earlier build.

+Compiler-backed repository gates that resolve the consumer surface have the same prerequisite even when their primary inputs are source files. The public `typecheck`, `lint`, and `doc-typecheck` commands run the Host contract pass first. The gate scheduler may use their `*:contracts-ready` variants only after an explicit TypeRT-contract or complete-build dependency, so parallel lanes neither read missing declarations nor run concurrent generators against the same outputs.
+
 ## The `/remote` package entry

 Every business package that provides Remote methods exports a generated `/remote` subpath:
@@ -490,6 +492,7 @@ The package topology is `api/remotes → api/gateway → client/connection → h

 - Goal Service directly decorates mutation methods whose business signatures already match the Remote contract and keeps `remoteExportCreate(...)` only to adapt `GoalView` into `CreateGoalResult`, without a second route, codec, or Client method list.
 - A clean `build:lib` emits Host and consumer Remote artifacts before Client compilation, including the business package's JS, DTS, and declaration map under `/remote`.
+- After `clean`, standalone `typecheck`, `lint`, and `doc-typecheck` regenerate the Remote contracts; the pre-push hook uses the same prepared typecheck, and CI source consumers wait for one shared contract pass.
 - Importing `@deepseek-ai/dsh-goal/remote` adds the strict `ctx.remote.goals.create(...)` type and declaration navigation to `remoteExportCreate`; omitting that import omits the namespace.
 - Mounting the same import's JS contribution supplies endpoint, parameter, result, lookup, Context, and Zod reflection and materializes the call without a handwritten stub.
 - Root and Agent-scoped calls cross the real shared `/api` carrier, resolve `agentId` to the live Agent, invoke the original Goal receiver, and return through the existing RPC envelope.
@@ -501,7 +504,7 @@ The package topology is `api/remotes → api/gateway → client/connection → h

 ## Consequences

-Remote API types depend on generated `lib` declarations. Build orchestration must finish the Host contract pass before compiling Host and Client consumers; an incorrect order makes a clean build depend on stale artifacts.
+Remote API types depend on generated `lib` declarations. Build and gate orchestration must finish the Host contract pass before compiling or semantically analyzing Host and Client consumers; an incorrect order makes a clean command depend on stale artifacts.

 Source navigation requires a Remote package to publish both its declaration map and the `src` file referenced by the map. If package `files` omits either side, types still compile but consumer navigation stops at the generated DTS. The workspace manifest check must therefore treat both as one publication contract.

@@ -217,6 +217,8 @@ Host lib build

 现有顶层 `build` 仍表现为先 `build:lib`、再 `build:web`，但 `build:lib` 内部必须先完成 Host 与 Remote artifact，再启动 Client TypeScript 编译。一次干净构建不能依赖上次残留的 `.d.ts`。

+即使主要输入是源文件，需要通过编译器解析消费方 surface 的仓库门禁也有相同的前置条件。公共 `typecheck`、`lint` 和 `doc-typecheck` 命令会先执行 Host 契约 pass。门禁调度器仅可在显式的 TypeRT 契约依赖或完整构建依赖完成后使用对应的 `*:contracts-ready` 变体，使并行 lane 既不会读取缺失的声明，也不会针对同一输出并发运行多个生成器。
+
 ## `/remote` 包入口

 每个提供 Remote 方法的业务包导出生成的 `/remote` 子路径：
@@ -490,6 +492,7 @@ Connection 提供共享 channel interceptor 与当前 HTTP carrier 映射。WebS

 - Goal Service 直接装饰业务签名已经符合 Remote 契约的变更类方法，仅保留 `remoteExportCreate(...)` 把 `GoalView` 适配为 `CreateGoalResult`，无需第二条路由、第二份 codec 或 Client 方法清单。
 - 一次干净的 `build:lib` 会在 Client 编译前生成 Host 与消费方 Remote 产物，包括业务包 `/remote` 下的 JS、DTS 和 declaration map。
+- `clean` 后，单独运行 `typecheck`、`lint` 或 `doc-typecheck` 都会重新生成 Remote 契约；pre-push 钩子使用同一个已包含契约准备步骤的 typecheck，CI 中的源码消费方则等待一次共享的契约 pass。
 - 导入 `@deepseek-ai/dsh-goal/remote` 会加入严格的 `ctx.remote.goals.create(...)` 类型，并可通过 declaration 导航到 `remoteExportCreate`；不导入时不会出现该 namespace。
 - 挂载同一次 import 得到的 JS contribution 会提供 endpoint、参数、结果、lookup、Context 和 Zod 反射，并在无需手写 stub 的情况下实体化调用。
 - Root 与 Agent-scoped 调用会经过真实的共享 `/api` carrier，将 `agentId` 解析为活 Agent，调用原始 Goal receiver，并通过既有 RPC envelope 返回。
@@ -501,7 +504,7 @@ Connection 提供共享 channel interceptor 与当前 HTTP carrier 映射。WebS

 ## 后果

-Remote API 类型依赖生成的 `lib` 声明，构建编排必须在 Host 和 Client 消费端编译前完成 contract pass；顺序错误会让干净构建依赖陈旧产物。
+Remote API 类型依赖生成的 `lib` 声明，构建与门禁编排必须在对 Host 和 Client 消费方进行编译或语义分析之前完成 Host 契约 pass；顺序错误会使干净环境中的命令依赖陈旧产物。

 源码导航依赖 Remote package 同时发布 declaration map 和 map 指向的 `src`。package `files` 漏掉任一侧时类型仍可编译，但消费端跳转会停在生成 DTS，因此 workspace manifest 校验必须把两者作为同一发布契约。

@@ -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/2026-08-05-profile-plugin-bundles.md
-2026-08-05-profile-plugin-bundles.md: 11a8ac3d4005371ca9596ba237aaf42a8e770dee
-2026-08-05-profile-plugin-bundles.zh.md: 0e9ebf657ccb9d05967d90a935b356acf287a24c
+2026-08-05-profile-plugin-bundles.md: 8613e600ad633818abb4319e614230340c3b3876
+2026-08-05-profile-plugin-bundles.zh.md: 03a771364c4f3262801f28e68b96ec5de633e5ec
@@ -12,7 +12,9 @@ The `dsh` launcher hardcoded its compositions: `base.cordis.yml` + `web.cordis.y

 Everything becomes a **profile**: a directory `$DSH_HOME/profiles/<name>` with a `package.json` (pnpm-managed out-of-tree plugin `dependencies` plus the profile manifest `dsh.profile` with its ordered `bundles` layer list) and a user `cordis.patch.yml`. A **bundle** is an npm package declaring `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }`; the two manifest kinds live under distinct `dsh.profile` / `dsh.bundle` keys so a package.json states which role it plays. The tree composes over an empty root by applying each bundle's patch in `dsh.profile.bundles` order, then the user layer, then `--patch` overlays, then flag patches — one `applyEntryPatches` call, identical for boot, flag derivation, and `--dump-config`.

-The shipped compositions became bundles: `@deepseek-ai/dsh-base` (the former base rows as one insert), `@deepseek-ai/dsh-web-app` (the former web overlay plus a runtime glue plugin that owns what used to be launcher code — frontend-dist resolution, the web-surface prompt section, bash runtime variables, the URL line), and `@deepseek-ai/dsh-headless` (a one-shot runner plugin over base + web-app). `dsh web` stays as an alias for `--profile web` carrying the Web flag family; `dsh --profile headless "task"` replaces `-p`; `dsh --config` is removed (its uses migrate to `--patch`). `dsh plugin --profile <name> <args...>` is a thin pnpm forwarder that initializes the profile and reconciles `dsh.profile.bundles` after `add`/`remove` (a bundle-less package warns and stays a plain dependency).
+The shipped compositions became bundles: `@deepseek-ai/dsh-base` (the former base rows as one insert), `@deepseek-ai/dsh-web-app` (the former web overlay plus a runtime glue plugin that owns what used to be launcher code — frontend-dist resolution, the web-surface prompt section, bash runtime variables, the URL line), and `@deepseek-ai/dsh-headless` (a one-shot runner plugin over base + web-app). `dsh web` stays as an alias for `--profile web` carrying the Web flag family; `dsh run [--profile <name>] "task"` owns one-shot execution and defaults to the headless profile, while generic `dsh --profile <name>` boots without a task; `dsh --config` is removed (its uses migrate to `--patch`). `dsh plugin --profile <name> <args...>` is a thin pnpm forwarder that initializes the profile and reconciles `dsh.profile.bundles` after `add`/`remove` (a bundle-less package warns and stays a plain dependency).
+
+The [`dsh run` command decision](../feature/2026-08-08-dsh-run-headless-command.md) owns the one-shot grammar; this note owns the profile composition it selects.

 Resolution is two-anchored by construction: `dsh.profile.bundles` names resolve from the dsh installation first, then the profile directory — so in-box bundles always come from the same installation as the running `dsh` and pnpm never manages them — while bare plugin names in patch rows resolve through the profile directory's Node parent-walk into the maintained flat fallback `$DSH_HOME/profiles/node_modules` (one symlink per package the installation's app and bundles depend on, healed on every launch).

@@ -12,7 +12,9 @@ Status: implemented

 一切都变成 **profile**：即目录 `$DSH_HOME/profiles/<name>`，其中包含一个 `package.json`（pnpm 管理的树外插件 `dependencies`，加上 profile manifest `dsh.profile` 及其有序的 `bundles` 层列表）和一份用户 `cordis.patch.yml`。**组合包**（bundle）是声明了 `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }` 的 npm 包；两种 manifest 分别位于互不相同的 `dsh.profile` / `dsh.bundle` 键下，因此一份 package.json 能说明自己扮演哪种角色。配置树在空的根之上组合：按 `dsh.profile.bundles` 顺序应用每个组合包的 patch，然后是用户层，然后是 `--patch` overlay，最后是 flag patch——全部收敛为一次 `applyEntryPatches` 调用，启动、flag 派生与 `--dump-config` 使用完全相同的路径。

-已交付的组合改造成了组合包：`@deepseek-ai/dsh-base`（原有基础行合并为一次插入）、`@deepseek-ai/dsh-web-app`（原 web overlay，外加一个接管原启动器代码的运行时粘合插件——前端 dist 解析、web 表层提示词段落、bash 运行时变量、URL 行）、`@deepseek-ai/dsh-headless`（叠加在 base + web-app 之上的一次性 runner 插件）。`dsh web` 保留为携带 Web flag 家族的 `--profile web` 别名；`dsh --profile headless "task"` 取代 `-p`；`dsh --config` 被移除（其用途迁移到 `--patch`）。`dsh plugin --profile <name> <args...>` 是一层薄薄的 pnpm 转发器，负责初始化 profile，并在 `add`／`remove` 后调和 `dsh.profile.bundles`（没有组合包声明的包会给出警告，保持为普通依赖）。
+已交付的组合改造成了组合包：`@deepseek-ai/dsh-base`（原有基础行合并为一次插入）、`@deepseek-ai/dsh-web-app`（原 web overlay，外加一个接管原启动器代码的运行时粘合插件——前端 dist 解析、web 表层提示词段落、bash 运行时变量、URL 行）、`@deepseek-ai/dsh-headless`（叠加在 base + web-app 之上的一次性 runner 插件）。`dsh web` 保留为携带 Web flag 家族的 `--profile web` 别名；`dsh run [--profile <name>] "task"` 负责一次性执行，默认使用 headless profile，而通用的 `dsh --profile <name>` 只启动 profile，不携带任务；`dsh --config` 被移除（其用途迁移到 `--patch`）。`dsh plugin --profile <name> <args...>` 是一层薄薄的 pnpm 转发器，负责初始化 profile，并在 `add`／`remove` 后调和 `dsh.profile.bundles`（没有组合包声明的包会给出警告，保持为普通依赖）。
+
+[`dsh run` 命令决策](../feature/2026-08-08-dsh-run-headless-command.md)负责一次性语法；本 Agent Note 负责该语法所选择的 profile 组合。

 解析在构造上就是双锚点的：`dsh.profile.bundles` 中的名称先从 dsh 安装目录解析，再从 profile 目录解析——因此内置组合包始终来自与运行中 `dsh` 相同的安装，pnpm 从不管理它们——而 patch 行中的裸插件名称经 profile 目录的 Node 父目录逐级查找，落到受维护的扁平回退目录 `$DSH_HOME/profiles/node_modules`（安装目录的应用与各组合包所依赖的每个包各一个符号链接，每次启动时修复）。

@@ -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/2026-07-20-error-cause-chain-diagnostics.md
-2026-07-20-error-cause-chain-diagnostics.md: 7de1f4f631cec90048ccc8eab7a6654560d84846
-2026-07-20-error-cause-chain-diagnostics.zh.md: 6ce642eb4a18a1a412fb63c3bb00042a921f4da3
+2026-07-20-error-cause-chain-diagnostics.md: 89edd4529cc16617fdca736dbbea4b170400d6bd
+2026-07-20-error-cause-chain-diagnostics.zh.md: 673921c913a9f1fefe6f85303cf5952f8edbcc1d
@@ -34,4 +34,4 @@ A TUI run against an unreachable DeepSeek endpoint failed with the single notice
 - Durable `turn/end` error messages include cause detail. Existing snapshot fixtures replay byte-identically because their scripted errors carry no `cause` (for such errors `errorChain(err)` equals `err.message`); only unit-test expectation strings changed. A fixture recorded from a real transport failure would carry the chain.
 - `errorChain` renders `message` without the class name (`String(error)` rendered `Error: <message>`), so a bare `TypeError` in a log line loses its type label unless its message is empty (then the name is the fallback). The chain detail was judged worth more than the class name at these seams.
 - `dsh-stdio` output for failed turns is no longer silent; piped consumers that parsed the transcript see new `[turn …]` lines.
- Remaining `renderThrown` copies in `dsh-subagent`, `dsh-workflow`, `dsh-skill`, `dsh-workflow-workerthread`, and `cli-demo` still render without the chain; they wrap package-local errors that carry their own messages, and can adopt `errorChain` when their diagnostics prove insufficient.
+- Remaining `renderThrown` copies in `dsh-subagent`, `dsh-workflow`, `dsh-skill`, and `dsh-workflow-workerthread` still render without the chain; they wrap package-local errors that carry their own messages, and can adopt `errorChain` when their diagnostics prove insufficient.
@@ -34,4 +34,4 @@ TUI 连接不可达的 DeepSeek 端点时，失败只显示一条 `fetch failed`
 - 持久化的 `turn/end` 错误消息包含 cause 细节。现有快照 fixture（测试前置数据）字节级一致地回放，因为其脚本化错误不带 `cause`（对这类错误 `errorChain(err)` 等于 `err.message`）；只有单元测试的期望字符串有变化。从真实传输失败录制的 fixture 会携带完整链。
 - `errorChain` 渲染 `message` 而不带类名（`String(error)` 会渲染 `Error: <message>`），因此日志行里的裸 `TypeError` 会丢失类型标签，除非消息为空（此时回退到类名）。在这些诊断界面上，链细节被判断为比类名更有价值。
 - `dsh-stdio` 对失败轮次的输出不再沉默；解析 transcript 的管道消费方会看到新的 `[turn …]` 行。
- `dsh-subagent`、`dsh-workflow`、`dsh-skill`、`dsh-workflow-workerthread`、`cli-demo` 里剩余的 `renderThrown` 副本仍不渲染链；它们包装的是自带消息的包内错误，等诊断信息证明不足时再采用 `errorChain`。
+- `dsh-subagent`、`dsh-workflow`、`dsh-skill`、`dsh-workflow-workerthread` 里剩余的 `renderThrown` 副本仍不渲染链；它们包装的是自带消息的包内错误，等诊断信息证明不足时再采用 `errorChain`。
@@ -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/2026-07-21-compaction-summary-prefix-cache-reuse.md
-2026-07-21-compaction-summary-prefix-cache-reuse.md: d05d25cfa7c3984ce0ce75c38068a91a0e07dfe8
-2026-07-21-compaction-summary-prefix-cache-reuse.zh.md: f31c33e680b3db60a6fb758a522addca63224fea
+2026-07-21-compaction-summary-prefix-cache-reuse.md: fb6524846f837b783423b3ed0e043cd4e1f7849d
+2026-07-21-compaction-summary-prefix-cache-reuse.zh.md: e6072313b7089b9dda14c298fcb94db786220501
@@ -29,7 +29,7 @@ Auto-compaction always anchors at the surface head, so the shadowed region is th
 - **Keep the summarizer system prompt but reuse the rest** — rejected: the system slot is the very first token region a provider caches on, so a distinct summarizer system prompt invalidates the whole prefix regardless of what follows. Only moving the directive off the front recovers the cache.
 - **Send only the shadowed region without the `system`/`tools` head** — rejected: a differently-headed sequence still diverges from the cached request at the first token, so it caches no better while losing the framing the summary needs.
 - **Omit `tools` from the summarization request** (the model never calls one) — rejected: tool schemas are part of the cached token sequence; omitting them misaligns every following token and defeats reuse.
- **A dedicated `assistant/chunk`-emitting summarization sub-session for snapshot replay** — out of scope here; the replay gap predates this change and is tracked in the [compaction-seam note](../feature/2026-06-18-compaction-capability-seam.md).
+- **A dedicated `assistant/chunk`-emitting summarization sub-session for snapshot replay** — rejected: the durable `compact/summary` event records the successful local call's position and complete output, while its explicit call marker prevents replay from treating template or remote output as a local stream.

 ## Consequences

@@ -42,4 +42,4 @@ Auto-compaction always anchors at the surface head, so the shadowed region is th

 - **Unit:** `compact-basic.spec.ts` asserts the auxiliary call forwards `system`/`tools`/leading messages and appends the compaction instruction as the final message, and that `compactRegion` replays the latest routed header prefix. Existing content assertions read the summarizer input through the replayed messages rather than a transcript string.
 - **Loop:** `compact-loop-repro.spec.ts` classifies the summarization request by the compaction instruction in its trailing user message, and the overflow-recovery tests continue to pin conversation-vs-summary request counts across the real loop.
- **Snapshot gap unchanged:** the summarization call still emits no `assistant/chunk` events, so it remains outside keyless replay; the pre-existing gap is owned by the [compaction-seam note](../feature/2026-06-18-compaction-capability-seam.md).
+- **Snapshot:** keyless replay reconstructs one canonical successful stream from a marked `compact/summary`; the [compaction-seam note](../feature/2026-06-18-compaction-capability-seam.md) owns the durable marker contract.
@@ -29,7 +29,7 @@ Status: implemented
 - **保留摘要器系统提示词但复用其余部分**——否决：system 槽位正是提供方最先做缓存的 token 区域，因此一个不同的摘要器系统提示词无论后面跟着什么都会使整个前缀失效。只有把指令移离前端才能恢复缓存。
 - **只发送被遮蔽区域而不带 `system`/`tools` 头部**——否决：头部不同的序列在第一个 token 处仍然与已缓存请求分叉，因此缓存效果并不更好，反而丢失了摘要所需的框架。
 - **从摘要请求中省略 `tools`**（模型从不调用任何工具）——否决：工具 schema 是已缓存 token 序列的一部分；省略它们会让后续每个 token 失去对齐，破坏复用。
- **为快照回放专门建立一个发出 `assistant/chunk` 的摘要子会话**——此处超出范围；该回放缺口早于本次改动，记录在 [compaction-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 中。
+- **为快照回放专门建立一个发出 `assistant/chunk` 的摘要子会话**——否决：持久的 `compact/summary` 事件会记录成功本地调用的位置和完整输出，而显式调用标记可防止回放把模板或远程输出当作本地流。

 ## 后果

@@ -42,4 +42,4 @@ Status: implemented

 - **单元：** `compact-basic.spec.ts` 断言辅助调用转发 `system`/`tools`/前导消息，并把压缩指令作为最后一条消息追加，且 `compactRegion` 回放最新的已路由 header 前缀。现有的内容断言通过回放的消息而非 transcript 字符串来读取摘要器输入。
 - **循环：** `compact-loop-repro.spec.ts` 依据摘要请求尾部 user 消息中的压缩指令对其分类，溢出恢复测试则继续在真实循环中固定对话请求与摘要请求的数量。
- **快照缺口未变：** 摘要调用仍然不发出 `assistant/chunk` 事件，因此它仍处于无密钥回放之外；这一既有缺口归 [compaction-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 所有。
+- **快照：** 无密钥回放会从带标记的 `compact/summary` 重建一条规范成功流；[compaction-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 负责持久标记契约。
@@ -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/2026-07-30-web-transcript-log-ordered-projection.md
-2026-07-30-web-transcript-log-ordered-projection.md: 558d60cf6f6638c3e776396dd754d31b95819b28
-2026-07-30-web-transcript-log-ordered-projection.zh.md: 2eb216fd1970700fb54a2aa17ec5ce515869e5b0
+2026-07-30-web-transcript-log-ordered-projection.md: 3b7aaeb1178ff79e38a1b9646a9dc78efaeae48b
+2026-07-30-web-transcript-log-ordered-projection.zh.md: acd198b6d3f3c5d57e233e09ee66f5d151e4f8f1
@@ -18,9 +18,11 @@ Node order is seq-monotonic by construction, and three things follow. The log-on

 `foldDegraded` is gone from `ConversationSnapshot`, and with it the padding sentinels, the `baseSeq` arithmetic they needed, and `degradedSeqs()`. They existed only to satisfy the core fold's `seq === index` assertion and to survive its throw; the fold they describe is no longer run. Deleting the flag is part of the fix, not cleanup after it — `degradedSeqs()` was already almost the log-ordered projection, reached after a thrown error instead of intended.

-The marker's summary text comes from the checkpoint's own `compact/summary` provenance, never from the framed checkpoint payload, which is an instruction envelope written for the model. A window cut that left the provenance outside makes the row non-expandable rather than empty, the same soft-fall as a call-less tool result, and a later page supplying the provenance resolves the text.
+The marker's summary text, replaced-item count, and estimated shadowed-token count come from the checkpoint's own `compact/summary` provenance, never from the framed checkpoint payload, which is an instruction envelope written for the model. A window cut that left the provenance outside makes those fields unavailable, the same soft-fall as a call-less tool result, and a later page supplying the provenance resolves them.

-No persisted event, RPC envelope, compaction transaction, or model-visible surface changed, and no migration is required.
+The [manual compaction command](../feature/2026-07-30-queued-manual-compaction.md) returns the summary event's seq as the successful `CommandResult.sourceEventSeq`, and `command/done` persists that optional reference. Chat pairs only a successful named `/compact` command whose reference equals exactly one loaded `CompactionSummaryNode.summaryEventSeq`. The running command first renders `compact · Compacting context…`; after the checkpoint lands, the same React key renders one collapsed `compact` disclosure at the checkpoint's flow position with the count and token estimate. Input rejection, no compactable history, cancellation, and failure remain generic command rows with complete handler-authored text. Automatic compaction has no command reference and keeps the standalone context-compacted marker.
+
+The explicit event reference matters because manual compaction permits durable context injection while its asynchronous summary is running: command and checkpoint rows are not guaranteed to be adjacent. The command lifecycle event gains one optional field, but the compaction transaction, RPC envelope, and model-visible surface do not change; pre-release persisted logs without the field keep the former two-row soft-fall and require no migration.

 ## Recognizing a checkpoint: one declaration, pinned at compile time

@@ -57,6 +59,10 @@ The unmerged manual-compaction-queueing branch fixes the same interleaving bug b

 **Keep `foldDegraded` as a defensive flag.** Rejected: it described a specific failure of a fold that no longer runs. A flag no consumer can act on, reachable only through a `console.error`, is a false contract.

+**Pair the nearest `/compact` row with the next checkpoint.** Rejected: context injection may land between them, and concurrent or malformed lifecycle records must degrade without stealing another checkpoint. The command result instead names the authoritative summary event, and ambiguous references pair nothing.
+
+**Parse the English settlement text for item and token counts.** Rejected: handler copy is presentation text, not a stable data contract. The marker reads the structured `compact/summary` payload already owning both values.
+
 ## Consequences

 Compaction no longer erases web history; a session compacted several times shows one marker per landed compaction, in log order, and the same window renders identically live and after a cold resume. The pagination hole is closed by construction rather than defended against, and `ConversationSnapshot` loses a published field, which touched thirteen files.
@@ -65,8 +71,8 @@ Compaction no longer erases web history; a session compacted several times shows

 The performance contract is unchanged and now simpler to state: one append materializes one node, an event that changes no node keeps the previous array reference — so a chunk storm costs nothing and `nodes()` is not even recomputed — and unchanged nodes keep their object identity. The window still grows with session length rather than with the surface, which is the trade the fix exists to make; a compaction used to bound the projection for exactly the long sessions compaction serves.

-The web e2e scenario now seeds a real compaction transaction over its recorded turn, so the aria golden pins both halves of the fix through the real host and a real browser: the recorded prompt and full tool output are still on screen, and one marker sits after them. The seed recording itself is untouched and stays model-authentic — replay derives the compacted turn from the recording's own surface.
+The web e2e scenario now seeds a real manual command lifecycle around a compaction transaction over its recorded turn, so the aria golden pins the complete behavior through the real host and a real browser: the recorded prompt and full tool output are still on screen, exactly one `compact` row reports scale after them, and its disclosure opens the exact summary. The seed recording itself is untouched and stays model-authentic — replay derives the manual compaction from the recording's own surface.

 ## Deferred

-The terminal's [archived compaction progress decision](../../archived/feature/2026-07-30-compaction-progress-visibility.md) uses the live standalone bracket to drive a one-cell indicator and does not change this browser projection. The marker still carries no **scale**: the checkpoint's `sourceEventSeqs` hold the shadowed count, so a separately justified count or range can be added without coupling it to progress.
+The terminal's [archived compaction progress decision](../../archived/feature/2026-07-30-compaction-progress-visibility.md) uses the live standalone bracket to drive a one-cell indicator and does not change this browser projection.
@@ -18,9 +18,11 @@ surface 顺序还让另外两个问题成为结构性的。一次替换之后它

 `foldDegraded` 从 `ConversationSnapshot` 消失，随之消失的是哨兵填充、它们所需的 `baseSeq` 算术，以及 `degradedSeqs()`。它们的存在只为满足核心 fold 的 `seq === index` 断言并在其抛错时存活；它们所描述的 fold 已不再运行。删除该标志是修复的一部分，而非修复之后的清理——`degradedSeqs()` 本身已几乎就是按日志顺序的投影，只是作为抛错后的落点而非本意到达。

-标记的摘要文本来自检查点自己的 `compact/summary` 溯源，绝不取自成框的检查点载荷——那是为模型撰写的指令信封。窗口切分把溯源留在窗口外时该行不可展开而非空白，与无调用的工具结果同一种软退让；后续补上溯源的分页会解析出文本。
+标记的摘要文本、被替换条目数量和估算的被遮蔽 token 数量都来自检查点自己的 `compact/summary` 溯源，绝不取自成框的检查点载荷——那是为模型撰写的指令信封。窗口切分把溯源留在窗口外时这些字段不可用，与无调用的工具结果同一种软退让；后续补上溯源的分页会解析出它们。

-没有任何持久化事件、RPC 信封、压缩事务或模型可见 surface 发生变化，也不需要迁移。
+[手动压缩命令](../feature/2026-07-30-queued-manual-compaction.md)会把摘要事件的 seq 作为成功结果的 `CommandResult.sourceEventSeq` 返回，`command/done` 则持久化这项可选引用。Chat 只会配对成功且名称为 `/compact`、其引用恰好等于唯一一个已加载 `CompactionSummaryNode.summaryEventSeq` 的命令。运行中的命令先渲染为 `compact · Compacting context…`；检查点落地后，同一个 React key 会在检查点的消息流位置渲染一条收起的 `compact` 展开项，并显示条目数量和 token 估算值。输入被拒绝、没有可压缩历史、取消和失败时仍使用通用命令行，并保留处理器撰写的完整文本。自动压缩没有命令引用，继续使用独立的上下文已压缩标记。
+
+显式事件引用之所以重要，是因为手动压缩允许在异步摘要运行期间注入持久上下文：命令行与检查点行不保证相邻。命令生命周期事件增加一个可选字段，但压缩事务、RPC 信封和模型可见 surface 均不变化；不含该字段的预发布持久日志继续采用原先的两行软退让，无须迁移。

 ## 识别检查点：同一份声明，在编译期钉住

@@ -57,6 +59,10 @@ const COMPACT_PLUGIN: typeof COMPACT_CHECKPOINT_SOURCE.plugin = 'compact'

 **把 `foldDegraded` 留作一个防御性标志。** 已拒绝：它描述的是一个已不再运行的 fold 的特定失败。一个消费方无法据以行动、只能通过 `console.error` 到达的标志，是一份虚假契约。

+**把最近的 `/compact` 行与下一个检查点配对。** 已拒绝：两者之间可能落入上下文注入，并发或格式异常的生命周期记录也必须降级而不误取其他检查点。命令结果则指明权威摘要事件；引用存在歧义时不配对任何内容。
+
+**解析英文结算文本中的条目数量和 token 数量。** 已拒绝：处理器文案是呈现文本，而非稳定的数据契约。标记读取本已持有这两个值的结构化 `compact/summary` 载荷。
+
 ## Consequences

 压缩不再抹掉 Web 历史；一个被压缩多次的会话按日志顺序显示每次落地压缩一个标记，而同一窗口在实时与冷恢复之后渲染完全相同。分页缺口是被构造性闭合而非被防御，`ConversationSnapshot` 少了一个已发布字段，这触及十三个文件。
@@ -65,8 +71,8 @@ const COMPACT_PLUGIN: typeof COMPACT_CHECKPOINT_SOURCE.plugin = 'compact'

 性能契约未变，且现在更易表述：一次追加物化一个节点，不改变任何节点的事件保持上一次的数组引用——因此分片风暴零成本、`nodes()` 甚至不会重算——未变化的节点保持其对象标识。窗口仍随会话长度而非随 surface 增长，这正是本修复存在所要做的交换；一次压缩过去恰好为压缩所服务的长会话限制了投影规模。

-Web e2e 场景现在在它录制的那一轮之上播种一次真实的压缩事务，因此 aria 基准经真实宿主与真实浏览器钉住修复的两半：录制的提问与完整工具输出仍在屏幕上，其后坐着一个标记。录制本身未被触碰、保持模型真实——回放从录制自身的 surface 派生出被压缩的那一轮。
+Web e2e 场景现在围绕它录制的那一轮上的压缩事务播种一次真实的手动命令生命周期，因此 aria 基准经真实宿主与真实浏览器钉住完整行为：录制的提问与完整工具输出仍在屏幕上，其后恰好一条 `compact` 行报告规模，展开后会显示确切摘要。录制本身未被触碰、保持模型真实——回放从录制自身的 surface 派生出手动压缩。

 ## Deferred

-终端的[已归档压缩进度决策](../../archived/feature/2026-07-30-compaction-progress-visibility.md)使用实时独立标记对驱动单格指示器，并不改变此浏览器投影。标记仍不携带**规模**信息：检查点的 `sourceEventSeqs` 保存被遮蔽的数量，因此可以另行论证后添加计数或区间，而无须将其与进度耦合。
+终端的[已归档压缩进度决策](../../archived/feature/2026-07-30-compaction-progress-visibility.md)使用实时独立标记对驱动单格指示器，并不改变此浏览器投影。
@@ -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/2026-08-03-cli-signal-shutdown-escalation.md
-2026-08-03-cli-signal-shutdown-escalation.md: 2746b5784baad0f3b14258280cd56a621db07c15
-2026-08-03-cli-signal-shutdown-escalation.zh.md: 0bda83327d4cc8fe2edb61f8145a89138610901e
+2026-08-03-cli-signal-shutdown-escalation.md: 7c9715c37ee57be9fa0f67af0c19f0bfa84845da
+2026-08-03-cli-signal-shutdown-escalation.zh.md: f3485edc9e453c0b774f442bfce6d678d63f2224
@@ -6,9 +6,9 @@ English | [中文](2026-08-03-cli-signal-shutdown-escalation.zh.md)

 ## Problem

-The default telemetry mount added SIGINT/SIGTERM handlers to `dsh web` and `dsh -p` so process exit could drain the Cordis tree instead of dropping queued telemetry. Each handler used a one-way boolean latch and exited only after `ctx.fiber.dispose()` settled. Headless normal completion also awaited that disposal without a bound.
+The default telemetry mount added SIGINT/SIGTERM handlers to `dsh web` and the headless command (now `dsh run`) so process exit could drain the Cordis tree instead of dropping queued telemetry. Each handler used a one-way boolean latch and exited only after `ctx.fiber.dispose()` settled. Headless normal completion also awaited that disposal without a bound.

-A user then reproduced `dsh -p` hanging immediately after the observation URL and ignoring repeated `Ctrl+C`; `DSH_TELEMETRY_DISABLED=1` removed the hang, while a standalone Node handler in the same Linux sandbox received SIGINT. This isolated the pending disposer to telemetry rather than terminal signal forwarding. OTel's `BatchLogRecordProcessor.shutdown()` awaits `exporter.forceFlush()` before the `exportTimeoutMillis`-bounded completion promise, and the OTLP exporter's `forceFlush()` waits directly on its in-flight HTTP Promise. A proxy/sandbox connection that never obtains a socket can therefore leave provider shutdown pending despite both configured SDK timeouts.
+A user then reproduced the headless command hanging immediately after the observation URL and ignoring repeated `Ctrl+C`; `DSH_TELEMETRY_DISABLED=1` removed the hang, while a standalone Node handler in the same Linux sandbox received SIGINT. This isolated the pending disposer to telemetry rather than terminal signal forwarding. OTel's `BatchLogRecordProcessor.shutdown()` awaits `exporter.forceFlush()` before the `exportTimeoutMillis`-bounded completion promise, and the OTLP exporter's `forceFlush()` waits directly on its in-flight HTTP Promise. A proxy/sandbox connection that never obtains a socket can therefore leave provider shutdown pending despite both configured SDK timeouts.

 The latch then turned that telemetry defect into an unkillable CLI: normal completion was already awaiting the single-shot root disposal; the first SIGINT joined the same pending disposal and set the signal latch; later SIGINTs returned at the latch, so the process had no remaining escape. A signal received before normal completion had the same unbounded wait. Web used the same latch shape.

@@ -6,9 +6,9 @@

 ## 问题

-默认挂载遥测后，`dsh web` 与 `dsh -p` 新增了 SIGINT/SIGTERM 处理器，使进程退出时可以排空 Cordis 插件树，而不是丢弃排队中的遥测数据。每个处理器都使用单向布尔闩锁（latch），并且只有在 `ctx.fiber.dispose()` 结算后才退出。headless 正常完成时同样会无界等待整棵树执行 dispose（资源释放）。
+默认挂载遥测后，`dsh web` 与 headless 命令（现为 `dsh run`）新增了 SIGINT/SIGTERM 处理器，使进程退出时可以排空 Cordis 插件树，而不是丢弃排队中的遥测数据。每个处理器都使用单向布尔闩锁（latch），并且只有在 `ctx.fiber.dispose()` 结算后才退出。headless 正常完成时同样会无界等待整棵树执行 dispose（资源释放）。

-随后有用户复现，`dsh -p` 在打印观察 URL 后立即卡死，重复按 `Ctrl+C` 也没有反应；设置 `DSH_TELEMETRY_DISABLED=1` 后不再卡死，而同一 Linux 沙箱中的独立 Node 信号处理器能够收到 SIGINT。这将待结算的 disposer 定位到遥测，而非终端信号转发。OTel 的 `BatchLogRecordProcessor.shutdown()` 会先等待 `exporter.forceFlush()`，再进入受 `exportTimeoutMillis` 限制的完成 promise；OTLP 导出器的 `forceFlush()` 则直接等待正在进行的 HTTP Promise。因此，代理／沙箱连接始终无法取得 socket 时，即使已经配置两项 SDK 超时，也会让提供方关闭一直待结算。
+随后有用户复现，headless 命令在打印观察 URL 后立即卡死，重复按 `Ctrl+C` 也没有反应；设置 `DSH_TELEMETRY_DISABLED=1` 后不再卡死，而同一 Linux 沙箱中的独立 Node 信号处理器能够收到 SIGINT。这将待结算的 disposer 定位到遥测，而非终端信号转发。OTel 的 `BatchLogRecordProcessor.shutdown()` 会先等待 `exporter.forceFlush()`，再进入受 `exportTimeoutMillis` 限制的完成 promise；OTLP 导出器的 `forceFlush()` 则直接等待正在进行的 HTTP Promise。因此，代理／沙箱连接始终无法取得 socket 时，即使已经配置两项 SDK 超时，也会让提供方关闭一直待结算。

 闩锁随后把这个遥测缺陷变成无法终止的 CLI（命令行界面）：正常完成流程已经在等待单次根级 dispose；第一次 SIGINT 会加入同一个待结算的 dispose，并设置信号闩锁；后续 SIGINT 在闩锁处直接返回，因此进程再无退出途径。正常完成之前收到信号时，同样会陷入无界等待。Web 使用的闩锁结构与此相同。

@@ -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/2026-06-18-compaction-capability-seam.md
-2026-06-18-compaction-capability-seam.md: 8dcbe74429a620027a570124383442b969c12196
-2026-06-18-compaction-capability-seam.zh.md: 27b63f29c2e6f35637185b47c882ae42e5d41088
+2026-06-18-compaction-capability-seam.md: 390d091fd6e6f7fa1694ba78b90522b70948fe92
+2026-06-18-compaction-capability-seam.zh.md: d72793e6adde911a8623ac1c6b65df899381923e
@@ -33,7 +33,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis"

 An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold.

-`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` requires an idle agent and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`.
+`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` requires an idle agent and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The result carries `llmStreamCall: true` because it consumed exactly one call through this context's LLM service; a subclass sets that marker only under the same condition, since retained `rawOutput` alone does not identify the call path. The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`.

 ### Automatic pressure runs after successful durable step work

@@ -76,7 +76,7 @@ Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` e
 ```
 compact/start    → log-only. Acquires the lock.
 [summarize older range via the backend]
-compact/summary  → log-only. Provenance: raw summary, range, shadowed seqs, token count.
+compact/summary  → log-only. Provenance: raw summary, local-call marker, range, shadowed seqs, token count.
 user/message     → canonical checkpoint source + surfaceOp { op:'replace', start, end }.
                   THE surface mutation (framed summary).
                   deriveMessages() renders it as a user-role message.
@@ -131,4 +131,4 @@ The lifecycle boundary makes crash state unambiguous:
 - **Loop:** Tests pin pre-step after the preceding `step/end` and before the next `step/start`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition.
 - **Manual:** Maintenance serialization, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key.
 - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task.
- **Snapshot gap:** The summarization call is session-associated and logs `compact/summary`, but ordinary transcript replay does not derive its auxiliary response; keyless assembled coverage therefore needs an explicit replay override.
+- **Snapshot:** The assembled context-overflow scenario derives the auxiliary call from `compact/summary` only when `llmStreamCall: true` proves that the local LLM service consumed it; canonical reconstructed blocks pin the complete recovery without provider delta partitioning.
@@ -33,7 +33,7 @@ Status: implemented

 早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将契约重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。

-`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 要求 agent 处于 idle，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。
+`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 要求 agent 处于 idle，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该结果携带 `llmStreamCall: true`，因为生成它时恰好通过此上下文的 LLM 服务发起了一次调用；只有满足相同条件时，子类才设置该标记，因为单有保留的 `rawOutput` 并不能判定调用路径。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。

 ### 成功的持久步骤工作完成后运行自动压力检查

@@ -76,7 +76,7 @@ retry → next numbered step/start      ⟵ derives from the replacement surface
 ```
 compact/start    → log-only. Acquires the lock.
 [summarize older range via the backend]
-compact/summary  → log-only. Provenance: raw summary, range, shadowed seqs, token count.
+compact/summary  → log-only. Provenance: raw summary, local-call marker, range, shadowed seqs, token count.
 user/message     → canonical checkpoint source + surfaceOp { op:'replace', start, end }.
                   THE surface mutation (framed summary).
                   deriveMessages() renders it as a user-role message.
@@ -131,4 +131,4 @@ compact/end      → log-only. Releases the lock (carries `error` on a recoverab
 - **循环测试：** 测试固定 pre-step 发生在前一个 `step/end` 之后、下一个 `step/start` 之前，使用实际 `agent/request` 路由，关闭失败步骤，分配新的重试编号，并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。
 - **手动测试：** 无需模型密钥即可固定 maintenance 串行化、标记顺序、注入保留、活动／陈旧未匹配标记分类、取消、闭合／flush 失败、命令映射以及排队 TUI 流程。
 - **带密钥 e2e：** 真实模型和 bash 会话在降低的限制下触发压缩，记录完整的 `compact/start…end` 对，缩小 surface，并完成任务。
- **快照缺口：** 摘要调用与会话关联并记录 `compact/summary`，但普通 transcript（文本记录）回放不会派生其辅助响应；因此，要实现无密钥的组装态覆盖，就必须显式提供回放 override。
+- **快照：** 组装后的上下文溢出场景仅在 `llmStreamCall: true` 证明本地 LLM 服务执行了辅助调用时，才从 `compact/summary` 派生该调用；规范重建的块在不固定提供方增量切分的情况下固定完整恢复过程。
@@ -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/2026-06-24-workspace-context.md
-2026-06-24-workspace-context.md: 3c21b7599e6bb2dd759e4a040c1b999f1b0516cd
-2026-06-24-workspace-context.zh.md: e913ecb22b4692e1ee7b96d4f5effe2606775cf8
+2026-06-24-workspace-context.md: 53a580aee50752b7c6daeff5caa42ba6409c8885
+2026-06-24-workspace-context.zh.md: dc1d6b5dc2c9f576e7298c891a3a1145f123a8db
@@ -14,7 +14,7 @@ The lifecycle has two distinct classes of content. The initial applicable chain

 ## Decision

-The implementation lives in `packages/context/workspace-context` as `@deepseek-ai/dsh-workspace-context`. It is a request-context extension, not a core service or a filesystem backend. The shared demo spine and Host Runtime mount it from an explicit `{ maxBytes } | false` deployment choice; `dsh web` enables a 65,536-byte budget while the Host Runtime's headless consumer disables it. The plugin consumes `agent/pre-step`, `tools/post-execute`, and the optional `ctx.fs` capability.
+The implementation lives in `packages/context/workspace-context` as `@deepseek-ai/dsh-workspace-context`. It is a request-context extension, not a core service or a filesystem backend. The shared demo spine and Host Runtime mount it from an explicit `{ maxBytes } | false` deployment choice; `dsh web` enables a 65,536-byte budget while the Host Runtime's headless consumer disables it. The plugin consumes `agent/pre-step`, immutable `tools/result` outcomes, `session/event` boundaries, and the optional `ctx.fs` capability.

 The plugin does not statically inject `fs`. Providerless product trees therefore boot normally and the plugin no-ops until a filesystem provider exists. All production reads go through that provider. Candidate probes resolve each path and stat the result, so a final-component symlink is followed to its target: a link to a regular file loads, while a missing path or a non-file target is a confirmed absence. Following repository-owned links across the trust boundary is a deliberate reversal of the original no-follow probe; the [instruction-symlink follow note](2026-07-21-follow-instruction-symlinks.md) owns that decision and its residual risk. The step signal and dynamic tool execution signal propagate through resolution, metadata probes, and streaming reads, so cancellation does not wait for an unrelated filesystem scan. A resolve or stat exception is classified as unavailable: it skips only that candidate and is never interpreted as the deletion of an already-loaded scope.

@@ -38,7 +38,7 @@ The baseline is a user-role `<system-reminder>` with `Instructions from: <path>`

 ### Dynamic Discovery And Refresh

-After a successful first-party `read`, `write`, or `edit` call, the `tools/post-execute` listener reconciles the touched descendant chain and every scope already known to the session. A newly reached scope is returned through `additionalContexts` for the next request using an `Additional instructions from: <path>` system-reminder. Under Code Mode, `run_code` defers sub-dispatch contexts onto its outer result, so the same update is appended only after the parent result rather than being injected mid-call.
+After a successful first-party `read`, `write`, or `edit` call, the immutable `tools/result` observer reconciles the touched descendant chain and every scope already known to the session, then queues an `Additional instructions from: <path>` system-reminder in the agent inbox for the next request. Under Code Mode, successful sub-dispatch touches bubble through opaque parent execution tokens until the top-level result settles. A touch produced inside an agent-loop step does not begin its asynchronous projection until the durable `step/end`; a direct tool execution outside an open step projects immediately. The two boundaries keep result and step adjacency deterministic without making the tool pipeline await filesystem discovery.

 A content edit appends `Updated instructions from: <path>`, states that the new content replaces the previous content, and includes the complete current file. If precedence changes from one candidate to another, the message also names the previous path and says it no longer applies. If no candidate remains, the plugin appends `Instructions removed: <path>` and states that the previously loaded instructions no longer apply.

@@ -50,7 +50,7 @@ Shell commands are not discovery triggers. Local bash calls start fresh shells,

 Every workspace context event stores versioned metadata with `{ action, scope, path, digest? }`, where `digest` is SHA-1 over the loaded content. Complete baselines additionally carry `baseline: true` and `baselineIdentity`. The model-facing prompt has no HTML comments, hidden markers, or headings that are parsed back into state.

-At reconciliation time the plugin scans workspace-sourced `user/message` events and derives the latest state for each visible scope. A short per-session pending map begins only after the immutable top-level `tools/result` proves an `additionalContexts` entry survived every post-execute listener, then covers the interval before the loop appends that context to the log. Each entry records the open `{ turn, step }`: an equal durable `user/message` at or after its sequence boundary confirms and removes it, while a matching `step/end` arriving first means the loop discarded its context buffer, so the plugin removes both the pending entry and its version-cache fast path. A nested Code Mode result stages its changes under the parent's opaque execution token so repeated sub-dispatches in one run do not duplicate them; the parent result rolls that provisional state back and commits only contexts retained by outer policy.
+At reconciliation time the plugin scans workspace-sourced `user/message` events and derives the latest state for each visible scope. Successful nested touches aggregate under their parent execution token, including when a later composite result is blocked; the top-level result transfers them either to the open session step or directly to a per-agent projection queue. A `step/end` releases its staged touches only after that boundary is durable, and the next `agent/pre-step` waits for the serialized projections. Each projection composes against visible history plus the current inbox and replaces the single pending workspace context instead of accumulating intermediate renderings.

 An unchanged path and digest is suppressed. A logged removal is a tombstone, so a reappearing candidate becomes a new `set`. Resume works from persisted metadata: a compatible visible baseline supplies comparison state rather than causing another complete baseline to be appended. If compaction removes an instruction event from the visible surface, that state no longer suppresses a later load, matching the fact that the model can no longer see it. Only changes actually included under the byte budget enter metadata or pending state, so an omitted file remains eligible on a later touch.

@@ -62,7 +62,7 @@ There is intentionally no watcher. Detection occurs at the next successful struc

 `maxBytes` is required and applies separately to a rendered baseline or one dynamic reconciliation batch; there is no implicit or unbounded render budget. Non-positive and non-finite values disable loading. When content exceeds the budget, broader files are omitted before the most-specific file is truncated. A visible `Workspace instruction budget ...` notice names omitted and truncated paths and byte counts, and output never exceeds the configured bytes.

-`maxSourceBytes` is a positive per-file cap with a 1 MiB default. The loader checks reported size before reading and still consumes content through `streamText()` with a running UTF-8 byte count, so missing/stale metadata cannot force an unbounded allocation. An oversized winning candidate is unavailable rather than a reason to fall through to another same-directory name. The plugin deliberately keeps no process-wide cache and never retains instruction prose. It keeps only `{ path, version, digest }` per effective scope in a `WeakMap<Session, Map<scope, state>>`: a matching provider `FsVersion` plus matching effective prompt state skips the read, while a changed version triggers a bounded read and SHA-1 confirmation. SHA-1 remains the cross-provider content identity persisted in visible structured metadata; provider versions are only an in-memory invalidation fast path. Cache transitions for model-visible changes commit only when the corresponding context survives the complete tool-result policy chain, and are invalidated if that accepted context is later dropped with its aborted step before reaching the log.
+`maxSourceBytes` is a positive per-file cap with a 1 MiB default. The loader checks reported size before reading and still consumes content through `streamText()` with a running UTF-8 byte count, so missing/stale metadata cannot force an unbounded allocation. An oversized winning candidate is unavailable rather than a reason to fall through to another same-directory name. The plugin deliberately keeps no process-wide cache and never retains instruction prose. It keeps only `{ path, version, digest }` per effective scope in a `WeakMap<Session, Map<scope, state>>`: a matching provider `FsVersion` plus matching effective prompt state skips the read, while a changed version triggers a bounded read and SHA-1 confirmation. SHA-1 remains the cross-provider content identity persisted in visible structured metadata; provider versions are only an in-memory invalidation fast path. Dynamic cache transitions occur while a serialized projection composes the one desired inbox context, and the next pre-step waits for that projection before deciding what enters the request.

 ## Alternatives considered

@@ -78,7 +78,7 @@ There is intentionally no watcher. Detection occurs at the next successful struc

 ## Consequences

-Workspace guidance is isolated per session and shared by the demo front doors, Web Host, and every tool presentation mode. Initial, nested, and changed instructions are durable and replayable. The generic session/agent context contract carries typed source data through injected messages and post-tool `additionalContexts` arrays without flattening entries.
+Workspace guidance is isolated per session and shared by the demo front doors, Web Host, and every tool presentation mode. Initial, nested, and changed instructions are durable and replayable. The generic session/agent context contract carries typed source data through inbox-staged and durably entered user messages without flattening entries.

 Repository text remains untrusted input. Lower-authority user-role framing, explicit precedence language, and delimiter escaping reduce risk but do not eliminate prompt injection. Following a candidate symlink to its target widens that surface to off-tree content, so the permission and sandbox layers that confine `ctx.fs` to trusted roots are the boundary that treats workspace files as data rather than authority (the [instruction-symlink follow note](2026-07-21-follow-instruction-symlinks.md) owns the residual risk).

@@ -14,7 +14,7 @@ Status: implemented

 ## 决策

-该实现在 `packages/context/workspace-context` 中，包（package）名为 `@deepseek-ai/dsh-workspace-context`。它是请求上下文扩展，不是核心服务或文件系统后端。共享 demo 主干与 Host Runtime 根据显式的 `{ maxBytes } | false` 部署选择挂载它；`dsh web` 启用 65,536 字节预算，Host Runtime 的 headless 消费方则禁用它。该插件使用 `agent/pre-step`、`tools/post-execute` 和可选的 `ctx.fs` 功能。
+该实现在 `packages/context/workspace-context` 中，包（package）名为 `@deepseek-ai/dsh-workspace-context`。它是请求上下文扩展，不是核心服务或文件系统后端。共享 demo 主干与 Host Runtime 根据显式的 `{ maxBytes } | false` 部署选择挂载它；`dsh web` 启用 65,536 字节预算，Host Runtime 的 headless 消费方则禁用它。该插件使用 `agent/pre-step`、不可变的 `tools/result` 结果、`session/event` 边界和可选的 `ctx.fs` 功能。

 插件不会静态注入 `fs`。因此，不带提供方的产品树仍能正常启动；在文件系统提供方出现之前，插件保持无操作。所有生产读取都通过该提供方完成。候选项探测会解析每个路径并对结果执行 stat，因此会跟随最终路径组件的符号链接至其目标：指向普通文件的链接会被加载，缺失路径或非文件目标则确认为不存在。允许仓库拥有的链接跨越信任边界，是对最初不跟随探测方式的刻意反转；[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明该决策及其残余风险。步骤信号与动态工具执行信号会贯穿解析、元数据探测和流式读取，因此取消不会等待无关的文件系统扫描。解析或 stat 异常归类为不可用：它只跳过该候选项，绝不被解释为已经加载的作用域被删除。

@@ -38,7 +38,7 @@ Status: implemented

 ### 动态发现与刷新

-第一方 `read`、`write` 或 `edit` 调用成功后，`tools/post-execute` 监听器会协调被触及的后代路径链，以及该会话已经知道的每个作用域。新到达的作用域通过 `additionalContexts` 返回，并在下一次请求中使用 `Additional instructions from: <path>` system-reminder。在 Code Mode 下，`run_code` 会把子分发上下文延后至其外层结果，因此同一更新只会在父结果之后追加，而不会在调用中途注入。
+第一方 `read`、`write` 或 `edit` 调用成功后，不可变的 `tools/result` 观察器会协调被触及的后代路径链，以及该会话已经知道的每个作用域，然后在 agent inbox 中排入一条 `Additional instructions from: <path>` system-reminder，供下一次请求使用。在 Code Mode 下，成功的子分派 touch 会沿不透明的父级执行 token 逐层上浮，直到顶层结果落定。在 agent loop 步骤内产生的 touch，须等持久 `step/end` 后才开始异步投影；打开的步骤之外直接执行工具时，则立即投影。这两个边界在不让工具流水线等待文件系统发现的前提下，保证结果／步骤的相邻关系具有确定性。

 内容编辑会追加 `Updated instructions from: <path>`，说明新内容取代先前内容，并包含当前的完整文件。如果优先级从一个候选项变为另一个，消息还会指出先前路径并说明它不再适用。如果没有候选项保留，插件会追加 `Instructions removed: <path>`，并说明先前加载的指令不再适用。

@@ -50,7 +50,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，

 每个工作区上下文事件都会存储带版本的元数据，其形态为 `{ action, scope, path, digest? }`；`digest` 是对已加载内容计算的 SHA-1。完整基线还会额外携带 `baseline: true` 和 `baselineIdentity`。模型可见提示词中没有 HTML 注释、隐藏标记，也没有会被解析回状态的标题。

-协调时，插件扫描带工作区来源的 `user/message` 事件，并派生每个可见作用域的最新状态。一个简短的逐会话待处理映射只会在不可变的顶层 `tools/result` 证明某个 `additionalContexts` 条目经过所有 post-execute 监听器后仍然保留时开始记录；随后，它覆盖循环将该上下文追加到日志之前的间隔。每个条目记录开启状态的 `{ turn, step }`：如果相同的持久 `user/message` 出现在其序列边界或之后，该条目得到确认并被移除；如果匹配的 `step/end` 先到达，则说明循环丢弃了上下文缓冲区，插件会同时移除待处理条目及其版本缓存快速路径。嵌套的 Code Mode 结果会把变更暂存在父级的不透明执行 token 下，确保一次运行中的重复子分发不会产生重复项；父级结果会回滚这份临时状态，并且只提交外层策略保留的上下文。
+协调时，插件扫描带工作区来源的 `user/message` 事件，并派生每个可见作用域的最新状态。即使后续复合结果被拦截，成功的嵌套 touch 也会聚合到父级执行 token 下；顶层结果会将它们交给打开的会话步骤，或直接交给逐 agent 投影队列。`step/end` 只会在自身边界持久化后释放其暂存的 touch；下一次 `agent/pre-step` 会等待串行投影完成。每次投影都会根据可见历史和当前 inbox 进行组合，并替换唯一一条待处理工作区上下文，而不会累积中间渲染结果。

 路径和 digest 均未变化时会被抑制。日志中的移除操作是一条墓碑记录，因此重新出现的候选项会成为新的 `set`。恢复操作从持久化元数据继续工作：兼容的可见基线会提供比较状态，而不会导致再次追加完整基线。如果压缩从可见表面移除某条指令事件，该状态不再抑制后续加载，这与模型已经无法看见它的事实一致。只有真正纳入字节预算的变更才会进入元数据或待处理状态，因此被省略的文件在之后的触碰中仍有资格加载。

@@ -62,7 +62,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，

 `maxBytes` 是必填项，分别作用于渲染后的基线或单个动态协调批次；系统不存在隐式或无界的渲染预算。非正数或非有限值会禁用加载。内容超过预算时，系统会先省略较宽泛的文件，再截断最具体的文件。可见的 `Workspace instruction budget ...` 提示会指出被省略和截断的路径与字节数，并且输出绝不超过配置字节数。

-`maxSourceBytes` 是正数的逐文件上限，默认为 1 MiB。loader 会在读取前检查报告的大小，同时仍通过 `streamText()` 消费内容并持续统计 UTF-8 字节数，因此缺失／陈旧的元数据无法迫使其进行无界分配。过大的胜出候选项会被视为不可用，而不是改为同目录中的下一个名称。插件刻意不保留进程级缓存，也绝不保留指令正文。它只为每个有效作用域保存 `{ path, version, digest }`，并将这些状态放在 `WeakMap<Session, Map<scope, state>>` 中：提供方 `FsVersion` 与有效提示词状态同时匹配时跳过读取；版本变化则触发有界读取和 SHA-1 确认。SHA-1 仍是持久化在可见结构化元数据中的跨提供方内容标识；提供方版本只作为内存中的失效快速路径。模型可见变更的缓存转换只有在相应上下文通过完整的工具结果策略链后才会提交；如果该已接受上下文随后与中止步骤一起被丢弃、未能进入日志，缓存转换就会失效。
+`maxSourceBytes` 是正数的逐文件上限，默认为 1 MiB。loader 会在读取前检查报告的大小，同时仍通过 `streamText()` 消费内容并持续统计 UTF-8 字节数，因此缺失／陈旧的元数据无法迫使其进行无界分配。过大的胜出候选项会被视为不可用，而不是改为同目录中的下一个名称。插件刻意不保留进程级缓存，也绝不保留指令正文。它只为每个有效作用域保存 `{ path, version, digest }`，并将这些状态放在 `WeakMap<Session, Map<scope, state>>` 中：提供方 `FsVersion` 与有效提示词状态同时匹配时跳过读取；版本变化则触发有界读取和 SHA-1 确认。SHA-1 仍是持久化在可见结构化元数据中的跨提供方内容标识；提供方版本只作为内存中的失效快速路径。动态缓存转换发生在串行投影组合唯一一条目标 inbox 上下文时；下一次 pre-step 会等待该投影完成，再决定哪些内容进入请求。

 ## 考虑过的替代方案

@@ -78,7 +78,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，

 ## 后果

-工作区指引按会话隔离，并由 demo 入口、Web Host 与每一种工具展示模式共享。初始、嵌套与变更指令都保持持久且可回放。通用的会话／agent 上下文契约通过注入消息与工具执行后的 `additionalContexts` 数组携带带类型的来源数据，而不会把条目展平。
+工作区指引按会话隔离，并由 demo 入口、Web Host 与每一种工具展示模式共享。初始、嵌套与变更指令都保持持久且可回放。通用的会话／agent 上下文契约通过先在 inbox 中暂存、再持久进入的 user 消息携带带类型的来源数据，而不会把条目展平。

 仓库文本仍是不受信任的输入。低权威 user 角色框架、显式优先级说明和分隔符转义可以降低风险，但无法消除提示词注入。跟随候选符号链接到目标，会把该攻击面扩大至树外内容；因此，把 `ctx.fs` 限制在可信根目录内的权限与沙箱层才是真正的边界，它们让系统把工作区文件当作数据而不是权威（[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明残余风险）。

@@ -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-skill-system.md
-2026-07-05-skill-system.md: dd2fb1d22949f55ea7cb2c9f280e7cfbfcbbb226
-2026-07-05-skill-system.zh.md: 96656a8e1dfc2ae1ce7301ba29e7739349b6aab6
+2026-07-05-skill-system.md: a998d70ec934aed4bf7ce32aa711abd47b508a1d
+2026-07-05-skill-system.zh.md: 4fa7c4fd657c2f41f16b30679ec95e61a75f8a0c
@@ -14,9 +14,11 @@ DeepSeek Harness uses the same primitive so project-specific review, plugin-auth

 `@deepseek-ai/dsh-skill` is the pure provider registry (`ctx.skills`), `@deepseek-ai/dsh-skill-local` is the shipped local filesystem provider, and `@deepseek-ai/dsh-tool-skill` owns the durable session catalog and model-facing loader tool. `dsh-agent-spine-demo` loads the registry, local provider, and consumer by default so TUI, headless, and ACP apps get the same behavior while embedded or remote providers contribute skills without changing the registry or consumer. Its `skills` config forwards `registry`, `local`, and `tool` branches to those owners.

+Dedicated packaged providers can contribute immutable skills without filesystem discovery. The shipped CLI declares `@deepseek-ai/dsh-skill-badge` disabled by default; enabling its composition row contributes the official badge instructions through the same registry and consumer ([decision](2026-08-06-bundled-dsh-badge-skill.md)).
+
 Provider plugins register synchronously during `apply()`. Provider membership is direct effect-owned state: registration and disposal invalidate completed catalogs synchronously, and discovery reads the current provider map on demand rather than observing registry-change events. Provider catalogs return ranked candidates from awaited `list()` calls, where remote providers perform initialization, authentication, and discovery while honoring the lookup abort signal. The registry validates each candidate, resolves same-name skills first-wins by rank, provider registration order, and provider-local order, then sorts summaries by skill name for deterministic consumers. It caches only completed catalog snapshots and retries when a provider/runtime revision changes during discovery, so an unload cannot freeze a stale, unresolvable skill into a session catalog. Runtime `ctx.skills.register(...)` remains a convenience for embedded in-process skills and uses project-over-user priority; `runtime` is reserved as the registry-owned provider name.

-The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. DeepSeek Harness does not ship built-in system skills; embedded or remote providers supply additional skills when configured.
+The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. The local provider does not synthesize built-in system skills; configured bundled roots and dedicated providers supply additional skills.

 Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `metadata`, `disable-model-invocation`, and `user-invocable` are optional. Names are kebab-case. The invocation fields project into a typed nested policy as defined by the [independent model and user invocation decision](2026-07-28-skill-invocation-policy.md); the parser rejects the old camel-case spellings. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.

@@ -48,7 +50,7 @@ The data structures and catalog/tool contract are documented in [skills.md](../.

 The agent-core spine includes one catalog contributor, one local provider, and one model-facing tool. Skill discovery is cwd-sensitive, so callers that create agents with different session cwd values can observe different project skill overrides by design.

-The catalog is deterministic for a fixed root set and runtime registration revision, but disk changes are not watched; discovery is memoized until runtime registration invalidates the cache or the process restarts.
+The catalog is deterministic for a fixed root set and runtime registration revision. The local provider watches configured roots and invalidates completed catalogs after relevant disk changes; runtime registration and provider disposal also invalidate them.

 ## Deferred

@@ -14,9 +14,11 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和

 `@deepseek-ai/dsh-skill` 是纯提供方注册表（`ctx.skills`），`@deepseek-ai/dsh-skill-local` 是随附的本地文件系统提供方，`@deepseek-ai/dsh-tool-skill` 负责持久化会话目录与面向模型的 loader 工具。`dsh-agent-spine-demo` 默认加载注册表、本地提供方和消费方，使 TUI、headless 与 ACP（Agent Client Protocol）应用获得相同行为，同时嵌入式或远程提供方可在不修改注册表或消费方的前提下贡献 skill。其 `skills` 配置将 `registry`、`local` 和 `tool` 分支分别转发给对应的所有者。

+专用的随包提供方可以贡献不可变的 skill，无需文件系统发现。交付的 CLI（命令行界面）默认将 `@deepseek-ai/dsh-skill-badge` 声明为禁用；启用其组合配置行，就会通过同一个注册表和消费方贡献官方徽章指令（见[决策](2026-08-06-bundled-dsh-badge-skill.md)）。
+
 提供方插件在 `apply()` 期间同步注册。提供方成员资格是由直接 effect 持有的状态：注册与 dispose（资源释放）同步地使已完成的目录失效，发现操作按需读取当前提供方映射而非监听注册表变更事件。提供方目录从等待的 `list()` 调用返回排序后的候选项，远程提供方在此过程中执行初始化、认证和发现，同时遵守查找的 abort 信号。注册表校验每个候选项，按排名、提供方注册顺序和提供方内部顺序以先到先得方式解决同名 skill 冲突，然后按 skill 名称排序摘要以保证消费方获得确定性结果。它仅缓存已完成的目录快照，并在发现过程中提供方/运行时修订版本发生变化时重试，因此卸载操作不会将一个陈旧且不可解析的 skill 冻结到会话目录中。运行时 `ctx.skills.register(...)` 仍作为嵌入式进程内 skill 的便捷方式保留，使用 project 优先于 user 的优先级；`runtime` 保留为注册表拥有的提供方名称。

-本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录：项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`，然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`，以免系统拥有的目录被当作普通用户内容处理。DeepSeek Harness 不随附内置系统 skill；嵌入式或远程提供方在配置后提供额外 skill。
+本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录：项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`，然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`，以免系统拥有的目录被当作普通用户内容处理。本地提供方不会合成内置系统 skill；已配置的 bundled 根目录和专用提供方会提供额外 skill。

 每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填；`whenToUse`、`metadata`、`disable-model-invocation` 和 `user-invocable` 为可选。名称采用 kebab-case。调用字段会投影到类型化的嵌套策略中，具体由[模型与用户独立调用决策](2026-07-28-skill-invocation-policy.md)定义；解析器会拒绝旧的驼峰拼写。YAML frontmatter 使用 `yaml` 包（package）解析，而非 `js-yaml` 或手写解析器：`yaml` 是本包有限 frontmatter 需求已声明的现代解析器，窄解析器要么拒绝用户预期可用的合法 YAML，要么膨胀为一个未经评审的 YAML 子集。

@@ -48,7 +50,7 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和

 agent-core 主干包含一个目录贡献者、一个本地提供方和一个面向模型的工具。Skill 发现是 cwd 敏感的，因此以不同会话 cwd 值创建 agent 的调用方可以按设计观察到不同的项目 skill 覆盖。

-目录对于固定的根目录集合和运行时注册修订版本是确定性的，但不监视磁盘变化；发现结果被缓存，直到运行时注册使缓存失效或进程重启。
+目录对于固定的根目录集合和运行时注册修订版本是确定性的。本地提供方会监视已配置的根目录，并在发生相关磁盘变化后使已完成的目录失效；运行时注册和提供方释放也会使其失效。

 ## 延后

@@ -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/2026-07-06-sandbox.md
-2026-07-06-sandbox.md: aed5ac1ceb02130ce97a8c83c0f77869fdc32146
-2026-07-06-sandbox.zh.md: db95b1a5b7a7cae1e0fcdd8deba9dcb6ad020a67
+2026-07-06-sandbox.md: 583b388815cd9b2b9cf94ce393839169ce3ffac3
+2026-07-06-sandbox.zh.md: e435b671a42ca5c3ea4f6800bf91d6e006da35d3
@@ -64,7 +64,7 @@ Left open, for the phase that needs them: whether network restriction arrives as

 The launcher is a ~300-line C program (plain C11 over the raw Landlock UAPI — no libraries beyond a statically linked musl, so the audit surface is that one file plus the kernel's stable syscall contract): `--ro <path>` / `--rw <path>` grants, `--`, the wrapped argv; it installs the ruleset on itself and `exec`s (rulesets are inherited across `execve`, and it sets `no_new_privs` before restricting); `--probe` enforces a maximal ruleset in a short-lived child and exits 0 only when the kernel actually enforces; every launcher failure exits 125 without running the child and prints a fatal `landlock-run:` line. A successfully exec'd child may also return 125, so status alone is not launcher evidence. An older ABI prints the exact `landlock-run: partial enforcement (older Landlock ABI)` notice before it executes the child, so that line is not fatal evidence.

-The Landlock launcher source and package workspace live at `native/landlock-run`, next to the harness consumers. The standalone [`node-addon-landlock-run`](https://github.com/deepseek-harness/node-addon-landlock-run) repository is the release mirror used to pack and publish the npm package family; `native/README.md` owns the export procedure. Platform binaries are selected by npm, and the entry package owns path resolution, probing, CLI flags, the fatal prefix, and the partial-enforcement notice while the harness maps sandbox modes to grants. Versioning the entry point with its binaries keeps probe parsing and launch syntax aligned.
+The Landlock launcher source and package family live at `native/landlock-run`, next to the harness consumers and inside the root pnpm workspace. The [in-repository Landlock release decision](../process/2026-08-06-in-repository-landlock-release.md) owns the shared lockfile, native build, pack rehearsal, and npm publication boundary. Platform binaries are selected by npm, and the entry package owns path resolution, probing, CLI flags, the fatal prefix, and the partial-enforcement notice while the harness maps sandbox modes to grants. Versioning the entry point with its binaries keeps probe parsing and launch syntax aligned.

 Backend profiles share the mode contract but differ in necessary host grants. Landlock and Seatbelt allow only `/dev/null` in read-only mode; workspace-write also permits their required host temp roots. Each wrap carries backend-specific denial signatures. Landlock reports partial enforcement on older ABIs that cannot govern every operation, while successful bwrap and Seatbelt profiles report full enforcement.

@@ -118,7 +118,7 @@ fs/web/todo execute in-process, so their sandbox semantics are policy at their s
 ### Testing

 - **Unit:** pin platform selection and profiles, direct provider-argv handoff, spawn-level failures with invalid-workdir controls, missing/non-executable/missing-interpreter evidence, malformed-runner negative controls, confined `BASH_ENV` ordering, structured runner classification (including partial-Landlock notice-only child outcomes, gated fatal evidence, child exits 126/127, and foreground/background parity), per-call mode/root resolution, per-process facts, escalation validation and outcomes, permission preset folding and write-through, and runtime-context ordering and materialization.
- **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; one real Cordis context concurrently drives two project sessions through shipped bash and fs tools, proving own-root success and sibling-root denial. Packed-install coverage proves the registry launcher remains executable. CI rejects a silent all-skip.
+- **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; one real Cordis context concurrently drives two project sessions through shipped bash and fs tools, proving own-root success and sibling-root denial. Packed-install coverage installs the current checkout's native tarballs and proves the launcher remains executable and byte-identical. CI rejects a silent all-skip.
 - **With-key:** start the real ACP composition in read-only mode, let a model-driven bash write hit the runner's denial marker, then drive the bridge answerer and disk effect through granted and rejected workspace-write retries; unavailable credentials or runners self-skip.
 - **Snapshot:** pin the atomic current-policy context and both scripted approval branches. A real ACP example scenario places its session under the user home while the deployment fallback points at `/tmp`, then pins both the workspace-write runtime-context message and a successful deployment-selected mutation; this distinguishes session-root resolution from the process fallback without depending on runner-specific denial text. A POSIX fake partial-Landlock provider pins direct bash `false` as an ordinary child result and a missing provider executable as foreground/background infrastructure failure through the assembled app. Other snapshots start unconfined so unrelated fixtures remain platform-independent.

@@ -128,15 +128,15 @@ Each phase gets its full design when picked up, validated against the code at th

 - **Second consumer** — `subagent-acp` optionally confines child agents (per-call policy; unconfined default — a child agent must write its own persistence).
 - **More environments** — an environment-coherent capability group example (e.g. bash+fs against one container).
- **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from its own repository on the `node-addon-landlock-run` template, plus its profile dialect, denial signatures, and runner-failure rules. Wrapping the third-party landstrip runner instead was [considered and rejected](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) — not battle-tested enough for a security invariant.
+- **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from the main repository under `native/` following the `@deepseek-ai/node-addon-landlock-run` template, plus its profile dialect, denial signatures, and runner-failure rules. Wrapping the third-party landstrip runner instead was [considered and rejected](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) — not battle-tested enough for a security invariant.

 ## Alternatives considered

 - **Command-string heuristic preflight** — rejected: cannot understand expansion/subprocesses/symlinks; the strict attempt (run it, let the kernel decide) is the only trustworthy denial signal.
 - **Functionally probe even a platform's sole backend** — rejected: probing arbitrates between candidates; with one there is nothing to decide, and probe cost taxes the first confined command of every session (prohibitive for heavy future backends). The runner's own exec-time fail-closed refusal plus structured `runnerFailureRules` classification carries the safety property instead.
- **Commit the built launcher binaries** — rejected: a binary in a diff is unreviewable and churns history; reviewed source + native CI builds + the launcher repo's byte-pinned publish rehearsal keep bytes out of every tree.
+- **Commit the built launcher binaries** — rejected: a binary in a diff is unreviewable and churns history; reviewed source + native CI builds + the main repository's byte-pinned publish rehearsal keep bytes out of every tree.
 - **Compile the launcher on install** — rejected: pushes a C toolchain onto every consumer; a fallback that exists only where a compiler happens to be is not a fallback.
- **Cross-compile both architectures from one builder** — rejected: requires carrying a pinned cross toolchain (rustup targets, zig, or a container image) solely to rebuild two ~70 KB binaries; per-architecture native runners already exist and each builds its own platform package (the `node-addon-require-builtin` model, the launcher repo's own pipeline).
+- **Cross-compile both architectures from one builder** — rejected: requires carrying a pinned cross toolchain (rustup targets, zig, or a container image) solely to rebuild two ~70 KB binaries; per-architecture native runners already exist and each builds its own platform package (the `node-addon-require-builtin` model, retained by the main repository's native pipeline).
 - **No fallback (bwrap or fail closed)** — rejected: concentrates failure on the hosts a sandbox matters most, degrading to `danger-full-access` by resignation.
 - **Keep the mechanism inside `dsh-bash-sandbox`** — rejected: blocks the existing second consumer, makes future phases read mode out of a bash plugin's config, and cannot express escalation.
 - **Config-fixed mode on the provider** — rejected: one mode per process; cannot serve concurrent consumers with different policies nor the one-shot widened retry.
@@ -175,7 +175,7 @@ Costs and accepted limits:
 - **The Seatbelt rung leans on Apple's deprecated-but-shipped `sandbox-exec` CLI.** As darwin's sole candidate it is selected without probing, so a future removal under a usable workdir surfaces as a runner-attributable spawn failure and an executable refusal through its fatal signature — both become `SANDBOX_UNAVAILABLE`, and the command never runs; fail closed, never open.
 - **Landlock confinement is only as complete as the running kernel's ABI.** Reported as `enforcement: 'partial'` rather than refused — the deliberate trade that keeps the fallback available on older-kernel hosts.
 - **Runner attribution uses an in-band protocol.** Exit status plus stderr cannot cryptographically identify the writer, so a confined child can mimic a fatal runner line and status to cause an availability/diagnostic false attribution. The conjunction and exact notice exclusion reduce accidental matches; this is not a sandbox bypass because the child is already confined.
- **The launcher arrives as a registry dependency.** Trusted through its own repository's release pipeline (reviewed C source, native CI builders, byte-pinned publish rehearsal) plus this repo's version pin — the real-kernel e2e legs are what vouch for behavior through the installed bytes.
+- **The launcher is a workspace dependency in source and an npm dependency after publication.** The main repository tests reviewed C source, native CI builds, and byte-pinned local tarballs together before publishing the same package family; the real-kernel e2e legs vouch for behavior through those installed bytes.
 - **The model may over-ask.** Escalating without denial grounding, or picking `danger-full-access` where `workspace-write` suffices: the description steers and the enum forces the ladder, but the human prompt is the actual gate; the `approval/asked` reasons make over-asking auditable, and a `prepend` policy answerer can auto-reject patterns a deployment never wants.
 - **The advertised target set is static while the effective mode is per-session** (schemas are registry-global) — a session already at the widest mode is still offered the fields. Harmless by construction: the strict-wider check at execution, not the enum, is the safety boundary — a non-widening request fails with its own text and never prompts anyone.
 - **A granted escalation is not a working sandbox.** An unavailable backend still fails closed even for a granted escalation to a confining mode — at `confine()` when the platform has no chain or every probe fails, through the spawn channel when the selected executable cannot start, or through a structured rule when a started runner refuses — while a granted `danger-full-access` run never touches the provider at all: there the grant, not the probe, is the authority.
@@ -187,7 +187,7 @@ Costs and accepted limits:
 - **A command came back with `[sandbox: file access denied under read-only mode]` — did it fail?** It RAN, and the kernel refused a file effect: the denial is a result fact orthogonal to exit code. The teaching forbids retrying around it; the one sanctioned move is the same command retried once with an escalation request.
 - **How is a BROKEN sandbox told apart from a failing command?** Any provider-argv spawn rejection proves the confined launch never started, but it identifies a broken runner only when the caller-owned workdir is usable and Node reports attributable `ENOENT` or `EACCES` for that argv[0]. A bare `syscall: 'spawn'` without an exact error path and all other rejections remain ordinary command-start errors. After a process starts, runner failure outranks denial only when one `runnerFailureRules` entry matches both its optional exit-code gate and a fatal stderr line after exact informational exclusions. Foreground failures throw structured `SANDBOX_UNAVAILABLE` with spawn or matched-line detail; an asynchronously rejected or settled background task stamps `sandbox.runnerFailed` and renders its own marker. A `SubprocessService` that synchronously throws the same provenanced `ENOENT`/`EACCES` shape makes background start throw the structured error; other synchronous errors propagate unchanged. A Landlock partial-enforcement notice plus an ordinary child failure remains a command result.
 - **What happens on a platform with no backend — Windows today?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE` and the command never spawns; `win32` is a reserved EMPTY chain, pinned by test to fail closed identically until a Windows runner fills it (§ Deferred phases).
- **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the registry-installed Landlock launcher, and the verdict is cached for the provider's lifetime.
+- **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the packaged Landlock launcher, and the verdict is cached for the provider's lifetime.
 - **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam.
 - **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively — plus the filesystem tools (`read`/`write`/`edit`) through the sandboxed `ctx.fs` provider (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)): bash confines via the OS runner, fs via an in-process path fence, both keying off the same `ctx.sandboxPolicy` mode. web/todo stay in-process and unfenced (web's only effect is network, outside the file-effect mode vocabulary).
 - **Does a granted escalation persist?** No. The grant is consumed by the exact foreground or background call that asked; every neighboring call keeps its own effective mode. A later background denial surfaces through `task_output` and may ground a new exact-command retry.
@@ -64,7 +64,7 @@ OS 子进程约束适用于 bash 执行器（包括钩子命令），后续还

 launcher 是一个约 300 行的 C 程序（纯 C11，直接使用 Landlock UAPI——除静态链接的 musl 外无其他库，因此审计面仅为该文件加内核的稳定 syscall 契约）：`--ro <path>` / `--rw <path>` 授权，`--`，被包装的 argv；它为自身安装规则集并执行 `exec`（规则集跨 `execve` 继承，且它在限制前设置 `no_new_privs`）；`--probe` 在一个短生命周期子进程中强制最大规则集，仅当内核确实强制时才以 0 退出；所有 launcher 失败都会以 125 退出且不运行子进程，并打印一行致命的 `landlock-run:` 诊断。成功完成 exec 的子进程也可能返回 125，因此仅凭退出状态不能作为 launcher 失败的证据。较旧的 ABI 会在执行子进程之前打印精确的 `landlock-run: partial enforcement (older Landlock ABI)` 通知，因此该行不是致命证据。

-Landlock launcher 源码和包工作区位于 `native/landlock-run`，与 harness 消费方同仓。独立的 [`node-addon-landlock-run`](https://github.com/deepseek-harness/node-addon-landlock-run) 仓库是用于打包并发布 npm 包族的发布镜像；导出流程归 `native/README.md` 所有。平台二进制由 npm 选择，入口包拥有路径解析、探测、CLI 参数、致命前缀和部分强制执行通知，而 harness 将沙箱模式映射为授权。将入口点与其二进制一起版本化，使探测解析和启动语法保持对齐。
+Landlock launcher 源码和包家族位于 `native/landlock-run`，与 harness 消费方同仓，并属于根 pnpm workspace。[仓库内 Landlock 发布决策](../process/2026-08-06-in-repository-landlock-release.md)负责共享锁文件、原生构建、打包演练和 npm 发布边界。平台二进制由 npm 选择，入口包拥有路径解析、探测、CLI 参数、致命前缀和部分强制执行通知，而 harness 将沙箱模式映射为授权。将入口点与其二进制一起版本化，使探测解析和启动语法保持对齐。

 后端 profile 共享模式契约但在必要的主机授权上有所不同。Landlock 和 Seatbelt 在 read-only 模式下仅允许 `/dev/null`；workspace-write 还允许各自所需的主机临时目录根。每次包装携带后端特定的拒绝签名。Landlock 在较旧的 ABI 无法管控所有操作时报告 partial enforcement，而成功的 bwrap 和 Seatbelt profile 报告 full enforcement。

@@ -118,7 +118,7 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
 ### 测试

 - **单元测试：** 固定平台选择和 profile、直接交接提供方返回的 argv、带有无效 workdir 对照的 spawn 层失败、runner 缺失／不可执行／解释器缺失证据、格式错误 runner 阴性对照、受约束的 `BASH_ENV` 求值顺序、结构化 runner 分类（包括只有部分强制执行通知的子进程结果、带门控的致命证据、子进程退出码 126／127，以及前台／后台一致性）、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传，以及运行时上下文排序与具体化。
- **Keyless 真实 runner：** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试；一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话，证明在自身根目录写入成功、在兄弟根目录写入被拒绝。打包安装测试证明注册表 launcher 保持可执行。CI 拒绝静默全跳过。
+- **Keyless 真实 runner：** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试；一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话，证明在自身根目录写入成功、在兄弟根目录写入被拒绝。打包安装测试会安装当前 checkout 的原生 tarball，并证明 launcher 保持可执行且字节完全一致。CI 拒绝静默全跳过。
 - **With-key：** 以只读模式启动真实 ACP 组合，让模型驱动的 bash 写入命中 runner 的拒绝标记，再通过已授权与被拒绝的 workspace-write 重试驱动 bridge 应答器和磁盘效果；不可用的凭证或 runner 自动跳过。
 - **快照：** 固定原子化的当前策略上下文和两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下，同时让部署后备根目录指向 `/tmp`，然后固定 workspace-write 运行时上下文消息与一次成功的、由部署选定的变更；这能区分会话根目录解析与进程后备值，而不依赖 runner 特定的拒绝文本。一个模拟 Landlock 部分强制执行行为的 POSIX 提供方会在组装后的应用中固定直接执行 bash `false` 时仍得到普通子进程结果，并固定提供方可执行文件缺失时在前台／后台均为基础设施失败。其他快照以无约束启动，使无关 fixture（测试前置数据）保持平台无关。

@@ -128,15 +128,15 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层

 - **第二个消费方**——`subagent-acp` 可选地约束子 agent（按调用策略；默认无约束——子 agent 必须写入自己的持久化）。
 - **更多环境**——环境一致的能力组示例（如 bash+fs 对一个容器）。
- **Windows 链**——`PLATFORM_CHAINS.win32` 保留为空（失败关闭）；填充它意味着来自 AppContainer/restricted-token 家族的约束 runner，从其自己的仓库按 `node-addon-landlock-run` 模板交付，加上其 profile 方言、拒绝签名和 runner 失败规则。改为包装第三方 landstrip runner 的方案[经考虑后已驳回](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md)——它所经受的实战检验还不足以承载安全不变式。
+- **Windows 链**——`PLATFORM_CHAINS.win32` 保留为空（失败关闭）；填充它意味着来自 AppContainer/restricted-token 家族的约束 runner，由主仓库在 `native/` 下按 `@deepseek-ai/node-addon-landlock-run` 模板交付，加上其 profile 方言、拒绝签名和 runner 失败规则。改为包装第三方 landstrip runner 的方案[经考虑后已驳回](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md)——它所经受的实战检验还不足以承载安全不变式。

 ## 曾考虑的替代方案

 - **命令字符串启发式预检**：否决。无法理解展开/子进程/符号链接；严格尝试（运行它，让内核决定）是唯一可信的拒绝信号。
 - **即使平台仅有一个后端也功能性探测**：否决。探测用于在候选者之间仲裁；只有一个时无需决策，且探测开销对每个会话的首次约束命令征税（对未来重量级后端而言代价过高）。runner 自身执行时的失败关闭拒绝加结构化 `runnerFailureRules` 分类承载了安全属性。
- **提交构建好的 launcher 二进制**：否决。diff 中的二进制不可审查且膨胀历史；经审查的源码 + 原生 CI 构建 + launcher 仓库的字节固定发布演练使二进制远离所有代码树。
+- **提交构建好的 launcher 二进制**：否决。diff 中的二进制不可审查且膨胀历史；经审查的源码 + 原生 CI 构建 + 主仓库的字节固定发布演练使二进制远离所有代码树。
 - **安装时编译 launcher**：否决。将 C 工具链强加给每个消费方；仅在碰巧有编译器时才存在的备选不是备选。
- **从一个构建器交叉编译两种架构**：否决。仅为重建两个约 70 KB 的二进制就需要携带一个固定的交叉工具链（rustup targets、zig 或容器镜像）；每架构的原生 runner 已存在，各自构建自己的平台包（`node-addon-require-builtin` 模式，launcher 仓库自己的流水线）。
+- **从一个构建器交叉编译两种架构**：否决。仅为重建两个约 70 KB 的二进制就需要携带一个固定的交叉工具链（rustup targets、zig 或容器镜像）；每架构的原生 runner 已存在，各自构建自己的平台包（`node-addon-require-builtin` 模式，由主仓库的原生流水线保留）。
 - **无备选（bwrap 或失败关闭）**：否决。将失败集中在沙箱最重要的主机上，最终因放弃而降级到 `danger-full-access`。
 - **将机制保留在 `dsh-bash-sandbox` 内部**：否决。阻塞既有的第二个消费方，使未来阶段从一个 bash 插件的配置中读取模式，且无法表达升级。
 - **提供方上的配置固定模式**：否决。每进程一个模式；无法服务具有不同策略的并发消费方，也无法表达一次性放宽重试。
@@ -175,7 +175,7 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
 - **Seatbelt 层级依赖 Apple 已弃用但仍交付的 `sandbox-exec` CLI。** 作为 darwin 的唯一候选，它无需探测即被选中，因此在 workdir 可用时，未来移除会表现为可归因于 runner 的 spawn 失败，可执行文件拒绝则通过其致命签名体现——两者都会变为 `SANDBOX_UNAVAILABLE`，且命令绝不会运行；失败关闭，绝不开放。
 - **Landlock 约束的完整度取决于运行内核的 ABI。** 报告为 `enforcement: 'partial'` 而非拒绝——这是有意的权衡，使备选在旧内核主机上仍可用。
 - **Runner 归因使用带内协议。** 退出状态与 stderr 无法以密码学方式识别写入者，因此受限子进程可以模仿 runner 的致命诊断行和状态，造成可用性或诊断误归因。多项证据的合取与精确通知排除减少了意外匹配；这不是沙箱绕过，因为子进程已经受到限制。
- **launcher 作为注册表依赖到达。** 通过其自身仓库的发布流水线（经审查的 C 源码、原生 CI 构建器、字节固定的发布演练）加上本仓库的版本固定获得信任——真实内核 e2e 测试环节会验证安装产物的实际行为。
+- **launcher 在源码中是 workspace 依赖，发布后是 npm 依赖。** 主仓库会在发布同一个包家族之前，一起测试经审查的 C 源码、原生 CI 构建和字节固定的本地 tarball；真实内核 e2e 测试环节会验证这些安装字节的实际行为。
 - **模型可能过度请求。** 在没有拒绝依据的情况下升级，或在 `workspace-write` 足够时选择 `danger-full-access`：描述引导且枚举强制阶梯，但人的提示词是实际门控；`approval/asked` 原因使过度请求可审计，且 `prepend` 策略应答器可以自动拒绝部署永远不想要的模式。
 - **公布的目标集是静态的，而有效模式是按会话的**（schema 是注册表全局的）——已处于最宽模式的会话仍被提供这些字段。构造上无害：执行时的严格放宽检查（而非枚举）是安全边界——非放宽请求以自身文本失败且不提示任何人。
 - **授权的升级不等于可工作的沙箱。** 不可用的后端即使对授权升级到约束模式也仍然失败关闭——平台没有链或所有探测失败时在 `confine()` 阶段失败，所选可执行文件无法启动时通过 spawn 通道失败，已启动的 runner 拒绝时则通过结构化规则失败——而授权的 `danger-full-access` 运行根本不触及提供方：此时授权（而非探测）是权威。
@@ -187,7 +187,7 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
 - **一个命令返回了 `[sandbox: file access denied under read-only mode]`——它失败了吗？** 它运行了，内核拒绝了一个文件操作：拒绝是与退出码正交的结果事实。相关指令禁止通过绕过限制来重试；唯一被认可的动作是以升级请求重试同一命令一次。
 - **如何区分损坏的沙箱与失败的命令？** 提供方 argv 的任何 spawn 拒绝都能证明受限启动从未开始，但只有在调用方拥有的 workdir 可用，且 Node 为该 argv[0] 报告可归因的 `ENOENT` 或 `EACCES` 时，才能据此判定 runner 损坏。没有精确错误路径的裸 `syscall: 'spawn'` 和其他所有拒绝仍是普通的命令启动错误。进程启动后，只有当 `runnerFailureRules` 中某一条目同时匹配其可选退出码门控，以及排除整行精确信息性行后的一行致命 stderr 诊断时，runner 失败才会优先于拒绝。前台失败会抛出结构化的 `SANDBOX_UNAVAILABLE`，并附带 spawn 错误或匹配行作为详细信息；遭异步拒绝或已结算的后台任务则盖章 `sandbox.runnerFailed` 并渲染自己的标记。如果 `SubprocessService` 同步抛出同样带有来源信息的 `ENOENT`／`EACCES` 形态，后台启动会抛出该结构化错误；其他同步错误原样传播。Landlock 部分强制执行通知加上普通子进程失败时，仍返回命令结果。
 - **在没有后端的平台上会发生什么——今天的 Windows？** `confine()` 抛出失败关闭的 `SANDBOX_UNAVAILABLE`，命令永不 spawn；`win32` 是保留的空链，由测试固定为同样失败关闭，直到 Windows runner 填充它（§ 延迟阶段）。
- **`bwrap` 已安装在我的主机上但不可用（禁用了非特权 userns、LSM 拒绝 `mount`）——会发生什么？** 链探测是功能性的——它构建并强制一个真实 profile 而非检查 `--version`——因此存在但不可用的 `bwrap` 探测失败，选择落到注册表安装的 Landlock launcher，结论在提供方生命周期内缓存。
+- **`bwrap` 已安装在我的主机上但不可用（禁用了非特权 userns、LSM 拒绝 `mount`）——会发生什么？** 链探测是功能性的——它构建并强制一个真实 profile 而非检查 `--version`——因此存在但不可用的 `bwrap` 探测失败，选择落到已打包的 Landlock launcher，结论在提供方生命周期内缓存。
 - **沙箱限制网络或进程可见性吗？** 不——`SandboxMode` 仅声称文件操作；bwrap profile 刻意不 unshare pid，没有后端声称网络。网络限制是否成为自己的旋钮留在 § seam 中开放。
 - **哪些工具实际在约束下运行？** 通过 `ctx.bash` 的 OS 子进程——bash 工具及传递性的钩子命令——再加上通过沙箱化 `ctx.fs` 提供方运行的文件系统工具（`read`/`write`/`edit`，见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)）：bash 通过 OS runner 约束，fs 通过进程内路径围栏约束，二者都以同一个 `ctx.sandboxPolicy` 模式为键。web/todo 仍在进程内且不受限制（web 的唯一效果是网络，不在文件效果模式词汇内）。
 - **授权的升级会持久化吗？** 不会。授权由发起请求的确切前台或后台调用消费；每个相邻调用保留自己的有效模式。后续的后台拒绝通过 `task_output` 呈现，并且可以作为一次新的精确命令重试的依据。
@@ -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/2026-08-02-win32-in-process-folder-dialog.md
-2026-08-02-win32-in-process-folder-dialog.md: 91a1ed0d7b1c1938a5e038ce36f1ca90bf3c9e82
-2026-08-02-win32-in-process-folder-dialog.zh.md: 6b90dc1c5fa0042b3e2bcbea8ed554f1f0ea2acf
+2026-08-02-win32-in-process-folder-dialog.md: 5389293605169ce5ca269a127de5f609b8b7dd11
+2026-08-02-win32-in-process-folder-dialog.zh.md: ef81bc1f65b2859de1eb60f74f79e4869da4746b
@@ -14,7 +14,7 @@ The Windows directory picker's primary tier was a spawned PowerShell script arou

 ## Alternatives considered

- **A prebuilt native helper (`native/` family like `node-addon-landlock-run`).** Rejected: a mirror repository, an npm package family, MSVC provisioning, and a release handoff — all to ship ~150 lines of C the repository cannot exercise on CI (no real-Windows lane); koffi delivers the same COM surface with zero new supply chain.
+- **A prebuilt native helper (`native/` family like `@deepseek-ai/node-addon-landlock-run`).** Rejected: another npm package family, MSVC provisioning, and a Windows build/release lane — all to ship ~150 lines of C the repository cannot currently exercise on CI (no real-Windows lane); koffi delivers the same COM surface with zero new supply chain.
 - **An N-API in-process addon.** Rejected for the same CI/toolchain reasons plus owned C++ for STA threading and message pumping that a child process + koffi express in TypeScript.
 - **Keep PowerShell primary and probe versions.** Rejected: the picker stays hostage to shell packaging (6 vs 7, Store aliases, profiles), and 5.1's legacy dialog remains the floor wherever pwsh is absent; the fallback-trigger widening alone was accepted into the fallback tier instead.
 - **Blocking the main thread for the modal call.** Rejected outright: the web host must keep serving RPC while the dialog is open.
@@ -14,7 +14,7 @@ Windows 目录选择器的主层此前是围绕 WinForms `FolderBrowserDialog`

 ## 考虑过的替代方案

- **预编译原生助手（`native/` 家族，如 `node-addon-landlock-run`）。** 否决：镜像仓库、npm 包家族、MSVC 供给和发布交接——只为交付约 150 行 CI 无法执行的 C（没有真 Windows 通道）；koffi 以零新增供应链提供同一 COM 面。
+- **预编译原生助手（`native/` 家族，如 `@deepseek-ai/node-addon-landlock-run`）。** 否决：再增加一个 npm 包家族、MSVC 供给和 Windows 构建／发布通道——只为交付约 150 行目前无法在 CI 中执行的 C（现有 CI 没有真 Windows 通道）；koffi 以零新增供应链提供同一 COM 面。
 - **N-API 进程内插件。** 否决：同样的 CI／工具链原因，另加需要自有 C++ 处理 STA 线程与消息泵，而子进程 + koffi 用 TypeScript 就能表达。
 - **保留 PowerShell 为主层并探测版本。** 否决：选择器仍被 shell 打包形态挟持（6 与 7、Store 别名、profile），且没有 pwsh 的机器地板仍是 5.1 的旧版对话框；仅把回退触发条件的拓宽吸收进回退层。
 - **在主线程上阻塞模态调用。** 直接否决：对话框打开期间 web 宿主必须继续服务 RPC。
@@ -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/feature/2026-08-06-bundled-dsh-badge-skill.md
+2026-08-06-bundled-dsh-badge-skill.md: 512f67ca347ca311a1f80fef932f6af8c91b0fe9
+2026-08-06-bundled-dsh-badge-skill.zh.md: 88fcadf66944cb91419441be3916ae04968be663
@@ -0,0 +1,25 @@
+# Agent Note: Bundled dsh badge skill
+
+Status: implemented
+
+English | [中文](2026-08-06-bundled-dsh-badge-skill.zh.md)
+
+## Problem
+
+The [Cordis tutorial](../../../../docs/cordis-tutorial/index.md) uses an official “powered by dsh” badge across its pages, but the shipped CLI has no reusable instructions or explicit opt-in provider for applying the same attribution elsewhere.
+
+## Decision
+
+`@deepseek-ai/dsh-skill-badge` is a native Cordis plugin that registers one immutable bundled provider on `ctx.skills`. The provider owns the `dsh-badge` summary, instruction body, and PNG resource base; `dsh-tool-skill` remains the sole owner of model-facing catalog and loader rendering.
+
+The shipped CLI composition declares `skill-badge` as disabled. Enabling that existing row is the explicit opt-in; disabled installations advertise no badge skill and gain no model-visible content.
+
+The provider uses the bundled rank after project, custom, and user filesystem sources, so a user-owned `dsh-badge` definition can override it through the ordinary registry precedence contract. Provider disposal removes the contribution through the registry-owned effect.
+
+## Alternatives considered
+
+**Mount packaged files through `dsh-skill-local`.** Rejected because filesystem discovery, parsing, and watching add lifecycle machinery that an immutable single-skill provider does not need.
+
+## Consequences
+
+The badge instructions and source PNG are versioned with DSH and resolve through a packaged directory resource base. The provider has no configuration surface. Package tests pin provider lifecycle and the official PNG bytes, while a keyless assembled-application snapshot pins the enabled catalog and loaded skill body.
@@ -0,0 +1,25 @@
+# Agent Note: 内置 dsh 徽章 skill
+
+Status: implemented
+
+[English](2026-08-06-bundled-dsh-badge-skill.md) | 中文
+
+## 问题
+
+[Cordis 教程](../../../../docs/cordis-tutorial/index.md)的各个页面都使用官方「powered by dsh」徽章，但交付的 CLI（命令行界面）既没有用于在其他位置应用同样署名的可复用指令，也没有可显式选择加入的提供方。
+
+## 决策
+
+`@deepseek-ai/dsh-skill-badge` 是一个原生 Cordis 插件，会在 `ctx.skills` 上注册一个不可变的内置提供方。该提供方负责 `dsh-badge` 的摘要、指令正文和 PNG 资源基底；`dsh-tool-skill` 仍是面向模型的目录与 loader 渲染的唯一归属方。
+
+交付的 CLI 组合将 `skill-badge` 声明为禁用。启用这个现有配置行就是显式选择加入；禁用它的安装实例不会公开任何徽章 skill（技能），也不会获得任何模型可见内容。
+
+该提供方使用排在项目、自定义及用户文件系统来源之后的内置 rank，因此用户自有的 `dsh-badge` 定义可通过注册表的常规优先级契约覆盖它。提供方释放时，注册表拥有的 effect 会移除该贡献。
+
+## 曾考虑的替代方案
+
+**通过 `dsh-skill-local` 挂载随包文件。** 否决，因为文件系统发现、解析和监视会引入生命周期机制，而不可变的单一 skill 提供方并不需要这些机制。
+
+## 后果
+
+徽章指令和源 PNG 随 DSH 一同纳入版本管理，并通过以随包目录为基础的资源基底解析。该提供方没有配置面。包测试固定提供方生命周期和官方 PNG 的字节内容；无密钥的组装应用快照则固定启用后的目录和已加载的 skill 正文。
@@ -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/feature/2026-08-08-dsh-run-headless-command.md
+2026-08-08-dsh-run-headless-command.md: d1cc0573d1d94bb7b30e98aa685d2b7d89878a99
+2026-08-08-dsh-run-headless-command.zh.md: 7b48dfd708efb197babcfcbeaf4f8a4ca76cde3f
@@ -0,0 +1,41 @@
+# Agent Note: `dsh run` owns one-shot headless execution
+
+Status: implemented
+
+English | [中文](2026-08-08-dsh-run-headless-command.zh.md)
+
+## Problem
+
+The product launcher attached optional task text to its generic profile boot: `dsh --profile headless "task"`. That made one argv shape mean either a long-lived profile or a one-shot run according to a row discovered only after composition. The parser's `ProfileInvocation` carried optional task state, help presented a profile implementation detail as the user command, and a custom profile could accept a task only through the same overloaded root.
+
+The former `dsh -p` spelling was already absent from the parser, so restoring it or detecting it specially would add compatibility machinery to a pre-release interface. A separate application-file proposal also used the `run` verb, leaving two incompatible owners for one top-level command.
+
+## Decision
+
+One-shot execution owns an explicit grammar:
+
+```text
+dsh run [--profile <name>] [--patch <path>...] <task...>
+```
+
+`--profile` defaults to `headless` and remains available for custom one-shot compositions. `--patch` is repeatable and occupies the existing overlay layer. Commander joins the variadic task arguments with spaces and rejects a missing or blank task before boot.
+
+The [profile plugin bundle decision](../architecture/2026-08-05-profile-plugin-bundles.md) owns the composition selected by this grammar.
+
+`RunInvocation` is a separate `DshInvocation` member. The generic profile invocation no longer carries task text, and its root command accepts no positional arguments. Both dispatch paths call the existing deep `runProfile` module: `profile` omits `task`, while `run` supplies it. There is no shallow `run.ts` forwarding module and no alias, warning, or custom detector for former spellings; they fail through the ordinary Commander grammar. A one-shot profile without `headless-runner` still fails through the existing composed-row check, while booting a profile that contains that row without a task points to `dsh run --profile <name> "<task>"`.
+
+The `run` verb belongs to one-shot task execution. Launching an application file must choose another command name; two top-level meanings selected by positional shape would recreate the ambiguity this command removes.
+
+The runner's user-visible contract stays the same: a fresh persisted session, browser observation URL on stderr, final assistant text on stdout, completed/non-completed exit mapping, and bounded signal shutdown. The product-level keyless acceptance exposed that the in-process mux consumer could lag the same-process `agent/status: idle` notification and derive output before reading the final frames. The idle notification now captures the authoritative final session sequence, and the runner waits until the ordered mux reaches that boundary (or the stream ends) before deriving text and exit reason. This enforces the existing idle-to-idle contract without adding a wire field or a timing delay.
+
+## Alternatives considered
+
+- **Keep task text on `dsh --profile`.** Rejected because profile boot and one-shot execution remain one grammar whose meaning depends on a late composition check.
+- **Preserve `dsh -p` or the positional profile form as aliases.** Rejected under the pre-release stance: compatibility branches would outlive the interface they were meant to retire.
+- **Make `--profile headless` mandatory under `run`.** Rejected because the shipped one-shot surface should have the shortest canonical spelling, while optional `--profile` preserves plugin-defined one-shot compositions.
+- **Give `dsh run` to application-file launch and choose another headless verb.** Rejected because `run` describes executing a task through the harness; application-file ownership would make the product's primary one-shot command less direct and collide with custom one-shot profiles.
+- **Add `apps/cli/src/run.ts`.** Rejected because it would only forward to `runProfile`, splitting command ownership without hiding any complexity.
+
+## Consequences
+
+This is an intentional breaking CLI change. Documentation, help, parser tests, built-bin acceptance, PTY shutdown coverage, and the assembled keyless snapshot use `dsh run`. Existing custom one-shot profiles keep working through `--profile`; long-lived profiles and config dumps retain their existing root grammar. The competing application-file command must be renamed and rebased separately rather than sharing or overloading `run`.
@@ -0,0 +1,41 @@
+# Agent Note: `dsh run` 负责一次性 headless 执行
+
+Status: implemented
+
+[English](2026-08-08-dsh-run-headless-command.md) | 中文
+
+## 问题
+
+产品启动器过去把可选任务文本挂在通用 profile 启动命令上：`dsh --profile headless "task"`。于是，同一种 argv 形态会表示常驻 profile 或一次性运行，具体含义取决于组合完成后才发现的配置行。解析器的 `ProfileInvocation` 携带可选任务状态，帮助信息把 profile 的实现细节呈现为用户命令，自定义 profile 也只能通过同一个过载的根命令接收任务。
+
+解析器中已经没有原来的 `dsh -p` 写法，因此恢复该写法或加入特殊检测，会给预发布接口增加兼容机制。另一个应用文件提案也使用 `run` 动词，使同一个顶层命令同时归属两个互不兼容的功能。
+
+## 决策
+
+一次性执行采用明确语法：
+
+```text
+dsh run [--profile <name>] [--patch <path>...] <task...>
+```
+
+`--profile` 默认为 `headless`，同时保留对自定义一次性组合的支持。`--patch` 可重复使用，并沿用既有 overlay 层的位置。Commander 用空格拼接可变数量的任务参数，并在启动前拒绝缺失或空白任务。
+
+[profile 插件组合包决策](../architecture/2026-08-05-profile-plugin-bundles.md)负责该语法所选择的组合。
+
+`RunInvocation` 是单独的 `DshInvocation` 成员。通用 profile 调用不再携带任务文本，其根命令也不接受位置参数。两条分派路径都调用已有的深层 `runProfile` 模块：`profile` 省略 `task`，`run` 则提供该字段。实现中没有只负责转发的浅层 `run.ts` 模块，也没有面向旧写法的别名、警告或自定义检测器；旧写法会按普通 Commander 语法失败。缺少 `headless-runner` 的一次性 profile 仍会触发既有的组合行检查；如果启动的 profile 包含该行却未提供任务，错误会指向 `dsh run --profile <name> "<task>"`。
+
+`run` 动词只负责一次性任务执行。应用文件启动必须选择其他命令名；如果让两个顶层含义由位置参数形态决定，就会重新引入本命令消除的歧义。
+
+运行器面向用户的契约保持不变：创建新的持久化会话，在 stderr 打印浏览器观察 URL，在 stdout 打印最终 assistant 文本，将完成／未完成映射为退出状态，并执行有界的信号关闭。产品级无密钥验收用例发现，进程内 mux 消费方可能落后于同进程的 `agent/status: idle` 通知，在读到最终帧之前就生成输出。idle 通知现在会捕获权威的会话最终事件序号，运行器则等待有序 mux 到达该边界（或流结束），再生成文本和退出原因。这一机制在不增加 wire 字段或定时延迟的前提下，落实了既有的 idle-to-idle 契约。
+
+## 考虑过的替代方案
+
+- **把任务文本保留在 `dsh --profile` 上。** 不予采纳：profile 启动和一次性执行仍共用同一套语法，其含义取决于较晚发生的组合检查。
+- **保留 `dsh -p` 或位置参数 profile 形式作为别名。** 不予采纳：根据预发布立场，这些兼容分支会比本应退役的接口存续更久。
+- **要求在 `run` 下必须指定 `--profile headless`。** 不予采纳：已交付的一次性接口应采用最短的规范写法，同时用可选的 `--profile` 保留插件定义的一次性组合。
+- **把 `dsh run` 交给应用文件启动，并为 headless 选择另一个动词。** 不予采纳：`run` 描述的是通过 harness 执行任务；若归应用文件所有，产品的主要一次性命令会更不直接，并与自定义一次性 profile 冲突。
+- **新增 `apps/cli/src/run.ts`。** 不予采纳：它只会转发到 `runProfile`，拆分命令归属，却没有隐藏任何复杂度。
+
+## 后果
+
+这是一次有意为之的 CLI（命令行界面）破坏性变更。文档、帮助信息、解析器测试、构建后二进制验收、PTY 关闭覆盖和组装应用的无密钥快照都使用 `dsh run`。现有自定义一次性 profile 可继续通过 `--profile` 工作；常驻 profile 和配置 dump 保留既有的根命令语法。与之竞争的应用文件命令必须单独改名并 rebase，不得共享或重载 `run`。
@@ -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/process/2026-07-06-node-engine-floor.md
-2026-07-06-node-engine-floor.md: ef047d885a442106a35922f4716d2996d8a98ca7
-2026-07-06-node-engine-floor.zh.md: c409b006baa3451eb5fc5260be4e14ffe88776c8
+2026-07-06-node-engine-floor.md: e42b809f83fe388526ecbd74192989e0bcdbba67
+2026-07-06-node-engine-floor.zh.md: 92fa00f7a270f4506cba6c899e9edf6a2fdd3209
@@ -15,7 +15,7 @@ Set `engines.node` to `^22.19.0 || >=24.0.0` and test keyless CI on `['22.19', 2
 Two Node features gate the source runtime:

 - **`node:sqlite`** — `packages/session-persistence/session-persistence-sqlite` does a top-level `import { DatabaseSync } from 'node:sqlite'`. The module dropped its `--experimental-sqlite` flag requirement at **22.13** (LTS) and **23.4** (Current); before those, importing it throws at load.
- **Native TypeScript type-stripping** — the built-mode `examples/headless-agent/tests/keyless-smoke.e2e.ts` smoke boots `dsh-cli-demo`'s published `lib/bin.js` under plain `node` (no tsx) and loads the example's `.ts` test adapter (`cli-mock-llm.ts`). Type-stripping is the default from **22.18** (LTS) and **23.6** (Current); before those it needs `--experimental-strip-types`.
+- **Native TypeScript type-stripping** — the built-mode `examples/headless-agent/tests/keyless-smoke.e2e.ts` smoke boots its unexported `.ts` driver under plain `node` (no tsx) and loads the example's `.ts` test adapter (`cli-mock-llm.ts`). Type-stripping is the default from **22.18** (LTS) and **23.6** (Current); before those it needs `--experimental-strip-types`.

 Those source features clear on the 22.x line at **22.18**, but the installed Pi adapter dependency raises the advertised LTS floor. `@deepseek-ai/dsh-llm-pi-ai` depends on `@earendil-works/pi-ai@0.79.3`, whose package declares `engines.node >=22.19.0`, so the LTS floor is **22.19**. The 24.x branch remains `>=24.0.0`. The disjoint range excludes Node 23 entirely: Node 23.0–23.5 still has at least one flagged source feature, and the 23 line is non-LTS/EOL, so advertising `>=23.6` would add a dead release line and a CI leg no deployment should use.

@@ -25,7 +25,7 @@ Those source features clear on the 22.x line at **22.18**, but the installed Pi

 - The advertised LTS branch no longer undercuts the Pi adapter dependency floor.
 - CI proves the Node 22 LTS floor directly with Node 22.19, keeps primary coverage on `node: 24`, and exercises Node 26 as the next even line; focused compatibility smokes run on all three versions.
- The built-bin smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the test stays the plain `node lib/bin.js` path it documents.
+- The built-mode smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the example-owned TypeScript driver stays a plain `node fixture.ts` path.
 - A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this Agent Note in the same change.

 ## Alternatives considered
@@ -15,7 +15,7 @@ Status: implemented
 两个 Node 特性决定了源码运行时的门槛：

 - **`node:sqlite`**：`packages/session-persistence/session-persistence-sqlite` 在顶层执行 `import { DatabaseSync } from 'node:sqlite'`。该模块在 **22.13**（LTS）和 **23.4**（Current）取消了 `--experimental-sqlite` 标志要求；在此之前，导入它会在加载时抛出异常。
- **原生 TypeScript 类型剥离**——构建模式的 `examples/headless-agent/tests/keyless-smoke.e2e.ts` 冒烟测试使用纯 `node`（无 tsx）启动 `dsh-cli-demo` 已发布的 `lib/bin.js`，并加载示例的 `.ts` 测试适配器（`cli-mock-llm.ts`）。类型剥离从 **22.18**（LTS）和 **23.6**（Current）起成为默认行为；更早版本需要 `--experimental-strip-types`。
+- **原生 TypeScript 类型剥离**——构建模式的 `examples/headless-agent/tests/keyless-smoke.e2e.ts` 冒烟测试使用纯 `node`（无 tsx）启动该示例未导出的 `.ts` driver，并加载示例的 `.ts` 测试适配器（`cli-mock-llm.ts`）。类型剥离从 **22.18**（LTS）和 **23.6**（Current）起成为默认行为；更早版本需要 `--experimental-strip-types`。

 这些源码特性在 22.x 线上于 **22.18** 全部就绪，但已安装的 Pi 适配器依赖将宣传的 LTS 下限进一步提高。`@deepseek-ai/dsh-llm-pi-ai` 依赖 `@earendil-works/pi-ai@0.79.3`，后者的包声明 `engines.node >=22.19.0`，因此 LTS 下限为 **22.19**。24.x 分支保持 `>=24.0.0`。该不相交范围完全排除了 Node 23：Node 23.0–23.5 至少还有一个源码特性需要标志，而 23 线是非 LTS/已 EOL 的，宣传 `>=23.6` 会增加一条已终止的发布线和一条 CI 分支，而没有任何部署应当使用它。

@@ -25,7 +25,7 @@ Status: implemented

 - 宣传的 LTS 分支不再低于 Pi 适配器依赖的下限。
 - CI 通过 Node 22.19 直接验证 Node 22 LTS 下限，将主要覆盖率任务保留在 `node: 24`，并用 Node 26 验证下一个偶数线；三个版本均运行聚焦的兼容性冒烟测试。
- built-bin 冒烟测试无需版本条件标志：在 22.19 上类型剥离已是默认行为，因此测试保持其文档所述的纯 `node lib/bin.js` 路径。
+- 构建模式冒烟测试无需版本条件标志：在 22.19 上类型剥离已是默认行为，因此示例自有的 TypeScript driver 保持使用纯 `node fixture.ts` 路径。
 - 未来若依赖或源码 API 提高运行时下限，必须在同一变更中同步调整 `engines.node`、兼容性矩阵和本 Agent Note。

 ## 曾考虑的替代方案
@@ -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/process/2026-07-22-fast-local-git-hooks.md
-2026-07-22-fast-local-git-hooks.md: 838024c4293372b1430d357774feb06cd9742b9b
-2026-07-22-fast-local-git-hooks.zh.md: 26968dd19ffb42f4a618dc760b2a6edeb4900393
+2026-07-22-fast-local-git-hooks.md: af8a9380fc3cbf4f672ca0b32faa7b187522cf11
+2026-07-22-fast-local-git-hooks.zh.md: 04f3a407e421c4d585b8b78b16b9055fd19ac756
@@ -12,9 +12,9 @@ Fast hooks still need to reject cheap, high-confidence defects before work leave

 ## Decision

-[lefthook.yml](../../../../lefthook.yml) keeps both hooks as bounded local checkpoints. Pre-commit runs sequentially: a formatting-only ESLint config fixes and re-stages changed JavaScript and TypeScript, [Oxlint](2026-07-29-oxlint-linter.md) validates those files and applies native safe fixes, `git diff --cached --check` rejects staged whitespace errors, and the vendor manifest guard checks vendored-source metadata. Pre-push invokes the repository TypeScript binary directly in incremental build mode.
+[lefthook.yml](../../../../lefthook.yml) keeps both hooks as bounded local checkpoints. Pre-commit runs sequentially: a formatting-only ESLint config fixes and re-stages changed JavaScript and TypeScript, a project-free [Oxlint](2026-07-29-oxlint-linter.md) profile validates those files and applies native safe fixes, `git diff --cached --check` rejects staged whitespace errors, and the vendor manifest guard checks vendored-source metadata. Pre-push runs `pnpm run typecheck`, which prepares the generated Host TypeRT contracts before the Client incremental typecheck.

-Neither hook runs tests, snapshots, documentation checks, builds, hygiene, or the gate scheduler. The opt-in `check:all` package script selects the `check-all` scheduler inventory in [scripts/run-gates.ts](../../../../scripts/run-gates.ts) independently of the hooks; it is a contributor command, not an agent instruction.
+Pre-commit does not run type analysis, tests, snapshots, documentation checks, builds, hygiene, or the gate scheduler. Pre-push adds only the Host contract build required by repository typecheck. The opt-in `check:all` package script selects the `check-all` scheduler inventory in [scripts/run-gates.ts](../../../../scripts/run-gates.ts) independently of the hooks; it is a contributor command, not an agent instruction.

 Agents inspect the outgoing diff and run the narrowest tests and checks that cover its behavior once. CI owns exhaustive coverage, built-artifact checks, and the platform matrix. A complete local rehearsal is reserved for an explicit request, CI diagnosis, or a repository-wide change that cannot be validated credibly by narrower evidence.

@@ -31,6 +31,6 @@ This decision supersedes the local-hook portion of [Parallel pre-push gates](202

 ## Consequences

-Normal commits take the staged formatter-and-lint critical path, and warm pushes take the incremental typecheck critical path. Contributors retain a one-command opt-in rehearsal without widening the hook critical paths or the agent-required validation set. Hook latency is observed in development and PR evidence rather than enforced by a timing test whose result would depend on host load and cache state.
+Normal commits take the project-free staged formatter-and-lint critical path, and warm pushes take the prepared incremental typecheck critical path. Contributors retain a one-command opt-in rehearsal without widening the hook critical paths or the agent-required validation set. Hook latency is observed in development and PR evidence rather than enforced by a timing test whose result would depend on host load and cache state.

 Local publication no longer proves the exhaustive repository matrix. Agents must select relevant behavioral evidence, reviewers must evaluate whether that selection matches the diff, and CI supplies the comprehensive signal once per pushed revision.
@@ -12,9 +12,9 @@ agent（智能体）已经会运行能够覆盖自身改动的测试和检查，

 ## 决策

-[lefthook.yml](../../../../lefthook.yml) 将两个钩子都保留为有界的本地检查点。Pre-commit 按顺序运行：仅用于格式化的 ESLint 配置修复改动过的 JavaScript 和 TypeScript 文件并重新暂存，[Oxlint](2026-07-29-oxlint-linter.md) 验证这些文件并应用原生安全修复，`git diff --cached --check` 拒绝暂存 diff 中的空白错误，vendor manifest（元数据清单）守卫检查 vendor 源码元数据。Pre-push 直接调用仓库内的 TypeScript 二进制，并启用增量构建模式。
+[lefthook.yml](../../../../lefthook.yml) 将两个钩子都保留为有界的本地检查点。Pre-commit 按顺序运行：仅用于格式化的 ESLint 配置修复改动过的 JavaScript 和 TypeScript 文件并重新暂存，不加载项目的 [Oxlint](2026-07-29-oxlint-linter.md) 配置验证这些文件并应用原生安全修复，`git diff --cached --check` 拒绝暂存 diff 中的空白错误，vendor manifest（元数据清单）守卫检查 vendor 源码元数据。Pre-push 运行 `pnpm run typecheck`；该命令会先准备好生成的 Host TypeRT 契约，再运行 Client 增量类型检查。

-两个钩子都不运行测试、快照、文档检查、构建、`hygiene` 或门禁调度器。可选运行的 `check:all` 包脚本独立于这些钩子，从 [scripts/run-gates.ts](../../../../scripts/run-gates.ts) 中选择 `check-all` 调度器清单；它是贡献者命令，而非对 agent 的指令。
+Pre-commit 不运行类型分析、测试、快照、文档检查、构建、`hygiene` 或门禁调度器。Pre-push 只增加仓库类型检查所需的 Host 契约构建。可选运行的 `check:all` 包脚本独立于这些钩子，从 [scripts/run-gates.ts](../../../../scripts/run-gates.ts) 中选择 `check-all` 调度器清单；它是贡献者命令，而非对 agent 的指令。

 agent 检查待推送的 diff，并仅运行一次能够覆盖其行为的最小范围测试和检查。CI 负责全量覆盖率门禁、构建产物检查与平台矩阵。只有在明确要求、诊断 CI，或涉及全仓库的改动无法由范围更窄的证据得到可信验证时，才完整运行一遍本地检查矩阵。

@@ -31,6 +31,6 @@ agent 检查待推送的 diff，并仅运行一次能够覆盖其行为的最小

 ## 结果

-普通提交的关键路径是暂存文件格式化与 lint，缓存已预热时推送的关键路径是增量类型检查。贡献者仍可选择用一条命令完整演练，且不会扩展钩子关键路径或 agent 必须运行的验证集合。钩子耗时只作为开发观察数据和 PR（Pull Request）证据记录，不设置会受主机负载与缓存状态影响的计时测试。
+普通提交的关键路径是不加载项目的暂存文件格式化与 lint，缓存已预热时推送的关键路径是经过准备的增量类型检查。贡献者仍可选择用一条命令完整演练，且不会扩展钩子关键路径或 agent 必须运行的验证集合。钩子耗时只作为开发观察数据和 PR（Pull Request）证据记录，不设置会受主机负载与缓存状态影响的计时测试。

 从本地推送成功不再能证明仓库完整矩阵已通过。agent 必须选择相关的行为证据，评审人必须判断该选择是否与 diff 相符，CI 则对每个推送版本提供一次全面信号。
@@ -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/process/2026-07-27-dependabot-version-updates.md
-2026-07-27-dependabot-version-updates.md: 725649652c5b91ba4897d03b548b9aa5c3694c21
-2026-07-27-dependabot-version-updates.zh.md: 6400ba8ed94bf138fcece90e5d7ff82886d33ed1
+2026-07-27-dependabot-version-updates.md: 5d42563788d9f1e72da65c8e9750d6b1ecba06a5
+2026-07-27-dependabot-version-updates.zh.md: 4847059944e7e35de5719a6cbfd3d5b133467ccb
@@ -6,23 +6,23 @@ English | [中文](2026-07-27-dependabot-version-updates.zh.md)

 ## Problem

-Maintained registry and GitHub Actions dependencies need a regular update path. Adopting every release immediately increases exposure to compromised releases and early regressions, while leaving updates entirely manual lets dependency drift accumulate. Vendored Cordis sources and independently locked workspaces also cannot be treated as one undifferentiated package tree.
+Maintained registry and GitHub Actions dependencies need a regular update path. Adopting every release immediately increases exposure to compromised releases and early regressions, while leaving updates entirely manual lets dependency drift accumulate. Vendored Cordis sources cannot be treated like registry dependencies, and workspaces sharing one lockfile must be updated through the same package tree.

 ## Decision

-The default branch carries [`.github/dependabot.yml`](../../../../.github/dependabot.yml) with weekly version-update checks for the root pnpm workspace, the independently locked `native/landlock-run` pnpm workspace, the `python/sdk` uv project, and GitHub Actions. Every entry sets `cooldown.default-days` to `30`, so a version release becomes eligible only after it is at least 30 days old and is proposed on the next weekly check.
+The default branch carries [`.github/dependabot.yml`](../../../../.github/dependabot.yml) with weekly version-update checks for the root pnpm workspace, including `native/landlock-run`, the `python/sdk` uv project, and GitHub Actions. Every entry sets `cooldown.default-days` to `30`, so a version release becomes eligible only after it is at least 30 days old and is proposed on the next weekly check. The [in-repository Landlock release decision](2026-08-06-in-repository-landlock-release.md) owns the shared-workspace boundary.

-The root pnpm version-update scan excludes `vendor/**`, whose source and manifests move only through the [vendoring procedure](../../../../vendor/README.md), and `native/landlock-run/**`, which its dedicated entry owns. GitHub applies `exclude-paths` only to version updates; a security pull request that touches a vendored manifest is replaced through the vendoring procedure instead of being merged as generated. Dependabot pull requests receive the repository's `cleanup` kind and `area/infra` area labels, run the normal pull-request checks, and remain subject to maintainer review; this automation does not merge them.
+The root pnpm version-update scan excludes `vendor/**`, whose source and manifests move only through the [vendoring procedure](../../../../vendor/README.md). GitHub applies `exclude-paths` only to version updates; a security pull request that touches a vendored manifest is replaced through the vendoring procedure instead of being merged as generated. Dependabot pull requests receive the repository's `cleanup` kind and `area/infra` area labels, run the normal pull-request checks, and remain subject to maintainer review; this automation does not merge them.

 Repository settings enable dependency vulnerability alerts and Dependabot security updates. GitHub does not apply version-update cooldowns to those security updates, so security fixes remain eligible immediately. A generated pnpm security pull request can still fail the repository's lockfile release-age verification when dependency resolution selects unrelated fresh transitive versions; that pull request waits or is narrowed instead of weakening the policy. The repository's coordinated fresh-release exceptions are not copied into Dependabot's cooldown exclusions: automated version updates use the uniform 30-day wait, while an explicitly reviewed manual update can still follow its owning release procedure.

-The pnpm entries keep both workspaces on their pinned pnpm 11 instead of introducing an automation-only downgrade. The current Dependabot updater installs the version requested by `packageManager` and reads both workspaces' lockfile format `9.0`; the provider-run update job remains the integration check.
+The pnpm entry keeps the unified workspace on its pinned pnpm 11 instead of introducing an automation-only downgrade. The current Dependabot updater installs the version requested by the root `packageManager` and reads the root lockfile format `9.0`; the provider-run update job remains the integration check.

 ## Alternatives considered

 - **Immediate version updates.** Rejected because they remove the requested release-age quarantine and make the project an early consumer of every upstream release.
 - **Automatic merging after CI.** Rejected because dependency changes can alter runtime, build, and release behavior; the normal review decision remains part of accepting an update.
- **One recursive npm scan.** Rejected because it could admit vendored manifests or conflate the root and native lockfiles. Explicit exclusions and a dedicated native entry preserve their ownership boundaries.
+- **A separate native npm scan.** Rejected because the Landlock manifests belong to the root workspace and lockfile; splitting their update would recreate an ownership boundary the package manager no longer has. The root scan excludes only vendored manifests.
 - **Renovate or a scheduled agent.** Both can propose aged updates, but Dependabot is the requested service and the repository's CI already recognizes its pull requests as an untrusted dependency source.
 - **Cooldown exemptions for coordinated fresh releases.** Rejected for the automated path because those releases require an explicit synchronization or model-catalog decision rather than a generic update proposal.

@@ -6,23 +6,23 @@ Status: implemented

 ## 问题

-来自包注册表的依赖与 GitHub Actions 依赖都需要定期更新机制。每个新版本一经发布便立即采用，会增加受到遭入侵的版本和早期回归影响的风险；但完全依靠手动更新，又会导致依赖版本差距持续扩大。以源码形式纳入仓库的 Cordis 与各自维护独立锁文件的工作区，也不能不加区分地视为同一棵包树。
+来自包注册表的依赖与 GitHub Actions 依赖都需要定期更新机制。每个新版本一经发布便立即采用，会增加受到遭入侵的版本和早期回归影响的风险；但完全依靠手动更新，又会导致依赖版本差距持续扩大。以源码形式纳入仓库的 Cordis 不能当作注册表依赖处理，而共用一份锁文件的工作区必须通过同一棵包树更新。

 ## 决策

-默认分支包含 [`.github/dependabot.yml`](../../../../.github/dependabot.yml)，其中为根 pnpm 工作区、独立维护锁文件的 `native/landlock-run` pnpm 工作区、`python/sdk` uv 项目和 GitHub Actions 配置了每周一次的版本更新检查。每个更新项都将 `cooldown.default-days` 设为 `30`，因此某个版本只有在发布至少 30 天后才符合更新条件，并会在下一次每周检查时生成更新提案。
+默认分支包含 [`.github/dependabot.yml`](../../../../.github/dependabot.yml)，其中为包含 `native/landlock-run` 的根 pnpm 工作区、`python/sdk` uv 项目和 GitHub Actions 配置了每周一次的版本更新检查。每个更新项都将 `cooldown.default-days` 设为 `30`，因此某个版本只有在发布至少 30 天后才符合更新条件，并会在下一次每周检查时生成更新提案。[仓库内 Landlock 发布决策](2026-08-06-in-repository-landlock-release.md)负责共享工作区边界。

-根 pnpm 工作区的版本更新扫描排除 `vendor/**`，其中的源码和 manifest（元数据清单）只能通过 [vendoring 流程](../../../../vendor/README.md)变更；扫描还排除由专用更新项负责的 `native/landlock-run/**`。GitHub 仅将 `exclude-paths` 用于版本更新；如果安全更新 PR（Pull Request）涉及随源码纳入仓库的 manifest，则改由 vendoring 流程处理，以替代自动生成的 PR，而不会将其原样合并。Dependabot PR 会获得仓库的 `cleanup` 类型标签和 `area/infra` 区域标签，运行常规 PR 检查，并且仍须由维护者评审；该自动化不会合并这些 PR。
+根 pnpm 工作区的版本更新扫描排除 `vendor/**`，其中的源码和 manifest（元数据清单）只能通过 [vendoring 流程](../../../../vendor/README.md)变更。GitHub 仅将 `exclude-paths` 用于版本更新；如果安全更新 PR（Pull Request）涉及随源码纳入仓库的 manifest，则改由 vendoring 流程处理，以替代自动生成的 PR，而不会将其原样合并。Dependabot PR 会获得仓库的 `cleanup` 类型标签和 `area/infra` 区域标签，运行常规 PR 检查，并且仍须由维护者评审；该自动化不会合并这些 PR。

 仓库设置已启用依赖项漏洞警报和 Dependabot 安全更新。GitHub 不会对这些安全更新应用版本更新冷却期，因此安全修复仍可立即进入更新流程。如果依赖解析还选中了其他刚发布的传递依赖，pnpm 安全更新 PR 仍可能无法通过仓库的锁文件发布时长校验；此类 PR 应等待隔离期结束或缩小更新范围，不得因此放宽政策。仓库为协调刚发布版本而设置的例外，不会纳入 Dependabot 的冷却期排除项：自动版本更新统一等待 30 天；经过明确评审的手动更新仍可遵循相应的发布流程。

-pnpm 更新项让两个工作区继续使用已固定的 pnpm 11，不会仅为了自动化而降级版本。当前 Dependabot 更新器会安装 `packageManager` 指定的版本，并读取两个工作区使用的 `9.0` 锁文件格式；由提供方运行的更新任务仍作为集成检查。
+pnpm 更新项让统一工作区继续使用已固定的 pnpm 11，不会仅为了自动化而降级版本。当前 Dependabot 更新器会安装根 `packageManager` 指定的版本，并读取根锁文件的 `9.0` 格式；由提供方运行的更新任务仍作为集成检查。

 ## 考虑过的替代方案

 - **立即进行版本更新。** 不采用，因为这会取消所要求的版本发布后隔离期，使项目在每个上游版本的发布初期就采用该版本。
 - **CI 通过后自动合并。** 不采用，因为依赖变更可能改变运行时、构建和发布行为；是否接受更新仍须经过常规评审决策。
- **使用一次递归 npm 扫描。** 不采用，因为它可能将随源码纳入仓库的 manifest 纳入更新范围，或混淆根工作区与 native 工作区的锁文件。显式排除项和专用 native 更新项可维持各自的归属边界。
+- **为 native 配置独立的 npm 扫描。** 不采用，因为 Landlock manifest 属于根工作区和根锁文件；拆分更新会重建一个包管理器已不存在的归属边界。根扫描仅排除随源码纳入的 manifest。
 - **Renovate 或定期运行的 agent（智能体）。** 二者都能为发布已满一定时长的版本提出更新，但所要求的服务是 Dependabot，而且仓库 CI 已将其 PR 视为不可信的依赖来源。
 - **为需协调的刚发布版本设置冷却期豁免。** 自动化路径不采用，因为此类版本需要明确的同步决策或模型目录决策，不能由通用更新提案代替。

@@ -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/process/2026-07-29-oxlint-linter.md
-2026-07-29-oxlint-linter.md: 41a50a9d08819809f954aa99007081f270692f38
-2026-07-29-oxlint-linter.zh.md: 85d053af867353ff1b4c53822013f55660c89cca
+2026-07-29-oxlint-linter.md: 3e3de24be33b8f9461cea2967b0fa18f59ddb52a
+2026-07-29-oxlint-linter.zh.md: 5388416b54a5ff44b9ab9551d726705a84a8b1a1
@@ -12,19 +12,19 @@ A faster runner cannot justify losing rules. The migration must preserve the str

 ## Decision

-The root [`.oxlintrc.json`](../../../../.oxlintrc.json) is the authoritative repository lint configuration. The `lint` package script, gate scheduler, CI, and lefthook invoke Oxlint through [`scripts/run-oxlint.ts`](../../../../scripts/run-oxlint.ts) for repository-wide, type-aware, or staged validation. The `lint:fix` script and lefthook first invoke the formatting-only [`eslint.format.config.mjs`](../../../../eslint.format.config.mjs), then run Oxlint. The direct `eslint` and `@typescript-eslint/parser` development dependencies exist only for this parser-without-project formatting pass; their exact versions pin the tested parser/fixer pairing, and that config contains no correctness or type-aware rules.
+The root [`.oxlintrc.json`](../../../../.oxlintrc.json) is the authoritative type-aware repository lint configuration. The project-free [`.oxlintrc.staged.json`](../../../../.oxlintrc.staged.json) profile inherits its source rules but disables type analysis for the bounded pre-commit path. The `lint` package script, gate scheduler, CI, and lefthook invoke Oxlint through [`scripts/run-oxlint.ts`](../../../../scripts/run-oxlint.ts); `lint:fix` and lefthook first invoke the formatting-only [`eslint.format.config.mjs`](../../../../eslint.format.config.mjs). The direct `eslint` and `@typescript-eslint/parser` development dependencies exist only for this parser-without-project formatting pass; their exact versions pin the tested parser/fixer pairing, and that config contains no correctness or type-aware rules.

 `options.typeAware` enables `oxlint-tsgolint`. Its backend performs per-file TypeScript-project discovery: package sources use their package projects, host tests/examples/website use `tsconfig.host.json`, and client tests plus `scripts/client-bundle-purity.spec.ts` use `tsconfig.client.json`. The program-less root solution is never flattened. Oxlint's `--tsconfig` override affects import resolution but is ignored by type-aware linting, so this repository does not set it. The configuration explicitly carries the migrated strict-type-checked rules and repository overrides instead of enabling broad Oxlint categories whose contents may change. `typescript/no-unnecessary-condition` remains enabled from Oxlint's nursery set because it was an enforced repository rule before migration.

 Oxlint's JavaScript-plugin compatibility layer runs `@stylistic/eslint-plugin` and `eslint-plugin-sonarjs` so the existing formatting and file-local duplicate-logic rules remain enforced. The compatibility layer reports `@stylistic` violations but does not execute their fixers, so the formatting-only ESLint pass owns only the corresponding auto-fixes; an executable parity check keeps those fixable rule definitions aligned while `max-len` remains validation-only. Owned-source suppressions use `oxlint-*` directives and the `typescript/*` namespace, and unused directives remain warnings; vendored sources keep their upstream directives because Oxlint excludes `vendor/**`.

-CI does not restore or save a lint-result cache. `DSH_OXLINT_THREADS` makes the shared runner pass the same bound to Oxlint's `--threads` option and the type-aware backend's `GOMAXPROCS` environment variable; ordinary local runs use both defaults. Pre-commit applies the formatting-only ESLint fixes, runs Oxlint validation and native safe fixes, accepts selections containing only ignored files, and re-stages the result through lefthook.
+CI does not restore or save a lint-result cache. `DSH_OXLINT_THREADS` makes the shared runner pass the same bound to Oxlint's `--threads` option and the type-aware backend's `GOMAXPROCS` environment variable; ordinary local runs use both defaults. Pre-commit applies the formatting-only ESLint fixes, runs project-free Oxlint validation and native safe fixes, accepts selections containing only ignored files, and re-stages the result through lefthook. Public `lint` and CI retain the complete type-aware rules after preparing generated declarations.

 ## Verification

 The migrated configuration reports the same clean owned-source baseline after resolving two analyzer differences: one redundant test assertion was removed, while one structural cast required by `tsc` carries a narrow Oxlint suppression. A one-time audit against the exact deleted ESLint configuration blob established source 88-to-88, examples 87-to-87, and tests 83-to-83 after the rule-name translations. The committed fingerprint pins those audited Oxlint profiles and the complete override shape; it neither executes the deleted configuration nor propagates later upstream preset changes. Evaluating `typescript-eslint@8.61.0` also confirms that `strictTypeChecked` did not enable `@typescript-eslint/no-empty-function`; the deleted tests-only `off` entry was inert.

-Executable contract tests require type-aware diagnostics from the package, host, and client projects; assert the client-only script's project; reject unmatched fallback analysis; and exercise the Stylistic, SonarJS, and nursery compatibility paths. They also pin unused-suppression reporting, ignored-only staged selections, formatter/validator rule parity, and final formatted bytes. Runner tests pin both worker controls, and typecheck confirms that migration-driven source edits preserve the TypeScript programs.
+Executable contract tests require type-aware diagnostics from the package, host, and client projects; assert the client-only script's project; reject unmatched fallback analysis; and exercise the Stylistic, SonarJS, and nursery compatibility paths. They also pin the staged profile's project-free inheritance, unused-suppression reporting, ignored-only staged selections, formatter/validator rule parity, and final formatted bytes. Runner tests pin both worker controls, and typecheck confirms that migration-driven source edits preserve the TypeScript programs.

 ## Alternatives considered

@@ -42,4 +42,4 @@ Local migration measurements reduced a clean type-aware lint run from about 61 s

 Type-aware diagnostics now come from the TypeScript Go analyzer bundled through `oxlint-tsgolint`, so edge-case inference can differ from typescript-eslint even when `tsc` accepts the same program. Lint and typecheck remain separate required evidence.

-The JavaScript-plugin compatibility API and staged formatter are additional boundaries to maintain. Commits pay one project-free ESLint startup before Oxlint, and the root development graph retains ESLint plus the TypeScript parser. Repository-wide validation, type-aware analysis, cache policy, worker control, and inline directives remain Oxlint-owned.
+The JavaScript-plugin compatibility API, staged profile, and staged formatter are additional boundaries to maintain. Commits defer type-aware diagnostics to public lint and CI, pay one project-free ESLint startup before Oxlint, and avoid depending on generated declarations. The root development graph retains ESLint plus the TypeScript parser. Repository-wide validation, type-aware analysis, cache policy, worker control, and inline directives remain Oxlint-owned.
@@ -12,19 +12,19 @@ Status: implemented

 ## 决策

-根目录的 [`.oxlintrc.json`](../../../../.oxlintrc.json) 是仓库 lint 配置的权威来源。`lint` 包脚本、门禁调度器、CI 和 lefthook 通过 [`scripts/run-oxlint.ts`](../../../../scripts/run-oxlint.ts) 调用 Oxlint，进行全仓库、类型感知或暂存验证。`lint:fix` 脚本和 lefthook 先调用仅用于格式化的 [`eslint.format.config.mjs`](../../../../eslint.format.config.mjs)，再运行 Oxlint。直接的 `eslint` 和 `@typescript-eslint/parser` 开发依赖仅用于这次不加载项目的格式化流程；其精确版本锁定经过测试的解析器与修复器配对，该配置不包含正确性规则或类型感知规则。
+根目录的 [`.oxlintrc.json`](../../../../.oxlintrc.json) 是仓库类型感知 lint 配置的权威来源。不加载项目的 [`.oxlintrc.staged.json`](../../../../.oxlintrc.staged.json) 配置继承其源码规则，但会为有界的 pre-commit 路径禁用类型分析。`lint` 包脚本、门禁调度器、CI 和 lefthook 通过 [`scripts/run-oxlint.ts`](../../../../scripts/run-oxlint.ts) 调用 Oxlint；`lint:fix` 和 lefthook 会先调用仅用于格式化的 [`eslint.format.config.mjs`](../../../../eslint.format.config.mjs)。直接的 `eslint` 和 `@typescript-eslint/parser` 开发依赖仅用于这次不加载项目的格式化流程；其精确版本锁定经过测试的解析器与修复器配对，该配置不包含正确性规则或类型感知规则。

 `options.typeAware` 启用 `oxlint-tsgolint`。其后端按文件发现 TypeScript 项目：包源码使用各自的包项目，host 测试、示例和网站使用 `tsconfig.host.json`，client 测试及 `scripts/client-bundle-purity.spec.ts` 使用 `tsconfig.client.json`。不含程序的根解决方案绝不会被扁平化。Oxlint 的 `--tsconfig` 覆盖项会影响导入解析，但类型感知 lint 会忽略它，因此本仓库不设置该选项。该配置显式载入迁移后的严格类型检查规则和仓库覆盖配置，而不启用内容可能发生变化的 Oxlint 宽泛类别。`typescript/no-unnecessary-condition` 仍从 Oxlint 的 nursery 规则集中启用，因为它在迁移前就是仓库强制执行的规则。

 Oxlint 的 JavaScript 插件兼容层运行 `@stylistic/eslint-plugin` 和 `eslint-plugin-sonarjs`，从而继续强制执行现有的格式和文件内重复逻辑规则。兼容层会报告 `@stylistic` 违规，但不会执行其修复器，因此仅用于格式化的 ESLint 流程只负责相应的自动修复；一项可执行检查确保这些可修复规则定义保持一致，而 `max-len` 仅用于验证。自有源码中的抑制指令使用 `oxlint-*` 指令和 `typescript/*` 命名空间，未使用的指令仍作为警告报告；vendor 源码保留其上游指令，因为 Oxlint 会排除 `vendor/**`。

-CI 不恢复或保存 lint 结果缓存。`DSH_OXLINT_THREADS` 使共享运行器将同一上限传给 Oxlint 的 `--threads` 选项和类型感知后端的 `GOMAXPROCS` 环境变量；普通本地运行对两者均采用默认值。Pre-commit 应用仅用于格式化的 ESLint 修复，运行 Oxlint 验证和原生安全修复，接受仅含已忽略文件的文件选择，并通过 lefthook 重新暂存结果。
+CI 不恢复或保存 lint 结果缓存。`DSH_OXLINT_THREADS` 使共享运行器将同一上限传给 Oxlint 的 `--threads` 选项和类型感知后端的 `GOMAXPROCS` 环境变量；普通本地运行对两者均采用默认值。Pre-commit 应用仅用于格式化的 ESLint 修复，运行不加载项目的 Oxlint 验证并应用原生安全修复，接受仅含已忽略文件的文件选择，并通过 lefthook 重新暂存结果。公共 `lint` 和 CI 会先准备生成的声明，并保留完整的类型感知规则。

 ## 验证

 解决两处分析器差异后，迁移后的配置报告与迁移前一致的自有源码无问题基线：移除了一项冗余测试断言，而 `tsc` 要求的一处结构性类型转换使用了窄范围的 Oxlint 抑制指令。以已删除 ESLint 配置的精确 blob 为基准进行的一次性审核在完成规则名映射后确认：源码为 88 项对 88 项，示例为 87 项对 87 项，测试为 83 项对 83 项。已提交的指纹锁定这些经审核的 Oxlint 规则配置及完整的覆盖结构；它既不执行已删除的配置，也不纳入后续的上游预设变更。对 `typescript-eslint@8.61.0` 的评估还确认，`strictTypeChecked` 并未启用 `@typescript-eslint/no-empty-function`；已删除、仅用于测试的 `off` 条目不起作用。

-可执行契约测试要求包、host 和 client 项目产生类型感知诊断，断言 client 专用脚本所用的项目，拒绝未匹配的回退分析，并检验 Stylistic、SonarJS 和 nursery 兼容路径。它们还锁定未使用抑制指令的报告行为、仅选择已忽略暂存文件的情况、格式化器与验证器之间的规则一致性，以及最终格式化后的字节。运行器测试锁定两项工作线程控制，类型检查则确认迁移引发的源码改动没有破坏 TypeScript 程序。
+可执行契约测试要求包、host 和 client 项目产生类型感知诊断，断言 client 专用脚本所用的项目，拒绝未匹配的回退分析，并检验 Stylistic、SonarJS 和 nursery 兼容路径。它们还锁定暂存配置不加载项目的继承行为、未使用抑制指令的报告行为、仅选择已忽略暂存文件的情况、格式化器与验证器之间的规则一致性，以及最终格式化后的字节。运行器测试锁定两项工作线程控制，类型检查则确认迁移引发的源码改动没有破坏 TypeScript 程序。

 ## 考虑过的替代方案

@@ -42,4 +42,4 @@ CI 不恢复或保存 lint 结果缓存。`DSH_OXLINT_THREADS` 使共享运行

 类型感知诊断现在来自通过 `oxlint-tsgolint` 捆绑的 TypeScript Go 分析器，因此即使 `tsc` 接受同一程序，边界场景下的类型推断也可能与 typescript-eslint 不同。lint 与类型检查仍是两项相互独立的必要证据。

-JavaScript 插件兼容 API 和暂存文件格式化器是需要维护的额外边界。每次提交在 Oxlint 之前需要启动一次不加载项目的 ESLint，根目录开发依赖图仍保留 ESLint 和 TypeScript 解析器。全仓库验证、类型感知分析、缓存政策、工作线程控制和内联指令仍由 Oxlint 负责。
+JavaScript 插件兼容 API、暂存配置和暂存文件格式化器是需要维护的额外边界。每次提交把类型感知诊断留给公共 lint 和 CI，在 Oxlint 之前启动一次不加载项目的 ESLint，并避免依赖生成的声明。根目录开发依赖图仍保留 ESLint 和 TypeScript 解析器。全仓库验证、类型感知分析、缓存政策、工作线程控制和内联指令仍由 Oxlint 负责。
@@ -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/process/2026-07-30-generated-third-party-notices.md
-2026-07-30-generated-third-party-notices.md: cbabd1142ad292f78a3184723182a834dfb234fc
-2026-07-30-generated-third-party-notices.zh.md: b135c3626b661f1a5b0317a90b700a26d679bf1e
+2026-07-30-generated-third-party-notices.md: f2591c8d0c7d4b83ecc96bf237ded667e322d55c
+2026-07-30-generated-third-party-notices.zh.md: 74c95cc4349e9d1288d6635b0ae8617e7b929115
@@ -24,7 +24,7 @@ The file discloses **direct** dependencies by default. The complete npm closure

 The runtime tier deliberately covers **every mountable plugin**, not just what the CLI, Web UI, and Python runtime load by default. `scripts/install.sh` installs the repository itself, so a user's `cordis.yml` can mount any plugin package; `@modelcontextprotocol/sdk` and the OpenTelemetry packages reach real users even though no default assembly imports them. Under-disclosure is the costly direction for a legal notice.

-The manifest set is derived from the `packages:` members each `pnpm-workspace.yaml` declares — the root one and the nested Landlock workspace's — so a new member area is read the day it is declared rather than the day someone remembers to extend a list. License and repository metadata come from the installed pnpm stores, both the root one and the Landlock workspace's, so the generator requires an installed tree and fails loud when a package resolves to neither, rather than emitting an empty cell. `OVERRIDES` carries the packages whose published manifest cannot answer — Rust-built npm bins that omit `license`, and the `modelcontextprotocol/servers` packages whose repository is mid MIT→Apache-2.0 relicensing, so their effective terms are per-contribution. A runtime dependency whose license is not on the permissive list is a hard error: shipping copyleft is a distribution decision, not something a regenerated table may absorb silently. Vendored packages are cross-checked against `vendor/README.md` and rejected if any is not MIT, and `pnpm-workspace.yaml`'s `patchedDependencies` are listed under the runtime table because pnpm applies those patches at install time — shipped artifacts carry modified copies of `@earendil-works/pi-tui` and `node-pty`, and the patch files are the record of what changed.
+The manifest set is derived from the `packages:` members the root `pnpm-workspace.yaml` declares, including the Landlock workspace and its public packages, so a new member area is read the day it is declared rather than the day someone remembers to extend a list. License and repository metadata come from the root workspace's installed pnpm store and package-local link farms, so the generator requires an installed tree and fails loud when a package resolves to neither, rather than emitting an empty cell. `OVERRIDES` carries the packages whose published manifest cannot answer — Rust-built npm bins that omit `license`, and the `modelcontextprotocol/servers` packages whose repository is mid MIT→Apache-2.0 relicensing, so their effective terms are per-contribution. A runtime dependency whose license is not on the permissive list is a hard error: shipping copyleft is a distribution decision, not something a regenerated table may absorb silently. Vendored packages are cross-checked against `vendor/README.md` and rejected if any is not MIT, and `pnpm-workspace.yaml`'s `patchedDependencies` are listed under the runtime table because pnpm applies those patches at install time — shipped artifacts carry modified copies of `@earendil-works/pi-tui` and `node-pty`, and the patch files are the record of what changed.

 The project owner separately authorizes distribution of every official `@anthropic-ai/claude-agent-sdk` version and the official Claude Code CLI/platform payloads that version declares through `optionalDependencies`. The generator represents this as one exact direct-package identity exception, not as a permissive-license override: `SEE LICENSE IN README.md` and `SEE LICENSE IN LICENSE.md` remain non-permissive classifications, and every unrelated non-permissive runtime still fails closed. When the SDK is present, the generator reads its installed manifest, rejects optional identities outside the official SDK payload prefix, derives the current SDK, CLI, and payload versions, verifies the installed host payload's identity, version, and declared-license field, and renders the complete SDK-declared payload set in a separate notices section. Version, declared-license, and payload-set changes do not require new identity authorization, but they still require ordinary dependency, lockfile, compatibility, terms, and notices review.

@@ -24,7 +24,7 @@ Status: implemented

 运行时层刻意覆盖**所有可挂载的插件**，而不止 CLI、Web UI 与 Python 运行时默认加载的那些。`scripts/install.sh` 安装的就是仓库本身，用户的 `cordis.yml` 可以挂载任何插件包；`@modelcontextprotocol/sdk` 与 OpenTelemetry 系列即使没有任何默认装配引入，也会触达真实用户。对法务披露而言，披露不足才是代价更高的那个方向。

-清单集合由两个 `pnpm-workspace.yaml`——根工作区与嵌套的 Landlock 工作区——各自声明的 `packages:` 成员派生，因此新增成员区域在声明当天就会被读取，而不必等谁想起来去补一份列表。许可证与仓库地址取自已安装的 pnpm store，根 store 与 Landlock 工作区的 store 都会查；某个包两处都解析不到时直接失败，而不是留下空单元格。`OVERRIDES` 收录已发布清单答不上来的包：用 Rust 构建、发布时省略 `license` 字段的 npm 可执行包，以及 `modelcontextprotocol/servers` 系列——该仓库正处在 MIT 向 Apache-2.0 的重新许可过程中，实际条款按贡献逐条而定。运行时依赖的许可证若不在宽松清单内即为硬失败：交付 copyleft 是一项分发决策，不该被一次重新生成悄悄吸收。被源码收编的包会与 `vendor/README.md` 交叉核对，出现非 MIT 即报错；`pnpm-workspace.yaml` 的 `patchedDependencies` 列在运行时表格之后，因为 pnpm 在安装期就会打上这些补丁——交付产物携带的是改动过的 `@earendil-works/pi-tui` 与 `node-pty`，补丁文件本身就是改动的完整记录。
+清单集合由根 `pnpm-workspace.yaml` 声明的 `packages:` 成员派生，其中包括 Landlock 工作区及其公开包，因此新增成员区域在声明当天就会被读取，而不必等谁想起来去补一份列表。许可证与仓库地址取自根工作区已安装的 pnpm store 和包本地链接场；某个包两处都解析不到时直接失败，而不是留下空单元格。`OVERRIDES` 收录已发布清单答不上来的包：用 Rust 构建、发布时省略 `license` 字段的 npm 可执行包，以及 `modelcontextprotocol/servers` 系列——该仓库正处在 MIT 向 Apache-2.0 的重新许可过程中，实际条款按贡献逐条而定。运行时依赖的许可证若不在宽松清单内即为硬失败：交付 copyleft 是一项分发决策，不该被一次重新生成悄悄吸收。被源码收编的包会与 `vendor/README.md` 交叉核对，出现非 MIT 即报错；`pnpm-workspace.yaml` 的 `patchedDependencies` 列在运行时表格之后，因为 pnpm 在安装期就会打上这些补丁——交付产物携带的是改动过的 `@earendil-works/pi-tui` 与 `node-pty`，补丁文件本身就是改动的完整记录。

 项目所有者另行授权分发每个官方 `@anthropic-ai/claude-agent-sdk` 版本，以及该版本通过 `optionalDependencies` 声明的官方 Claude Code CLI 与平台载荷。生成器将其表示为一项精确匹配直接包身份的例外，而非宽松许可证覆盖项：`SEE LICENSE IN README.md` 与 `SEE LICENSE IN LICENSE.md` 仍归类为非宽松，所有无关的非宽松运行时依赖仍以默认拒绝方式失败。存在该 SDK 时，生成器会读取其已安装清单，拒绝不符合官方 SDK 载荷前缀的可选包身份，推导当前 SDK、CLI 与载荷版本，核验已安装宿主载荷的身份、版本和声明许可证字段，并在单独的声明章节中渲染 SDK 声明的完整载荷集合。版本、声明许可证和载荷集合发生变化时无需新的身份授权，但仍须经过常规的依赖、锁文件、兼容性、条款和声明评审。

@@ -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/process/2026-08-06-in-repository-landlock-release.md
+2026-08-06-in-repository-landlock-release.md: 3ae9e9c3c50a1d0202a345e419cb2b7079e29ffa
+2026-08-06-in-repository-landlock-release.zh.md: 9f2233f6ae95620d7221f83648b5dc9b4cf8c7d2
@@ -0,0 +1,44 @@
+# Agent Note: In-repository Landlock release
+
+Status: implemented
+
+English | [中文](2026-08-06-in-repository-landlock-release.zh.md)
+
+## Problem
+
+The `@deepseek-ai/node-addon-landlock-run` source already lives beside its DeepSeek Harness consumers under `native/landlock-run`, but it previously kept a separate pnpm workspace and lockfile and depended on a standalone repository for npm publication. Harness packages consumed a fixed registry version, so one pull request could change the launcher contract and its consumer without testing those changes together. The source repository's native workflow could rehearse the package, but it did not publish the artifact it tested.
+
+The mirror also duplicated release coordination: export the source, update another lockfile, run another release workflow, publish the native family, then return to this repository to bump registry dependencies. That split made source-to-binary provenance, rollback, and security-fix coordination harder without changing what npm users actually needed.
+
+The existing unscoped npm names are owned by the standalone publisher account rather than the `@deepseek-ai` organization. Moving only the workflow would therefore leave publication dependent on a personal credential outside the repository's release ownership.
+
+The consolidation must preserve platform selection. The public distribution is deliberately one JavaScript entry package plus separate Linux x64 and arm64 binary packages; merging repository ownership does not imply putting every binary into one tarball or publishing every DeepSeek Harness package at the launcher version.
+
+## Decision
+
+`native/landlock-run` and `native/landlock-run/packages/*` belong to the repository's root pnpm workspace and use the root `pnpm-lock.yaml`. Harness consumers declare `@deepseek-ai/node-addon-landlock-run` with `workspace:*`, so development, type checking, builds, and pull-request tests resolve the entry package from the same checkout. The root TypeScript project graph builds that entry package before consumers, and the repository cleaner owns its direct `lib/` output.
+
+The public npm boundary is three organization-owned packages with one launcher-family version: `@deepseek-ai/node-addon-landlock-run`, `@deepseek-ai/node-addon-landlock-run-linux-x64`, and `@deepseek-ai/node-addon-landlock-run-linux-arm64`. The entry package retains both platform packages as `optionalDependencies`; their `os` and `cpu` manifest fields let npm install only the compatible package. Repository constraints allow public publication only for those three names, require `publishConfig.access: public`, and require their versions to match the private launcher workspace root. The former unscoped names are not release targets of this repository; other repository workspaces remain private under the existing constraint.
+
+The main repository owns both native CI and publication. `Landlock Run` runs for relevant pull requests and `master` pushes and builds each platform on its matching native runner. The manually dispatched `Landlock Run Release` workflow builds both platform binaries, transfers them as workflow artifacts, assembles and verifies the complete package family, packs immutable npm tarballs, installs and exercises those tarballs, and only then permits the protected publish job. Platform tarballs publish before the entry tarball that optionally depends on them. Publication uses `landlock-run-vX.Y.Z` tags so launcher releases cannot collide with other release families in the monorepo; prereleases use the npm `next` dist-tag.
+
+The sandbox packed-install rehearsal no longer permits the npm registry to supply the launcher. It packs the current checkout's entry and matching native package alongside the harness dependency closure, installs those local tarballs into an external plain-Node consumer, and proves that the installed launcher is executable, byte-identical to the native build, and the correct ELF architecture before testing confinement or fail-closed behavior.
+
+## Alternatives considered
+
+- **Keep the standalone repository as a release mirror** — rejected because it preserves the split lockfiles, source export, stale-registry test window, and cross-repository release sequence after the source of record has already moved here.
+- **Publish one npm package containing every platform binary** — rejected because users would download binaries they cannot run and npm could no longer use package-level `os`/`cpu` filtering. Repository ownership and npm package layout are separate choices.
+- **Give the launcher the root DeepSeek Harness version and publish the complete monorepo recursively** — rejected because this change owns one three-package public family, not the independent `@deepseek-ai/dsh-*` baseline. The [artifact-first npm baseline proposal](../../proposed/process/2026-08-04-artifact-first-npm-baseline-publication.md) explicitly keeps native workspaces outside its target set.
+- **Cross-compile both binaries in one release job** — rejected because the checked-in package matrix already assigns each architecture a native GitHub runner and avoids adding a cross-toolchain trust surface.
+
+## Consequences
+
+Launcher protocol, TypeScript entry code, native source, harness consumption, and publish-path tests can change in one pull request and resolve from one lockfile. A release tag now identifies the source, consumer integration, build instructions, and tarballs tested by the main repository. The standalone mirror is no longer part of the release path and can be archived after the first successful in-repository publication.
+
+npm consumers install `@deepseek-ai/node-addon-landlock-run`; the old unscoped package names are not silently redirected. A supported Linux host downloads the scoped entry package and its matching architecture package; the other architecture package is skipped. An unsupported host receives no platform binary and follows the existing deterministic fail-closed probe path.
+
+The implementation touches more files than a dependency-line edit because the repository must also own workspace constraints, TypeScript build order, cleanup, CI triggers, release tags, lockfile generation, packed-install provenance, release documentation, and generated notices. The behavioral boundary stays narrow: it changes only the Landlock package family and its three direct workspace consumers, not the version or publication state of other DeepSeek Harness packages.
+
+The first scoped release must use an `@deepseek-ai` organization token through the `npm-publish` environment's `NPM_TOKEN`, because npm cannot configure trusted publishing until a package exists. After bootstrap, all three packages must authorize this repository's release workflow before the fallback token can be removed. npm still publishes packages sequentially and offers no cross-package transaction, so a failed publish can leave a partial version. Because npm rejects an already-published name and version, an operator must inspect the registry and publish only the missing tarballs rather than rerunning the workflow unchanged. Linux x64 and arm64 runners remain the authoritative binary and real-kernel checks; a macOS checkout can verify the entry package and unsupported-platform behavior but cannot replace those jobs.
+
+This note supersedes only the release-mirror and registry-pinned source-development statements in the [sandbox Agent Note](../feature/2026-07-06-sandbox.md); that note continues to own sandbox behavior, runner selection, and enforcement semantics.
@@ -0,0 +1,44 @@
+# Agent Note: 仓库内 Landlock 发布
+
+Status: implemented
+
+[English](2026-08-06-in-repository-landlock-release.md) | 中文
+
+## 问题
+
+`@deepseek-ai/node-addon-landlock-run` 源码已经与其 DeepSeek Harness 消费方一同位于 `native/landlock-run` 下，但此前仍保留独立的 pnpm workspace 和锁文件，并依赖一个独立仓库发布到 npm。Harness 包使用 npm 注册表中的固定版本，因此同一个 PR（Pull Request）可以同时修改启动器契约及其消费方，却无法一起测试这些改动。源码仓库的原生工作流可以演练打包流程，但不会发布它实际测试过的产物。
+
+发布镜像还造成重复的发布协调工作：导出源码、更新另一份锁文件、运行另一套发布工作流、发布原生包家族，然后回到本仓库更新注册表依赖。npm 用户的实际需求并未改变，这种拆分却增加了从源码到二进制的溯源、回滚和安全修复协调难度。
+
+现有的非 scoped npm 包名归独立发布账号所有，而不属于 `@deepseek-ai` 组织。因此，仅迁移工作流仍会让发布依赖仓库发布归属之外的个人凭证。
+
+此次整合必须保留平台选择机制。公开分发有意采用一个 JavaScript 入口包，并为 Linux x64 和 arm64 分别提供二进制包；合并仓库归属并不意味着要把所有二进制文件放进同一个 tarball，也不意味着要按照启动器版本发布所有 DeepSeek Harness 包。
+
+## 决策
+
+`native/landlock-run` 和 `native/landlock-run/packages/*` 属于仓库根 pnpm workspace，并使用根 `pnpm-lock.yaml`。Harness 消费方将 `@deepseek-ai/node-addon-landlock-run` 声明为 `workspace:*`，因此开发、类型检查、构建和 PR 测试都会从同一个 checkout 解析入口包。根 TypeScript 项目图会先构建该入口包，再构建消费方；仓库清理器负责清理其直接生成的 `lib/` 输出目录。
+
+公开 npm 分发边界由 3 个归组织所有的包组成，它们共用一个启动器包家族版本：`@deepseek-ai/node-addon-landlock-run`、`@deepseek-ai/node-addon-landlock-run-linux-x64` 和 `@deepseek-ai/node-addon-landlock-run-linux-arm64`。入口包继续通过 `optionalDependencies` 声明两个平台包；它们在 manifest（元数据清单）中的 `os` 和 `cpu` 字段让 npm 只安装兼容的包。仓库约束只允许公开发布这 3 个包名，要求设置 `publishConfig.access: public`，并要求其版本与私有启动器 workspace 根包一致。原先的非 scoped 包名不属于本仓库的发布目标；仓库中的其他 workspace 仍受现有约束保护，保持私有状态。
+
+主仓库同时负责原生 CI 和发布。`Landlock Run` 会为相关 PR 和 `master` 推送运行，并在各自匹配的原生 runner 上构建每个平台包。手动触发的 `Landlock Run Release` 工作流会构建两个平台的二进制文件，将其作为工作流产物传递，组装并验证完整的包家族，打包出内容不可变的 npm tarball，安装并实际运行这些 tarball，之后才允许受保护的发布作业执行。发布顺序是平台 tarball 在前，最后发布将它们列为可选依赖的入口 tarball。发布使用 `landlock-run-vX.Y.Z` tag，避免启动器版本与 monorepo 中其他发布家族发生冲突；预发布版本使用 npm 的 `next` dist-tag。
+
+沙箱打包安装演练不再允许 npm 注册表提供启动器。它会将当前 checkout 的入口包、匹配的原生包和 harness 依赖闭包一起打包，把这些本地 tarball 安装到仓库外部的纯 Node 消费方中，并在测试约束效果或失败闭合行为之前，证明所安装的启动器可执行、与原生构建产物字节完全一致，且具有正确的 ELF 架构。
+
+## 曾考虑的替代方案
+
+- **保留独立仓库作为发布镜像**：不予采纳，因为在权威源码已经迁入本仓库后，这仍会保留拆分的锁文件、源码导出、测试使用陈旧注册表版本的时间窗，以及跨仓库发布序列。
+- **发布一个包含所有平台二进制文件的 npm 包**：不予采纳，因为用户会下载无法在其主机上运行的二进制文件，而且 npm 无法再利用包级 `os`／`cpu` 筛选。仓库归属与 npm 包布局是两个彼此独立的选择。
+- **让启动器使用 DeepSeek Harness 根版本，并递归发布整个 monorepo**：不予采纳，因为本次改动负责的是一个由 3 个包组成的公开包家族，而不是独立的 `@deepseek-ai/dsh-*` 基线。[产物优先的 npm 基线提案](../../proposed/process/2026-08-04-artifact-first-npm-baseline-publication.md)明确将原生 workspace 排除在其目标集合之外。
+- **在一个发布作业中交叉编译两个二进制文件**：不予采纳，因为仓库内已提交的包矩阵已经为每种架构分配了原生 GitHub runner，无需再把交叉工具链纳入信任边界。
+
+## 后果
+
+同一个 PR 可以同时修改启动器协议、TypeScript 入口代码、原生源码、harness 消费方式和发布路径测试，并从同一份锁文件解析这些内容。发布 tag 现在标识源码、消费方集成、构建指令，以及主仓库测试过的 tarball。第一次成功从本仓库发布后，独立镜像便不再属于发布路径，可以归档。
+
+npm 消费方改为安装 `@deepseek-ai/node-addon-landlock-run`；原先的非 scoped 包名不会被静默重定向。受支持的 Linux 主机会下载 scoped 入口包及与其架构匹配的包，并跳过另一架构的包。不受支持的主机不会收到平台二进制文件，并继续沿用现有的确定性失败闭合探测路径。
+
+实现涉及的文件比只修改一行依赖更多，因为仓库还必须负责 workspace 约束、TypeScript 构建顺序、清理、CI 触发条件、发布 tag、锁文件生成、打包安装来源证明、发布文档和生成的第三方声明。行为边界仍然很窄：此次改动只影响 Landlock 包家族及其 3 个直接 workspace 消费方，不改变其他 DeepSeek Harness 包的版本或发布状态。
+
+第一次发布 scoped 包时，必须通过 `npm-publish` 环境的 `NPM_TOKEN` 使用 `@deepseek-ai` 组织 token，因为 npm 只有在包已经存在后才能配置 trusted publishing。完成 bootstrap 后，必须让 3 个包都授权本仓库的发布工作流，才能移除后备 token。npm 仍会按顺序发布各个包，且不提供跨包事务，因此发布失败可能留下只完成了一部分的版本。由于 npm 会拒绝已经发布的同名同版本包，操作人员必须检查注册表并只发布缺失的 tarball，而不能原样重新运行工作流。Linux x64 和 arm64 runner 仍提供权威的二进制构建与真实内核检查；macOS checkout 可以验证入口包和不受支持平台上的行为，但不能取代这些作业。
+
+本说明仅取代[沙箱 Agent Note](../feature/2026-07-06-sandbox.md)中有关发布镜像和开发源码时依赖注册表固定版本的表述；该 Agent Note 仍负责沙箱行为、runner 选择和强制执行语义。
@@ -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/simplification/2026-07-20-remove-stdio-and-echo-agents.md
-2026-07-20-remove-stdio-and-echo-agents.md: 1c7ff4b5337341ea7678c1455dd7bbd3365df6ba
-2026-07-20-remove-stdio-and-echo-agents.zh.md: 67445d25f6a0534c92c50568da898a5bffc73a52
+2026-07-20-remove-stdio-and-echo-agents.md: 256e626f4ff41016d0227eef7cc3e4e51e15058b
+2026-07-20-remove-stdio-and-echo-agents.zh.md: bb7a2abd8be73ac3ea089121592b3f26162bf619
@@ -19,18 +19,18 @@ The stdio and Echo agents are removed without compatibility packages, modes, com
 The remaining application roles are explicit:

 - `@deepseek-ai/dsh-tui` owns terminal-interactive execution. It rejects non-TTY streams before Loader boot; `apps/cli/config/base.cordis.yml` plus the `tui.cordis.yml` overlay own the complete coding composition, with PTY plus terminal-snapshot coverage in `apps/cli/tests/`.
- [`@deepseek-ai/dsh-cli-demo`](../../../../packages/examples/cli-demo/README.md) owns non-interactive execution, including pipes. `examples/headless-agent` owns the real-model one-shot composition, replay snapshots, generic real-agent suites, and test-only keyless Loader fixtures.
+- [`dsh run`](../../../../apps/cli/README.md) owns non-interactive execution. Its `headless` profile is the product composition; `examples/headless-agent` owns replay snapshots, generic real-agent suites, and an unexported keyless Loader driver.
 - [`@deepseek-ai/dsh-acp-demo`](../../../../packages/examples/acp-demo/README.md) and `@deepseek-ai/dsh-jsonrpc` own their framed protocol integrations.

 The SDK project model and create/config workflows replace the `stdio` run-interface option with `tui`; generated TUI projects compose `@deepseek-ai/dsh-tui` and create or resume one exact session. Repository-facing demo documentation requires a DeepSeek API key and leads with the real Headless or TUI agents.

-Keyless validation is test-owned. The Headless Loader smoke uses a fixture adapter to exercise a real tool round trip, the CLI built-bin suite pins output, persistence, failure, and signal semantics, and package-specific Loader tests keep deterministic adapters beside their scenarios. None is exposed as a runnable mock agent.
+Keyless validation is test-owned. The Headless Loader smoke uses a fixture adapter to exercise a real tool round trip, the `dsh` built-bin suite pins the published one-shot entry and output, the product Headless snapshot pins persistence, and the Headless PTY shutdown e2e pins signal escalation. Package-specific Loader tests keep deterministic adapters beside their scenarios. None is exposed as a runnable mock agent.

 ## Verification

 TUI and Headless Loader coverage run the real app packages in source and built modes. PTY-driven subprocess coverage is reserved for the TUI lifecycle; other entry-point smokes use the one-shot pipe protocol. Headless proves its task/result and tool-call contracts. Generated graphs and repository searches reject stale package, command, leaf, SDK-interface, `createStdioChat`, and `StdioRuntime` references.

-The built `dsh` bin rejects a piped TUI launch before Loader boot and points at its one-shot `-p` mode; `apps/cli/tests/built-bin.e2e.ts` pins that path, while `cli-demo`'s built-bin suite runs text, JSON, and structurally parsed `stream-json` output under plain Node, persists fresh sessions, and rejects invalid arguments and missing config without contaminating stdout. Code Mode has programmatic TUI snapshots and an ACP overlay demo. Time-context integration uses the real Headless composition for two ordered turns, while its package tests own finer elapsed-time behavior.
+The built `dsh` bin rejects a piped TUI launch before Loader boot and points at `dsh run`; `apps/cli/tests/built-bin.e2e.ts` pins the product one-shot entry under plain Node, including output and invalid arguments. `examples/headless-agent/tests/headless.snapshot.ts` pins product persistence, while `apps/cli/tests/headless-shutdown.e2e.ts` owns bounded signal escalation. The headless example's test-only JSONL driver preserves assembled canonical-event snapshots without creating a second CLI contract. Code Mode has programmatic TUI snapshots and an ACP overlay demo. Time-context integration uses the explicit Headless test composition for two ordered turns, while its package tests own finer elapsed-time behavior.

 ## Alternatives considered

@@ -19,18 +19,18 @@ DeepSeek Harness 在 TUI 和 Headless coding agent 之外，还提供了两个
 保留的应用角色均有明确归属：

 - `@deepseek-ai/dsh-tui` 负责终端交互式执行。它会在 Loader 启动前拒绝非 TTY 流；`apps/cli/config/base.cordis.yml` 与 `tui.cordis.yml` overlay 拥有完整 coding 组装，PTY 与终端快照覆盖则位于 `apps/cli/tests/`。
- [`@deepseek-ai/dsh-cli-demo`](../../../../packages/examples/cli-demo/README.md) 负责非交互式执行，包括管道方式。`examples/headless-agent` 拥有真实模型的单次任务组装、回放快照、通用真实 agent 测试套件，以及仅供测试使用的无密钥 Loader fixture。
+- [`dsh run`](../../../../apps/cli/README.md) 负责非交互式执行。其 `headless` profile 是产品组装；`examples/headless-agent` 负责回放快照、通用真实 agent 测试套件和未导出的无密钥 Loader driver。
 - [`@deepseek-ai/dsh-acp-demo`](../../../../packages/examples/acp-demo/README.md) 和 `@deepseek-ai/dsh-jsonrpc` 负责各自的分帧协议集成。

 SDK 工程模型与 create/config 工作流将 `stdio` 运行接口选项替换为 `tui`；生成的 TUI 工程组合 `@deepseek-ai/dsh-tui`，并创建或恢复一个确切会话。仓库中的演示文档要求 DeepSeek API key，并优先引导到真实的 Headless 或 TUI agent。

-无密钥验证由测试负责。Headless Loader 冒烟测试使用 fixture 适配器验证真实工具往返；CLI built-bin 测试套件固定输出、持久化、失败和信号语义；各包专属的 Loader 测试则将确定性适配器放在对应场景旁。其中任何一项都不会作为可运行的 mock agent 对外暴露。
+无密钥验证由测试负责。Headless Loader 冒烟测试使用 fixture 适配器验证真实工具往返；`dsh` built-bin 测试套件固定已发布的一次性入口和输出；产品 Headless 快照固定持久化；Headless PTY 关闭 e2e 固定信号升级。各包专属的 Loader 测试则将确定性适配器放在对应场景旁。其中任何一项都不会作为可运行的 mock agent 对外暴露。

 ## 验证

 TUI 与 Headless 的 Loader 覆盖以源码和构建产物两种模式运行真实 app 包。由 PTY 驱动的子进程覆盖仅用于 TUI 生命周期；其他入口冒烟测试使用单次管道协议。Headless 验证任务/结果契约和工具调用契约。生成图谱与仓库搜索会拒绝陈旧的包、命令、叶节点、SDK 接口、`createStdioChat` 和 `StdioRuntime` 引用。

-构建后的 `dsh` 可执行文件会在 Loader 启动前拒绝通过管道启动 TUI，并指向其单次 `-p` 模式；`apps/cli/tests/built-bin.e2e.ts` 固定了该执行路径，而 `cli-demo` 的 built-bin 套件在普通 Node 下运行文本、JSON 和经过结构化解析的 `stream-json` 输出，持久化新建会话，并在不污染 stdout 的情况下拒绝无效参数和缺失配置。Code Mode 由程序化 TUI 快照与 ACP overlay demo 覆盖。时间上下文集成通过真实 Headless 组装执行两个有序轮次，而更细粒度的耗时行为由时间上下文的包级测试负责。
+构建后的 `dsh` 可执行文件会在 Loader 启动前拒绝通过管道启动 TUI，并指向 `dsh run`；`apps/cli/tests/built-bin.e2e.ts` 在普通 Node 下固定产品的一次性入口，包括输出和无效参数。`examples/headless-agent/tests/headless.snapshot.ts` 固定产品持久化，`apps/cli/tests/headless-shutdown.e2e.ts` 则负责有界信号升级。headless 示例仅供测试的 JSONL driver 保留组装后的规范事件快照，而不会创建第二套 CLI（命令行界面）契约。Code Mode 由程序化 TUI 快照与 ACP overlay demo 覆盖。时间上下文集成通过显式的 Headless 测试组装执行两个有序轮次，而更细粒度的耗时行为由时间上下文的包级测试负责。

 ## 曾考虑的替代方案

@@ -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/simplification/2026-08-04-remove-tui-package.md
-2026-08-04-remove-tui-package.md: 7f7a0dd86ddd36e940ed8b7d6154185d9740341c
-2026-08-04-remove-tui-package.zh.md: 36cb4b6a5e4eddd152eccee92c913bcca5b7fbae
+2026-08-04-remove-tui-package.md: 1057243c70f6f2775a5d0c5f5eddcb72cbad699e
+2026-08-04-remove-tui-package.zh.md: 0e03d6913aafaa3ce01c0f5732935d2c304c8e0e
@@ -16,7 +16,7 @@ The `packages/ui/tui` package is deleted without a compatibility package or alia

 The SDK run-interface union now contains only `acp` and `embed`. `create-sdk` defaults to ACP, generated templates contain no terminal startup, resume, session-environment, or model-argument branch, and the builtin `ask-user` feature is removed because neither remaining generated interface supplies a `UserInteractionProvider`. Host applications may still mount the provider-neutral `dsh-user-interaction`, `dsh-commands`, and presentation seams directly.

-This decision supersedes the reusable-package retention in [the explicit-config `dsh` entrypoint decision](2026-08-03-explicit-config-dsh-entrypoint.md) and the current applicability of the archived TUI implementation notes. Their historical records remain frozen, but they are not authority for the supported package or application inventory.
+This decision supersedes the reusable-package retention in [the explicit-config `dsh` entrypoint decision](../../archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.md) and the current applicability of the archived TUI implementation notes. Their historical records remain frozen, but they are not authority for the supported package or application inventory.

 This note consolidates the deleted package-only records that could not remain current after removal. The terminal UI had kept session identity visible during long conversations, removed duplicate model labels, attached elapsed timing and phase status to messages, showed workspace and branch context beside the prompt, and conservatively parsed complete XML wrappers for human-readable fallback output. Those choices improved one terminal frontend but do not justify retaining it without a deployment. A future XML fallback must still use a real parser rather than regular expressions.

@@ -16,7 +16,7 @@ Status: implemented

 SDK 的运行接口联合类型现在只包含 `acp` 与 `embed`。`create-sdk` 默认使用 ACP，生成的模板不再包含终端启动、恢复、会话环境或模型参数分支；内置的 `ask-user` 功能也被移除，因为剩余两个生成接口都不提供 `UserInteractionProvider`。宿主应用仍可直接挂载提供方无关的 `dsh-user-interaction`、`dsh-commands` 和呈现 seam。

-本决策取代[显式配置 `dsh` 入口决策](2026-08-03-explicit-config-dsh-entrypoint.md)中保留可复用包的决定，也使已归档 TUI 实现记录不再适用于当前状态。这些历史记录继续保持冻结，但不再作为受支持包或应用清单的依据。
+本决策取代[显式配置 `dsh` 入口决策](../../archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.md)中保留可复用包的决定，也使已归档 TUI 实现记录不再适用于当前状态。这些历史记录继续保持冻结，但不再作为受支持包或应用清单的依据。

 本记录汇总了删除后无法继续保持当前状态的仅限包记录。终端 UI 曾在长对话期间保持会话身份可见、移除重复模型标签、为消息附加耗时与阶段状态、在提示词旁显示 workspace 与分支上下文，并保守地解析完整 XML 包装层，以生成人类可读的回退输出。这些选择改善了一个终端前端，但没有部署时不足以证明应保留它。未来的 XML 回退仍必须使用真实解析器而非正则表达式。

@@ -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/simplification/2026-08-08-remove-cli-demo.md
+2026-08-08-remove-cli-demo.md: c1153f5e9fcc89585e926f8f088829c849d1f6c1
+2026-08-08-remove-cli-demo.zh.md: 1f9719b176c05009900a268a5bb2d2d7fcc79df3
@@ -0,0 +1,34 @@
+# Agent Note: Remove the separate CLI demo
+
+Status: implemented
+
+English | [中文](2026-08-08-remove-cli-demo.zh.md)
+
+## Problem
+
+After [`dsh run`](../feature/2026-08-08-dsh-run-headless-command.md) became the product one-shot command, `@deepseek-ai/dsh-cli-demo` remained a second application package for the same job. It carried another executable, argument grammar, app composition, cancellation lifecycle, text/JSON/stream-JSON output contract, built artifact, documentation surface, and test suite. The two front doors also assembled different trees, so a successful demo did not prove the shipped `headless` profile and users had to choose between overlapping commands.
+
+The replay suites still need canonical session events to pin assembled backend behavior. That testing need does not require a published command or compatibility contract.
+
+## Decision
+
+Delete `@deepseek-ai/dsh-cli-demo` completely: its package, bin, parser, app plugin, output formats, tests, workspace references, generated-catalog entries, and active documentation. No alias or compatibility package remains. The root `demo:headless` script is retained only as a direct alias of `dsh run`; the product command owns final-text stdout, the observation URL on stderr, persistence, exit status, and shutdown.
+
+`examples/headless-agent` becomes an explicit test composition. Its Loader configs mount `@deepseek-ai/dsh-agent-spine-demo`, one root agent, JSONL persistence, and checkpoint policy as separate rows instead of hiding them behind an app bundle. The support-tier `@deepseek-ai/dsh-loader-smoke` package owns the shared direct-agent turn helper; unexported example-local drivers select their Loader configuration and render canonical events as JSONL. They are launched only by tests, have no bin, and do not define a supported product output format.
+
+## Alternatives considered
+
+- **Keep `dsh-cli-demo` as an alias or wrapper around `dsh run`.** Rejected because a second bin and package would preserve two discoverable owners without adding capability.
+- **Move JSON and stream-JSON flags onto `dsh run`.** Rejected because no current product consumer requires them; adopting the old demo protocol would enlarge the canonical CLI contract solely to save test machinery.
+- **Delete the canonical-event snapshots with the package.** Rejected because they pin model-visible assembled behavior that final-text product acceptance cannot observe.
+- **Keep the app plugin but delete only its bin.** Rejected because the hidden composition would still duplicate the explicit headless profile and conceal which services the test leaf mounts.
+
+## Consequences
+
+This is intentionally breaking. `dsh-cli-demo`, its `--output-format` choices, and imports from `@deepseek-ai/dsh-cli-demo/src/cli.ts` no longer resolve. There is no public event-stream replacement in this change; callers use `dsh run` for one-shot execution and must choose an existing protocol surface when they need structured automation.
+
+The repository retains backend replay coverage through test-only infrastructure, while product smoke and built-bin acceptance exercise `dsh run`. A separate one-shot package may return only if it owns a genuinely independent, versioned protocol that cannot belong to the product launcher; a second spelling or output shim is not enough.
+
+## Verification
+
+Focused Loader smokes cover the explicit composition in source and plain-Node built modes, snapshot tests diff its canonical JSONL and persisted logs, product acceptance covers `dsh run`, and documentation plus generated graph/catalog gates reject live references to the removed package. The frozen Agent Note archive remains historical evidence and is not rewritten.
@@ -0,0 +1,34 @@
+# Agent Note: 移除独立的 CLI demo
+
+Status: implemented
+
+[English](2026-08-08-remove-cli-demo.md) | 中文
+
+## 问题
+
+在 [`dsh run`](../feature/2026-08-08-dsh-run-headless-command.md) 成为产品的一次性命令后，`@deepseek-ai/dsh-cli-demo` 仍是承担同一工作的第二个应用包。它另行拥有一套可执行文件、参数语法、应用组装、取消生命周期、文本／JSON／stream-JSON 输出契约、构建产物、配套文档和测试套件。两个入口组装的树也不相同，因此 demo 成功不能证明已交付的 `headless` profile 可用，用户还必须在功能重叠的命令之间作出选择。
+
+回放套件仍需要规范会话事件来固定组装后的后端行为。这一测试需求不需要已发布命令或兼容性契约。
+
+## 决策
+
+彻底删除 `@deepseek-ai/dsh-cli-demo`：包括它的包、bin、解析器、应用插件、输出格式、测试、workspace 引用、生成目录条目和现行文档。不保留别名或兼容包。根目录的 `demo:headless` 脚本仅作为 `dsh run` 的直接别名保留；stdout 上的最终文本、stderr 上的观察 URL、持久化、退出状态和关闭行为均由产品命令负责。
+
+`examples/headless-agent` 成为显式测试组装。其 Loader 配置把 `@deepseek-ai/dsh-agent-spine-demo`、一个根 agent（智能体）、JSONL 持久化和检查点策略挂载为独立配置行，不再将其隐藏在应用组合包之后。支持层的 `@deepseek-ai/dsh-loader-smoke` 包负责共享的直接 agent 轮次 helper；未导出的示例本地 driver 选择各自的 Loader 配置，并将规范事件渲染为 JSONL。这些 driver 只由测试启动，不提供 bin，也不定义受支持的产品输出格式。
+
+## 考虑过的替代方案
+
+- **保留 `dsh-cli-demo` 作为 `dsh run` 的别名或包装层。** 不予采纳：第二个 bin 和包会让同一功能继续存在两个可发现的归属方，却没有增加任何能力。
+- **把 JSON 和 stream-JSON 标志移到 `dsh run`。** 不予采纳：当前没有产品消费方需要这些标志；沿用旧 demo 协议，只会为了保留测试机制而扩大规范 CLI（命令行界面）契约。
+- **随包一并删除规范事件快照。** 不予采纳：这些快照固定了模型可见的组装行为，而只检查最终文本的产品验收无法观察这些行为。
+- **保留应用插件，只删除它的 bin。** 不予采纳：隐藏的组装仍会重复显式的 headless profile，并掩盖测试叶节点挂载了哪些服务。
+
+## 后果
+
+这是有意为之的破坏性变更。`dsh-cli-demo`、它的 `--output-format` 选项以及对 `@deepseek-ai/dsh-cli-demo/src/cli.ts` 的导入都不再可解析。本变更不提供公开的事件流替代接口；调用方使用 `dsh run` 执行一次性任务，需要结构化自动化时则必须选择现有的协议接口。
+
+仓库通过仅供测试的基础设施保留后端回放覆盖，产品冒烟测试和 built-bin 验收则运行 `dsh run`。只有当独立的一次性包负责一套真正独立、带版本且不能归产品启动器所有的协议时，它才可以重新引入；第二种命令写法或输出 shim 并不足以构成理由。
+
+## 验证
+
+聚焦的 Loader 冒烟测试在源码模式和由普通 Node 启动的构建模式下覆盖显式组装，快照测试对比其规范 JSONL 和持久化日志，产品验收覆盖 `dsh run`，文档检查及生成图谱／目录门禁则拒绝对已移除包的活跃引用。冻结的 Agent Note 归档保留为历史证据，不会被重写。
@@ -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/testing/2026-06-19-acp-snapshot-tests.md
-2026-06-19-acp-snapshot-tests.md: c7b95bd68027705b99d850d596405e56eea0dfca
-2026-06-19-acp-snapshot-tests.zh.md: 43d43262684920cae5feedb5f2eb109db00f9f8c
+2026-06-19-acp-snapshot-tests.md: c6e81dc4a51083ed37ad6f837fe7dbb08c212e23
+2026-06-19-acp-snapshot-tests.zh.md: 5a579c3373442dc4cfc7d661ea2f2f398b804dc7
@@ -24,7 +24,7 @@ Every committed session-format fixture uses the canonical packed physical layout

 ### Replay derives the model script from the log

-`llm-replay` short-circuits the provider-agnostic `llm/stream` waterfall. `deriveReplayScript()` groups recorded chunks by `(turn, step)` and serves one group per model call. The loop makes one stream call per step, so the grouping is exact and includes error finish chunks without special handling.
+`llm-replay` short-circuits the provider-agnostic `llm/stream` waterfall. `deriveReplayScript()` splits recorded `assistant/chunk` events at terminal `finish` chunks and uses `(turn, step)` changes to reject an unterminated prior call. A `compact/summary` with `llmStreamCall: true` contributes one call at its durable log position: replay reconstructs canonical block boundaries from `rawOutput`, retains recorded usage when present, and supplies a terminal `stop`. The marker distinguishes that local call from template or remote summaries whose retained `rawOutput` did not consume this context's adapter.

 ### The in-memory replay entry honors the full LLM contract

@@ -36,7 +36,7 @@ Every committed session-format fixture uses the canonical packed physical layout
 | { kind: 'hang' }
 ```

-Logs derive chunk entries. Pre-stream throws and hangs have no reconstructable chunk representation, so those scenarios provide `replay.override.json`. A throw entry may include prefix chunks for mid-stream failure. Explicit overrides avoid inferring adapter behavior from lossy turn-end reasons.
+Logs derive chunk entries from finished assistant streams and explicitly marked compaction calls. Pre-stream throws, hangs, and external summarizer calls have no reconstructable local chunk representation, so those scenarios provide `replay.override.json`. A throw entry may include prefix chunks for mid-stream failure. Explicit overrides avoid inferring adapter behavior from lossy turn-end reasons or provider output alone.

 ### Positional replay, one in-flight stream

@@ -74,12 +74,13 @@ Tool determinism comes from a generated cwd, scrubbed environment, fresh non-log
 ## Alternatives considered

 - **A hand-authored `llm.json` of model chunks** — the earlier draft; reusing the real session log makes the fixture a genuine product of the system rather than a hand-built mock, and doubles it as a behavioral expected output.
+- **A compulsory replay override for every compaction summary** — rejected: the durable summary event already fixes a successful local call's position, complete output, and optional usage. An explicit local-call marker preserves that single-source fixture without inventing a call for template or remote summarizers.
 - **A byte-level HTTP-record library (Polly/nock/MSW)** — rejected: adapter-specific, awkward with streaming SSE, and lower-level than the thing under test.
 - **Synthesizing throw/cancel entries from `turn/end {kind:'error'|'aborted'}`** — rejected: it couples `llm-replay` to loop-internal turn-closing semantics, and the `turn/end` reason is lossy (it cannot distinguish a thrown 401 from a finish-error); the explicit `replay.override.json` sidecar is the cleaner seam.
 - **Copying both request-header sidecars beside every class pin** — rejected: prompt and tool-schema composition vary independently, so a change to one shared component would churn byte-identical files across unrelated class pins. Explicit per-component sources retain one structural pin per class without duplicating content.

 ## Consequences

-The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here until it can move to a transport-neutral headless suite without losing coverage.
+The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition, including an assembled context-overflow recovery whose marked compaction summary supplies the auxiliary call. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here until it can move to a transport-neutral headless suite without losing coverage.

 This Agent Note relates to but does not supersede the [proposed determinism Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md): that proposal's "universal replay fixture" re-derives session *message history* after every test (an internal-consistency invariant), whereas these snapshots pin assembled behavior plus the external automation output. They are complementary until the backend corpus moves off ACP.
@@ -24,7 +24,7 @@ Status: implemented

 ### 回放从日志推导模型脚本

-`llm-replay` 短路了提供方无关的 `llm/stream` waterfall（瀑布式事件）。`deriveReplayScript()` 按 `(turn, step)` 对已录制的分片分组，每次模型调用服务一组。agent loop（智能体循环）每个步骤发起一次流调用，因此分组精确对应，错误结束分片也无需特殊处理。
+`llm-replay` 短路了提供方无关的 `llm/stream` waterfall（瀑布式事件）。`deriveReplayScript()` 在终止的 `finish` 分片处切分已记录的 `assistant/chunk` 事件，并用 `(turn, step)` 变化拒绝前一条未终止的调用。携带 `llmStreamCall: true` 的 `compact/summary` 会在其持久日志位置贡献一次调用：回放根据 `rawOutput` 重建规范块边界，保留已记录的 usage（如有），并提供终止的 `stop`。该标记将这次本地调用与模板摘要或远程摘要区分开；后两者即使保留了 `rawOutput`，也未使用此上下文的适配器。

 ### 内存中的回放条目遵守完整的 LLM 契约

@@ -36,7 +36,7 @@ Status: implemented
 | { kind: 'hang' }
 ```

-日志推导出分片条目。流开始前的抛出和挂起没有可重建的分片表示，因此这些场景提供 `replay.override.json`。throw 条目可以包含前缀分片以模拟流中途失败。显式覆盖避免了从有损的轮次结束原因推断适配器行为。
+日志从已结束的 assistant 流和显式标记的压缩（compaction）调用推导分片条目。流开始前的抛出、挂起和外部摘要器调用没有可重建的本地分片表示，因此这些场景提供 `replay.override.json`。throw 条目可以包含前缀分片以模拟流中途失败。显式覆盖避免了从有损的轮次结束原因或单独的提供方输出推断适配器行为。

 ### 位置式回放，单个在途流

@@ -74,12 +74,13 @@ Status: implemented
 ## 曾考虑的替代方案

 - **手工编写包含模型分片的 `llm.json`**——早期草案；复用真实会话日志，使 fixture 成为系统的真实产物而非手工构建的 mock，并让它同时充当行为预期输出。
+- **为每个压缩摘要强制提供回放 override**——否决：持久摘要事件已经固定成功本地调用的位置、完整输出与可选 usage。显式的本地调用标记保留了这份单一来源 fixture，而不会为模板摘要器或远程摘要器凭空构造调用。
 - **字节级 HTTP 录制库（Polly/nock/MSW）**：否决。与适配器耦合，处理流式 SSE（Server-Sent Events）时笨拙，且层级低于被测对象。
 - **从 `turn/end {kind:'error'|'aborted'}` 合成抛错/取消条目**：否决。这会将 `llm-replay` 耦合到 loop 内部的轮次关闭语义，且 `turn/end` 原因是有损的（无法区分抛出的 401 与 finish-error）；显式的 `replay.override.json` 伴随文件是更清晰的 seam。
 - **在每个类别 pin 旁复制两个请求头伴随文件**：否决。提示词与工具 schema 的组合各自独立变化，因此一个共享组件发生变更，就会使不相关类别 pin 中字节完全相同的文件产生无意义改动。显式的分组件来源可在不重复内容的情况下，为每个类别保留一个结构性 pin。

 ## 后果

-该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与回放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，直至它能够在不损失覆盖的情况下迁移到传输无关的 headless 套件。
+该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与回放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖，其中包括一个组装后的上下文溢出恢复场景，其带标记的压缩摘要提供辅助调用。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，直至它能够在不损失覆盖的情况下迁移到传输无关的 headless 套件。

 本 Agent Note 与[拟议的确定性 Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md)相关，但不取代它：该提案的“通用回放 fixture”在每次测试后重新派生会话*消息历史*（内部一致性不变量），而这些快照固定组装后的行为与外部自动化输出。在后端语料迁出 ACP 之前，两者相互补充。
@@ -6,20 +6,6 @@ updates:
    exclude-paths:
      # Vendored Cordis sources follow vendor/README.md instead of registry updates.
      - "vendor/**"
-      # This independently locked pnpm workspace has its own update entry below.
-      - "native/landlock-run/**"
-    schedule:
-      interval: "cron"
-      cronjob: "0 4 * * *"
-      timezone: "Asia/Shanghai"
-    cooldown:
-      default-days: 30
-    labels:
-      - "cleanup"
-      - "area/infra"
-
-  - package-ecosystem: "npm"
-    directory: "/native/landlock-run"
    schedule:
      interval: "cron"
      cronjob: "0 4 * * *"
@@ -0,0 +1,176 @@
+# Build and publish the @deepseek-ai/node-addon-landlock-run package family from the
+# harness source of record. Rehearsal and publication consume the same packed
+# tarballs; each native binary is built on its matching architecture.
+name: Landlock Run Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      publish:
+        description: Publish packed tarballs to npm. Must run from a landlock-run-v* tag.
+        required: true
+        type: boolean
+        default: false
+
+permissions:
+  contents: read
+
+concurrency:
+  # Stable/prerelease dist-tags are shared registry state; serialize release
+  # runs so two versions cannot race the final tag assignment.
+  group: ${{ github.workflow }}
+  cancel-in-progress: false
+
+defaults:
+  run:
+    working-directory: native/landlock-run
+
+jobs:
+  matrix:
+    name: Matrix
+    runs-on: ubuntu-24.04
+    outputs:
+      prebuilds: ${{ steps.matrix.outputs.prebuilds }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - id: matrix
+        run: echo "prebuilds=$(node ./scripts/github-matrix.mjs release-prebuild)" >> "$GITHUB_OUTPUT"
+
+  build-prebuilds:
+    name: ${{ matrix.package }}
+    needs: matrix
+    runs-on: ${{ matrix.runner }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.matrix.outputs.prebuilds) }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          package_json_file: package.json
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 24
+          cache: pnpm
+          cache-dependency-path: pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: pnpm install --filter @deepseek-ai/node-addon-landlock-run-workspace... --frozen-lockfile
+
+      - name: Install musl toolchain
+        run: |
+          sudo apt-get update -q
+          sudo apt-get install -yq musl-tools
+
+      - name: Build native binaries
+        run: pnpm build:native
+
+      - name: Verify binary metadata
+        run: node ./scripts/verify-launcher-binary.mjs ${{ matrix.dir }}
+
+      - name: Upload prebuild artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.artifact }}
+          path: native/landlock-run/${{ matrix.dir }}/bin/*
+          if-no-files-found: error
+          retention-days: 7
+
+  pack:
+    name: Pack npm tarballs
+    needs: build-prebuilds
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          package_json_file: package.json
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 24
+          cache: pnpm
+          cache-dependency-path: pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: pnpm install --filter @deepseek-ai/node-addon-landlock-run-workspace... --frozen-lockfile
+
+      - name: Build TypeScript
+        run: pnpm build:ts
+
+      - name: Verify release version
+        run: node ./scripts/verify-release.mjs
+        env:
+          RELEASE_PUBLISH: ${{ inputs.publish }}
+
+      - name: Download prebuild artifacts
+        uses: actions/download-artifact@v4
+        with:
+          pattern: prebuild-*
+          path: native/landlock-run/.release/prebuild-artifacts
+
+      - name: Assemble and verify prebuilds
+        run: node ./scripts/assemble-prebuilds.mjs .release/prebuild-artifacts
+
+      - name: Verify release payload
+        run: node ./scripts/verify-release.mjs --prebuilds
+        env:
+          RELEASE_PUBLISH: ${{ inputs.publish }}
+
+      - name: Pack release tarballs
+        run: node ./scripts/pack-release.mjs dist/npm
+
+      - name: Verify packed install
+        run: node ./scripts/verify-packed-install.mjs dist/npm
+        env:
+          NALR_REQUIRE_LANDLOCK: 1
+
+      - name: Upload npm tarballs
+        uses: actions/upload-artifact@v4
+        with:
+          name: npm-tarballs
+          path: native/landlock-run/dist/npm/*
+          if-no-files-found: error
+          retention-days: 7
+
+  publish:
+    name: Publish to npm
+    if: inputs.publish
+    needs: pack
+    runs-on: ubuntu-24.04
+    environment: npm-publish
+    permissions:
+      contents: read
+      id-token: write
+    steps:
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 24
+          registry-url: https://registry.npmjs.org
+
+      - name: Download npm tarballs
+        uses: actions/download-artifact@v4
+        with:
+          name: npm-tarballs
+          path: native/landlock-run/dist/npm
+
+      - name: Configure npm token fallback
+        env:
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: |
+          if [[ -n "$NPM_TOKEN" ]]; then
+            echo "NODE_AUTH_TOKEN=$NPM_TOKEN" >> "$GITHUB_ENV"
+          fi
+
+      - name: Publish tarballs
+        run: |
+          version="${GITHUB_REF#refs/tags/landlock-run-v}"
+          tag_args=()
+          case "$version" in *-*) tag_args=(--tag next);; esac
+          while IFS= read -r tarball; do
+            npm publish "dist/npm/${tarball}" --access public "${tag_args[@]}"
+          done < dist/npm/publish-order.txt
@@ -1,15 +1,27 @@
-# Manually-dispatched CI for the landlock-run source of record
-# (native/landlock-run). A separate workflow from ci.yml on purpose: the
-# subtree is a self-contained pnpm workspace with its own gates, exercised on
-# demand — per-architecture native legs (build + behavioral tests + pack
-# rehearsal on real kernels) plus one darwin leg proving the documented
-# degradation on hosts without a platform package. Legs derive from the
-# subtree's checked-in package matrix (scripts/github-matrix.mjs). Packing
-# for npm happens in the release mirror (node-addon-landlock-run) after an
-# export — see native/README.md; this workflow never packs for release.
+# CI for the landlock-run packages under native/landlock-run. A separate
+# workflow from ci.yml keeps the native OS/architecture matrix independent of
+# the harness Node matrix. Release assembly and publication use the companion
+# Landlock Run Release workflow.
 name: Landlock Run

 on:
+  pull_request:
+    paths:
+      - '.github/workflows/landlock-run.yml'
+      - '.github/workflows/landlock-run-release.yml'
+      - 'native/landlock-run/**'
+      - 'package.json'
+      - 'pnpm-lock.yaml'
+      - 'pnpm-workspace.yaml'
+  push:
+    branches: [master]
+    paths:
+      - '.github/workflows/landlock-run.yml'
+      - '.github/workflows/landlock-run-release.yml'
+      - 'native/landlock-run/**'
+      - 'package.json'
+      - 'pnpm-lock.yaml'
+      - 'pnpm-workspace.yaml'
  workflow_dispatch:

 concurrency:
@@ -52,16 +64,16 @@ jobs:

      - uses: pnpm/action-setup@v4
        with:
-          package_json_file: native/landlock-run/package.json
+          package_json_file: package.json

      - uses: actions/setup-node@v4
        with:
          node-version: 24
          cache: pnpm
-          cache-dependency-path: native/landlock-run/pnpm-lock.yaml
+          cache-dependency-path: pnpm-lock.yaml

      - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+        run: pnpm install --filter @deepseek-ai/node-addon-landlock-run-workspace... --frozen-lockfile

      - name: Install musl toolchain
        run: |
@@ -103,16 +115,16 @@ jobs:

      - uses: pnpm/action-setup@v4
        with:
-          package_json_file: native/landlock-run/package.json
+          package_json_file: package.json

      - uses: actions/setup-node@v4
        with:
          node-version: 24
          cache: pnpm
-          cache-dependency-path: native/landlock-run/pnpm-lock.yaml
+          cache-dependency-path: pnpm-lock.yaml

      - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+        run: pnpm install --filter @deepseek-ai/node-addon-landlock-run-workspace... --frozen-lockfile

      - name: Build TypeScript
        run: pnpm build:ts
@@ -3,9 +3,8 @@
 # .agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.md.
 # A separate workflow from ci.yml because the axis is different — these jobs
 # fan out over OS×runner (kernel capabilities), not node versions. The Landlock
-# launcher arrives from the registry with `pnpm install` (the npm package family
-# `node-addon-landlock-run`, built and released from its own repository), so
-# these legs exercise the true consumer path — nothing is compiled here.
+# launcher is built from native/landlock-run on each Landlock leg and installed
+# from the same tarballs the main-repository release workflow publishes.
 name: Sandbox

 on:
@@ -30,7 +29,7 @@ jobs:
  # an OS×runner matrix — bwrap and Landlock on Linux (separate legs: the
  # Landlock files force the bwrap rung off, so each leg proves exactly one
  # rung; Landlock twice, once per architecture, each confining through the
-  # registry-installed launcher), Seatbelt on macOS (sandbox-exec ships with
+  # locally built launcher), Seatbelt on macOS (sandbox-exec ships with
  # the OS). One node
  # version only: kernel confinement does not vary by node, and ci.yml's
  # node matrix already covers the node axis.
@@ -80,6 +79,14 @@ jobs:
          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
            || echo "apparmor userns knob absent — the functional probe decides"

+      - name: Build Landlock launcher for this architecture
+        if: matrix.runner == 'landlock'
+        run: |
+          sudo apt-get update -q
+          sudo apt-get install -yq musl-tools
+          pnpm --dir native/landlock-run run build:ts
+          pnpm --dir native/landlock-run run build:native
+
      # The unit suite runs on ubuntu in `checks`; this is the one darwin leg
      # in the workflow, so run it here too — the platform-dependent unit
      # expectations (Seatbelt path canonicalization: /tmp IS /private/tmp)
@@ -105,14 +112,10 @@ jobs:
          # the very platform that exists to prove it) is a failure, not a pass.
          echo "$out" | grep -qE 'Test Files[[:space:]]+2 passed \(2\)'

-      # Publish-path rehearsal, Landlock legs only (the pack gates need built
-      # lib/). The e2e packs the workspace closure, installs the tarballs
-      # into a throwaway consumer — npm pulling `node-addon-landlock-run`
-      # and its platform package from the registry, the true consumer path —
-      # and confines through the INSTALLED launcher, asserting it executable
-      # apart (a mode-stripped binary must not masquerade as a non-enforcing
-      # kernel). Same no-silent-skip guard as above.
-      - name: Build packages (lib/ for the pack rehearsal)
+      # Publish-path rehearsal, Landlock legs only. Build the launcher on its
+      # native architecture, then install the local native and harness tarballs
+      # together so registry state cannot mask source/package drift.
+      - name: Build packages for the pack rehearsal
        if: matrix.runner == 'landlock'
        run: pnpm run build

@@ -0,0 +1,7 @@
+{
+  "$schema": "./node_modules/oxlint/configuration_schema.json",
+  "extends": ["./.oxlintrc.json"],
+  "options": {
+    "typeAware": false
+  }
+}
@@ -41,7 +41,7 @@ packages/    @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/
  support/     dev/test infrastructure
  util/        zero-dependency utilities
 python/      Python SDK and bundled runtime (see python/README.md)
-native/      node-addon-landlock-run source of record (see native/README.md)
+native/      @deepseek-ai/node-addon-landlock-run source of record (see native/README.md)
 examples/    Runnable cordis.yml leaves over packages/examples bundles (see examples/AGENTS.md)
 .agents/     Agent workflows and Agent Notes (`notes/`)
 docs/        architecture, generated catalogs, postmortems, cookbook (see docs/AGENTS.md)
@@ -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 README.md
-README.md: d8d3e767d5a9805f34f4df57a5b1f8ff7fdaa955
-README.zh.md: 89abf8d817deeed2bf4416035790c8696c8c8e33
+README.md: 64f06c0aec0905fa7deabbec0deea61e1c7a40d4
+README.zh.md: fee03118926028833c828809764ebb5f6375259e
@@ -56,7 +56,7 @@ The [CLI contract](apps/cli/README.md#profiles) describes profile layout, layer
 Run one task, print the final answer, and exit:

 ```sh
-dsh --profile headless "summarize this workspace"
+dsh run "summarize this workspace"
 ```

 ### Automation and SDKs
@@ -56,7 +56,7 @@ profile 布局、层语义与配置输出命令详见 [CLI（命令行界面）
 运行一项任务，打印最终答案后退出：

 ```sh
-dsh --profile headless "summarize this workspace"
+dsh run "summarize this workspace"
 ```

 ### 自动化与 SDK
@@ -7,7 +7,7 @@ DeepSeek Harness is licensed under [BSD 3-Clause](LICENSE). It depends on the th

 This file lists **direct** dependencies declared by the workspace and the explicitly disclosed official Claude platform payload closure. It is generated from the workspace manifests by `scripts/gen-third-party-notices.ts`: a pre-commit hook regenerates it whenever a staged file changes one of its inputs, and `scripts/gen-third-party-notices.spec.ts` asserts in the test lane that the committed bytes match. Deleting a manifest runs no hook, so that case is caught by the assertion instead. Run `pnpm run verify-third-party-notices` for the standalone check.

-The complete npm transitive closure, with exact pinned versions, is recorded in [`pnpm-lock.yaml`](pnpm-lock.yaml) — inspect it with `pnpm licenses list`. The Python closure is recorded in [`python/sdk/uv.lock`](python/sdk/uv.lock), and the Landlock launcher workspace keeps its own in [`native/landlock-run/pnpm-lock.yaml`](native/landlock-run/pnpm-lock.yaml).
+The complete npm transitive closure, including the Landlock launcher workspace, is recorded with exact pinned versions in [`pnpm-lock.yaml`](pnpm-lock.yaml) — inspect it with `pnpm licenses list`. The Python closure is recorded separately in [`python/sdk/uv.lock`](python/sdk/uv.lock).

 ## Vendored source (`vendor/`)

@@ -191,6 +191,6 @@ Direct dependencies of the `pyproject.toml` manifests, plus `uv` as the developm
 | --- | --- | --- |
 | [`@yao-pkg/pkg`](https://github.com/yao-pkg/pkg) | MIT | invoked by `scripts/build-exe-for-python-sdk.ts` to assemble the single-file SDK runtime executable |

-## First-party sibling releases
+## First-party native packages

-`node-addon-landlock-run` (and its platform packages) is released from a DeepSeek Harness sibling repository under BSD 3-Clause. It is listed here for completeness; it is first-party, not third-party.
+`@deepseek-ai/node-addon-landlock-run` (and its platform packages) is built and released from this repository under BSD 3-Clause. It is listed here for completeness; it is first-party, not third-party.
@@ -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 apps/cli/README.md
-README.md: f50f26ec5de54e094e17221f7cd355483483754e
-README.zh.md: 242e64a0c42064b9f0b7621e665e85fe44523fe5
+README.md: 12108fcbff4e649d0bcb3e01e688fa334ab91b14
+README.zh.md: 9518feed1d5d40c3e5ec2d346b929118ccc08810
@@ -9,11 +9,11 @@ The `dsh` command is the product launcher for profiles: ordered stacks of plugin
 | Command | Purpose |
 |---|---|
 | `dsh --profile <name>` | Boot the named profile under `$DSH_HOME/profiles/<name>`. |
-| `dsh --profile headless "task"` | Run one fresh persisted session, print the final answer, and exit. |
+| `dsh run [--profile <name>] [--patch <path>...] "task"` | Run one fresh persisted session, print the final answer, and exit; the profile defaults to `headless`. |
 | `dsh web` | Alias of `--profile web` with the Web flag family (`--host`, `--port`, `--dev`, ...). |
 | `dsh plugin --profile <name> <pnpm args>` | Manage a profile's plugins by forwarding to pnpm in the profile directory. |

-The invoking directory is the default workspace root. The `web` and `headless` profiles auto-initialize on first use from shipped templates; any other profile must be created through `dsh plugin`.
+The invoking directory is the default workspace root. `dsh run` requires non-blank task text and the selected profile must mount the `headless-runner` row; `--profile` preserves custom one-shot profiles. The `web` and `headless` profiles auto-initialize on first use from shipped templates; any other profile must be created through `dsh plugin`.

 ## Profiles

@@ -9,11 +9,11 @@
 | 命令 | 用途 |
 |---|---|
 | `dsh --profile <name>` | 启动位于 `$DSH_HOME/profiles/<name>` 的指定 profile。 |
-| `dsh --profile headless "task"` | 运行一个新的持久化会话，打印最终答案并退出。 |
+| `dsh run [--profile <name>] [--patch <path>...] "task"` | 运行一个新的持久化会话，打印最终答案并退出；profile 默认为 `headless`。 |
 | `dsh web` | `--profile web` 的别名，附带 Web flag 系列（`--host`、`--port`、`--dev` 等）。 |
 | `dsh plugin --profile <name> <pnpm args>` | 通过在 profile 目录中转发给 pnpm 来管理该 profile 的插件。 |

-调用目录是默认 workspace 根目录。`web` 和 `headless` profile 在首次使用时会从随附模板自动初始化；其他任何 profile 都必须通过 `dsh plugin` 创建。
+调用目录是默认 workspace 根目录。`dsh run` 要求任务文本非空白，且所选 profile 必须挂载 `headless-runner` 行；`--profile` 保留对自定义一次性 profile 的支持。`web` 和 `headless` profile 在首次使用时会从随附模板自动初始化；其他任何 profile 都必须通过 `dsh plugin` 创建。

 ## Profile

@@ -80,6 +80,8 @@ flowchart LR
  cfg --> plugin_dsh_base_skill
  plugin_dsh_base_skill_local["skill-local<br/>@deepseek-ai/dsh-skill-local"]
  cfg --> plugin_dsh_base_skill_local
+  plugin_dsh_base_skill_badge["skill-badge<br/>@deepseek-ai/dsh-skill-badge"]
+  cfg --> plugin_dsh_base_skill_badge
  plugin_dsh_base_tool_skill["tool-skill<br/>@deepseek-ai/dsh-tool-skill"]
  cfg --> plugin_dsh_base_tool_skill
  plugin_dsh_base_commands["commands<br/>@deepseek-ai/dsh-commands"]
@@ -196,6 +198,7 @@ flowchart LR
 | `workspace-context` | `@deepseek-ai/dsh-workspace-context` |
 | `skill` | `@deepseek-ai/dsh-skill` |
 | `skill-local` | `@deepseek-ai/dsh-skill-local` |
+| `skill-badge` | `@deepseek-ai/dsh-skill-badge` |
 | `tool-skill` | `@deepseek-ai/dsh-tool-skill` |
 | `commands` | `@deepseek-ai/dsh-commands` |
 | `command-feedback` | `@deepseek-ai/dsh-command-feedback` |
@@ -36,11 +36,14 @@
    "node-addon-require-builtin": "^0.1.4"
  },
  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
    "@deepseek-ai/dsh-frontend-static": "workspace:^",
    "@deepseek-ai/dsh-host-apiproxy": "workspace:^",
    "@deepseek-ai/dsh-host-webserver": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
    "@deepseek-ai/dsh-llm-mock-server": "workspace:^",
    "@deepseek-ai/dsh-loader-smoke": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
    "@deepseek-ai/dsh-system-prompt": "workspace:^",
    "@deepseek-ai/dsh-tools": "workspace:^",
    "@types/js-yaml": "^4.0.9",
@@ -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 apps/cli/reference/README.md
-README.md: c7c7b2aa231d4c9f4b3fbf31663237c8457eb051
-README.zh.md: 5439aa78b74415c8e6264d21f5c52e5cee5b38ee
+README.md: 496cecdb64e3254a2a77690f55f760b4cd90b521
+README.zh.md: 4673bf764347307a9b91e2a5474a8439cf67b481
@@ -2,7 +2,7 @@

 English | [中文](README.zh.md)

-This reference defines the profile, web-alias, plugin-management, and config-dump command modes. Argv is parsed once through [`src/args.ts`](../src/args.ts), and [`src/bin.ts`](../src/bin.ts) dynamically imports only the selected runner.
+This reference defines the profile, one-shot run, web-alias, plugin-management, and config-dump command modes. Argv is parsed once through [`src/args.ts`](../src/args.ts), and [`src/bin.ts`](../src/bin.ts) dynamically imports only the selected runner.

 ## Profile boot

@@ -12,7 +12,7 @@ Bundle names resolve from the dsh installation first, then from the profile dire

 The `web` and `headless` profiles auto-initialize from shipped templates on first use (`web`: base + web-app; `headless`: base + web-app + headless). Any other missing profile fails loud with a hint to run `dsh plugin --profile <name> add <package>`.

-A positional task (`dsh --profile headless "run the tests"`) requires the composition to mount the one-shot runner row (`headless-runner`); the launcher patches the task text into that row, the runner drives one fresh persisted session through the in-process API carrier, prints the final assistant text on stdout, and exits 0 on a completed turn, else 1. The session's Web host runs on an OS-assigned port and is announced on stderr, so the run is observable in a browser.
+Profile boot accepts no positional task. A profile that mounts the one-shot runner row (`headless-runner`) therefore fails loud with the canonical `dsh run --profile <name> "<task>"` command instead of reaching the row's raw required-field error.

 Inspect the composed tree without booting it:

@@ -23,6 +23,12 @@ dsh --profile web --patch ./extra.yml --dump-config

 `--dump-default-config` prints only the bundle layers; `--dump-config` adds the profile's `cordis.patch.yml`, the home-level `$DSH_HOME/cordis.patch.yml`, and `--patch` overlays. Both print provenance comments per layer; `!!js` expressions remain unevaluated, and unmatched patch targets are reported on stderr.

+## One-shot run
+
+`dsh run [--profile <name>] [--patch <path>...] <task...>` joins the task arguments with spaces, rejects a missing or blank task, and defaults `--profile` to `headless`. Repeatable `--patch` overlays occupy the same layer position as profile-boot overlays. A custom selected profile must mount `headless-runner`; otherwise launch fails before boot with a diagnostic naming that missing row.
+
+The launcher patches the task text into the runner row, which drives one fresh persisted session through the in-process API carrier, prints the final assistant text on stdout, and exits 0 on a completed turn, else 1. At the idle boundary, the runner waits until its mux consumer has observed the session's final event sequence before deriving that output and exit reason. The session's Web host runs on an OS-assigned port and is announced on stderr, so the run is observable in a browser.
+
 ## Plugin management

 `dsh plugin --profile <name> <args...>` initializes the profile when missing (shipped template, or `@deepseek-ai/dsh-base` alone for other names), then forwards `<args...>` to `pnpm` with the profile directory as working directory — `add`, `remove`, `why`, `update`, and every other pnpm verb work unchanged; pnpm must be on PATH. Relative path specs (`.`, `../plugin`, and their `file:`/`link:` forms) are anchored to the invoking directory first, so `add .` from a plugin checkout installs that checkout, not the profile. After every successful run, `dsh.profile.bundles` is reconciled against the installed state: each dependency resolving to a package whose manifest declares `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }` joins the layer stack (so an `update` that gains the declaration activates it), a bundle-less dependency stays plain with a one-time warning, and a removed dependency leaves the stack.
@@ -2,7 +2,7 @@

 [English](README.md) | 中文

-本参考定义 profile、web 别名、插件管理和配置 dump 命令模式。参数由 [`src/args.ts`](../src/args.ts) 统一解析，[`src/bin.ts`](../src/bin.ts) 只动态导入选中的运行器。
+本参考定义 profile、一次性运行、web 别名、插件管理和配置 dump 命令模式。参数由 [`src/args.ts`](../src/args.ts) 统一解析，[`src/bin.ts`](../src/bin.ts) 只动态导入选中的运行器。

 ## Profile 启动

@@ -12,7 +12,7 @@

 `web` 和 `headless` profile 首次使用时会从随附模板自动初始化（`web`：base + web-app；`headless`：base + web-app + headless）。其他缺失的 profile 会显式报错，并提示运行 `dsh plugin --profile <name> add <package>`。

-位置参数任务（`dsh --profile headless "run the tests"`）要求组合挂载一次性运行器行（`headless-runner`）；启动器把任务文本 patch 进该行，运行器通过进程内 API 载体驱动一个全新的持久化会话，在 stdout 打印最终 assistant 文本，并在轮次完成时以 0 退出，否则以 1 退出。会话的 Web 宿主运行在 OS 分配的端口上并公布到 stderr，因此该次运行可在浏览器中观察。
+Profile 启动不接受位置参数任务。因此，挂载了一次性运行器行（`headless-runner`）的 profile 会显式报错，并提示规范命令 `dsh run --profile <name> "<task>"`，而不会触发该行原始的必填字段错误。

 可在不启动的情况下检查组合出的配置树：

@@ -23,6 +23,12 @@ dsh --profile web --patch ./extra.yml --dump-config

 `--dump-default-config` 只打印组合包各层；`--dump-config` 额外加上 profile 的 `cordis.patch.yml`、home 级的 `$DSH_HOME/cordis.patch.yml` 和 `--patch` overlay。两者都会按层打印来源注释；`!!js` 表达式保持未求值，找不到目标的 patch 会报告到 stderr。

+## 一次性运行
+
+`dsh run [--profile <name>] [--patch <path>...] <task...>` 会用空格拼接任务参数，拒绝缺失或空白任务，并让 `--profile` 默认为 `headless`。可重复使用的 `--patch` overlay 与 profile 启动的 overlay 位于同一层。所选的自定义 profile 必须挂载 `headless-runner`；否则启动器会在启动前失败，并在诊断中指明缺少该行。
+
+启动器把任务文本 patch 进运行器行，运行器再通过进程内 API 载体驱动一个全新的持久化会话，在 stdout 打印最终 assistant 文本，并在轮次完成时以 0 退出，否则以 1 退出。到达 idle 边界时，运行器会等到 mux 消费方观察到会话的最终事件序号，再生成输出与退出原因。会话的 Web 宿主运行在 OS 分配的端口上并公布到 stderr，因此该次运行可在浏览器中观察。
+
 ## 插件管理

 `dsh plugin --profile <name> <args...>` 在 profile 缺失时先初始化它（有随附模板的用模板，其他名称只装 `@deepseek-ai/dsh-base`），然后以 profile 目录为工作目录，把 `<args...>` 转发给 `pnpm`：`add`、`remove`、`why`、`update` 及其他所有 pnpm 子命令都照常可用；pnpm 必须在 PATH 上。相对路径 spec（`.`、`../plugin` 及其 `file:`/`link:` 形式）会先锚定到调用目录，因此在插件 checkout 中执行 `add .` 安装的是该 checkout，而不是 profile。每次成功运行后，`dsh.profile.bundles` 都会与已安装状态对齐：每个解析到 manifest 中声明了 `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }` 的包的依赖加入层栈（因此让包获得该声明的 `update` 会将其激活），没有组合包声明的依赖保持为普通依赖并给出一次性警告，已移除的依赖则退出层栈。
--- a/Show More
+++ b/Show More