Merge remote-tracking branch 'origin/master' into fix/windows-native-ci-local-validation

# Conflicts: # packages/client/ui-trajectory/tests/client-bundle.client.spec.ts
2026-08-29 04:26:38 +00:00 · 2026-08-12 14:12:41 +08:00
parent 06891c7628 76805df26e
commit e0a83884ac
206 changed files with 4331 additions and 1806 deletions
@@ -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/2026-08-06-app-owned-command-line.md
-2026-08-06-app-owned-command-line.md: 2480775f654fd5c2fecebc8d59e311acee878920
-2026-08-06-app-owned-command-line.zh.md: d754c125d5bc683156f5ac3f285e2cd711e6773b
+2026-08-06-app-owned-command-line.md: 6d84ba457564ef250e1acfbcc71fcc91b1d49aee
+2026-08-06-app-owned-command-line.zh.md: f964f7a7de7aae7e97b52fbc572443352dc5ae26
@@ -12,7 +12,7 @@ After profiles, compositions were installable but their command lines were not.

 The launcher parses only what it owns — `--profile`, `--patch`, the config dumps — and hands **everything after its own flags** to the booted tree verbatim. The split is positional: the first token the launcher does not recognize starts the app's arguments (commander's `passThroughOptions` + `allowUnknownOption` + `helpOption(false)`). A bare `dsh -h`, which has no app to hand the flag to, still prints the launcher's own help.

-The new `@deepseek-ai/dsh-cmdline` package owns the handoff. A launcher calls `provideCmdline(ctx, host)` before any entry mounts, providing `ctx.cmdlineArgs` (whose whole interface is `get(): readonly string[]`) and `ctx.appExit`. Any ordinary app plugin may inject `cmdlineArgs`, call `parseCmdline(ctx, program, plan)` with its own commander program, and provide the returned value as an app-owned service. Its Loader row carries no launcher marker or special kind, and the launcher does not inspect the composition for an owner. Multiple plugins may read the same immutable snapshot; a profile with no reader ignores its app arguments. Rows configured from a provider inject its service and read direct lazy config expressions (`port: !!js ctx.webStartup.port ?? 3080`), so a flag beats the value written beside it and nothing is written back into any row.
+The new `@deepseek-ai/dsh-cmdline` package owns the handoff. A launcher calls `provideCmdline(ctx, host)` before any entry mounts, providing `ctx.cmdlineArgs` (whose whole interface is `get(): readonly string[]`) and `ctx.appExit`. Any ordinary app plugin may inject `cmdlineArgs`, call `parseCmdline(ctx, program)` with its own commander program, and provide the resolved value as an app-owned service from the program's action. Its Loader row carries no launcher marker or special kind, and the launcher does not inspect the composition for an owner. Multiple plugins may read the same immutable snapshot; a profile with no reader ignores its app arguments. Rows configured from a provider inject its service and read direct lazy config expressions (`port: !!js ctx.webStartup.port ?? 3080`), so a flag beats the value written beside it and nothing is written back into any row.

 The boot mounts the composition once. Cordis holds each row until its injections are active; Loader then interpolates that row's `!!js` against the injection-ready plugin context immediately before activation. Include keeps nested row expressions raw until their target row reaches this point. `--help` leaves the provider's service absent, so dependent rows never activate, and a live patch reload interpolates again against the service that remains active, so a served port cannot be silently reset.

@@ -12,7 +12,7 @@ profile 落地之后，组合可以安装，命令行却不能。`apps/cli` 仍

 启动器只解析属于自己的部分（`--profile`、`--patch`、配置 dump），并把**自己 flag 之后的一切**原样交给引导起来的配置树。切分按位置进行：启动器不认识的第一个 token 就是应用参数的起点（依靠 commander 的 `passThroughOptions` + `allowUnknownOption` + `helpOption(false)`）。裸的 `dsh -h` 没有可交付的应用，仍然打印启动器自己的 help。

-新包 `@deepseek-ai/dsh-cmdline` 持有这次交接。启动器在任何条目挂载之前调用 `provideCmdline(ctx, host)`，提供 `ctx.cmdlineArgs`（其全部接口就是 `get(): readonly string[]`）与 `ctx.appExit`。任何普通应用插件都可以注入 `cmdlineArgs`，用自己的 commander program 调用 `parseCmdline(ctx, program, plan)`，再把返回值作为应用自有服务提供出去。它的 Loader 行不携带启动器标记或特殊类型，启动器也不会检查组合中的所有者。多个插件可以读取同一份不可变快照；没有读取方的 profile 会忽略自己的应用参数。由提供方配置的行注入其服务，并在惰性配置表达式中直接读取它（`port: !!js ctx.webStartup.port ?? 3080`），因此 flag 胜过写在它旁边的值，也没有任何东西被写回任何一行。
+新包 `@deepseek-ai/dsh-cmdline` 持有这次交接。启动器在任何条目挂载之前调用 `provideCmdline(ctx, host)`，提供 `ctx.cmdlineArgs`（其全部接口就是 `get(): readonly string[]`）与 `ctx.appExit`。任何普通应用插件都可以注入 `cmdlineArgs`，用自己的 commander program 调用 `parseCmdline(ctx, program)`，再在 program 自己的 action 中把解析出的取值作为应用自有服务提供出去。它的 Loader 行不携带启动器标记或特殊类型，启动器也不会检查组合中的所有者。多个插件可以读取同一份不可变快照；没有读取方的 profile 会忽略自己的应用参数。由提供方配置的行注入其服务，并在惰性配置表达式中直接读取它（`port: !!js ctx.webStartup.port ?? 3080`），因此 flag 胜过写在它旁边的值，也没有任何东西被写回任何一行。

 boot 只挂载一次整套组合。Cordis 让每一行等待其注入激活；Loader 随后在激活前一刻，基于已注入就绪的插件上下文插值该行的 `!!js`。Include 会保留嵌套的行表达式，直到目标行到达这一时点。`--help` 会让提供方服务保持缺失，因此依赖行永不激活；活动 patch 重载会针对仍然在线的服务再次插值，所以已经服务中的端口不会被悄悄重置。

@@ -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/2026-08-11-preset-authoring-agent-validates-its-own-composition.md
-2026-08-11-preset-authoring-agent-validates-its-own-composition.md: 6b9cdf32b70e3ab4adc9f3b0e20bb3d2245486c7
-2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: e6e8dabcd886a6331d294744b667552caa01e7b4
+2026-08-11-preset-authoring-agent-validates-its-own-composition.md: eb21094f0d859a31d5f16d780cada6818a508b36
+2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: 02c245348a9c7e9968472044d7ff95e1ff21120c
@@ -32,7 +32,9 @@ The agent reaches the roster service the way `cordis_mount` documents: a tempora

 "Whether a row publishes a service" resolves through `cordis_inspect what:"services"`, which names the owning fiber of every live service.

-The guidance keeps `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` as the answer to "where do my presets live" — it is where every `dsh` launcher puts them — while routing the path an agent actually reads or edits through `list()` or `resolve()`. `Config.roots` defaults to `[]` and `apps/cli` patches both roots in, `writableRoot()` takes the first `user` one, and no call reports either path; `authorable` answers only whether a writable root exists, and `list()` cannot reveal a user root that holds nothing yet. Stating the path is therefore right for talking to a person and wrong for feeding a file tool.
+The guidance keeps `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` as the answer to "where do my presets live" while routing the path an agent actually reads or edits through `list()` or `resolve()`. Stating the path is right for talking to a person and wrong for feeding a file tool: a deployment may configure other roots, and `list()` cannot reveal a user root that holds nothing yet.
+
+That path is now a property of the package rather than of one launcher. `AgentPresets` derives `<dshHome>/.agent-presets` as a `user` root unless `includeUserRoot` is false, the way [`dsh-skill-local`](../../../../packages/skill/skill-local/README.md) derives `<dshHome>/skills`, and `apps/cli` supplies only the SHIPPED root — the one path an installed app alone can resolve. The asymmetry it replaces cost a bug: with both roots patched in by one launcher, `dsh run` booted a roster with no roots at all and failed resolving `standard` (fixed then by teaching every launcher the patch). The derived root is appended after every configured root, so a shipped id still shadows a home directory claiming it, and `writableRoot()` still prefers an explicitly configured `user` root. It is resolved once at construction: a root set that changed between a `list()` and the `copy()` acting on its answer would author into a directory the caller never saw.

 The prohibition on touching the shipped install is promoted from a paragraph inside the authoring steps to a top `## Off-limits` section, extended to cover editing the host composition as a workaround. The new self-validation calls do not weaken it: `copy()` refuses an id any root supplies, and `remove()` refuses a preset that ships with the deployment.

@@ -32,7 +32,9 @@ agent 按 `cordis_mount` 自身文档所述的方式够到 roster 服务：挂

 「某行是否发布服务」改由 `cordis_inspect what:"services"` 回答，它会给出每个存活服务的持有 fiber。

-指导保留 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` 作为「我的 preset 在哪」的答案——每个 `dsh` 启动器都把它们放在那里——同时把 agent 实际读取或编辑的路径改走 `list()` 或 `resolve()`。`Config.roots` 默认为 `[]`，两个根均由 `apps/cli` 补入，`writableRoot()` 取其中第一个 `user` 根，且没有任何调用会报告任一路径；`authorable` 只回答是否存在可写根，而 `list()` 无法揭示一个尚且为空的用户根。因此写出该路径对人讲是对的，喂给文件工具是错的。
+指导保留 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` 作为「我的 preset 在哪」的答案，同时把 agent 实际读取或编辑的路径改走 `list()` 或 `resolve()`。写出该路径对人讲是对的，喂给文件工具是错的：部署可以配置其他根目录，而 `list()` 无法揭示一个尚且为空的用户根。
+
+该路径如今是本包的属性，而非某个启动器的属性。除非 `includeUserRoot` 为 false，`AgentPresets` 自行推导 `<dshHome>/.agent-presets` 作为 `user` 根，正如 [`dsh-skill-local`](../../../../packages/skill/skill-local/README.md) 推导 `<dshHome>/skills`；`apps/cli` 只提供**随附**根——那是唯有已安装 app 才能解析的路径。它取代的那种不对称曾付出过代价：两个根都由单一启动器补入时，`dsh run` 启动的 roster 一个根都没有，解析 `standard` 直接失败（当时的修法是让每个启动器都执行该 patch）。推导出的根追加在全部已配置根之后，因此随附 id 仍会遮蔽占用它的家目录目录，而 `writableRoot()` 仍优先选择显式配置的 `user` 根。它在构造时解析一次：若根目录集合在一次 `list()` 与依据其答案执行的 `copy()` 之间发生变化，写入的将是调用方从未见过的目录。

 禁止改动随发布安装的约束，从创作步骤中的一段提升为顶部的 `## Off-limits` 一节，并扩展到禁止改宿主组装绕行。新增的自校验调用不削弱它：`copy()` 拒绝任何根已提供的 id，`remove()` 拒绝随部署发布的 preset。

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-12-onboarding-reads-every-provider.md
+2026-08-12-onboarding-reads-every-provider.md: 1f247a6c93257c24052f55eb4297ec3c9c3df06d
+2026-08-12-onboarding-reads-every-provider.zh.md: fc6e43195a46eaea881f8b4bee3219b5e583b284
@@ -0,0 +1,38 @@
+# Agent Note: First-run readiness reads every provider, and the setup card closes
+
+Status: implemented
+
+English | [中文](2026-08-12-onboarding-reads-every-provider.zh.md)
+
+## Problem
+
+The first-run step and the Models page both asked one question — is `deepseek-official`'s credential stored? — of a join that describes every provider. Two defects followed from that single reading.
+
+A user who configured some other provider (a pi-ai gateway, a self-hosted route) and never wanted the official DeepSeek endpoint was taken over by the full-screen credential prompt on every blank session, with a working model already selected in the composer behind it. Nothing they could do short of storing a DeepSeek key would end it, because the step's readiness projection never looked at the row they had configured.
+
+On the Models page the same reading opened the DeepSeek setup card over them on every visit, and that card could not be closed: it was rendered from row data with no local state a Cancel could flip, so its Cancel button did nothing visible. Worse, it shared the row-editor/add/declare close handler, which unconditionally clears all three of those states — so cancelling the card that owned none of them discarded the add card's draft while staying open itself.
+
+## Decision
+
+One predicate answers what both surfaces actually need. `providerUsable(row)` is true when the route is registered with the adapter registry (`entry.active`) and whatever credential its resolved profile names is stored; a profile naming no reference authenticates through the provider's own path, as does a live route with no settings address, so neither owes this page a key.
+
+`onboardingReadiness` (renamed from `deepSeekReadiness`, which no longer describes what it reads) returns `provider-ready` as soon as any joined row is usable. Only a user with none of those reaches the official DeepSeek lookup, which is unchanged: it is the one route the prompt can offer a key field for. The gate subsumes two diagnostics the old projection carried — `settings-unavailable` and `credential-ref-unavailable` — because both described an active route the new gate now calls usable; the outcome for the user was already identical (the step completed without rendering).
+
+`needsSetup(row, anyUsable)` takes the same fact, so the setup card is the first-run posture alone. With another provider reachable, DeepSeek is an ordinary row carrying the missing-key dot, one Edit click from the same card.
+
+Each card kind now owns its own close handler. `closeSetup` records the provider in a component-local `dismissedSetup` set and touches nothing else; `closeEditor` keeps clearing the three states its cards own. Both route the post-save reload through one `announceSaved` helper. Dismissal is viewing state, like the open editor and the add card: a reload restores the first-run posture for a user still in it.
+
+## Alternatives considered
+
+- **Deriving readiness from the model catalog (`llm.models`) instead of the join.** It answers "can the user talk to something" most directly, but it costs a per-provider listing round trip on a surface that already holds the join, and a provider whose listing fails transiently would re-open onboarding.
+- **Requiring `row.configured` in `providerUsable`.** It reads as the stricter check, and would exclude exactly the routes a deployment mounts through `cordis.yml` without a configurable-provider declaration — live routes serving models that this page cannot configure. Registration, not configurability, is what makes a provider usable.
+- **Only adding the dismissal, leaving the card auto-opening.** It fixes the Cancel button and nothing else: a user with a working provider would still be handed the DeepSeek form on every visit to Models, which is the same misreading in a quieter form.
+- **Persisting the dismissal to settings.** A durable "do not ask about DeepSeek" flag is a second fact about first-run state that can disagree with the join. The credential itself already ends the posture permanently, and every other card on this page is session-local.
+
+## Consequences
+
+Onboarding now ends for reasons the DeepSeek route knows nothing about, so the step's name is the last thing tying it to that adapter; a future step that offers more than one route to configure would replace the prompt, not the readiness projection. The narrowed diagnostic union means an unresolvable `llm-deepseek` settings address is reported as `provider-ready` rather than as its own reason — the user-visible behavior is unchanged, and the Models page remains the diagnostic surface.
+
+## Testing
+
+Package tests pin `providerUsable` over the four join states and `onboardingReadiness` over both the new gate and every surviving diagnostic; the section tests cover the first-run posture, the plain-row posture, and the cancel that collapses the setup card while the add card keeps its draft. The `onboarding-usable-provider` web e2e lane replays the whole scenario through the real wire: cancel with both cards open, configure `minimax-cn` instead, reload, and find no takeover — with one aria golden of the dismissed state.
@@ -0,0 +1,38 @@
+# Agent Note: First-run readiness reads every provider, and the setup card closes
+
+Status: implemented
+
+[English](2026-08-12-onboarding-reads-every-provider.md) | 中文
+
+## Problem
+
+首次使用引导步骤与 Models 页都只向一个描述全部提供方的联接快照提出了同一个问题——`deepseek-official` 的凭据存了吗？两个缺陷由这一次读取而来。
+
+配置了别的提供方（某个 pi-ai 网关、某条自建路由）、根本不打算用 DeepSeek 官方端点的用户，会在每一个空白会话上被全屏凭据提示接管，而其背后输入框里早已选好了一个可用模型。除了存入一把 DeepSeek 密钥，他们做什么都结束不了它——因为该步骤的就绪投影从不看他们已经配好的那一行。
+
+在 Models 页上，同一次读取每次进入都会把 DeepSeek 设置卡片展开在他们面前，而这张卡片关不掉：它由行数据渲染而来，没有任何本地状态可供「取消」翻转，因此那颗取消按钮不产生任何可见效果。更糟的是，它与行内编辑卡／新增卡／自定义声明卡共用同一个关闭回调，而该回调会无条件清空那三个状态——于是取消一张它们一个都不拥有的卡片，反而丢弃了新增卡里的草稿，自己却仍然开着。
+
+## Decision
+
+一个谓词回答两处界面真正需要的事实。`providerUsable(row)` 在路由已注册进适配器注册表（`entry.active`）、且其解析后 profile 所指名的凭据已存储时为真；不指名任何引用的 profile 走提供方自己的认证路径，没有 settings 地址的存活路由亦然，因此二者都不欠这个页面一把密钥。
+
+`onboardingReadiness`（原名 `deepSeekReadiness`，该名称已不再描述它读取的内容）只要联接中有任意一行可用，就返回 `provider-ready`。只有二者皆无的用户才会走到官方 DeepSeek 查找，那部分保持不变：它是这条提示唯一能为其提供密钥输入框的路由。这道门槛吸收了旧投影携带的两个诊断——`settings-unavailable` 与 `credential-ref-unavailable`——因为二者描述的都是新门槛现在判为可用的活跃路由；对用户而言结果本就一致（该步骤不渲染直接完成）。
+
+`needsSetup(row, anyUsable)` 接受同一个事实，因此设置卡片仅代表首次运行姿态。当另有可触达的提供方时，DeepSeek 就是一行带缺失密钥点的普通行，距离同一张卡片只有一次「编辑」点击。
+
+现在每一类卡片各自拥有自己的关闭回调。`closeSetup` 把该提供方记入组件本地的 `dismissedSetup` 集合，别的一概不碰；`closeEditor` 继续清空它那些卡片所拥有的三个状态。两者都经由同一个 `announceSaved` 助手完成保存后的重载。关闭状态属于查看态，与展开的编辑卡和新增卡一样：对仍处于首次运行姿态的用户，重载会恢复该姿态。
+
+## Alternatives considered
+
+- **从模型目录（`llm.models`）而非联接推导就绪状态。** 它最直接地回答「用户有没有能对话的东西」，但会在一个已经持有联接的界面上多花每提供方一次列举往返，而且某个提供方列举的瞬时失败会让引导重新弹出。
+- **在 `providerUsable` 中要求 `row.configured`。** 它读起来更严格，却会恰好排除部署通过 `cordis.yml` 挂载、没有可配置提供方声明的那些路由——它们是正在提供模型、只是这个页面配置不了的存活路由。使一个提供方可用的是注册，不是可配置性。
+- **只加关闭状态，保留卡片自动展开。** 那只修好取消按钮，别的什么都没修：已有可用提供方的用户每次进入 Models 仍会被塞一张 DeepSeek 表单，那是同一个误读的安静版本。
+- **把关闭状态持久化到 settings。** 一个「别再问 DeepSeek」的持久标志，是关于首次运行状态的第二个事实，可能与联接互相矛盾。凭据本身已经永久结束该姿态，而这个页面上其他每一张卡片都是会话内的。
+
+## Consequences
+
+引导现在会因为 DeepSeek 路由一无所知的理由而结束，因此该步骤的名字是最后一处把它和那个适配器绑在一起的东西；未来若有一个步骤能提供不止一条可配置路由，替换掉的会是提示本身，而非就绪投影。收窄后的诊断联合意味着无法解析的 `llm-deepseek` settings 地址会被报为 `provider-ready` 而非它自己的理由——用户可见行为不变，Models 页仍是诊断界面。
+
+## Testing
+
+包内测试针对四种联接状态钉住 `providerUsable`，并针对新门槛与每一个存留的诊断钉住 `onboardingReadiness`；分区测试覆盖首次运行姿态、普通行姿态，以及在新增卡保住草稿的同时折叠设置卡片的那次取消。`onboarding-usable-provider` web e2e 泳道通过真实协议重放整个场景：两张卡片都开着时取消、改配 `minimax-cn`、重载，然后不再出现接管——并附一份关闭后状态的 aria golden。
@@ -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/2026-07-25-session-list-browsing-and-manual-order.md
-2026-07-25-session-list-browsing-and-manual-order.md: 3d2125bdf67a70a1a5bca43c5d5acb09fda178b7
-2026-07-25-session-list-browsing-and-manual-order.zh.md: 161ebd2857073d4dd9cfc2883880cd3e2d91c040
+2026-07-25-session-list-browsing-and-manual-order.md: 52a0fe0c94106cb4178c57e737b1c9a3f458f803
+2026-07-25-session-list-browsing-and-manual-order.zh.md: a6c44579c685479ca460da8e52ea885f20e4776b
@@ -14,7 +14,7 @@ Two existing mechanisms stood in the way. First, the host durably promoted the a

 ### Flat rows and viewing state

-The group-by menu offers two modes, WorkSpace / In one list. WorkSpace mode renders peer session rows within each group in the manual order from `WorkspaceView.sessionIds`; In one list combines every session and sorts them strictly newest-first by `updatedAt`. Neither mode projects `parentId` into a list hierarchy; fork lineage remains session data only. [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the complete fork behavior. The mode choice persists in the browser (`dsh.workspace.view`) across reloads.
+The group-by menu offers two modes, WorkSpace / In one list. WorkSpace mode renders peer session rows within each group in the manual order from `WorkspaceView.sessionIds`; In one list combines every session and sorts them strictly newest-first by `updatedAt`. Neither mode projects `parentId` into a list hierarchy; fork lineage remains session data only. [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the complete fork behavior. The mode choice persists in the browser (`dsh.workspace.view`) across reloads. [Workspace Sidebar Order and Folding](2026-08-11-workspace-sidebar-order-and-folding.md) later added a browser-local recent-update view without changing the Host account's manual-order authority.

 ### Row interactions

@@ -50,7 +50,7 @@ ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine,

 ## Consequences

- Manual order is the sole authority over the workspace account: an order the user arranges is never scrambled by activity; the cost is losing float-to-top-on-activity, whose signal now rides the row status dot and time label. The `WorkspaceView.sessionIds` wire contract is reworded to the manual-order semantics.
+- Manual order is the sole authority over the Host workspace account: activity never mutates `WorkspaceView.sessionIds`. A later browser-local recent-update view may promote active rows without changing that account; its separate semantics are defined in [Workspace Sidebar Order and Folding](2026-08-11-workspace-sidebar-order-and-folding.md).
 - The two-fact shell/region contract funnels every future workspace-domain feature (Delete confirmation, cross-group moves, Ungrouped adoption) into the single ui-workspace package; ui-sidebar no longer evolves with session-list features.
 - Flat mode supports neither reordering nor a create-in-workspace entry point (switching back to grouped view is required) — an accepted scope reduction.
 - Wiring session Delete and growing the wire status enum remain future iterations.
@@ -14,7 +14,7 @@ Status: implemented

 ### 平铺行与浏览态

-group-by 菜单提供 WorkSpace / In one list 两种模式。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序在各组内展示同级 session 行；In one list 把所有 session 合并后严格按 `updatedAt` 新→旧排序。两种模式都不把 `parentId` 投影成列表层级，fork 谱系只保留为 session 数据；完整 fork 行为由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。模式选择持久化在浏览器(`dsh.workspace.view`),刷新保持。
+group-by 菜单提供 WorkSpace / In one list 两种模式。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序在各组内展示同级 session 行；In one list 把所有 session 合并后严格按 `updatedAt` 新→旧排序。两种模式都不把 `parentId` 投影成列表层级，fork 谱系只保留为 session 数据；完整 fork 行为由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。模式选择持久化在浏览器(`dsh.workspace.view`),刷新保持。[Workspace 侧边栏顺序与折叠](2026-08-11-workspace-sidebar-order-and-folding.md)随后加入浏览器本地的最近更新视图，而未改变 Host 记账的手动顺序权威。

 ### 行交互

@@ -50,7 +50,7 @@ ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settin

 ## Consequences

- 手动序是唯一的 workspace 账本序权威:用户排好的顺序不再被活动打乱;代价是「最近活跃浮到最上」的行为消失,活跃感知转由行内状态点与时间标签承担。`WorkspaceView.sessionIds` 的 wire 约定随之改为手动序措辞。
+- 手动序是 Host workspace 账本的唯一顺序权威：活动绝不改动 `WorkspaceView.sessionIds`。后续加入的浏览器本地最近更新视图可以把活跃行提到最前，但不会改变该账本；其独立语义见 [Workspace 侧边栏顺序与折叠](2026-08-11-workspace-sidebar-order-and-folding.md)。
 - 壳/区域两事实约定把 workspace 域的后续功能(Delete 确认、跨组移动、Ungrouped 收编)全部收进 ui-workspace 单包;ui-sidebar 不再随 session 列表功能演进。
 - 平铺模式不支持排序与分组入口(建到指定 workspace 需切回分组视图),是拍板接受的范围收窄。
 - session Delete 的功能接线与状态枚举扩 wire,留待后续迭代。
@@ -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/2026-07-25-workspace-ui-product-flow.md
-2026-07-25-workspace-ui-product-flow.md: 98e963195126df2ec8291a11b3d9fc7a2baeb0df
-2026-07-25-workspace-ui-product-flow.zh.md: 486093be0b8d10c2ae0b8083b305ecad5386351c
+2026-07-25-workspace-ui-product-flow.md: 76d279bf2101d7487fe4f5231c7cea4809e166f4
+2026-07-25-workspace-ui-product-flow.zh.md: e15ead7b437d8f2324f7ea51222eb4fcfb4a9e4a
@@ -20,6 +20,7 @@ The Host provides the following GUI wiring on the Workspace entity:
 | --- | --- |
 | `workspace.list` | Returns persistent Workspaces in order and filters out Session ids that fail header validation |
 | `workspace.create({ path })` | Adopts an existing directory by canonical path; basename-derived display titles may repeat |
+| `workspace.insertBefore({ workspaceId, beforeWorkspaceId? })` | Moves one Workspace within durable registry order and returns the complete committed order |
 | `workspace.delete({ workspaceId })` | Removes the Workspace registration while retaining its directory and session logs; its Sessions become Ungrouped |
 | `session.create({ workspaceId, sessionId? })` | Resolves cwd from the Workspace, idempotently creates a Session with an optional preallocated id, and attaches it |
 | `session.create({ cwd })` | Remains available to non-Workspace callers and creates an Ungrouped Session |
@@ -49,7 +50,7 @@ On initial entry, the application waits until both the Workspace and Session bas

 When no Workspace exists, the page creates a frontend Workspace object named `workspace` and a frontend Session that targets it. Neither writes to the Host, and the composer always accepts input; the first send materializes the Workspace, attaches the Session, and sends the message in that order.

-Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the most recent Workspace, or the Workspace Intent if no real Workspace exists. The Workspace picker's one Add workspace action ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md); it was a pair of Use-an-existing-folder and create-by-name actions when this was decided) immediately creates a real Workspace when the user confirms a directory, then retargets the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message.
+Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the current Session's Workspace, then the most recent Workspace, and enters the blank New Session page when no real Workspace exists. The Workspace picker's one Add workspace action ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md); it was a pair of Use-an-existing-folder and create-by-name actions when this was decided) immediately creates a real Workspace when the user confirms a directory, then retargets the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message.

 A new Workspace takes its display name from the directory it was created in. Distinct canonical paths may share the same basename-derived title ([identity decision](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)); the explicit rename operation retains its duplicate-title check. Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow.

@@ -67,11 +68,11 @@ Lost RPC responses, Host frames arriving before completions, and completions arr

 ### Sidebar and ordering

-Workspace groups strictly follow the persistent order returned by the Host. Bootstrap determines the historical order once, explicitly created Workspaces are placed first, and Session activity does not move Workspace groups.
+Workspace groups follow the persistent order returned by the Host. Bootstrap determines the historical order once, explicitly created Workspaces are placed first, and `workspace.insertBefore` durably applies user drag order. Session activity does not move Workspace groups.

-Within each group, order strictly follows `Workspace.sessionIds`. A newly attached Session is placed first; when a Session later becomes active, the Host moves only that id to the front and persists the change. The Client does not reorder the entire group by time after the Session list arrives, so it never displays one Workspace order and then jumps to another during hydration.
+The Host account remains the manual `Workspace.sessionIds` order: a newly attached Session is placed first and activity does not mutate it. The grouped browser can instead select a browser-local recent-update view that promotes a Session when its `updatedAt` advances and remains manually editable. Five Sessions are visible per open Workspace until the user transiently expands the remainder. The durable Workspace reorder and browser-local Session order are defined in [Workspace Sidebar Order and Folding](2026-08-11-workspace-sidebar-order-and-folding.md).

-A frontend Session Intent appears as a “New session” row and temporarily counts toward the group's Session total only when it targets a real Workspace. When it targets a Workspace Intent, neither the Workspace nor the Session appears in the sidebar. After the Intent is published, the real row with the same preallocated id takes its place; after refresh, both the Intent row and temporary count disappear. Search mode neither retains nor filters Intent rows.
+The current blank Session appears as a “New session” row without a count, time label, or row menu; other blank Sessions remain hidden and eligible for per-Workspace reuse. Search excludes blank rows.

 Real Sessions that cannot be assigned to any Workspace appear under Ungrouped. Host `session-added` and `workspace-changed` events may arrive in either order; list merging does not depend on frame order.

@@ -105,15 +106,15 @@ The Sidebar and conversation empty hero receive standardized actions through slo
 - Frontend Sessions and Workspaces preserve object identity across materialization; input, errors, focus, and sidebar projections always originate from the object layer.
 - The first send advances through Workspace, Session, and prompt in order; successful stages are not rolled back, input is not lost before the prompt is accepted, and creation retries use the same SessionId.
 - Workspace list performs one reentrant bootstrap using only headers; an initialized empty registry does not initialize again after restart, and membership reads validate both the index and canonical cwd.
- The initial default target is determined exactly once after both baselines are ready; Workspace groups are not reordered as a whole by hydration or Session activity, and an active Session moves only itself to the front.
- A frontend Session under a real Workspace temporarily counts toward the sidebar total, while a Workspace Intent remains hidden; neither publication nor refresh leaves duplicate rows or counts.
+- The initial default target is determined exactly once after both baselines are ready; Workspace groups are not reordered by hydration or Session activity, and explicit Workspace drag order survives reconnect.
+- The current blank Session can appear as a single New Session row without exposing other reusable blanks or a Session count.
 - The UI and Host admit distinct same-basename directories as separate Workspaces, while the explicit rename operation rejects duplicate titles; cwd-only Sessions, Sessions with invalid historical cwd values, and unattached Sessions remain Ungrouped.
 - Confirmed Workspace deletion removes only the registration, retains the current Session, directory, files, and session log, and survives reload; package tests pin unary/frame/baseline races and failure rollback.
 - Keyless runnable snapshots cover the zero state, explicit creation, and the first send; package-level tests cover bootstrap, membership validation, ordering, idempotency, failure recovery, and arbitrary frame order.

 ## Consequences

- SessionHeader does not record last-active time, so historical bootstrap can initialize order only by `createdAt`; real Session activity events move individual entries afterward.
+- SessionHeader does not record last-active time, so historical bootstrap can initialize the Host manual order only by `createdAt`; the browser's optional recent-update view begins from Session summaries after hydration.
 - Historical Sessions with a missing cwd, an invalid directory, or a failed realpath remain Ungrouped; this iteration has no manual-adoption entry point.
 - Refreshing the page discards unmaterialized Workspace and Session Intents and input not yet accepted by the Host; this is the page-local contract.
 - Explicit Create Workspace writes to disk immediately, so leaving without sending still leaves an empty Workspace.
@@ -20,6 +20,7 @@ Host 在 Workspace entity 上提供以下 GUI 接线：
 | --- | --- |
 | `workspace.list` | 返回持久有序的 Workspace，并过滤未通过 header 校验的 Session id |
 | `workspace.create({ path })` | 按 canonical path 收编已有目录；由 basename 派生的显示名可以重复 |
+| `workspace.insertBefore({ workspaceId, beforeWorkspaceId? })` | 在持久注册表顺序内移动一个 Workspace，并返回完整的已提交顺序 |
 | `workspace.delete({ workspaceId })` | 移除 Workspace 注册记录，同时保留目录和会话日志；相关 Session 进入 Ungrouped |
 | `session.create({ workspaceId, sessionId? })` | 从 Workspace 解析 cwd，以可选预分配 id 幂等创建 Session 并 attach |
 | `session.create({ cwd })` | 保留给非 Workspace 调用方，创建 Ungrouped Session |
@@ -49,7 +50,7 @@ Session 自己持有首条输入并驱动一条内部流水线：必要时以预

 完全没有 Workspace 时，页面创建默认名为 `workspace` 的前端 Workspace 对象和指向它的前端 Session。两者不写 Host，composer 始终可输入；首次发送才依次 materialize Workspace、attach Session、发送消息。

-顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作：显式 Workspace id 直接成为目标，未指定时使用最近 Workspace，没有真实 Workspace 时使用 Workspace Intent。Workspace picker 的单一 Add workspace 动作（见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)；本决策做出时是 Use an existing folder 与按名称创建两个动作）会在用户确认目录时立即创建真实 Workspace，再把前端 Session 定位到该 Workspace；即使用户不发送消息，显式创建的空 Workspace 也保留。
+顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作：显式 Workspace id 直接成为目标，未指定时先使用当前 Session 所属 Workspace，再使用最近 Workspace；没有真实 Workspace 时进入空白 New Session 页面。Workspace picker 的单一 Add workspace 动作（见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)；本决策做出时是 Use an existing folder 与按名称创建两个动作）会在用户确认目录时立即创建真实 Workspace，再把前端 Session 定位到该 Workspace；即使用户不发送消息，显式创建的空 Workspace 也保留。

 新建 Workspace 的显示名取自其所在目录。不同 canonical path 可以拥有相同的 basename 派生显示名（见[身份决策](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)）；显式的重命名操作仍保留显示名重名检查。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。

@@ -67,11 +68,11 @@ RPC 响应丢失、Host frame 先于 completion 和 completion 先于 Host frame

 ### Sidebar 与排序

-Workspace 组严格使用 Host 返回的持久顺序。Bootstrap 一次性确定历史顺序，显式创建的新 Workspace 放在首位；Session 活跃不会移动 Workspace 组。
+Workspace 组使用 Host 返回的持久顺序。Bootstrap 一次性确定历史顺序，显式创建的新 Workspace 放在首位，`workspace.insertBefore` 则持久应用用户拖拽顺序；Session 活跃不会移动 Workspace 组。

-组内严格使用 `Workspace.sessionIds`。新 attach 的 Session 放在首位，后续某个 Session 活跃时 Host 只前移该 id 并持久化。Client 不在 Session list 到达后按时间整体重排，因此不会先显示一套 Workspace 顺序再因 hydration 瞬间跳动。
+Host 记账保持手动的 `Workspace.sessionIds` 顺序：新 attach 的 Session 放在首位，活动不会改动该顺序。分组浏览器可以改选浏览器本地的最近更新视图；当 Session 的 `updatedAt` 增大时该视图会把它移到首位，同时仍允许手动调整。每个打开的 Workspace 默认显示五条 Session，用户可临时展开其余条目。持久 Workspace 重排序和浏览器本地 Session 顺序见 [Workspace 侧边栏顺序与折叠](2026-08-11-workspace-sidebar-order-and-folding.md)。

-前端 Session Intent 只有在目标是真实 Workspace 时才作为 「New session」 行显示，并临时计入该组 Session 数量；目标是 Workspace Intent 时，Workspace 与 Session 都不进入 sidebar。Intent 发布后由同一预分配 id 对应的真实行接替，刷新后 Intent 行和临时计数一起消失。搜索模式不保存或筛选 Intent 行。
+当前空白 Session 会显示为一条「New session」行，但不显示数量、时间标签或行菜单；其他空白 Session 保持隐藏，并可由对应 Workspace 复用。搜索会排除空白行。

 无法归入任何 Workspace 的真实 Session 进入 Ungrouped。Host `session-added` 与 `workspace-changed` 可以任意顺序到达，列表合并不依赖 frame 顺序。

@@ -105,15 +106,15 @@ Sidebar 与 conversation empty hero 通过 slot 获得标准化动作：`startSe
 - 前端 Session 与 Workspace 在 materialize 前后保持对象身份，输入、错误、焦点和 sidebar 投影始终来自对象层。
 - 首发按 Workspace、Session、提示词顺序推进，各成功阶段不回滚，输入在提示词被接受前不丢失，创建重试使用同一 SessionId。
 - Workspace list 只读取 header 完成一次可重入 bootstrap；initialized 的空 registry 重启不重复初始化，成员读取同时校验索引与 canonical cwd。
- 初始默认目标只在两份基线 ready 后确定一次；Workspace 组不因 hydration 或 Session 活跃整体重排，单个活跃 Session 只前移自身。
- 真实 Workspace 下的前端 Session 临时计入 sidebar 数量，Workspace Intent 保持隐藏，发布与刷新都不会留下重复行或重复计数。
+- 初始默认目标只在两份基线 ready 后确定一次；Workspace 组不因 hydration 或 Session 活跃重排，显式 Workspace 拖拽顺序在重连后仍然保持。
+- 当前空白 Session 可显示为唯一的 New Session 行，同时不暴露其他可复用空白会话，也不显示 Session 数量。
 - UI 与 Host 会将 canonical path 不同但 basename 相同的目录接纳为独立 Workspace，而显式的重命名操作会拒绝重复显示名；cwd-only Session、无效历史 cwd 和未 attach Session 保持 Ungrouped。
 - 经确认的 Workspace 删除只移除注册记录，保留当前 Session、目录、文件和会话日志，并在刷新后保持该状态；包级测试固定一元响应／帧／基线竞态和失败回滚行为。
 - keyless runnable snapshot 覆盖零态、显式创建和首次发送；包级测试覆盖 bootstrap、成员校验、排序、幂等、失败恢复及任意 frame 顺序。

 ## Consequences

- SessionHeader 不记录最后活跃时间，历史 bootstrap 只能按 `createdAt` 初始化；此后由真实 Session 活跃事件逐项前移。
+- SessionHeader 不记录最后活跃时间，历史 bootstrap 只能按 `createdAt` 初始化 Host 手动顺序；浏览器可选的最近更新视图在 hydration 后从 Session 摘要开始建立。
 - 历史 cwd 缺失、目录无效或 realpath 失败的 Session 留在 Ungrouped；本期没有手动收编入口。
 - 页面刷新会丢弃未 materialize 的 Workspace/Session Intent 和尚未被 Host 接受的输入，这是 page-local 约定。
 - 显式 Create Workspace 立即落盘，用户不发送就离开也会留下空 Workspace。
@@ -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/2026-08-10-durable-workflow-runs-in-chat.md
-2026-08-10-durable-workflow-runs-in-chat.md: 791a81e9e304a11f45557197ac1f97184132ccab
-2026-08-10-durable-workflow-runs-in-chat.zh.md: e6c87f61a144cebc0282055c8ae315d9068616fd
+2026-08-10-durable-workflow-runs-in-chat.md: 817fd4debd93a4768904e3934456ebdd4bdaa896
+2026-08-10-durable-workflow-runs-in-chat.zh.md: 7b09708d94783de5aff9a9fd59757120c661775a
@@ -20,7 +20,7 @@ The workflow package exposes browser-safe run and observation vocabulary through

 `ui-workflow-run` registers one `workflow-run` Conversation Definition and one keyed Chat renderer. Every event independently yields the same `runId`; run-start initializes State, later events update it in log order, and an update-only history tail remains pending until prepend supplies the unique start. The final node keeps the engine-owned key and anchors at run-start, placing it after the original tool call while preserving one React parent from running through terminal state.

-The renderer gives each level a distinct visual responsibility. The run uses a 32-pixel module-platform background row with persistent right/down chevrons and an inline state dot plus status text, without a badge. Phases use 32-pixel disclosure rows with title and member count in the flexible main area and a fixed precise aggregate-status tail, without another dot. Members use a 16-pixel dot slot, a truncating name area, and a fixed 64-pixel status column. Phases exist only when a member actually starts and group by the exact phase string; an omitted phase and the empty string retain distinct identities and localized names. Member settlement changes status without removing or reordering the member. A closed Turn or Step turns missing run or member endings into interrupted presentation; a durable ending remains authoritative when present.
+The renderer gives each level a distinct visual responsibility. The run uses a 32-pixel module-platform background row with persistent right/down chevrons and an inline state dot plus status text, without a badge. Phases use 32-pixel disclosure rows with title and member count in the flexible main area and a fixed precise aggregate-status tail, without another dot. Members use a 16-pixel dot slot, a truncating name area, and a fixed 64-pixel status column. Phases exist only when a member actually starts and group by the exact phase string; an omitted phase and the empty string retain distinct identities and localized names. Member settlement changes status without removing or reordering the member. A closed Turn or Step turns missing run or member endings into interrupted presentation; a durable ending remains authoritative when present. [Status-driven workflow disclosure](2026-08-11-workflow-run-status-driven-disclosure.md) owns which run and phase content remains visible as those facts change.

 Navigation is derived from two current authorities rather than persisted. A member row is interactive only while its durable member state is running and the current ordinary Session list contains the same id with `origin: 'subagent'`, `parentId` equal to the displayed parent, and `running: true`. Underlined member text is the only visible affordance; keyboard focus draws a two-pixel business-primary ring around the name area, and the fixed status label remains the lifecycle word rather than an action instruction. The renderer invokes only the injected ordinary `sessions.open(id)` callback. Addressed-only, remote, wrong-parent, and terminal members remain visible but static.

@@ -42,4 +42,4 @@ Package tests cover top-level and nested eligibility, zero-member and concurrent

 ## Consequences

-Workflow progress survives refresh and process recovery in the same log as its parent conversation, while execution ownership remains with the workflow run holder and the original tool card remains unchanged. The durable protocol adds four small events and one package-owned invariant; first-write failure intentionally sacrifices later observation rather than workflow correctness. Browser State is derived per loaded window, disclosure choices remain local, and navigation can disappear as list facts change. The design shows only actual runtime members and statuses, giving up static graph visualization, outputs, logs, controls, and terminal-member opening.
+Workflow progress survives refresh and process recovery in the same log as its parent conversation, while execution ownership remains with the workflow run holder and the original tool card remains unchanged. The durable protocol adds four small events and one package-owned invariant; first-write failure intentionally sacrifices later observation rather than workflow correctness. Browser State is derived per loaded window, the status-driven disclosure lifecycle keeps review choices local, and navigation can disappear as list facts change. The design shows only actual runtime members and statuses, giving up static graph visualization, outputs, logs, controls, and terminal-member opening.
@@ -20,7 +20,7 @@ workflow 包通过 `@deepseek-ai/dsh-workflow/types` 提供浏览器安全的运

 `ui-workflow-run` 注册一个 `workflow-run` Conversation Definition 和一个 keyed Chat renderer。每条事件都能独立给出同一 `runId`；run-start 初始化 State，后续事件按日志顺序更新；只有 update 的历史尾页会保持 pending，直到 prepend 补入唯一 start。最终节点保留引擎拥有的 key，并以 run-start 锚定在原工具调用之后，从运行中到终态始终保留同一个 React 父级。

-renderer 为每一层分配不同视觉职责。运行使用 32 像素 module-platform 背景行，常驻向右／向下 chevron，并以内联状态点加状态文字表达结局，不使用胶囊。阶段使用 32 像素 disclosure 行，在可伸缩主区显示标题与成员数，在固定尾部精确显示聚合状态且不重复状态点。成员使用 16 像素状态点槽、可省略名称区和固定 64 像素状态列。阶段只在成员真正开始时出现，并按精确阶段字符串分组；字段缺省与空字符串保留不同身份和本地化名称。成员结算只改变状态，不删除或重排成员。所属 Turn 或 Step 关闭时，缺少运行或成员终点会显示为已中断；存在持久终点时仍以它为权威。
+renderer 为每一层分配不同视觉职责。运行使用 32 像素 module-platform 背景行，常驻向右／向下 chevron，并以内联状态点加状态文字表达结局，不使用胶囊。阶段使用 32 像素 disclosure 行，在可伸缩主区显示标题与成员数，在固定尾部精确显示聚合状态且不重复状态点。成员使用 16 像素状态点槽、可省略名称区和固定 64 像素状态列。阶段只在成员真正开始时出现，并按精确阶段字符串分组；字段缺省与空字符串保留不同身份和本地化名称。成员结算只改变状态，不删除或重排成员。所属 Turn 或 Step 关闭时，缺少运行或成员终点会显示为已中断；存在持久终点时仍以它为权威。[状态驱动的工作流 disclosure](2026-08-11-workflow-run-status-driven-disclosure.md)拥有这些事实变化时运行与阶段内容的可见性。

 导航从两个当前权威派生，不写入持久记录。只有持久成员状态仍为运行中，且当前普通 Session 列表包含同一 id、`origin: 'subagent'`、`parentId` 等于当前父 Session、`running: true` 时，成员行才可交互。带下划线的成员文字是唯一可见提示；键盘聚焦时，名称区显示 2 像素 business-primary 焦点环，固定状态列继续只表达生命周期，而不写动作说明。renderer 只调用注入的普通 `sessions.open(id)` 回调。仅地址化、远程、父级不符或终态成员继续可见，但保持静态。

@@ -42,4 +42,4 @@ renderer 为每一层分配不同视觉职责。运行使用 32 像素 module-pl

 ## 后果

-工作流进度与父对话保存在同一日志中，能跨刷新与进程恢复；执行所有权仍属于工作流 run holder，原工具卡保持不变。持久协议增加四类小事件和一个包所有的 invariant；首次写入失败会刻意牺牲后续观察，而不是牺牲工作流正确性。浏览器 State 按已加载窗口派生，disclosure 选择保持本地，导航会随列表事实消失。设计只展示真实运行成员与状态，并放弃静态图、输出、日志、控制操作和终态成员打开。
+工作流进度与父对话保存在同一日志中，能跨刷新与进程恢复；执行所有权仍属于工作流 run holder，原工具卡保持不变。持久协议增加四类小事件和一个包所有的 invariant；首次写入失败会刻意牺牲后续观察，而不是牺牲工作流正确性。浏览器 State 按已加载窗口派生，状态驱动的 disclosure 生命周期把复盘选择留在本地，导航会随列表事实消失。设计只展示真实运行成员与状态，并放弃静态图、输出、日志、控制操作和终态成员打开。
@@ -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/2026-08-11-workflow-run-status-driven-disclosure.md
+2026-08-11-workflow-run-status-driven-disclosure.md: 2f452d25a8922bb6c275419af55e8af155dd2781
+2026-08-11-workflow-run-status-driven-disclosure.zh.md: 12cc106fea274a1681ee5615906ae6df266d567b
@@ -0,0 +1,43 @@
+# Agent Note: Status-driven disclosure for workflow runs
+
+Status: implemented
+
+English | [中文](2026-08-11-workflow-run-status-driven-disclosure.zh.md)
+
+## Problem
+
+A durable workflow Chat node updates in place from its running prefix to a terminal record. A disclosure choice initialized only at mount can hide a newly running phase, leave completed work occupying the conversation, or bury a failed, cancelled, or interrupted member behind two collapsed levels. Making openness a pure function of completion avoids those failures but also prevents users from reopening clean history for review.
+
+The renderer already receives every required lifecycle fact from the workflow Conversation Node. Visibility therefore needs a component-local lifecycle that gives current execution and attention states priority without adding another durable fact or taking ownership of workflow outcomes.
+
+## Decision
+
+Each phase derives one visibility requirement from its current members. A running, failed, cancelled, or interrupted member forces that phase open; a phase whose members are all completed is clean. The workflow forces itself open when its own status requires attention or any phase is forced open, so an abnormal member remains visible even when the workflow outcome is recorded as completed. A completed sibling phase remains independently collapsible.
+
+A forced-open level renders as an expanded static row. It exposes no button role, focus target, keyboard toggle, or `aria-expanded` value because collapsing cannot change the result. This keeps the visual hierarchy and status summaries while making the interaction promise match the available action.
+
+A clean level mounts an ordinary controlled disclosure in the closed state. Its local choice survives rerenders for the same continuous clean interval. New running or abnormal data replaces that manual interval with forced expansion; the next transition back to clean mounts a fresh closed disclosure, which produces one automatic fold per activity cycle. Closing the workflow naturally unmounts its phase controls, and a Session remount reconstructs every level from the current durable status rather than restoring an earlier choice.
+
+For example, a running workflow exposes its active phase and member without clicks. When that phase completes, only the phase folds while the workflow remains open; when the workflow and every phase complete, the workflow also folds. The user can then reopen both levels for review. If another member starts under the same phase key, both affected levels immediately return to forced expansion and fold again only after the new activity completes.
+
+The renderer owns only this visibility lifecycle. It does not add Session events, stores, settings, acknowledgement state, timers, focus movement, automatic scrolling, or cross-remount persistence. It does not change workflow status derivation, phase grouping, member order, navigation eligibility, copy, or the shared `DisclosureRow` API. Shared `data-expandable` styling owns pointer cursors, so forced-open static rows do not advertise an unavailable action. An interrupted durable prefix remains an attention state and therefore stays visible until the underlying facts change.
+
+## Verification
+
+Component tests drive the same keyed workflow and phase through running, clean completion, manual review, renewed activity, repeated clean completion, zero-member completion, and each abnormal status. They also verify abnormal-member propagation, clean-sibling independence, mouse and keyboard review, continuous-clean choice retention, and the absence of false button and ARIA semantics while expansion is mandatory.
+
+The shipped Web replay observes the real workflow, worker, Session log, browser plugin graph, and child navigation. It requires the live workflow and active phase to be visible without disclosure controls, the normally settled workflow and phase to fold, manual review to retain the terminal member without navigation, and a reload to reconstruct the folded history from durable facts.
+
+## Alternatives considered
+
+**Keep one manual state initialized from the first render.** Rejected because later lifecycle updates cannot reopen newly active or abnormal content and cannot fold normally settled work.
+
+**Derive `open` directly from whether a level is clean.** Rejected because completed history would remain permanently closed and could not be reopened for review.
+
+**Persist expansion, acknowledgement, or read state.** Rejected because current lifecycle facts already determine mandatory visibility, while review choice belongs only to the mounted presentation. Persistence would add a second state owner and require semantics for stale choices, abnormal acknowledgement, replay, and synchronization that the user result does not need.
+
+## Consequences
+
+Workflow records expose current work and abnormal outcomes without preparatory clicks, then reclaim conversation space after normal completion without sacrificing review. Interaction semantics remain truthful during automatic control, and the same durable record produces the same initial state during live rendering, refresh, and history reconstruction.
+
+The trade-off is deliberate local reset behavior. A phase choice disappears when its parent workflow closes or the component unmounts, and abnormal records cannot be manually hidden because the product has no acknowledgement state. Supporting either behavior later requires a separate ownership and persistence decision rather than extending this local lifecycle implicitly.
@@ -0,0 +1,43 @@
+# Agent Note: 工作流运行的状态驱动 disclosure
+
+Status: implemented
+
+[English](2026-08-11-workflow-run-status-driven-disclosure.md) | 中文
+
+## 问题
+
+持久工作流 Chat 节点会在同一位置从运行前缀更新为终态记录。只在挂载时初始化的 disclosure 选择可能隐藏新开始运行的阶段，让已完成工作继续占据对话空间，或者把失败、已取消或已中断成员埋在两层折叠内容之后。若只把开合状态作为完成状态的纯派生结果，虽然能避免这些问题，却也会阻止用户重新打开干净历史进行复盘。
+
+renderer 已经从工作流 Conversation Node 收到全部所需生命周期事实。因此，可见性需要一个组件本地生命周期：让当前执行与需注意状态优先，同时不增加另一项持久事实，也不取得工作流结果的所有权。
+
+## 决策
+
+每个阶段从当前成员派生一项可见性要求。存在运行中、失败、已取消或已中断成员时，该阶段强制展开；全部成员均已完成时，该阶段处于干净状态。工作流自身状态需要注意或任一阶段强制展开时，工作流也强制展开，因此即使工作流结果记录为已完成，异常成员仍保持可见。已完成的兄弟阶段继续可以独立折叠。
+
+强制展开层级渲染为静态展开行。它不提供按钮 role、焦点目标、键盘切换或 `aria-expanded` 值，因为折叠操作无法改变结果。这样既保留视觉层级与状态摘要，也让交互承诺与实际可执行动作一致。
+
+干净层级会以关闭状态挂载普通受控 disclosure。它的本地选择在同一段连续干净状态的 rerender 中保持。新的运行中或异常数据会用强制展开替代该手动区间；下一次回到干净状态时会挂载新的关闭 disclosure，从而让每个活动周期只自动折叠一次。关闭工作流会自然卸载其阶段控件；Session remount 会从当前持久状态重建每个层级，而不恢复更早的选择。
+
+例如，运行中的工作流无需点击即可展示活跃阶段与成员。该阶段完成时，只有阶段折叠，工作流继续展开；工作流自身和全部阶段均完成时，工作流也会折叠。用户随后可以重新打开两个层级复盘。若同一阶段 key 下又开始新成员，受影响的两个层级会立即恢复强制展开，并且只在新活动完成后再次折叠。
+
+renderer 只拥有这项可见性生命周期。它不增加 Session 事件、store、设置、确认状态、计时器、焦点迁移、自动滚动或跨 remount 持久化。它不改变工作流状态派生、阶段分组、成员顺序、导航准入、文案或共享 `DisclosureRow` API。pointer 光标由共享的 `data-expandable` 样式拥有，因此强制展开的静态行不会提示无法执行的操作。持久记录中的中断前缀仍属于需注意状态，因此在底层事实改变前始终可见。
+
+## 验证
+
+组件测试驱动同一个 keyed 工作流与阶段依次经过运行、干净完成、手动复盘、新活动、再次干净完成、零成员完成以及每种异常状态。测试还验证异常成员向上展开、干净兄弟阶段独立、鼠标和键盘复盘、连续干净状态中的选择保持，以及强制展开时不存在虚假按钮和 ARIA 语义。
+
+shipped Web 回放观察真实工作流、worker、Session 日志、浏览器插件图和子级导航。它要求实时工作流与活跃阶段无需 disclosure 控件即可见，正常结算的工作流与阶段会折叠，手动复盘仍能看到不再可导航的终态成员，并且刷新会从持久事实重建折叠历史。
+
+## 曾考虑的替代方案
+
+**保留一项从首次渲染初始化的手动状态。** 拒绝，因为后续生命周期更新无法重新打开新活动或异常内容，也无法折叠正常结算的工作。
+
+**只根据层级是否干净来派生 `open`。** 拒绝，因为已完成历史会永久保持关闭，无法重新打开复盘。
+
+**持久化展开、确认或已读状态。** 拒绝，因为当前生命周期事实已经决定强制可见性，而复盘选择只属于已挂载的展示层。持久化会增加第二个状态归属方，并要求定义陈旧选择、异常确认、回放和同步语义，而用户结果不需要这些机制。
+
+## 后果
+
+工作流记录无需预备点击即可展示当前工作与异常结果，并在正常完成后回收对话空间，同时不牺牲复盘能力。自动控制期间的交互语义保持真实，同一份持久记录在实时渲染、刷新和历史重建时得到相同初始状态。
+
+代价是有意保留的本地重置行为。父工作流关闭或组件卸载时，阶段选择会消失；由于产品没有确认状态，异常记录不能手动隐藏。以后若要支持任一行为，需要单独决定所有权与持久化，而不能隐式扩展这项本地生命周期。
@@ -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/2026-08-11-workspace-sidebar-order-and-folding.md
+2026-08-11-workspace-sidebar-order-and-folding.md: 3a88a61ca25550f1ad803a79e171ae2a7b8d4820
+2026-08-11-workspace-sidebar-order-and-folding.zh.md: e3e710bb9f38bcefcc9eeb50983c866ec5bc2619
@@ -0,0 +1,56 @@
+# Agent Note: Workspace Sidebar Order and Folding
+
+Status: implemented
+
+English | [中文](2026-08-11-workspace-sidebar-order-and-folding.zh.md)
+
+## Problem
+
+A Workspace with many Sessions can consume the entire sidebar and push other Workspaces out of reach. A compact list needs a bounded default while preserving an explicit route to every Session. The sidebar also needs an activity-oriented order, but `WorkspaceView.sessionIds` is the durable manual account and must not be rewritten by Session activity.
+
+Workspace groups themselves had no user-controlled durable order. Browser-native drag additionally rejects a drop released outside the list and animates the row back even when the application still has a valid insertion marker. Expanded Workspace sections make header-only hit testing ambiguous because the visual boundary between two groups does not match either header's midpoint.
+
+## Decision
+
+### Workspace order
+
+The Workspace registry owns a durable `workspaceIds` order and exposes `insertBefore(id, beforeId?)` with DOM `insertBefore` semantics. The Host RPC `workspace.insertBefore` returns the complete committed order, and a pure order mutation emits `host/workspace-order-changed` with the same complete order. Unknown source or anchor ids reject as `workspace-not-found`; self-anchored and already-positioned moves do not write.
+
+The client installs a Workspace drag optimistically. Request and frame generations ensure that only the latest unary echo can replace local order and that a newer Host frame outranks an older response; a latest rejected request restores the last complete order accepted from a Host baseline, frame, or current unary echo. Every successful list baseline restores Host order so reconnects adopt durable changes made elsewhere.
+
+### Session folding and view order
+
+Each Workspace persists one browser-local open state: closed means zero Session rows and open means up to five. When more Sessions exist, **Show more** reveals the remainder only for the current mount; closing the whole Workspace clears this transient expansion, so reopening returns to five. The current Session's group opens automatically only when the user has not already stored an explicit state for that Workspace. Creating a Session from a Workspace row opens the target group before starting the Session, keeping the new row visible when state propagation completes. After a ready Workspace baseline changes, the browser removes expansion, order, and observed-timestamp records for ids absent from that baseline while retaining the Ungrouped and flat-list accounts.
+
+The combined view menu offers **Manual** and **Last updated** in grouped and flat presentation, with one browser-local persisted order per account. A real Workspace initializes from `WorkspaceView.sessionIds`; Ungrouped and the cross-Workspace flat list initialize from recency and have no Host Session account. Entering Last updated performs one complete recency sort; a later user prompt or steer promotes that Session once, and dragging may edit the resulting order. Returning to Manual preserves the current order and only disables later activity promotion. Manual-mode drags for a real Workspace also write the Host Session account, while Ungrouped and flat-list drags and activity promotion remain browser-local. Flat rows omit an empty leading status slot because they have no parent hierarchy, while a visible status retains its slot.
+
+### Drag and compact chrome
+
+Workspace hit testing uses the complete rendered group section, including visible Session rows. One insertion boundary is shared by the preceding group's lower half and the following group's upper half, and the indicator is an absolutely positioned line with a joined right-facing chevron that does not affect layout. A tree-body overlay draws the first boundary at the same negative offset outside the scrolling clip, so the leading chevron remains visible without moving the list. During a Workspace or Session drag, document-level `dragover` and `drop` handlers accept the native operation; if release occurs outside the Workspace list, `dragend` commits the last valid marker.
+
+Search is a header action while collapsed and expands across the title and trailing actions. An outside click collapses a query that is empty after trimming but retains a non-empty query. Compact Workspace and Session rows, a 24px bottom fade, and the absence of per-Workspace Session counts preserve vertical space without removing navigation affordances.
+
+## Alternatives considered
+
+**Write every activity promotion into `Workspace.sessionIds`.** A browser presentation preference would overwrite the shared Host account whenever a user submits a prompt.
+
+**Keep independent Manual and Last updated orders.** Switching modes would replace the visible list with stale positions from the other order, even though choosing Manual only means that later activity stops moving rows.
+
+**Always show every Session in an open Workspace.** One large Workspace would continue to crowd out the rest, and remembering only the whole-group open state would not bound its height.
+
+**Persist the expanded-remainder state.** A Workspace reopened much later could unexpectedly occupy the full sidebar. Only the zero-or-five state represents a stable navigation preference; revealing the remainder is a local inspection.
+
+**Use numeric drop indices or header-only hit testing.** Indices drift when rows change during a drag, while header midpoints disagree with the visible boundary when a Workspace is expanded. Anchor ids and full-section geometry remain stable under both conditions.
+
+**Let the browser reject an outside release.** The application would commit the last valid marker while the browser displays a rejected-drop animation, presenting contradictory feedback.
+
+## Consequences
+
+- Workspace order is durable and shared through the Host, while grouping, open state, per-account Session view order, and query state remain browser-local presentation preferences. Ungrouped and the flat list support the same drag and promotion rules, but their orders are browser-local because neither has one Workspace account.
+- Last updated performs a complete recency sort on entry, then preserves manual adjustments until a user prompt or steer advances one Session and moves it to the front. Returning to Manual preserves every current position.
+- Opening a Workspace never shows more than five Sessions without an explicit **Show more** gesture, and closing it resets only that transient gesture.
+- The Host Session account retains the manual-order meaning established by [Session List Browsing and Manual Workspace Order](2026-07-25-session-list-browsing-and-manual-order.md).
+
+## Testing
+
+Domain and Host tests cover durable Workspace moves, no-op and invalid anchors, restart recovery, full-order RPC responses, order frames, and one Workspace snapshot per Host-stream baseline. Runtime tests cover optimistic order, frame/response precedence, overlapping rejection rollback to Host-confirmed order, reconnect baselines, and New Session target priority. UI tests cover five-row folding, transient expansion reset, pruning persisted state after Workspace removal, order-preserving mode switches, one-time recent-update promotion, browser-local Ungrouped and flat-list drag persistence, hierarchy-free flat-row leading spacing, selected view indicators, expanded-section Workspace hit testing, an unclipped first insertion boundary, outside-list Workspace and Session drops, search collapse rules, and compact CSS dimensions.
@@ -0,0 +1,56 @@
+# Agent Note: Workspace 侧边栏顺序与折叠
+
+Status: implemented
+
+[English](2026-08-11-workspace-sidebar-order-and-folding.md) | 中文
+
+## 问题
+
+Session 很多的 Workspace 会占满整个侧边栏，把其他 Workspace 挤出可见范围。紧凑列表需要有界的默认高度，同时仍要提供到达每条 Session 的明确入口。侧边栏还需要面向活动时间的顺序，但 `WorkspaceView.sessionIds` 是持久的手动记账，不能被 Session 活动改写。
+
+Workspace 分组本身没有用户可控的持久顺序。浏览器原生拖拽还会把列表外松手判为拒绝，并把行弹回原位，即使应用仍持有有效插入标记。Workspace 展开后，若只按组头命中，两个分组之间的视觉边界也不再等于任一组头的中点。
+
+## 决策
+
+### Workspace 顺序
+
+Workspace 注册表持有持久 `workspaceIds` 顺序，并提供采用 DOM `insertBefore` 语义的 `insertBefore(id, beforeId?)`。Host RPC `workspace.insertBefore` 返回完整的已提交顺序；单纯顺序变更通过 `host/workspace-order-changed` 推送同一份完整顺序。未知来源或锚点 id 以 `workspace-not-found` 拒绝；以自身为锚点或移动到当前位置不会写入。
+
+客户端对 Workspace 拖拽进行乐观安装。请求代次与帧代次保证只有最新一元回声可以替换本地顺序，且更新的 Host 帧优先于旧响应；最新请求被拒时会恢复最近一份由 Host 基线、帧或当前一元回声确认的完整顺序。每次成功的列表基线都会恢复 Host 顺序，因此重连会接纳其他位置提交的持久变更。
+
+### Session 折叠与视图顺序
+
+每个 Workspace 持久化一项浏览器本地打开状态：关闭表示零条 Session 行，打开表示最多五条。存在更多 Session 时，**展开其余**只在当前挂载期间显示剩余项；关闭整个 Workspace 会清除此临时展开，因此重新打开时恢复为五条。只有在用户尚未为该 Workspace 存储明确状态时，当前 Session 所在分组才会自动打开。从 Workspace 行创建 Session 时会在启动 Session 前打开目标分组，使状态传播完成后新行保持可见。就绪的 Workspace 基线发生变化后，浏览器会移除基线中不存在 id 的展开状态、顺序和已观察时间戳记录，同时保留 Ungrouped 和单列表记账。
+
+组合视图菜单在分组和单列表呈现中都提供**手动排序**和**最近更新**，每个记账各自持有一份浏览器本地持久顺序。真实 Workspace 从 `WorkspaceView.sessionIds` 初始化；Ungrouped 和跨 Workspace 的单列表从最近更新时间顺序初始化，且没有 Host Session 记账。进入最近更新时会执行一次完整的时间排序；后续 user prompt 或 steer 会将对应 Session 置顶一次，拖拽仍可编辑所得顺序。返回手动排序会保留当前顺序，只停用后续活动置顶。真实 Workspace 在手动模式下的拖拽还会写入 Host Session 记账，而 Ungrouped 和单列表的拖拽与活动置顶保留在浏览器本地。单列表没有父级层次，因此不显示空的左侧状态槽；存在可见状态时仍保留该槽。
+
+### 拖拽与紧凑界面
+
+Workspace 命中测试使用完整渲染分组区段，包括可见 Session 行。前一分组的下半部与后一分组的上半部共享同一条插入边界，指示器是一条带有相连右向尖角且不影响布局的绝对定位横线。树主体覆盖层会在滚动裁切区外以相同的负偏移绘制第一条边界，因此左侧尖角保持可见，列表位置也不会改变。Workspace 或 Session 拖拽期间，文档级 `dragover` 与 `drop` 处理器会接受原生操作；若在 Workspace 列表外松手，`dragend` 会提交最后一个有效标记。
+
+搜索在折叠时是区头操作，展开后占据标题与尾部操作的空间。查询经清除首尾空白后为空时，点击外部会收起搜索；非空查询则会保留。紧凑的 Workspace 与 Session 行、24px 底部渐隐以及取消每个 Workspace 的 Session 数量共同节省纵向空间，同时保留导航入口。
+
+## 考虑过的替代方案
+
+**把每次活动置顶写入 `Workspace.sessionIds`。** 浏览器呈现偏好会在用户每次提交提示词时覆盖共享的 Host 记账。
+
+**为手动排序和最近更新分别保留独立顺序。** 切换模式会用另一份顺序中的旧位置替换可见列表，而选择手动排序只表示后续活动不再移动条目。
+
+**打开 Workspace 时始终显示全部 Session。** 大型 Workspace 仍会挤占其他分组；只记忆整个分组的打开状态无法限制其高度。
+
+**持久化展开剩余状态。** 很久以后重新打开 Workspace 时，它可能意外占满侧边栏。只有零条或五条状态属于稳定导航偏好；显示剩余项只是一次本地查看。
+
+**使用数字下标或只按组头命中拖拽。** 拖拽期间行发生变化会使下标漂移；Workspace 展开时，组头中点与可见边界不一致。锚点 id 与完整区段几何在两种情况下都保持稳定。
+
+**让浏览器拒绝列表外松手。** 应用会提交最后一个有效标记，而浏览器同时播放拒绝动画，形成相互矛盾的反馈。
+
+## 后果
+
+- Workspace 顺序通过 Host 持久并共享；分组方式、打开状态、每个记账的 Session 视图顺序和查询状态仍是浏览器本地呈现偏好。Ungrouped 和单列表支持相同的拖拽与置顶规则，但因没有单一 Workspace 记账，其顺序只保存在浏览器本地。
+- 最近更新模式会在进入时执行完整时间排序，随后保持手动调整，直到 user prompt 或 steer 推进某条 Session 并将其置顶。返回手动排序会保留所有当前位置。
+- 未执行明确的**展开其余**手势时，打开 Workspace 最多显示五条 Session；关闭分组只重置这项临时手势。
+- Host Session 记账继续采用[会话列表浏览与 Workspace 手动排序](2026-07-25-session-list-browsing-and-manual-order.md)确立的手动顺序含义。
+
+## 测试
+
+领域与 Host 测试覆盖持久 Workspace 移动、无操作与无效锚点、重启恢复、完整顺序 RPC 响应、顺序帧以及每条 Host stream 基线只读取一份 Workspace 快照。运行时测试覆盖乐观顺序、帧／响应优先级、重叠拒绝后恢复 Host 已确认顺序、重连基线以及 New Session 目标优先级。UI 测试覆盖五行折叠、临时展开重置、Workspace 移除后清理持久状态、保持顺序的模式切换、一次性最近更新置顶、浏览器本地 Ungrouped 与单列表拖拽持久化、无层级单列表行左侧间距、当前视图标记、展开区段的 Workspace 命中、未裁切的第一条插入边界、列表外 Workspace 与 Session 松手、搜索收起规则和紧凑 CSS 尺寸。
@@ -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/2026-07-04-doc-tiers-and-budgets.md
-2026-07-04-doc-tiers-and-budgets.md: e7b3421d09a1ae5ab9a9373e8040832c1b0d4b97
-2026-07-04-doc-tiers-and-budgets.zh.md: 3bc04ae73a4d8c9c005e154a236772fc1845389e
+2026-07-04-doc-tiers-and-budgets.md: 3f263864b9b6ee9479d1133b908617f10073dd66
+2026-07-04-doc-tiers-and-budgets.zh.md: 63b0b2945e1ff3e3fdf6af3cddb80cf44cf448ee
@@ -12,6 +12,7 @@ Standing docs accumulated repeated rules, retold incidents, duplicated package m

 - **Structure follows the documentation tree.** [docs/AGENTS.md](../../../../docs/AGENTS.md) is the documentation standard: a document owns detail about its subject, summarizes only the purpose, responsibility, and high-level behavior of direct children, and links to deeper owners. [Agent Notes](../../README.md) remain outside this structural contract. Every human-facing document is a tutorial with an ordered outcome or a reference with an explicit lookup scope; a [postmortem](../../../../docs/postmortem/README.md) is an incident-scoped reference whose chronology records evidence. Tutorials introduce concepts in prerequisite order for the reader's starting knowledge.
 - **A tier taxonomy with one home per fact.** The standard assigns every Markdown tier one job, forbids restating a fact outside its home tier, and carries the slop checklist used when writing or reviewing any doc.
+- **One product onboarding path.** The root README owns the recommended package-run path, the source-run alternative, and compact `dsh plugin --profile` usage. The published user guide starts with tasks inside the running Web UI, then links to distinct tutorials or reference owners for other interfaces, plugin development, and advanced configuration instead of repeating Web startup.
 - **A narrow, hard budget gate.** [scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) joins `doc-sync`: every doc listed in [scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) must stay under its word ceiling (`wc -w` semantics, whole file), and a budgeted file that is missing fails the gate so a rename cannot silently orphan its budget. Scope is deliberately only the accretion-prone standing docs — the root and subtree `AGENTS.md` files, `architecture.md`, `packages/README.md`, and the standing policy docs they evict content into (`docs/testing.md`, `docs/defensive-patterns.md`). Reference docs, Agent Notes, and package READMEs are unbudgeted: length is legitimate there when every row is a fact, and review plus the slop checklist govern them.
 - **Ceilings are an enforcement frontier that ratchets.** A doc at or below its target keeps at least 5% headroom as its ceiling ratchets down; a doc above target keeps a frozen ceiling that prevents growth until it reaches the target (root `AGENTS.md` ≤ 1,600 words; `architecture.md` ≤ 1,800; subtree `AGENTS.md` ≤ 600 except `packages/AGENTS.md` ≤ 650 and `docs/AGENTS.md` ≤ 1,250; `packages/README.md` ≤ 600). When the gate goes red, relocate or condense; raise a ceiling only with explicit PR justification.
 - **A thin workflow skill, contracts in docs.** [.agents/skills/dsh-doc-standards](../../../skills/dsh-doc-standards/SKILL.md) carries the placement/audit/red-gate workflow and defers to the standard as its source of truth, the same split as [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) over the i18n contract.
@@ -20,11 +21,13 @@ Standing docs accumulated repeated rules, retold incidents, duplicated package m

 - **Skill and review discipline without a gate** — rejected: the accretion above happened while the current-state rule and reviewer attention already existed; a prose rule with no mechanical backstop demonstrably does not hold here, and this repo's own [quality-gates stance](2026-06-11-quality-gates.md) says invariants worth keeping are worth encoding.
 - **A broad gate over every doc tier** — rejected: a blanket ceiling punishes exactly the right kind of long doc (a feature matrix or type catalog where every row is a fact) and generates per-file override churn that trains contributors to rubber-stamp raises.
+- **Independent onboarding tutorials for each documentation entry point** — rejected: duplicated setup steps drift in command order, first outcome, and product identity. A short README path followed by task-focused guides keeps the transition explicit without maintaining competing tutorials.
 - **Housing the standard inside the skill** — rejected: contracts live in docs and workflows in skills; a standard packed into SKILL.md is invisible to an agent that edits docs without invoking the skill, and `docs/AGENTS.md` already loads as subtree instructions for anyone working under `docs/`.

 ## Consequences

 - Adding to a budgeted doc requires displacement: relocate the addition to its taxonomy home with a pointer, or condense existing prose to pay for it. Growth without pruning fails CI.
 - Structural review starts with ownership and document form before sentence-level editing, so lower-level detail moves to its owner instead of being polished in the wrong place.
+- Readers reach a running Web UI before encountering headless execution, SDK embedding, custom profiles, or direct settings files; those interfaces remain available from their reference owners.
 - Budgeted docs that remain above target cannot grow; reaching the target restores the 5% working headroom.
 - Word count is a crude proxy accepted deliberately: it cannot judge quality, but it forces the relocation decision at exactly the moment content is being added, which is when the author has the context to place it correctly.
@@ -12,6 +12,7 @@ Status: implemented

 - **结构遵循文档树。**[docs/AGENTS.md](../../../../docs/AGENTS.md) 是文档标准：文档负责承载其主题的详细内容，仅概述直接子项的目的、职责和高层行为，并链接到更深层内容的归属文档。[Agent Note](../../README.md) 仍不受这一结构约定约束。每份面向人的文档要么是按顺序引导读者达成结果的教程（tutorial），要么是查阅范围明确的参考文档（reference）；[事故复盘（postmortem）](../../../../docs/postmortem/README.md) 是范围限定于单起事故的参考文档，其时间线记录证据。教程结合读者的起始知识，按前置依赖顺序介绍概念。
 - **每项事实只归属一处的层级分类。**文档标准为每种 Markdown 层级分配单一职责，禁止在事实归属层级之外重复陈述，并包含编写或评审任何文档时使用的赘余检查清单。
+- **单一产品入门路径。**根 README 负责推荐的包运行路径、从源码运行的备选路径和简要的 `dsh plugin --profile` 用法。已发布的用户指南从运行中的 Web UI 内部任务开始，再链接到其他界面的独立教程或插件开发与进阶配置的参考文档归属处，而不会重复介绍 Web 启动步骤。
 - **范围窄且严格的预算门禁。**[scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) 接入 `doc-sync`：[scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) 列出的每份文档都必须低于其词数上限（采用 `wc -w` 语义，统计整个文件）；预算内文件缺失也会使门禁失败，使重命名无法悄然遗落其预算。范围刻意只涵盖容易膨胀的常设文档——根目录和子树中的 `AGENTS.md` 文件、`architecture.md`、`packages/README.md`，以及它们将内容移入的常设策略文档（`docs/testing.md`、`docs/defensive-patterns.md`）。参考文档、Agent Note 和包 README 不设预算：只要每一行都是事实，长度在这些位置就是合理的；评审和赘余检查清单负责约束它们。
 - **上限是只进不退的执行红线。** 达到或低于目标的文档在上限逐步下调时保留至少 5% 的余量；高于目标的文档则维持冻结的上限，在达到目标之前不得增长（根 `AGENTS.md` ≤ 1,600 词；`architecture.md` ≤ 1,800；子树 `AGENTS.md` ≤ 600，但 `packages/AGENTS.md` ≤ 650、`docs/AGENTS.md` ≤ 1,250；`packages/README.md` ≤ 600）。门禁变红时，迁移或压缩内容；只有在 PR（Pull Request）描述中给出明确理由时才提高上限。
 - **精简的工作流 skill（技能），约定归文档。**[.agents/skills/dsh-doc-standards](../../../skills/dsh-doc-standards/SKILL.md) 承载文档放置、审计和门禁失败处理工作流，并以文档标准为真源，与 [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) 和 i18n 约定之间的分工相同。
@@ -20,11 +21,13 @@ Status: implemented

 - **仅靠 skill 和评审纪律，不设门禁**：否决。上述膨胀正是在现行规则和评审注意力已经存在的情况下发生的；一条没有自动化保障的行文规则在此处已被证明无法维持，而本仓库自身的[质量门禁立场](2026-06-11-quality-gates.md)认为值得保持的不变式就值得编码。
 - **对所有文档层级全面设限**：否决。一刀切的上限恰好惩罚了那些正当的长文档（如功能矩阵或类型目录，每一行都是事实），并产生逐文件的例外变更，训练贡献者机械地批准提限。
+- **为每个文档入口维护独立入门教程**：否决。重复的设置步骤会在命令顺序、首个结果和产品定位上产生分歧。简短的 README 路径接上面向任务的指南，可明确衔接两者，且不需要维护相互竞争的教程。
 - **将标准放在 skill 内部**：否决。约定归文档，工作流归 skill；如果标准被塞进 SKILL.md，那些不调用该 skill 而直接编辑文档的 agent（智能体）就看不到它，而 `docs/AGENTS.md` 已经作为子树指令被任何在 `docs/` 下工作的人加载。

 ## 后果

 - 向受预算约束的文档添加内容需要腾挪空间：将新增内容迁移到其分类体系归属地并留下链接，或压缩现有行文来腾出空间。只增不减会导致 CI 失败。
 - 结构评审先检查归属关系和文档形式，再进行句子层面的编辑，使较低层级的细节迁移到其归属文档，而不是在错误的位置加以润色。
+- 读者会先进入可运行的 Web UI，再遇到 headless 执行、SDK 嵌入、自定义 profile 或直接 settings 文件；这些入口仍可从各自的参考文档归属处访问。
 - 仍高于目标的受预算约束文档不得增长；达到目标后，将恢复 5% 的工作余量。
 - 词数是一个粗糙的代理指标，这是有意接受的：它无法判断质量，但它在内容被添加的那一刻强制触发迁移决策，而那正是作者拥有足够上下文来正确放置内容的时刻。
@@ -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/2026-08-11-cmdline-program-action.md
+2026-08-11-cmdline-program-action.md: 40c4dae1d3461f25ac7f34dee7c166434e6cd24d
+2026-08-11-cmdline-program-action.zh.md: 91036f1c52b60d28055935813d6698205f045422
@@ -0,0 +1,29 @@
+# Agent Note: parseCmdline runs the program's own commander action
+
+Status: implemented
+
+English | [中文](2026-08-11-cmdline-program-action.zh.md)
+
+## Problem
+
+`dsh-cmdline`'s ([app-owned command line](../architecture/2026-08-06-app-owned-command-line.md)) `parseCmdline` carried a bespoke callback: `CmdlinePlan<T> = (program, ctx) => T`, invoked after a successful parse inside the helper's catch so a plan's `program.error(...)` shared the help/parse-error exit path, with a type-unsound `(() => ({}) as T)` default only tests used and a `ctx` argument no plan read. The whole seam duplicated a slot commander already defines: a command's action handler runs inside `parse`, and `program.error(...)` thrown from it obeys `exitOverride` exactly like a grammar rejection.
+
+## Decision
+
+`parseCmdline(ctx, program): void` only adapts commander control flow to the launcher: it parses the immutable `cmdlineArgs` snapshot and turns help, version, parse errors, and action rejections into a `ctx.appExit` request. App code — validation commander's grammar cannot express and the `ctx.provide` of the app-owned service — lives in the program's own synchronous `.action()`, which commander runs on a successful parse and never runs on help or rejection. The `CmdlinePlan` export, its `ctx` parameter, the default plan, and the `T | undefined` return are deleted; both bundle providers publish from their action. Because the `Command` type cannot express the action precondition, `parseCmdline` reads the handler structurally (as `isCommanderError` reads commander's control-flow errors) and refuses at load a program in which no command declares an action — without the guard, a provider that forgot its action (or a stale caller still passing the deleted third argument) parses successfully, publishes nothing, and surfaces only as dependent rows pending on the absent service at settlement. The helper configures `exitOverride` and output on the whole command tree, not the root alone: commander copies those settings into a subcommand only at registration, so a root-only override would let a pre-registered subcommand's rejection call `process.exit` past `ctx.appExit`. An action must reject before it publishes; statements before its `program.error(...)` have already run.
+
+Verified on commander 15 before shipping: an action runs inside `parse` and its `program.error(...)` throws a `CommanderError` through `exitOverride`; help and version short-circuit before the action; excess-argument handling is identical with and without an action.
+
+## Alternatives considered
+
+- **Keeping a bespoke `resolve`/plan callback**: it existed only so app rejection could share the helper's catch, which commander's action slot already provides; a second callback seam for the same moment in the parse lifecycle is duplication.
+- **Returning the parsed `Command` for the caller to read**: a post-parse `program.error(...)` in the caller escapes the helper's catch as an uncaught `CommanderError`, turning a usage rejection into a plugin load failure; every app with validation would rebuild the try/catch the helper owns.
+- **Moving all validation into commander option/argument parsers**: `InvalidArgumentError` covers per-value checks, but the headless bundle rejects a joined variadic ("task must be non-blank") with its own usage message, which per-argument parsers cannot express.
+- **Accepting an action-less program and relying on the settlement diagnostic**: the assembled launcher does fail loud (`pending (waiting for service: …)`), but that error names the consumers, not the misconfigured provider, and an embedding host without the settlement assertion would hang silently; the load-time guard reports the culprit program directly.
+- **Replacing the `CmdlineArgs` accessor with a bare frozen `readonly string[]` service**: the maintainer keeps the accessor object as the service's named interface.
+
+## Consequences
+
+- `parseCmdline` loses its generic, callback parameter, and `undefined` sentinel; callers lose the `if (values !== undefined)` publish guard.
+- An app's command is self-contained — flags, help text, validation, and the publishing effect travel together on the `Command`.
+- Actions must be synchronous: the helper calls `parse`, not `parseAsync`, so a returned promise would escape the catch unobserved.
@@ -0,0 +1,29 @@
+# Agent Note: parseCmdline 运行 program 自己的 commander action
+
+Status: implemented
+
+[English](2026-08-11-cmdline-program-action.md) | 中文
+
+## Problem
+
+`dsh-cmdline`（[应用自有命令行](../architecture/2026-08-06-app-owned-command-line.md)）的 `parseCmdline` 曾带着一个自造的回调：`CmdlinePlan<T> = (program, ctx) => T`，在解析成功后于该适配器的 catch 之内调用，使 plan 的 `program.error(...)` 与 help/解析错误共用同一条退出路径；它还带有只被测试使用、类型不健全的默认值 `(() => ({}) as T)`，以及没有任何 plan 读取的 `ctx` 参数。这整条接缝复制了 commander 本就定义的席位：命令的 action 处理器在 `parse` 内部运行，从中抛出的 `program.error(...)` 与语法拒绝一样遵循 `exitOverride`。
+
+## Decision
+
+`parseCmdline(ctx, program): void` 只把 commander 的控制流适配到启动器：它解析不可变的 `cmdlineArgs` 快照，并把 help、version、解析错误与 action 的拒绝转换为一次 `ctx.appExit` 请求。应用代码——commander 语法表达不了的校验，以及应用自有服务的 `ctx.provide`——放在 program 自己的同步 `.action()` 里，commander 在解析成功时运行它，在 help 或拒绝时绝不运行。`CmdlinePlan` 导出、其 `ctx` 参数、默认 plan 与 `T | undefined` 返回值全部删除；两个组合包提供方都在各自的 action 中发布。由于 `Command` 类型无法表达 action 前置条件，`parseCmdline` 按结构读取处理器（如同 `isCommanderError` 按结构识别 commander 的控制流错误），在加载时拒绝整棵命令树中没有任何命令声明 action 的 program 并点名它——若无此守卫，漏写 action 的提供方（或仍在传已删除第三参数的陈旧调用方）会解析成功、什么也不发布，只在 settlement 时以依赖行 pending 等待缺席服务的形式浮现。该适配器在整棵命令树而非仅根命令上配置 `exitOverride` 与输出：commander 只在注册时把这些设置复制进子命令，只配置根命令会让已注册子命令的拒绝绕过 `ctx.appExit` 直接调用 `process.exit`。action 必须先拒绝后发布；写在 `program.error(...)` 之前的语句已经执行。
+
+交付前已在 commander 15 上验证：action 在 `parse` 内部运行，其 `program.error(...)` 经 `exitOverride` 抛出 `CommanderError`；help 与 version 在 action 之前短路；有无 action 时的多余参数处理完全一致。
+
+## Alternatives considered
+
+- **保留自造的 `resolve`/plan 回调**：它存在的唯一理由是让应用侧的拒绝共用适配器的 catch，而 commander 的 action 席位本就提供这一点；为解析生命周期的同一时刻再造第二条回调接缝属于重复。
+- **返回解析后的 `Command` 交调用方读取**：调用方在解析之后调用 `program.error(...)` 会以未捕获的 `CommanderError` 逃出适配器的 catch，把一次用法拒绝变成插件加载失败；每个带校验的应用都得重建适配器持有的那套 try/catch。
+- **把全部校验移进 commander 的 option/argument 解析器**：`InvalidArgumentError` 覆盖逐值检查，但 headless 组合包用自己的用法信息拒绝拼接后的可变参数（"任务不得为空白"），逐参数解析器表达不了。
+- **接受没有 action 的 program，依赖 settlement 诊断**：组装好的启动器确实会大声失败（`pending (waiting for service: …)`），但那个错误点名的是消费者而非配置错误的提供方，且没有 settlement 断言的嵌入宿主会静默挂起；加载时守卫直接报出肇事的 program。
+- **用裸的冻结 `readonly string[]` 服务替换 `CmdlineArgs` 访问器**：维护者保留该访问器对象作为服务的具名接口。
+
+## Consequences
+
+- `parseCmdline` 失去泛型、回调参数与 `undefined` 哨兵值；调用方不再需要 `if (values !== undefined)` 的发布守卫。
+- 应用的命令是自包含的——flag、help 文本、校验与发布效果一起挂在 `Command` 上。
+- action 必须是同步的：适配器调用的是 `parse` 而非 `parseAsync`，返回的 promise 会在无人观察的情况下逃出 catch。
@@ -1,3 +1,3 @@
 # Running benchmarks

-To run benchmark tasks with the minimal agent composition, follow [Get started with the Python SDK](docs/user/guide/python-sdk.md). The guide covers installation, running [`minimal.cordis.yml`](examples/jsonrpc-agent/minimal.cordis.yml), and isolating workspaces and session IDs between tasks.
+Follow [Get started with the Python SDK](docs/user/guide/python-sdk.md) to install the SDK and run the `jsonrpc-agent` minimal variant. Use separate workspaces and session IDs for independent benchmark tasks.
@@ -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: 9c19dfec19cba6f1364e4f9d5734af49675d68c2
-README.zh.md: 31d83ede854e9f0dfbbba1f8ce1094d043f6d829
+README.md: 690cde099d93ea2a371b31f441030153b1aca973
+README.zh.md: 2a8046011da7c1970d1210f291973db36e379665
@@ -12,64 +12,43 @@ DeepSeek Harness is under internal testing. Features and interfaces may change.

 The internal build uploads all Session Logs by default to help diagnose reported problems. Set `DSH_TELEMETRY_DISABLED=1` to disable telemetry. Send feedback through the internal WeChat group.

-## Run from source
+## Run

-Clone this repo, complete the [dependency and API-key setup](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key), then run:
+Install Node.js ^22.19 or >= 24 and pnpm 11, then run the published package:

 ```sh
+npx @deepseek-ai/dsh web
+```
+
+The command initializes the Web profile and prints the Web UI URL, which is `http://127.0.0.1:3080` by default. Open it, add a DeepSeek API key under **Settings → Models**, then start a session. The invoking directory is the default workspace; try `Summarize this repository and identify its main packages.`
+
+Continue with the [Web UI guide](docs/user/guide/).
+
+### Run from source
+
+To run a repository checkout instead:
+
+```sh
+git clone https://github.com/deepseek-harness/deepseek-harness.git
+cd deepseek-harness
+pnpm install
 pnpm dsh web
 ```

-## Use DeepSeek Harness
+The last command builds the repository and opens the same Web UI path.

-### Web UI
+## Profiles and plugins

-Start the recommended local interface from the repository root:
+A profile is an ordered list of plugin bundles. The shipped `web` profile powers `dsh web`. Manage a profile with `dsh plugin --profile <name> <pnpm args>`, which forwards the remaining arguments to pnpm in that profile's directory:

 ```sh
-pnpm dsh web
+npx -p @deepseek-ai/dsh dsh plugin --profile web add <package>
+npx -p @deepseek-ai/dsh dsh plugin --profile web remove <package>
 ```

-The command builds the repository before starting the Web UI, which is served at `http://127.0.0.1:3080` by default.
+`add`, `remove`, `update`, `why`, and other pnpm commands work unchanged. The command initializes a missing profile before changing its packages and updates its bundle list from installed packages that declare `dsh.bundle`. See the [CLI reference](apps/cli/reference/README.md#plugin-management) for the exact behavior.

-### Profiles
-
-The source CLI boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/<name>`:
-
-```sh
-pnpm dsh --profile web                       # the browser UI
-pnpm dsh plugin --profile tui add <package>  # install a plugin into a custom profile
-pnpm dsh --profile tui                       # boot it
-```
-
-The [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer semantics, and config dump commands.
-
-### Headless
-
-Run one task, print the final answer, and exit:
-
-```sh
-pnpm dsh --profile headless "summarize this workspace"
-```
-
-### Automation and SDKs
-
-From a source checkout with `DEEPSEEK_API_KEY` in the environment or its root `.env`, start the ACP automation server:
-
-```sh
-pnpm run demo:acp
-```
-
-The [Python SDK](python/README.md) drives a bundled JSON-RPC runtime. The [examples](examples/README.md) cover the runnable headless, ACP, JSON-RPC, Code Mode, and self-referential compositions.
-
-## Why DeepSeek Harness
-
-Built-in capabilities cover file reading, editing, and search; shell and persistent PTY execution; reusable skills; task tracking, goals, plans, todos, and background tasks; subagents and workflows; sandboxing and approvals; settings and credentials; persistent, resumable, forkable, and queryable sessions; LSP and web access; context compaction; and telemetry. Each composition selects the subset appropriate to its surface. The Web UI includes Plan Mode.
-
- **Everything is a plugin.** Models, tools, policies, storage, context management, and interfaces are composable [Cordis plugins](docs/user/develop/basic/index.md), so deployments can extend or replace behavior without forking the agent loop. See the [architecture](docs/architecture.md) for the underlying design.
- **Runs are reconstructable.** Anything visible to the model is logged in the authoritative session stream; persistence, resume/fork/query, replay, telemetry, and UIs derive from the same events. See the [session-log architecture](docs/architecture.md#session-log).
- **Code Mode (opt-in).** It exposes a `run_code` tool and a generated TypeScript SDK; only program output re-enters model context. See [Code Mode](packages/core/tools/README.md#code-mode).
- **Self-referential Cordis tools are opt-in.** They let the agent inspect its live runtime and mount or unmount plugins while it runs. See the [Cordis tools](packages/self-modification/tool-cordis/README.md).
+The [CLI reference](apps/cli/README.md) covers headless execution and custom profiles. The [Python SDK](python/README.md) and [examples](examples/README.md) cover programmatic and custom compositions.

 ## Community

@@ -81,8 +60,6 @@ Start with the [development guide](docs/development.md) and read the [architectu

 For agents, follow [AGENTS.md](AGENTS.md).

-DeepSeek Harness is currently in internal testing.
-
 ## License

 [BSD 3-Clause](LICENSE)
@@ -12,64 +12,43 @@ DeepSeek Harness 正处于内部测试阶段，功能和接口可能发生变化

 为帮助诊断上报的问题，内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。

-## 从源码运行
+## 运行

-克隆本仓库，完成[依赖安装和 API 密钥配置](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key)，然后运行：
+安装 Node.js ^22.19 或 >= 24 和 pnpm 11，然后运行已发布的包：

 ```sh
+npx @deepseek-ai/dsh web
+```
+
+该命令会初始化 Web profile 并打印 Web UI 地址，默认地址为 `http://127.0.0.1:3080`。打开该地址，在**设置 → 模型**中添加 DeepSeek API 密钥，然后启动一个会话。调用目录是默认工作区；你可以尝试输入 `Summarize this repository and identify its main packages.`。
+
+下一步请阅读 [Web UI 指南](docs/user/guide/)。
+
+### 从源码运行
+
+如需改为运行仓库 checkout：
+
+```sh
+git clone https://github.com/deepseek-harness/deepseek-harness.git
+cd deepseek-harness
+pnpm install
 pnpm dsh web
 ```

-## 使用 DeepSeek Harness
+最后一条命令会构建仓库，并进入相同的 Web UI 路径。

-### Web UI
+## Profile 与插件

-请从仓库根目录启动推荐的本地界面：
+profile 是按顺序排列的插件 bundle 列表。随附的 `web` profile 为 `dsh web` 提供功能。使用 `dsh plugin --profile <name> <pnpm args>` 管理 profile；该命令会在对应 profile 目录中将剩余参数转发给 pnpm：

 ```sh
-pnpm dsh web
+npx -p @deepseek-ai/dsh dsh plugin --profile web add <package>
+npx -p @deepseek-ai/dsh dsh plugin --profile web remove <package>
 ```

-该命令会先构建仓库，再启动 Web UI。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。
+`add`、`remove`、`update`、`why` 等 pnpm 命令均可直接使用。该命令会先初始化不存在的 profile，再修改其中的包，并根据声明了 `dsh.bundle` 的已安装包更新 bundle 列表。准确行为见 [CLI 参考](apps/cli/reference/README.md#plugin-management)。

-### Profile
-
-源码 CLI（命令行界面）会启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/<name>` 中的自有覆盖层：
-
-```sh
-pnpm dsh --profile web                       # the browser UI
-pnpm dsh plugin --profile tui add <package>  # install a plugin into a custom profile
-pnpm dsh --profile tui                       # boot it
-```
-
-profile 布局、层语义与配置输出命令详见 [CLI（命令行界面）参考](apps/cli/README.md#profiles)。
-
-### Headless
-
-运行一项任务，打印最终答案后退出：
-
-```sh
-pnpm dsh --profile headless "summarize this workspace"
-```
-
-### 自动化与 SDK
-
-在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`，然后启动 ACP（Agent Client Protocol）自动化服务器：
-
-```sh
-pnpm run demo:acp
-```
-
-[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。
-
-## 为什么选择 DeepSeek Harness
-
-内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill（技能）、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩（context compaction），以及遥测。每个组合只选用适合其使用方式的能力子集。Web UI 包含 Plan Mode。
-
- **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均为可组合的 [Cordis 插件](docs/user/develop/basic/index.md)，部署方无需 fork agent loop（智能体循环）即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。
- **运行可重建。** 凡是模型可见的内容，都会记录在权威会话流中；持久化、恢复／fork／查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。
- **Code Mode（需显式启用）。** 它会提供 `run_code` 工具和生成的 TypeScript SDK，只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。
- **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时，并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/self-modification/tool-cordis/README.md)。
+[CLI（命令行界面）参考](apps/cli/README.md)介绍 headless 执行与自定义 profile。[Python SDK](python/README.md) 和[示例](examples/README.md)介绍程序化组合与自定义组合。

 ## 社区

@@ -85,8 +64,6 @@ pnpm run demo:acp

 面向 agent：遵循 [AGENTS.md](AGENTS.md)。

-DeepSeek Harness 目前处于内测阶段。
-
 ## 许可证

 [BSD 3-Clause](LICENSE)
@@ -25,13 +25,13 @@ Two planes, and the choice is not about how "agent-related" something feels —

 A preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name.

-Locally authored presets live one directory per preset under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. Both roots are configuration rather than fixed locations, though, and no call reports them — `authorable` says only whether a writable one exists — so take the path you actually read or edit from `list()` or `resolve()`, which is also where `copy()` reports what it just created.
+Locally authored presets live one directory per preset under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. A deployment can configure other roots, so the path you read or edit comes from `list()` or `resolve()` — which is also where `copy()` reports what it just created.

 ## The roster service

 `ctx.agentPresets` owns discovery, authoring, and mounting. You reach it by mounting a temporary plugin that injects it and registers a tool for yourself — `cordis_mount` returns only the mount acknowledgement, so a registered tool is how a service answer gets back to you, and it becomes callable on your next step.

-Read `cordis_inspect what:"api" name:"agentPresets"` for the current signatures before writing the code. The four calls this skill relies on:
+Read `cordis_inspect what:"api" name:"agentPresets"` for the current signatures before writing the code. What this skill relies on:

 - `list()` — every preset with its `id`, `trust` (`system` for the shipped set, `user` for authored ones), and the absolute `path` of its composition file. This is how you locate any composition without knowing the install layout; the directory is that path's parent.
 - `read(id)` — one preset's composition text, without a file tool or a path.
@@ -29,13 +29,11 @@ import {
  watchUserPatches,
  type Profile,
 } from '@deepseek-ai/dsh-app-boot'
-import { dshHomePath, resolveDshHome } from '@deepseek-ai/dsh-paths'
+import { resolveDshHome } from '@deepseek-ai/dsh-paths'

 /** Shipped agent-preset root: beside this app's own config, in both source and built layouts. */
 const SHIPPED_PRESET_ROOT = fileURLToPath(new URL('../config/agent-presets/', import.meta.url))

-/** Harness-home directory holding locally authored agent presets. */
-const USER_PRESET_DIR = '.agent-presets'
 import { DSH_ENVIRONMENT_KEY, type EnvironmentSnapshot } from '@deepseek-ai/dsh-environment'
 import { provideCmdline } from '@deepseek-ai/dsh-cmdline'
 import { createProcessShutdown, type ProcessShutdown } from './process-shutdown.ts'
@@ -154,16 +152,16 @@ function composeProfile(
    if (typeof row.id === 'string') rows.set(row.id, row)
  }
  const composedOverlays = [...overlays]
-  // Preset roots belong to every dsh composition that mounts the roster.
+  // The SHIPPED root is the part of the roster only this app can resolve: it
+  // sits beside this app's own config, in both the source and built layouts.
+  // The writable root the roster appends is `dsh-agent-presets`' own, so a
+  // launcher that never reaches this patch still finds a person's presets.
  if (rows.has('agent-presets')) {
    composedOverlays.push({
      id: 'agent-presets',
      config: {
        ...(rows.get('agent-presets')?.config ?? {}) as Record<string, unknown>,
-        roots: [
-          { path: SHIPPED_PRESET_ROOT, trust: 'system' },
-          { path: dshHomePath(USER_PRESET_DIR), trust: 'user' },
-        ],
+        roots: [{ path: SHIPPED_PRESET_ROOT, trust: 'system' }],
      },
    })
  }
@@ -227,8 +227,8 @@ function createStartupFixture(): StartupFixture {
    "export const inject = ['cmdlineArgs']",
    'export function apply(ctx) {',
    "  const program = new Command().name('fixture').option('--generation <value>', 'echoed generation')",
-    '  const values = parseCmdline(ctx, program, parsed => ({ generation: parsed.opts().generation }))',
-    '  if (values !== undefined) ctx.provide(\'fixtureStartup\', values)',
+    "  program.action(() => ctx.provide('fixtureStartup', { generation: program.opts().generation }))",
+    '  parseCmdline(ctx, program)',
    '}',
    '',
  ].join('\n'))
@@ -96,7 +96,11 @@ async function bootWeb(settingsFile: string, extra: PatchOptions[] = []): Promis
    // document overrides.
    {
      id: 'agent-presets',
-      config: { default: 'standard', roots: [{ path: join(CONFIG_DIR, 'agent-presets'), trust: 'system' }] },
+      config: {
+        default: 'standard',
+        roots: [{ path: join(CONFIG_DIR, 'agent-presets'), trust: 'system' }],
+        includeUserRoot: false,
+      },
    },
    ...extra,
  ]
@@ -442,6 +446,7 @@ describe('product subagent rows in user presets', () => {
          { path: join(CONFIG_DIR, 'agent-presets'), trust: 'system' },
          { path: userRoot, trust: 'user' },
        ],
+        includeUserRoot: false,
      },
    }])
  }, 120_000)
@@ -624,6 +629,66 @@ describe('a delegated child', () => {
  })
 })

+describe('a launcher that configures no writable root', () => {
+  // The claim this default exists for, asserted through the real shipped
+  // bundles rather than a hand-built context: `apps/cli` patches in only the
+  // system root, and a person's own presets are found anyway because the
+  // roster derives `<dshHome>/.agent-presets` itself. `$DSH_HOME` is pointed
+  // at a temp home BEFORE boot — the derived root is resolved when the plugin
+  // is constructed, and an unpinned run would read the developer's own.
+  let derivedCtx: Context
+  let previousHome: string | undefined
+
+  beforeAll(async () => {
+    const home = await mkdtemp(join(tmpdir(), 'dsh-preset-derived-'))
+    previousHome = process.env.DSH_HOME
+    process.env.DSH_HOME = home
+    await mkdir(join(home, '.agent-presets', 'derived-mine'), { recursive: true })
+    await writeFile(
+      join(home, '.agent-presets', 'derived-mine', 'agent.cordis.yml'),
+      '- id: tool-todo\n  name: \'@deepseek-ai/dsh-tool-todo\'\n  config:\n    allowParallelInProgress: true\n',
+    )
+    const settingsFile = join(await mkdtemp(join(tmpdir(), 'dsh-preset-derived-settings-')), 'settings.yaml')
+    await writeFile(settingsFile, '{}\n')
+    // Only the shipped root, exactly what `composeProfile` supplies; the
+    // writable one is the roster's own default rather than this patch's job.
+    derivedCtx = await bootWeb(settingsFile, [{
+      id: 'agent-presets',
+      config: {
+        default: 'standard',
+        roots: [{ path: join(CONFIG_DIR, 'agent-presets'), trust: 'system' }],
+        includeUserRoot: true,
+      },
+    }])
+  }, 120_000)
+
+  afterAll(async () => {
+    if (previousHome === undefined) delete process.env.DSH_HOME
+    else process.env.DSH_HOME = previousHome
+    await derivedCtx.fiber.dispose()
+  })
+
+  it('discovers and mounts a preset the person authored under the harness home', async () => {
+    const listed = await derivedCtx.agentPresets.list()
+
+    const mine = listed.find(preset => preset.id === 'derived-mine')
+    expect(mine).toMatchObject({ trust: 'user' })
+    // Omitted rather than undefined: a healthy row carries no `broken` key.
+    expect(mine?.broken).toBeUndefined()
+    expect(derivedCtx.agentPresets.authorable).toBe(true)
+
+    const handle = await derivedCtx.agents.create({
+      sessionId: SessionId('preset-derived-root'),
+      setup: agentCtx => derivedCtx.agentPresets.mount(agentCtx, 'derived-mine').then(() => undefined),
+    })
+    try {
+      expect(toolNames(derivedCtx, handle.agent)).toContain('todo_write')
+    } finally {
+      await handle.dispose()
+    }
+  })
+})
+
 describe('authoring a preset on the shipped composition', () => {
  let authorCtx: Context
  let userRoot: string
@@ -642,6 +707,7 @@ describe('authoring a preset on the shipped composition', () => {
          // nothing is the normal first-run state.
          { path: userRoot, trust: 'user' },
        ],
+        includeUserRoot: false,
      },
    }])
  })
@@ -21,7 +21,12 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn

  // The sidebar renders from the boot graph: every inject layer activated.
  const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
-  await within(tree).findByText('4 sessions')
+  // The compact layout dropped group session counts; the fixture workspace
+  // group row renders immediately with its sessions beneath it.
+  const fixtureGroup = (await within(tree).findAllByText('fixture'))
+    .map(el => el.closest<HTMLElement>('[role="treeitem"]'))
+    .find(el => el?.getAttribute('aria-expanded') !== null)
+  if (fixtureGroup === undefined) throw new Error('fixture Workspace group missing')

  // The resident fixture has both a question and an approval; composer routing
  // exposes the question first, and the assembled workspace plugin mirrors that
@@ -77,8 +77,13 @@ async function nextPaint(page: Page): Promise<void> {
 }

 async function openSeed(page: Page): Promise<void> {
-  await page.getByText(/^\d+ sessions?$/, { exact: true }).waitFor({ timeout: 30_000 })
-  const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
+  // The compact layout dropped group session counts; the seeded baseline is
+  // the Ungrouped bucket once cold summaries load.
+  await page.getByText('Ungrouped', { exact: true }).waitFor({ timeout: 30_000 })
+  // Search collapsed into a header action; expand it before filling.
+  const searchButton = page.getByRole('button', { name: 'Search sessions' })
+  if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+  const search = page.getByRole('textbox', { name: 'Search sessions...', exact: true })
  await search.fill(FIXTURE.markers.user(1))
  const results = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
  await results.first().waitFor({ timeout: 60_000 })
@@ -168,8 +168,10 @@ async function launchScrollWorld(options: ScrollWorldOptions): Promise<ScrollWor
    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
    // Session-list bootstrap can replace the controlled search state. Wait
-    // for the seeded baseline before openSeed starts the lazy content query.
-    await page.getByText(/^\d+ sessions?$/, { exact: true }).waitFor({ timeout: 30_000 })
+    // for the seeded baseline before openSeed starts the lazy content query
+    // (the compact layout dropped group session counts; the Ungrouped bucket
+    // row is the barrier).
+    await page.getByText('Ungrouped', { exact: true }).waitFor({ timeout: 30_000 })
    return {
      events,
      page,
@@ -258,7 +260,10 @@ async function conversationTurns(page: Page): Promise<number> {
 }

 async function openSeed(page: Page, fixture: ChatScrollFixture, tailMarker?: string): Promise<void> {
-  const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
+  // Search collapsed into a header action; expand it before filling.
+  const searchButton = page.getByRole('button', { name: 'Search sessions' })
+  if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+  const search = page.getByRole('textbox', { name: 'Search sessions...', exact: true })
  // Cold summaries initially show the temporary workspace basename, so the
  // persisted first-message marker is the stable user-facing identity. The
  // query itself triggers lazy content-index reconciliation; no transient
@@ -249,7 +249,10 @@ async function compareTabsWithoutReservation(page: Page): Promise<TabComparison>
 * @param page - the page under test.
 */
 async function openSeededSession(page: Page): Promise<void> {
-  const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
+  // Search collapsed into a header action; expand it before filling.
+  const searchButton = page.getByRole('button', { name: 'Search sessions' })
+  if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+  const search = page.getByRole('textbox', { name: 'Search sessions...', exact: true })
  await search.fill(FIXTURE.markers.user(1))
  const results = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
  const deadline = Date.now() + 60_000
@@ -197,8 +197,13 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
  it.skipIf(MODE === 'record')('materialized a real Workspace and Session over the wire', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-lifecycle-materialize'))
    // Browser: the sidebar tree now carries the auto-created workspace group
-    // with its one session, and the opened session is the selected row.
-    await expect.poll(() => page.getByText('1 session', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
+    // with its one session, and the opened session is the selected row. The
+    // compact layout dropped group session counts, so the group row itself is
+    // the barrier.
+    await expect.poll(
+      () => page.locator('[role="treeitem"][aria-expanded]').filter({ hasText: 'workspace' }).count(),
+      { timeout: 15_000 },
+    ).toBeGreaterThanOrEqual(1)
    await expect.poll(() => page.locator('[role="treeitem"][aria-selected="true"]').count(), { timeout: 10_000 }).toBe(1)
    await expect.poll(() => page.getByText('LIGHTHOUSE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
    // Host: the session's durable header cwd is the folder the workspace
@@ -53,7 +53,10 @@ async function assertBaselineSucceeded(response: Response, method: string): Prom

 async function ensureSeedOpen(page: Page): Promise<void> {
  const chat = page.getByRole('tab', { name: 'Chat', exact: true })
-  const search = page.getByPlaceholder('Search name, keywords', { exact: false })
+  // Search is a collapsed header action; expand it so the input is actionable.
+  const searchButton = page.getByRole('button', { name: 'Search sessions' })
+  if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+  const search = page.getByPlaceholder('Search sessions', { exact: false })
  if (await chat.count() === 0) {
    await search.fill('WATERFALL')
    const result = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
@@ -119,8 +122,9 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
    // The frame mounts before the asynchronous session-list baseline lands.
    // Search must target the settled seeded row, not the startup input that
-    // the ready projection replaces.
-    await page.getByText('1 session', { exact: true }).waitFor({ timeout: 30_000 })
+    // the ready projection replaces (the compact layout dropped group session
+    // counts; the Ungrouped bucket row is the barrier).
+    await page.getByText('Ungrouped', { exact: true }).waitFor({ timeout: 30_000 })
  }, 120_000)

  afterEach(async () => {
@@ -176,9 +180,13 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
  it.skipIf(MODE === 'record')('finds an unopened seeded session by message content and opens it', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search'))
    // The API baselines can settle before React commits their projection. The
-    // seeded count is the final user-visible barrier before editing search.
-    await page.getByText('1 session', { exact: true }).waitFor({ timeout: 30_000 })
-    const search = page.getByPlaceholder('Search name, keywords', { exact: false })
+    // seeded Ungrouped bucket row is the final user-visible barrier before
+    // editing search (the compact layout dropped group session counts).
+    await page.getByText('Ungrouped', { exact: true }).waitFor({ timeout: 30_000 })
+    // Search is a collapsed header action; expand it so the input is actionable.
+    const searchButton = page.getByRole('button', { name: 'Search sessions' })
+    if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+    const search = page.getByPlaceholder('Search sessions', { exact: false })
    // The cold row has not been opened, so only the persisted log can satisfy
    // this query. First search lazily reconciles the SQLite content index.
    await search.fill('zzzqx-no-such-session')
@@ -0,0 +1,128 @@
+// Keyless browser e2e: a user who configures some OTHER provider is not asked
+// for the official DeepSeek key again, and the first-run setup card is a card
+// they can close. The shipped DeepSeek adapter stays mounted without a
+// credential throughout, so the only thing that ends onboarding here is the
+// pi-ai route the user configures through the real wire. Zero model calls:
+// configuration is pure settings/credentials/llm-domain traffic.
+import { readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import {
+  acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
+  launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/onboarding-usable-provider', import.meta.url))
+const DISMISSED_EXPECTED = join(SNAPSHOT_DIR, 'dismissed.expected.md')
+const MODE = webSnapshotMode()
+const CREDENTIAL_STEP = '添加一个 API Key 开始使用'
+
+describe.skipIf(MODE === 'record')('web e2e: another usable provider ends first-run onboarding', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({ deepSeekMissingCredential: true })
+    browser = await chromium.launch()
+    // The scenario asserts the shipped Chinese copy, so the browser asks for it.
+    page = await browser.newPage({ viewport: { width: 1440, height: 960 }, locale: ZH_BROWSER_LOCALE })
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('closes the setup card without discarding the add card beside it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-setup-card-cancel'))
+    const credentialStep = page.getByRole('region', { name: CREDENTIAL_STEP })
+    await credentialStep.waitFor({ timeout: 15_000 })
+    await credentialStep.getByRole('button', { name: '前往配置' }).click()
+    await credentialStep.waitFor({ state: 'detached', timeout: 15_000 })
+
+    const settings = page.getByRole('dialog', { name: '设置' })
+    await settings.waitFor({ timeout: 10_000 })
+    // Nothing is reachable yet, so DeepSeek presents itself as its open card.
+    const setupKey = settings.getByRole('textbox', { name: 'API 密钥', exact: true })
+    await setupKey.waitFor({ timeout: 10_000 })
+
+    const add = settings.getByRole('button', { name: '添加提供方' })
+    await expect.poll(async () => add.isEnabled(), { timeout: 10_000 }).toBe(true)
+    await add.click()
+    const pick = settings.getByLabel('提供方')
+    await pick.waitFor({ timeout: 10_000 })
+    await pick.selectOption('minimax-cn')
+    await expect.poll(
+      async () => settings.getByRole('textbox', { name: 'API 密钥', exact: true }).count(),
+      { timeout: 10_000 },
+    ).toBe(2)
+
+    // Cancelling the setup card is the regression: it used to leave itself open
+    // and close the add card, discarding that draft.
+    await settings.getByRole('button', { name: '取消', exact: true }).first().click()
+    expect(await settings.getByLabel('提供方').count()).toBe(1)
+    await expect.poll(
+      async () => settings.getByRole('textbox', { name: 'API 密钥', exact: true }).count(),
+      { timeout: 10_000 },
+    ).toBe(1)
+    // DeepSeek is now an ordinary row: a missing-key dot and an Edit button.
+    await settings.getByRole('button', { name: '编辑 DeepSeek (deepseek-official)' }).waitFor({ timeout: 10_000 })
+    const dismissed = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(DISMISSED_EXPECTED, dismissed, MODE)
+
+    expect(tripwire.warnings).toEqual([])
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('stops prompting for DeepSeek once the other provider can serve requests', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-other-provider'))
+    const settings = page.getByRole('dialog', { name: '设置' })
+    await settings.getByRole('textbox', { name: 'API 密钥', exact: true }).fill('sk-e2e-minimax')
+    await settings.getByRole('button', { name: '保存', exact: true }).click()
+    await settings.getByText('已保存 minimax-cn。', { exact: true }).waitFor({ timeout: 15_000 })
+
+    // Only minimax-cn is reachable; DeepSeek still holds no credential.
+    const document = await readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8')
+    expect(document).toContain('apiKeyEnv: MINIMAX_CN_API_KEY')
+    const credentials = await readFile(join(scaffold.harnessHome, '.credentials.yaml'), 'utf8')
+    expect(credentials).toContain('MINIMAX_CN_API_KEY: sk-e2e-minimax')
+    expect(credentials).not.toContain('DEEPSEEK_API_KEY')
+
+    const warningsBefore = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    acknowledgeReloadConnectionLoss(tripwire, warningsBefore)
+    await page.waitForSelector('[class*="frame"]', { timeout: 15_000 })
+    // The regression: the step read only the official route's credential, so a
+    // fully configured user was taken over on every blank session.
+    await expect.poll(
+      async () => page.getByRole('region', { name: CREDENTIAL_STEP }).count(),
+      { timeout: 10_000 },
+    ).toBe(0)
+    expect(await page.locator('[class*="onboardingStage"]').count()).toBe(0)
+    expect(await page.locator('#root').evaluate(root => (root as HTMLElement).inert)).toBe(false)
+
+    // The Models page agrees: DeepSeek stays a row rather than reopening its
+    // setup card over a user who already has somewhere to send a request.
+    await page.getByRole('button', { name: '设置', exact: true }).click()
+    await settings.waitFor({ timeout: 10_000 })
+    await settings.getByRole('button', { name: '模型' }).click()
+    await settings.getByRole('button', { name: '编辑 DeepSeek (deepseek-official)' }).waitFor({ timeout: 10_000 })
+    expect(await settings.getByRole('textbox', { name: 'API 密钥', exact: true }).count()).toBe(0)
+
+    expect((await page.content()).includes('sk-e2e-minimax')).toBe(false)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('keeps the fixture inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['dismissed.expected.md'])
+  })
+})
@@ -68,8 +68,11 @@ describe.skipIf(MODE === 'record' || !HAS_PWSH)('web e2e: pwsh calls use the bas
    onTestFailed(() => saveFailureShot(page, 'web-e2e-pwsh-terminal'))
    // Open the seeded session through content search: the sidebar groups
    // sessions by workspace and its row order is world-dependent, while the
-    // search index covers the seeded log deterministically.
-    const search = page.getByPlaceholder('Search name, keywords', { exact: false })
+    // search index covers the seeded log deterministically. Search is a
+    // collapsed header action; expand it so the input is actionable.
+    const searchButton = page.getByRole('button', { name: 'Search sessions' })
+    if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+    const search = page.getByPlaceholder('Search sessions', { exact: false })
    await search.fill('Run a PowerShell command')
    const result = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
    await expect.poll(() => result.count(), { timeout: 15_000 }).toBe(1)
@@ -385,7 +385,11 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
    // able to change a golden.
    {
      id: 'agent-presets',
-      config: { default: 'standard', roots: [{ path: SHIPPED_PRESET_DIR, trust: 'system' }] },
+      config: {
+        default: 'standard',
+        roots: [{ path: SHIPPED_PRESET_DIR, trust: 'system' }],
+        includeUserRoot: false,
+      },
    },
    { id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
    { id: 'session-query-sqlite', config: { path: ':memory:', openAt: 'first-search' } },
@@ -445,7 +449,9 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
    ] },
    ...options.agentPresets === undefined
      ? []
-      : [{ id: 'agent-presets', config: options.agentPresets }],
+      // Never the derived harness-home root: a developer's own presets must not
+      // be able to change a golden, whatever roots a scenario asks for.
+      : [{ id: 'agent-presets', config: { ...options.agentPresets, includeUserRoot: false } }],
    ...options.toolsMode === undefined ? [] : [{ id: 'tools', config: { mode: options.toolsMode } }],
    ...options.cordisTools === true
      ? [{ insert: [{ id: 'tool-cordis', name: 'cordis:tool-cordis' }] }]
@@ -349,9 +349,9 @@ async function pointAt(page: Page, where: 'list' | 'away'): Promise<void> {

 /**
 * Reveal the seeded rows: every seeded session is unattached, so they all sit
- * in the collapsed Ungrouped bucket. Converges on expanded rather than
- * clicking once — startup auto-selection can expand the bucket first, and a
- * second click would collapse it again. Hand-rolled polling because
+ * in the collapsed Ungrouped bucket. Open the bucket, then use its transient
+ * Show-more control because an open group intentionally renders only five
+ * rows by default. Hand-rolled polling because
 * `expect.poll` is test-scoped and this runs in `beforeAll`.
 * @param page - the page under test.
 */
@@ -364,6 +364,12 @@ async function expandSeededSessions(page: Page): Promise<void> {
    if (await bucket.getAttribute('aria-expanded') !== 'true') {
      await page.getByText('Ungrouped', { exact: true }).click()
    }
+    const showMore = page.getByRole('button', { name: /Show \d+ more sessions/ })
+    if (await bucket.getAttribute('aria-expanded') === 'true'
+      && await rows.count() <= SEED_COUNT / 2
+      && await showMore.count() > 0) {
+      await showMore.click()
+    }
    if (await bucket.getAttribute('aria-expanded') === 'true' && await rows.count() > SEED_COUNT / 2) return
    if (Date.now() > deadline) {
      throw new Error(`Ungrouped bucket never revealed more than ${SEED_COUNT / 2} rows`)
@@ -5,17 +5,17 @@
  - img
  - text: New Session
 - text: Workspaces
- button "Group by":
+- button "Search sessions":
+  - img
+- textbox "Search sessions..."
+- button "View options":
  - img
 - button "Add workspace":
  - img
- button "Search sessions":
-  - img
- textbox "Search name, keywords..."
 - tree "Sessions":
-  - treeitem "workspace 1 session" [expanded]:
+  - treeitem "workspace" [expanded]:
    - img
-    - text: workspace 1 session
+    - text: workspace
  - treeitem "New Session" [selected]
 - button "Settings":
  - img
@@ -5,17 +5,17 @@
  - img
  - text: New Session
 - text: Workspaces
- button "Group by":
+- button "Search sessions":
+  - img
+- textbox "Search sessions..."
+- button "View options":
  - img
 - button "Add workspace":
  - img
- button "Search sessions":
-  - img
- textbox "Search name, keywords..."
 - tree "Sessions":
-  - treeitem "workspace 1 session" [expanded]:
+  - treeitem "workspace" [expanded]:
    - img
-    - text: workspace 1 session
+    - text: workspace
  - treeitem "New Session" [selected]
 - button "Settings":
  - img
@@ -1,7 +1,7 @@
 - tree "Sessions":
-  - treeitem "Ungrouped 3 sessions" [expanded]:
+  - treeitem "Ungrouped" [expanded]:
    - img
-    - text: Ungrouped 3 sessions
-  - treeitem "Use the read tool twice (2) now" [selected]
-  - treeitem "Use the read tool twice (1) now"
+    - text: Ungrouped
  - treeitem "Use the read tool twice 1min"
+  - treeitem "Use the read tool twice (1) now"
+  - treeitem "Use the read tool twice (2) now" [selected]
@@ -0,0 +1,71 @@
+- dialog "设置":
+  - navigation:
+    - text: 设置
+    - button "通用设置":
+      - img
+      - text: 通用设置
+    - button "模型":
+      - img
+      - text: 模型
+    - button "Agent 预设":
+      - img
+      - text: Agent 预设
+    - button "插件配置":
+      - img
+      - text: 插件配置
+  - button "打开配置文件"
+  - button "关闭":
+    - img
+    - text: 关闭
+  - heading "模型" [level=2]
+  - paragraph: 填入各提供方的 API 密钥即可使用其模型。
+  - list:
+    - listitem:
+      - text: DeepSeek
+      - img "API 密钥缺失"
+      - button "编辑 DeepSeek (deepseek-official)": 编辑
+  - text: 提供方
+  - combobox "提供方":
+    - option "amazon-bedrock"
+    - option "ant-ling"
+    - option "anthropic"
+    - option "azure-openai-responses"
+    - option "cerebras"
+    - option "cloudflare-ai-gateway"
+    - option "cloudflare-workers-ai"
+    - option "deepseek"
+    - option "fireworks"
+    - option "github-copilot"
+    - option "google"
+    - option "google-vertex"
+    - option "groq"
+    - option "huggingface"
+    - option "kimi-coding"
+    - option "minimax"
+    - option "minimax-cn" [selected]
+    - option "mistral"
+    - option "moonshotai"
+    - option "moonshotai-cn"
+    - option "nvidia"
+    - option "openai"
+    - option "openai-codex"
+    - option "opencode"
+    - option "opencode-go"
+    - option "openrouter"
+    - option "qwen-token-plan"
+    - option "qwen-token-plan-cn"
+    - option "together"
+    - option "vercel-ai-gateway"
+    - option "xai"
+    - option "xiaomi"
+    - option "xiaomi-token-plan-ams"
+    - option "xiaomi-token-plan-cn"
+    - option "xiaomi-token-plan-sgp"
+    - option "zai"
+    - option "zai-coding-cn"
+  - text: API 密钥
+  - textbox "API 密钥":
+    - /placeholder: 输入 API 密钥，或留空使用环境认证
+  - group: 自定义设置
+  - button "取消"
+  - button "保存"
@@ -1,6 +1,6 @@
 - tree "Sessions":
-  - treeitem "workspace 2 sessions" [expanded]:
+  - treeitem "workspace" [expanded]:
    - img
-    - text: workspace 2 sessions
-  - treeitem "1 subagent running Delegate a background task. now"
+    - text: workspace
  - treeitem "New Session" [selected]
+  - treeitem "1 subagent running Delegate a background task. now"
@@ -1,6 +1,6 @@
 - tree "Sessions":
-  - treeitem "workspace 2 sessions" [expanded]:
+  - treeitem "workspace" [expanded]:
    - img
-    - text: workspace 2 sessions
-  - treeitem "Explain event sourcing in one (1) now" [selected]
+    - text: workspace
  - treeitem "Ask a research subagent to now"
+  - treeitem "Explain event sourcing in one (1) now" [selected]
@@ -1,5 +1,5 @@
 - tree "Sessions":
-  - treeitem "workspace 1 session" [expanded]:
+  - treeitem "workspace" [expanded]:
    - img
-    - text: workspace 1 session
+    - text: workspace
  - treeitem "Ask a research subagent to now"
@@ -31,6 +31,8 @@ const ONE_SHOT_LABEL = 'event-sourcing reviewer'
 const NESTED_LABEL = 'example editor'
 const PARENT_PROMPT = 'Ask a research subagent to explain event sourcing.'
 const INITIAL_PROMPT = 'Explain event sourcing in one sentence.'
+/** The grandchild's own first message; its arrival is what says its history finished loading. */
+const NESTED_PROMPT = 'Give one concrete event sourcing example.'
 const FOLLOWUP = 'Now give the same explanation to a human reader.'
 const POST_FORK_FOLLOWUP = 'Continue the original conversation after the fork.'

@@ -176,7 +178,7 @@ describe('web e2e: persisted subagent conversation and human continuation', () =
        seq: 1,
        time: authoredAt + 1,
        data: {
-          content: [{ type: 'text', text: 'Give one concrete event sourcing example.' }],
+          content: [{ type: 'text', text: NESTED_PROMPT }],
          source: { kind: 'user' },
        },
        surfaceOp: 'append',
@@ -404,6 +406,11 @@ describe('web e2e: persisted subagent conversation and human continuation', () =
    )
    await nestedRow.click()
    await page.getByText('The parent session is offline; reopen it to continue sending messages.').waitFor()
+    // The offline banner renders from the descriptor alone, so it says nothing
+    // about the transcript below it. The golden pins that transcript, and
+    // `captureStableAria` calls two identical polls stable — including two of
+    // "Loading history…". Wait for the message the golden asserts.
+    await page.getByText(NESTED_PROMPT).waitFor()
    const hierarchy = page.getByRole('navigation', { name: 'Session hierarchy' })
    const crumbs = await hierarchy.getByRole('button').allTextContents()
    expect(crumbs.slice(-2)).toEqual([LABEL, NESTED_LABEL])
@@ -59,7 +59,10 @@ interface RowAnchor {
 }

 async function openSeed(page: Page): Promise<void> {
-  const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
+  // Search collapsed into a header action; expand it before filling.
+  const searchButton = page.getByRole('button', { name: 'Search sessions' })
+  if (await searchButton.getAttribute('aria-expanded') !== 'true') await searchButton.click()
+  const search = page.getByRole('textbox', { name: 'Search sessions...', exact: true })
  await search.fill(FIXTURE.markers.user(1))
  const result = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
  await expect.poll(() => result.count(), { timeout: 60_000 }).toBe(1)
@@ -182,7 +185,9 @@ describe('web e2e: Trajectory virtualization over tail-paged history', () => {
    tripwire = watchConsole(page)
    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await page.getByText('1 session', { exact: true }).waitFor({ timeout: 30_000 })
+    // The compact layout dropped group session counts; the seeded baseline is
+    // the Ungrouped bucket once cold summaries load.
+    await page.getByText('Ungrouped', { exact: true }).waitFor({ timeout: 30_000 })
  }, 120_000)

  afterAll(async () => {
@@ -74,12 +74,16 @@ describe.skipIf(MODE === 'record')('web e2e: durable workflow run in Chat', () =
    await input.fill(prompt)
    await input.press('Enter')

-    const workflow = page.getByRole('button', { name: /^snapshot-flow/ })
+    const workflow = page.locator('[data-workflow-run][data-run-status="running"]')
    await workflow.waitFor({ timeout: 30_000 })
-    expect(await workflow.getAttribute('aria-expanded')).toBe('true')
-    const phase = page.getByRole('button', { name: /^Run/ })
-    await phase.waitFor({ timeout: 15_000 })
-    await phase.click()
+    const disclosures = workflow.locator('[data-disclosure-row]')
+    await disclosures.nth(1).waitFor({ timeout: 15_000 })
+    expect(await disclosures.nth(0).getAttribute('role')).toBeNull()
+    expect(await disclosures.nth(0).getAttribute('aria-expanded')).toBeNull()
+    expect(await disclosures.nth(1).getAttribute('role')).toBeNull()
+    expect(await disclosures.nth(1).getAttribute('aria-expanded')).toBeNull()
+    expect(await disclosures.nth(0).evaluate(element => getComputedStyle(element).cursor)).not.toBe('pointer')
+    expect(await disclosures.nth(1).evaluate(element => getComputedStyle(element).cursor)).not.toBe('pointer')
    const member = page.getByRole('button', { name: /^Open Reply with exactly the word/ })
    await member.waitFor({ timeout: 15_000 })
    await member.focus()
@@ -139,15 +143,20 @@ describe.skipIf(MODE === 'record')('web e2e: durable workflow run in Chat', () =
    const sessions = page.getByRole('tree', { name: 'Sessions' })
    await sessions.getByRole('treeitem', { name: /Use the workflow tool exactly/ }).click()
    await settled
+    await page.locator('[data-workflow-run][data-run-status="completed"]').waitFor()

    expect(await page.locator('[data-chat-flow-kind="tool-call"]').count()).toBeGreaterThanOrEqual(1)
    expect(await page.locator('[data-chat-flow-kind="workflow-run"]').count()).toBe(1)
    const terminalWorkflow = page.getByRole('button', { name: /^snapshot-flow/ })
    await terminalWorkflow.waitFor()
-    if (await terminalWorkflow.getAttribute('aria-expanded') !== 'true') await terminalWorkflow.click()
+    expect(await terminalWorkflow.getAttribute('aria-expanded')).toBe('false')
+    expect(await terminalWorkflow.evaluate(element => getComputedStyle(element).cursor)).toBe('pointer')
+    await terminalWorkflow.click()
    const terminalPhase = page.getByRole('button', { name: /^Run/ })
    await terminalPhase.waitFor()
-    if (await terminalPhase.getAttribute('aria-expanded') !== 'true') await terminalPhase.click()
+    expect(await terminalPhase.getAttribute('aria-expanded')).toBe('false')
+    expect(await terminalPhase.evaluate(element => getComputedStyle(element).cursor)).toBe('pointer')
+    await terminalPhase.click()
    await page.getByText(CHILD_PROMPT, { exact: false }).waitFor()
    await expect.poll(
      () => page.getByRole('button', { name: /^Open Reply with exactly the word/ }).count(),
@@ -165,6 +174,7 @@ describe.skipIf(MODE === 'record')('web e2e: durable workflow run in Chat', () =
    await workflow.click()
    const phase = page.getByRole('button', { name: /^Run/ })
    await phase.waitFor()
+    expect(await phase.getAttribute('aria-expanded')).toBe('false')
    await phase.click()
    await page.getByText(CHILD_PROMPT, { exact: false }).waitFor()
    expect(await page.getByRole('button', { name: /^Open Reply with exactly the word/ }).count()).toBe(0)
@@ -372,21 +372,22 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff
    // Grouped default: workspace group rows render (the seeded session sits
    // under Ungrouped; the created workspaces are empty groups).
    await expect.poll(() => page.getByText('Workspaces', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
-    await page.getByRole('button', { name: 'Group by' }).click()
+    // Grouping and ordering moved into the View options menu.
+    await page.getByRole('button', { name: 'View options' }).click()
    await page.getByRole('menuitem', { name: 'In one list' }).click()
    // Flat mode: the section label flips and the seeded session is a
    // top-level row with no group headers above it.
    await expect.poll(() => page.getByText('Sessions', { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
    await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 5_000 }).toBe(0)
    await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
-    expect(await page.evaluate(() => localStorage.getItem('dsh.workspace.view'))).toContain('flat')
+    expect(await page.evaluate(() => localStorage.getItem('dsh.workspace.view.v4'))).toContain('flat')
    // Persisted across reload; then restore grouped for inter-spec hygiene.
    const warningStart = tripwire.warnings.length
    await page.reload({ waitUntil: 'load' })
    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
    acknowledgeReloadConnectionLoss(tripwire, warningStart)
    await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 15_000 }).toBe(0)
-    await page.getByRole('button', { name: 'Group by' }).click()
+    await page.getByRole('button', { name: 'View options' }).click()
    await page.getByRole('menuitem', { name: 'WorkSpace' }).click()
    await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
    expect(tripwire.pageErrors).toEqual([])
@@ -42,6 +42,7 @@
    "tests/default-model.e2e.ts",
    "tests/declared-reasoning.e2e.ts",
    "tests/onboarding-deepseek-config.e2e.ts",
+    "tests/onboarding-usable-provider.e2e.ts",
    "tests/remote-welcome.e2e.ts",
    "tests/workspace-management.e2e.ts",
    "tests/replay-round-trip.e2e.ts",
@@ -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 docs/config-catalog.md
-config-catalog.md: e7ab120218c6de909bbd799c19b38eef524c7555
-config-catalog.zh.md: 622a0372de2f194e7063312ad7b8343a0bc58f06
+config-catalog.md: 2bb1f315e02c3f4bab379593227f1c381818a9fa
+config-catalog.zh.md: 4be51942de65a7e8afdaf71a44573ba1cdd6230d
@@ -135,6 +135,11 @@ export interface Config {
  default: string
  /** Scanned roots in precedence order; an earlier root wins a duplicate id. */
  roots: PresetRoot[]
+  /**
+   * Append the harness home's `USER_PRESET_DIR` as a `user` root, after every
+   * configured root. False mounts a roster over `roots` alone.
+   */
+  includeUserRoot: boolean
 }

 /** One directory scanned for preset subdirectories. */
@@ -137,6 +137,11 @@ export interface Config {
  default: string
  /** Scanned roots in precedence order; an earlier root wins a duplicate id. */
  roots: PresetRoot[]
+  /**
+   * Append the harness home's `USER_PRESET_DIR` as a `user` root, after every
+   * configured root. False mounts a roster over `roots` alone.
+   */
+  includeUserRoot: boolean
 }

 /** One directory scanned for preset subdirectories. */
@@ -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 docs/cordis-tutorial/index.md
-index.md: fb700344e6d07d3864655009d2edac15ee9eede8
-index.zh.md: a68e931d81e745164d8f9a5dc7ec9aec4cd0e590
+index.md: a10a0f93fde4f710af2ab14f74b854ee07d7c03f
+index.zh.md: fb2c4f0959eab8c7a072c44207943c31b0bed8ea
@@ -10,7 +10,7 @@ If you want the condensed concept reference instead of a walkthrough, read the [

 ## Setup

-You need a clone of this repository with dependencies installed — the [quick start](../user/guide/quickstart.md) covers prerequisites. No API key is needed for this tutorial; every example runs keylessly.
+You need a clone of this repository with dependencies installed; the [development guide](../development.md#setup-tutorial) lists the prerequisites. No API key is needed for this tutorial; every example runs keylessly.

 ```sh
 git clone https://github.com/deepseek-ai/deepseek-harness.git
@@ -10,7 +10,7 @@ Cordis 是 DeepSeek Harness SDK 底层的插件框架：它是一个小型运行

 ## 准备工作

-你需要克隆本仓库并安装依赖，具体前置条件见[快速入门](../user/guide/quickstart.md)。本教程不需要 API 密钥；所有示例均可在无密钥环境中运行。
+你需要克隆本仓库并安装依赖；[开发指南](../development.md#setup-tutorial)列出了前置条件。本教程不需要 API 密钥；所有示例均可在无密钥环境中运行。

 ```sh
 git clone https://github.com/deepseek-ai/deepseek-harness.git
@@ -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 docs/subsystems/core.md
-core.md: e52a7619085b2956496be6234f711441902fc259
-core.zh.md: e9cfe19129e33a1c17e87561397b13139a6d7537
+core.md: 2e89bac4c0468c094814aa7137381f4be569fc29
+core.zh.md: 2a8a35bb46adf28fd2ba07d0a319cdca0cbb4a2f
@@ -546,7 +546,7 @@ async standingKeyFor(id?: string): Promise<ScopeKey>

 Types: [ScopeKey](scope.md)

-Source: [`packages/preset/agent-presets/src/index.ts:81`](../../packages/preset/agent-presets/src/index.ts)
+Source: [`packages/preset/agent-presets/src/index.ts:82`](../../packages/preset/agent-presets/src/index.ts)

 <a id="ctxagents--agentregistry"></a>

@@ -554,7 +554,7 @@ async standingKeyFor(id?: string): Promise<ScopeKey>

 Types: [ScopeKey](scope.md)

-Source: [`packages/preset/agent-presets/src/index.ts:81`](../../packages/preset/agent-presets/src/index.ts)
+Source: [`packages/preset/agent-presets/src/index.ts:82`](../../packages/preset/agent-presets/src/index.ts)

 <a id="ctxagents--agentregistry"></a>

@@ -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 docs/subsystems/workspace.md
-workspace.md: 7bd5fda31e5d5c29d7446589b9af2679a46cba9a
-workspace.zh.md: 288b9468cc9e75613ab89efbe516eb287dae0441
+workspace.md: 480279cf4ed2c7a0005ea6a8ca8f58c208219e86
+workspace.zh.md: 6d9a9ad5dab1d11ea61fb0274ea3a91eb8929c5a
@@ -194,6 +194,15 @@ list(): Workspace[]
 */
 delete(id: WorkspaceId): Promise<boolean>

+/**
+ * Move one workspace within the durable display order, DOM-insertBefore-like.
+ * With an anchor it lands before that workspace; without one it appends.
+ * @param id - Workspace to move.
+ * @param beforeId - Workspace anchor; omitted appends.
+ * @returns the complete committed workspace order.
+ */
+insertBefore(id: WorkspaceId, beforeId?: WorkspaceId): Promise<readonly WorkspaceId[]>
+
 /**
 * Archive one session durably. The session must exist (live or in session
 * persistence); its workspace accounting — or lack of one — is irrelevant.
@@ -215,5 +224,5 @@ async resolveByPath(path: string): Promise<Workspace | undefined>

 Types: [SessionId](core.md)

-Source: [`packages/workspace/workspace/src/index.ts:81`](../../packages/workspace/workspace/src/index.ts)
+Source: [`packages/workspace/workspace/src/index.ts:92`](../../packages/workspace/workspace/src/index.ts)
 <!-- END GENERATED cordis-surface -->
@@ -194,6 +194,15 @@ list(): Workspace[]
 */
 delete(id: WorkspaceId): Promise<boolean>

+/**
+ * Move one workspace within the durable display order, DOM-insertBefore-like.
+ * With an anchor it lands before that workspace; without one it appends.
+ * @param id - Workspace to move.
+ * @param beforeId - Workspace anchor; omitted appends.
+ * @returns the complete committed workspace order.
+ */
+insertBefore(id: WorkspaceId, beforeId?: WorkspaceId): Promise<readonly WorkspaceId[]>
+
 /**
 * Archive one session durably. The session must exist (live or in session
 * persistence); its workspace accounting — or lack of one — is irrelevant.
@@ -215,5 +224,5 @@ async resolveByPath(path: string): Promise<Workspace | undefined>

 Types: [SessionId](core.md)

-Source: [`packages/workspace/workspace/src/index.ts:81`](../../packages/workspace/workspace/src/index.ts)
+Source: [`packages/workspace/workspace/src/index.ts:92`](../../packages/workspace/workspace/src/index.ts)
 <!-- END GENERATED cordis-surface -->
@@ -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 docs/user/develop/basic/index.md
-index.md: e57a42b42690bd92450cc26876c13a1622bb80cc
-index.zh.md: 240623341618acd6501f2897ae2844fde0a5b73b
+index.md: 71b5bd5ef5d296999420c40d3b8c9cf46c918841
+index.zh.md: 5dafe8bf0938337fa1f38634088acf00a2fcab46
@@ -2,7 +2,7 @@

 English | [中文](index.zh.md)

-This tutorial creates a minimal Harness plugin and loads it into the Web UI. Start from a repository checkout that has completed the [quick start](../../guide/quickstart.md).
+This tutorial creates a minimal Harness plugin and loads it into the Web UI. Start from a repository checkout that has completed the [run-from-source path](../../../../README.md#run-from-source).

 ## Create a local project

@@ -2,7 +2,7 @@

 [English](index.md) | 中文

-本教程会创建一个最小的 Harness 插件，并将其加载到 Web UI 中。请从已完成[快速开始](../../guide/quickstart.md)的仓库检出开始。
+本教程会创建一个最小的 Harness 插件，并将其加载到 Web UI 中。请从已完成[从源码运行路径](../../../../README.md#run-from-source)的仓库检出开始。

 ## 创建本地项目

@@ -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 docs/user/develop/basic/publish.md
-publish.md: 8437c7ea5c4cb966f9f3d68977949c78986ec9a5
-publish.zh.md: 4409dbfda060a84b316029d87ec985209cfa286a
+publish.md: 588531a28020ebe620643cd1aaaa43de000e658a
+publish.zh.md: 938e4b0aa2ea09f80fce897413e9c57f90d3209a
@@ -117,7 +117,7 @@ A bundle that defines a runnable app mounts an ordinary provider plugin:
  name: 'dsh-hello-plugin/startup'
 ```

-The plugin exports `inject = ['cmdlineArgs']`, calls `parseCmdline` from [`@deepseek-ai/dsh-cmdline`](../../../../packages/boot/cmdline/README.md) with its own commander program, and provides the returned value as its app-owned service. The launcher hands every plugin the same immutable arguments after launcher flags, so app-specific flags need no launcher change and multiple plugins may parse the snapshot. The Loader row needs no launcher marker or special kind.
+The plugin exports `inject = ['cmdlineArgs']`, calls `parseCmdline` from [`@deepseek-ai/dsh-cmdline`](../../../../packages/boot/cmdline/README.md) with its own commander program, and provides its app-owned service from the program's action. The launcher hands every plugin the same immutable arguments after launcher flags, so app-specific flags need no launcher change and multiple plugins may parse the snapshot. The Loader row needs no launcher marker or special kind.

 Rows configured by those arguments inject the provider's service and read it from their own `!!js` options, with the deployment value beside it as the fallback:

@@ -117,7 +117,7 @@ dsh --profile demo
  name: 'dsh-hello-plugin/startup'
 ```

-该插件导出 `inject = ['cmdlineArgs']`，使用自己的 commander program 调用 [`@deepseek-ai/dsh-cmdline`](../../../../packages/boot/cmdline/README.md) 中的 `parseCmdline`，再把返回值作为应用自有服务提供出去。启动器把自身 flag 之后的同一份不可变参数交给每个插件，因此添加应用专属 flag 无需修改启动器，多个插件也可以解析该快照。Loader 行不需要启动器标记或特殊类型。
+该插件导出 `inject = ['cmdlineArgs']`，使用自己的 commander program 调用 [`@deepseek-ai/dsh-cmdline`](../../../../packages/boot/cmdline/README.md) 中的 `parseCmdline`，再在 program 自己的 action 中把应用自有服务提供出去。启动器把自身 flag 之后的同一份不可变参数交给每个插件，因此添加应用专属 flag 无需修改启动器，多个插件也可以解析该快照。Loader 行不需要启动器标记或特殊类型。

 受这些参数配置的行会注入提供方服务，并在自己的 `!!js` 选项中读取它，同时把部署取值写在旁边作为回退：

@@ -1,6 +0,0 @@
-# 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 docs/user/guide/config.md
-config.md: 1d3ad5ce36d4b360ba5156b6be28a6caae4a23d4
-config.zh.md: 7f8bfaa77066f2976a5667e3ac402814a7afdf96
@@ -1,72 +0,0 @@
-# Configuration
-
-English | [中文](config.zh.md)
-
-Harness uses `cordis.yml` to describe which plugins an agent loads and the configuration passed to each one. The file composes capabilities; the generated configuration catalog records the fields and defaults each package actually supports.
-
-## Start from a real configuration
-
-The repository examples are runnable configurations and the most reliable starting points for a new project:
-
- [the `dsh-base` bundle patch](../../../packages/bundle/base/cordis.patch.yml) provides the common model, tools, persistence, policy, and telemetry rows every profile starts from.
- [the `dsh-web-app` bundle patch](../../../packages/bundle/web-app/cordis.patch.yml) adds the browser host, Workspace management, browser interaction, and client plugins.
- [headless-agent](../../../examples/headless-agent/cordis.yml) exposes the coding composition as a one-shot task.
- [acp-agent](../../../examples/acp-agent/cordis.yml) exposes fresh sessions to programmatic ACP clients.
-
-A minimal configuration is a list of plugin entries:
-
-```yaml
- id: llm-deepseek
-  name: '@deepseek-ai/dsh-llm-deepseek'
-  config:
-    apiKey: !!js process.env.DEEPSEEK_API_KEY
-    models:
-      - deepseek-v4-flash
-
- id: bash
-  name: '@deepseek-ai/dsh-bash-local'
-
- id: agent-loop
-  name: '@deepseek-ai/dsh-agent-loop'
-  config:
-    agents:
-      - id: main
-        provider: deepseek-official
-        model: deepseek-v4-flash
-```
-
-## Plugin entries
-
-`name` identifies an npm package or a local module relative to `cordis.yml`; `id` gives the plugin instance a stable identity; and `config` supplies plugin-specific configuration. Set `disabled: true` to skip an entry temporarily.
-
-```yaml
- id: local-tool
-  name: './src/my-tool.ts'
-  disabled: false
-  config:
-    toolName: my_tool
-```
-
-Cordis starts sibling entries concurrently. A plugin declares required services through `inject`; Cordis waits for those services before applying the plugin, so file order does not establish dependency readiness. Missing models, tools, and plugins fail as early as possible instead of being silently ignored.
-
-## CLI patch layers
-
-`dsh --profile <name>` composes the profile's bundle patch layers (its manifest's `dsh.profile.bundles` list, in order) over an empty root, then the profile's own `~/.dsh/profiles/<name>/cordis.patch.yml`, the home-level `$DSH_HOME/cordis.patch.yml`, and each `--patch <path>` overlay. Later layers win per row. App flags are not another patch layer: an ordinary bundle plugin injects `cmdlineArgs` and provides parsed values as its own service, while rows that inject and retain a `!!js` read of that service give the invocation value precedence.
-
-A patch replaces a row's entire `config` value; it does not deep-merge keys. For example, patching `llm-deepseek` with only `config: { thinking: disabled }` also removes that row's configured `apiKey` and `baseURL`, so restate every key the row must retain.
-
-## JavaScript values and environment variables
-
-The Cordis loader evaluates runtime expressions tagged with `!!js`. Keep API keys and other secrets in the gitignored `.env` file at the repository root, never in committed configuration.
-
-```yaml
-config:
-  apiKey: !!js process.env.DEEPSEEK_API_KEY
-  cwd: !!js process.cwd()
-```
-
-The tag is `!!js`, not `!js`.
-
-## Exact configuration reference
-
-The generated [plugin configuration catalog](../../config-catalog.md) lists every current field, type, and default. For composition concepts, continue to the [architecture](../../architecture.md) and [capability seams](../../capability-seams.md). To create a configuration, copy the closest entry from the [examples overview](../../../examples/README.md) and adapt it.
@@ -1,72 +0,0 @@
-# 配置文件
-
-[English](config.md) | 中文
-
-Harness 使用 `cordis.yml` 描述 agent（智能体）加载哪些插件以及每个插件的参数。配置文件负责组合能力；每个包真正支持的字段和默认值由源码生成的配置目录负责记录。
-
-## 从真实配置开始
-
-仓库中的示例就是可以运行的配置，也是新项目最可靠的起点：
-
- [`dsh-base` 组合包补丁](../../../packages/bundle/base/cordis.patch.yml) 提供通用的模型、工具、持久化、策略与遥测配置项，每个 profile 都以此为起点。
- [`dsh-web-app` 组合包补丁](../../../packages/bundle/web-app/cordis.patch.yml) 添加浏览器宿主、Workspace 管理、浏览器交互与客户端插件。
- [headless-agent](../../../examples/headless-agent/cordis.yml) 以单次任务形式暴露 coding 组装。
- [acp-agent](../../../examples/acp-agent/cordis.yml) 向程序化 ACP（Agent Client Protocol）客户端提供全新会话。
-
-最小配置由一组插件条目组成：
-
-```yaml
- id: llm-deepseek
-  name: '@deepseek-ai/dsh-llm-deepseek'
-  config:
-    apiKey: !!js process.env.DEEPSEEK_API_KEY
-    models:
-      - deepseek-v4-flash
-
- id: bash
-  name: '@deepseek-ai/dsh-bash-local'
-
- id: agent-loop
-  name: '@deepseek-ai/dsh-agent-loop'
-  config:
-    agents:
-      - id: main
-        provider: deepseek-official
-        model: deepseek-v4-flash
-```
-
-## 插件条目
-
-`name` 指定 npm 包或相对于 `cordis.yml` 的本地模块，`id` 为插件实例提供稳定标识，`config` 传入插件自己的配置。需要临时跳过某个条目时可设置 `disabled: true`。
-
-```yaml
- id: local-tool
-  name: './src/my-tool.ts'
-  disabled: false
-  config:
-    toolName: my_tool
-```
-
-Cordis 会并发启动同级配置项。插件通过 `inject` 声明必需服务；Cordis 会等到这些服务就绪后再应用该插件，因此文件顺序不能保证依赖已就绪。引用不存在的模型、工具或插件会尽早报错，而不是被静默忽略。
-
-## CLI 补丁层
-
-`dsh --profile <name>` 按该 profile 的 manifest（元数据清单）中 `dsh.profile.bundles` 列表的顺序，在空根之上组合各组合包补丁层，随后依次应用该 profile 自己的 `~/.dsh/profiles/<name>/cordis.patch.yml`、home 级的 `$DSH_HOME/cordis.patch.yml` 与每个 `--patch <path>` overlay。同一行以较后的层为准。应用 flag 并不是另一层 patch：组合包中的普通插件注入 `cmdlineArgs`，再把解析值作为自身服务提供；注入该服务并保留其 `!!js` 读取的行会让本次调用的取值优先。
-
-补丁会替换目标行的整个 `config` 值，而不是深度合并各个键。例如，只用 `config: { thinking: disabled }` 修补 `llm-deepseek`，也会移除该行原有的 `apiKey` 与 `baseURL`；因此必须重新写出该行需要保留的全部键。
-
-## JavaScript 值和环境变量
-
-Cordis loader 使用 `!!js` 标签读取运行时表达式。API key 等凭据应放在仓库根目录、已被 Git 忽略的 `.env` 中，不能提交到配置文件。
-
-```yaml
-config:
-  apiKey: !!js process.env.DEEPSEEK_API_KEY
-  cwd: !!js process.cwd()
-```
-
-标签是 `!!js`，不是 `!js`。
-
-## 精确配置参考
-
-每个插件当前支持的字段、类型和默认值见自动生成的[插件配置目录](../../config-catalog.md)。理解插件如何组合可继续阅读[架构说明](../../architecture.md)和[能力接口](../../capability-seams.md)；要创建自己的配置，优先复制并修改[示例目录说明](../../../examples/README.md)中最接近的例子。
@@ -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 docs/user/guide/index.md
-index.md: a04698e29755d4a08b012f8b61accb79c470dcb0
-index.zh.md: 3808d9506fa9cb3a3e455ed478e4f02c18fc09ab
+index.md: 80d288b1aba37e7f0863fe5fc8237cbd2a6ab9b5
+index.zh.md: addfbc94ff93ed015e52f509a23a3f981e36770b
@@ -1,52 +1,28 @@
-# Introduction
+# Use the Web UI

 English | [中文](index.zh.md)

-DeepSeek Harness is a **plugin-based agent development framework** built on the [Cordis](https://github.com/cordiverse/cordis) microkernel. Its central idea is simple: **everything is a plugin**.
+Start the Web UI through the [root README](../../../README.md#run); the command prints its URL. This guide begins after that server is running.

-## What it is
+The invoking directory is the default workspace, so the agent can inspect and modify the project where you started `dsh`.

-Harness implements every capability an AI agent needs—including LLM calls, tool execution, session management, and subtask delegation—as a composable plugin. A `cordis.yml` file declares which plugins to load and how to configure them, assembling a complete agent.
+## Configure a model

-```yaml
-# Select the LLM backend
- name: '@deepseek-ai/dsh-llm-deepseek'
+Open **Settings → Models**, enter a DeepSeek API key, and save it. The model route becomes usable immediately without restarting the server.

-# Compose one configured agent
- id: agent-spine
-  name: '@deepseek-ai/dsh-agent-spine-demo'
-  config:
-    agents:
-      - id: main
-        provider: deepseek-official
-        model: deepseek-v4-flash
-    workspaceContext: false
-```
+The [model configuration guide](./providers.md) covers other providers and custom OpenAI-compatible endpoints.

-## Who it is for
+## Run a task

-### Application users
+Start a session and send:

-To run an existing agent application, such as a coding assistant or conversational agent:
+> Summarize this repository and identify its main packages.

-1. Copy an example template.
-2. Add an API key.
-3. Run it.
+The agent can read and edit workspace files, run commands, delegate work, and maintain a plan. The Web UI asks before operations that require approval under the active permission policy.

-No code is required. See the [quick start](./quickstart.md).
+## Continue

-### Plugin developers
-
-To add a custom tool, a new LLM adapter, or another execution backend, write a plugin. Harness provides explicit extension interfaces and a type-safe development experience. See [development](../develop/basic/).
-
-## Core features
-
- **Configuration only** — `cordis.yml` selects the capability set; changing a model or adding a tool is a configuration edit.
- **Hot replacement (HMR)** — edit plugin code during development without restarting the process.
-
-## Technology
-
- **Runtime**: Node.js ^22.19 or >= 24
- **Language**: TypeScript (ESM)
- **Framework**: Cordis
- **Package manager**: pnpm workspaces (the repository pins pnpm 11)
+- [Configure models](./providers.md)
+- [Use the Python SDK](./python-sdk.md)
+- [Use other CLI modes](../../../apps/cli/README.md)
+- [Develop a plugin](../develop/basic/)
@@ -1,52 +1,28 @@
-# 介绍
+# 使用 Web UI

 [English](index.md) | 中文

-DeepSeek Harness 是一个**插件化的 agent（智能体）开发框架**，基于 [Cordis](https://github.com/cordiverse/cordis) 微内核构建。它的核心理念是：**一切皆插件**。
+先按照[根 README](../../../README.md#run)启动 Web UI；命令会打印其访问地址。本指南从服务器已经运行的状态开始。

-## 它是什么
+调用目录是默认工作区，因此 agent（智能体）可以检查并修改启动 `dsh` 时所在的项目。

-Harness 将 AI（人工智能） agent 所需的所有能力——LLM（大语言模型）调用、工具执行、会话管理、子任务分配——全部构建为可组合的插件。你通过一个 `cordis.yml` 配置文件来声明加载哪些插件、使用什么参数，就能组装出一个完整的 agent。
+## 配置模型

-```yaml
-# Select the LLM backend
- name: '@deepseek-ai/dsh-llm-deepseek'
+打开**设置 → 模型**，输入 DeepSeek API 密钥并保存。模型路由会立即可用，不需要重启服务器。

-# Compose one configured agent
- id: agent-spine
-  name: '@deepseek-ai/dsh-agent-spine-demo'
-  config:
-    agents:
-      - id: main
-        provider: deepseek-official
-        model: deepseek-v4-flash
-    workspaceContext: false
-```
+[模型配置指南](./providers.md)介绍其他提供方和自定义 OpenAI 兼容端点。

-## 适合谁
+## 运行任务

-### 应用使用者
+启动一个会话并发送：

-如果你只是想用一个现成的 agent 应用（如编程助手、对话代理），你需要的全部操作就是：
+> Summarize this repository and identify its main packages.

-1. 复制一个示例模板。
-2. 填写 API 密钥。
-3. 运行。
+agent 可以读取和编辑工作区文件、运行命令、委派工作并维护计划。当操作在当前权限策略下需要审批时，Web UI 会先询问你。

-不需要写任何代码。详见 [快速开始](./quickstart.md)。
+## 继续使用

-### 插件开发者
-
-如果你想为 agent 添加新能力——一个自定义工具、一个新的 LLM 适配器、一个新的执行后端——你需要编写一个插件。Harness 提供了清晰的扩展接口和类型安全的开发体验。详见 [开发](../develop/basic/)。
-
-## 核心功能
-
- **只需要配置** — `cordis.yml` 决定能力集合，换模型、加工具只需改一行
- **HMR（热模块替换）** — 开发时修改插件代码，无需重启进程
-
-## 技术栈
-
- **运行时**：Node.js ^22.19 或 >= 24
- **语言**：TypeScript（ESM）
- **框架**：Cordis
- **包管理**：pnpm workspaces（仓库固定使用 pnpm 11）
+- [配置模型](./providers.md)
+- [使用 Python SDK](./python-sdk.md)
+- [使用其他 CLI 模式](../../../apps/cli/README.md)
+- [开发插件](../develop/basic/)
@@ -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 docs/user/guide/providers.md
-providers.md: 0e7ed11d1b09a8361d75b576a400978ac66d08a7
-providers.zh.md: 060bf3dc41b773e89cd0d78de921c3a20cfc6076
+providers.md: a3f94f0cc86401c0f9e5b94cfd823bf9f08e6bfc
+providers.zh.md: 7d74e0086e62d8a0c2fb39085207125b4b4354e7
@@ -2,151 +2,44 @@

 English | [中文](providers.zh.md)

-Harness ships with DeepSeek and mounts a generic multi-provider adapter alongside it, for the providers in pi-ai's installed catalog — Anthropic, OpenAI, and the rest — and for any OpenAI-compatible gateway or self-hosted server. You have two entry points: the **Models** page in the web UI, and `$DSH_HOME/settings.yaml`. Both write the same document, and a change takes effect on the next request without a restart.
+This guide assumes you started the Web UI through the [root README](../../../README.md#run). Model changes take effect on the next request without restarting the server.

-## Where providers come from
+## Configure DeepSeek

-`cordis.yml` decides which **adapters** are installed; the settings document decides which **providers** run. The shipped composition carries two LLM adapters:
-
- `llm-deepseek` serves the `deepseek-official` route, the one available out of the box.
- `llm-pi-ai` mounts **dormant**: zero routes and no extra entries in the model picker until an `llm-pi-ai:` settings section supplies provider profiles, at which point those routes register live and drop again when the section empties.
-
-Adding a provider therefore rarely means editing `cordis.yml` — writing settings is enough, and that is exactly what the Models page does.
-
-## Configure from the web UI
-
-Start `pnpm dsh web` and open **Settings → Models**.
+Open **Settings → Models**. The DeepSeek card exposes one API-key field; enter the key and save it.

 ![The Models page: the DeepSeek card, with Add provider and Add a custom provider below it](providers-models-page.png)

-**Give DeepSeek its key.** The DeepSeek card carries one API-key field; fill it in, save, and the provider is ready.
+Keys are write-only. The page receives a redacted descriptor after saving, never the literal secret. The key is stored in `$DSH_HOME/.credentials.yaml`, while settings retain only its credential reference.

-**Add a provider from the installed catalog.** Choose **Add provider**, pick one of pi-ai's catalog providers (anthropic, openai, and so on), and enter that provider's API key. The endpoint, protocol, and model catalog all come from the catalog; the key is the only thing you owe.
+## Add a catalog provider

-That holds for providers that authenticate with an API key. The catalog also carries Bedrock, Vertex, Azure, and Codex, which need AWS credentials and a region, an ADC project, an `api-version`, and OAuth respectively: filling in the key field alone will not make them work. Those authenticate through pi-ai's own environment discovery, with credentials prepared the way each one requires.
+Choose **Add provider**, select a provider such as Anthropic or OpenAI, enter its API key, and save. The installed catalog supplies the endpoint, protocol, and model list.

-**Add a custom provider.** Choose **Add a custom provider** for a route the catalog does not ship — a company gateway, a self-hosted server, or a provider newer than the installed catalog. It asks for a Provider ID (the lowercase identifier that names the route in requests and as its credential), a base URL, a protocol, and at least one model.
+Providers with native authentication need their native credentials instead. Bedrock, Vertex, Azure, and Codex use AWS credentials and a region, an ADC project, an `api-version`, and OAuth respectively; filling only the API-key field does not configure them.
+
+## Add a custom provider
+
+Choose **Add a custom provider** for a company gateway, self-hosted server, or provider absent from the installed catalog. Supply a lowercase Provider ID, base URL, API protocol, credential, and at least one model.

 ![The custom provider form: Provider ID, display name, base URL, API protocol, and API key](providers-custom-form.png)

-Every field but the Provider ID stays editable afterwards: **Edit** on the row reopens the same fields, with the display name and the protocol under **Customized settings** beside the base URL. Clearing the display name falls back to the Provider ID. The Provider ID itself is fixed: it names the route in requests, in `agent-default-model`, and in every session already logged, and it is the stem of the credential reference the page can never read back — so renaming a route means declaring a new provider and deleting the old one.
+The Provider ID is permanent because requests, saved sessions, model defaults, and credential references use it. To rename a provider, add a new provider and delete the old one. The display name, base URL, protocol, credential, and models remain editable.

-**Let the endpoint report its models.** Expand **Model catalog** and choose **Fetch available models**: the interrogation asks the endpoint **the form currently shows** — including a base URL edited but not yet saved and a key typed but not yet stored — and offers what it reports as candidates to pick from. A route the installed catalog describes is answered from that catalog with no network call. Adopting a candidate only writes rows into the draft; nothing is stored until you save.
+Under **Model catalog**, choose **Fetch available models** to query the base URL and credential currently shown in the form. Selecting candidates updates the draft; the provider is not stored until you save. Catalog providers use their installed catalog without a network request.

-Keys are write-only: the page only ever holds a redacted descriptor, never the literal secret. A key you enter is stored in `$DSH_HOME/.credentials.yaml`, and the profile records only the variable name that references it.
+## Select a model

-## settings.yaml for advanced configuration
+Configured providers appear in the model picker. Selecting a model also makes it the default for new sessions. A session that has already sent a request retains the model recorded in its own log.

-The document lives at `$DSH_HOME/settings.yaml` (`$DSH_HOME` defaults to `~/.dsh`). The Models page writes this file, and you can edit it directly; neither source outranks the other.
-
-```yaml
-llm-deepseek:
-  reasoningEffort: high
-
-llm-pi-ai:
-  providers:
-    # Catalog route: endpoint, protocol, and models come from pi-ai; you supply
-    # the credential.
-    openai:
-      apiKeyEnv: OPENAI_API_KEY
-
-    # Also a catalog route, moved to a private proxy, with its catalog narrowed
-    # to one model and that model's capacity corrected. Every unset field still
-    # comes from the catalog.
-    anthropic:
-      apiKeyEnv: ANTHROPIC_API_KEY
-      baseURL: https://proxy.example.com:8443
-      reasoning: high
-      models:
-        - id: claude-sonnet-4-5
-          contextWindow: 200000
-
-    # Catalog route with one model reshaped in place; the rest of the catalog
-    # keeps serving (a models list would replace it instead).
-    deepseek:
-      apiKeyEnv: DEEPSEEK_API_KEY
-      modelOverrides:
-        deepseek-v4-pro:
-          reasoningEfforts:
-            off:
-            high: high
-
-    # Hand-declared route: pi-ai ships nothing under this key, so the profile
-    # supplies the whole provider.
-    acme-gateway:
-      displayName: Acme Gateway
-      apiKeyEnv: ACME_GATEWAY_API_KEY
-      api: openai-completions
-      baseURL: https://gateway.acme.example/v1
-      # Reasoning dialect for an endpoint whose URL pi-ai cannot recognize.
-      compat:
-        thinkingFormat: deepseek
-      models:
-        - id: acme-large
-          name: Acme Large
-          contextWindow: 65536
-          maxTokens: 4096
-        - id: acme-think
-          name: Acme Think
-          # key = level offered in the picker, value = what goes on the wire;
-          # only off may leave the value empty (supported, send nothing).
-          reasoningEfforts:
-            off:
-            high: high
-            max: ultra
-```
-
-A settings section merges over the matching `cordis.yml` configuration **per provider**, so you can override one field of one route and leave the rest as the composition set them.
-
-A profile the adapter could not serve is refused **where it is written**: a hand-declared route needs `api`, `baseURL`, and at least one model, and a profile missing any of them fails naming the offending route and model rather than being stored and quietly disabling the whole namespace. When an already-stored document is broken by an external edit, settings keeps the last good value and warns.
-
-## The model catalog
-
-A profile's `models` list *replaces* that route's installed catalog rather than extending it; omitting it or leaving it empty serves the catalog unchanged. Each entry defaults its unset fields from the installed model of the same `id`, so narrowing a route to two models, correcting one capacity, or adding a model newer than the installed catalog are each a one-line edit — but once you declare the list, every model the route should keep serving must appear in it, an entry of nothing but `id` being enough.
-
-Reshaping a few catalog models while keeping the rest is `modelOverrides`' job: it is keyed by catalog model id, takes the same fields a `models` entry does, and leaves the rest of the catalog serving untouched. An override naming a model the catalog does not describe — or set beside a `models` list, or on a custom provider — is refused rather than silently skipped.
-
-The configurable model fields are `id`, `name`, `contextWindow`, `maxTokens`, `reasoningEfforts`, and `compat`. Pricing and input modalities have no consumer and ride the installed entry.
-
-**Declare reasoning levels per model.** `reasoningEfforts` lists the levels a model offers: each key appears in the composer's effort picker, and its value is what dispatch sends on the wire — `high: high` passes the name through, `max: ultra` renames it for a gateway with its own vocabulary. A level you leave out is not offered. `off` is special: declared without a value, Off appears in the picker and selecting it sends nothing; left out entirely, the picker offers no Off and requests carry no off switch — the provider's own default decides. `reasoningEfforts: false` declares a non-reasoning model, which is also how you strip reasoning from a catalog model your gateway cannot serve. Without this field a custom model does not reason and a catalog model keeps its catalog levels.
-
-**Pick the reasoning dialect.** How a level travels — plain `reasoning_effort`, DeepSeek's `thinking: {type}` plus effort, and so on — is normally guessed from the endpoint URL, and a private gateway's URL says nothing, so a DeepSeek-style gateway would be spoken to in the OpenAI dialect. `compat.thinkingFormat` sets the dialect explicitly, and `compat.supportsReasoningEffort: false` holds the parameter back from an endpoint that rejects it; both work on the route (its models' default) or per model, for `openai-completions` routes only.
-
-A model neither the entry nor the catalog sizes takes the route's `defaultContextWindow` (262,144) and `defaultMaxTokens` (32,768). Both are guesses by construction, which is why they are route fields: a deployment whose gateway serves smaller models corrects them once.
-
-Model ids are not lifecycle configuration. Requesting a model the route does not configure fails with `UNKNOWN_MODEL` before any provider request goes out.
-
-## Credentials
-
-Use `apiKeyEnv`: it is a *reference* resolved per request, so no secret enters the configuration file. Omitting it leaves a route unauthenticated, which for a catalog route means pi-ai's own environment discovery. A reference that resolves to nothing fails the request with `MISSING_CREDENTIAL` rather than falling through to whatever unrelated key the environment happens to hold.
-
-Under `dsh`, references resolve from the inherited environment, the Models page's `$DSH_HOME/.credentials.yaml` store, the invoking directory's `.env`, then `$DSH_HOME/.env`. Without a credential service, a reference reads only the matching environment variable. One credential serves every model on its route.
-
-## Point an agent at the new provider
-
-A configured route appears in the web model picker and can be switched at any time.
-
-Switching there also sets the default: the model you pick becomes the one the next new session starts on, recorded in `settings.yaml` under `agent-default-model`. There is no separate gesture.
-
-```yaml
-agent-default-model:
-  provider: acme-gateway
-  model: acme-large
-  reasoningEffort: high   # optional
-```
-
-After a session has run a turn, its own log remains authoritative for its model selection; the default applies only to sessions without a recorded request. The shipped fallback under this section is the base bundle's `agent-default-model` composition entry (`deepseek-official` / `deepseek-v4-flash`). A self-assembled `cordis.yml` mounts and configures `@deepseek-ai/dsh-agent-default-model`; both direct entry points and Host-backed entry points read that same service.
-
-If the provider a saved default names is later removed, the composer says **Select model** and refuses input until you pick one, rather than sending to a route nothing serves.
+If a saved default names a provider that was deleted, the composer displays **Select model** and blocks input until another model is selected.

 ## Troubleshooting

- **`MISSING_CREDENTIAL`** — the variable the profile's `apiKeyEnv` names holds no value. Store the key once through the Models page, or export the variable.
- **`UNKNOWN_MODEL`** — the requested model is not in the route's configured catalog. Add it to `models`, or use an id the catalog already carries.
- **`UNSUPPORTED_REASONING_EFFORT`** — the request asked the model for a level it does not offer. Pick a level the composer lists for that model, or declare the missing one in the model's `reasoningEfforts`.
- **`settings-rejected`** — the written profile cannot be served, and the message names the route and model. For a hand-declared route, check that `api`, `baseURL`, and `models` are all present.
- **Fetching available models answers 401** — the endpoint refused the interrogation. Check the key; if the base URL points at an Anthropic-style gateway, note that the interrogation reads only the OpenAI-compatible `GET /models`, so enter the models by hand instead.
+- **`MISSING_CREDENTIAL`** — Store the provider key through the Models page or supply the referenced environment variable.
+- **`UNKNOWN_MODEL`** — Select a configured model or add the missing model to the custom provider.
+- **Fetching available models returns 401** — Check the key. Model discovery calls the OpenAI-compatible `GET /models` endpoint; enter models manually for endpoints that do not provide it.

-## Exact field reference
+## Advanced configuration

-The complete fields, types, and defaults each plugin currently supports live in the generated [plugin configuration catalog](../../config-catalog.md). Each adapter's own semantics belong to its README: [`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) and [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md). For `cordis.yml` itself, see [Configuration](./config.md).
+The generated [plugin configuration catalog](../../config-catalog.md) lists every supported field and default. The [`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) and [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md) references own direct `settings.yaml` configuration, catalog resolution, reasoning controls, credentials, and adapter errors.
@@ -2,151 +2,44 @@

 [English](providers.md) | 中文

-Harness 出厂自带 DeepSeek，同时预装了一个通用的多提供方适配器，用来接入 pi-ai 已安装目录中的 Anthropic、OpenAI 等提供方，或任何 OpenAI 兼容的网关与自建服务。你有两个入口：Web 界面的**模型**页，以及 `$DSH_HOME/settings.yaml`。两者写的是同一份文档，改完下一次请求即生效，不用重启。
+本指南假定你已按照[根 README](../../../README.md#run)启动 Web UI。模型变更会在下一次请求时生效，不需要重启服务器。

-## 提供方从哪里来
+## 配置 DeepSeek

-`cordis.yml` 决定装了哪些**适配器**，settings 文档决定跑哪些**提供方**。出厂组合里有两个 LLM 适配器：
-
- `llm-deepseek` 提供 `deepseek-official` 路由，是默认可用的那个。
- `llm-pi-ai` 以**休眠**状态挂载：零路由，模型选择器里也不会多出条目，直到 settings 里的 `llm-pi-ai:` 段落给出提供方 profile，路由才注册上来；段落清空则一并撤下。
-
-因此新增一个提供方通常不需要改 `cordis.yml`，写 settings 就够了——而模型页做的正是这件事。
-
-## 在 Web 界面里配置
-
-启动 `pnpm dsh web`，打开**设置 → 模型**。
+打开**设置 → 模型**。DeepSeek 卡片提供一个 API 密钥字段；输入密钥并保存。

 ![模型页：DeepSeek 卡片，以及添加提供方与添加自定义提供方两个入口](providers-models-page.zh.png)

-**填 DeepSeek 的密钥。** DeepSeek 卡片上只有一个 API 密钥输入框，填好保存即可开始用。
+密钥是只写的。保存后，页面只会收到脱敏描述符，永远不会收到明文密钥。密钥存储在 `$DSH_HOME/.credentials.yaml` 中，settings 只保留它的凭据引用。

-**添加内置目录里的提供方。** 点**添加提供方**，从 pi-ai 内置目录中选一个（anthropic、openai 等），填入该提供方的 API 密钥。端点、协议和模型目录都由内置目录提供，你只需要给密钥。
+## 添加目录提供方

-只对以 API 密钥认证的提供方成立。目录里也有 Bedrock、Vertex、Azure、Codex：它们分别需要 AWS 凭据与区域、ADC 项目配置、`api-version`、OAuth，只填密钥框不会让它们工作——这类提供方靠 pi-ai 自己的环境发现认证，凭据按各自的原生方式准备。
+选择**添加提供方**，选取 Anthropic 或 OpenAI 等提供方，输入其 API 密钥并保存。已安装目录会提供端点、协议和模型列表。

-**添加自定义提供方。** 点**添加自定义提供方**，用于内置目录没有的路由——公司网关、自建服务，或比内置目录更新的提供方。需要填 Provider ID（请求里点名它、也作为凭据名的小写标识）、API 地址、协议，以及至少一个模型。
+使用原生认证的提供方需要各自的原生凭据。Bedrock、Vertex、Azure 和 Codex 分别使用 AWS 凭据与区域、ADC 项目、`api-version` 和 OAuth；只填写 API 密钥字段无法完成配置。
+
+## 添加自定义提供方
+
+对于公司网关、自建服务器或已安装目录中不存在的提供方，选择**添加自定义提供方**。提供小写 Provider ID、基础 URL、API 协议、凭据和至少一个模型。

 ![自定义提供方表单：Provider ID、显示名称、API 地址、API 协议、API 密钥](providers-custom-form.zh.png)

-除 Provider ID 外的每个字段之后都还能改：行上的**编辑**会重新打开这些字段，显示名称和协议在「自定义设置」里、紧挨着 API 地址；显示名称清空即退回 Provider ID。Provider ID 本身固定不可改：它在请求里、在 `agent-default-model` 里、在每一条已记录的会话里点名这条路由，同时还是凭据引用的词干，而页面永远读不回凭据值——因此重命名一条路由等于声明一个新提供方再把旧的删掉。
+Provider ID 是永久的，因为请求、已保存会话、模型默认值和凭据引用都会使用它。如需重命名提供方，请添加新提供方并删除旧提供方。显示名称、基础 URL、协议、凭据和模型仍可编辑。

-**让端点自己报模型。** 展开**模型目录**后点**获取可用模型**，会按你**当前表单里**的地址与密钥去问端点（地址改了但没保存、密钥刚输入还没存下，都算数），把它报告的模型列成候选让你勾选。内置目录里的路由直接由目录作答，不联网。采纳只是把行写进草稿，最终还是你点保存才落盘。
+在**模型目录**中选择**获取可用模型**，可查询表单当前显示的基础 URL 和凭据。选择候选项只会更新草稿；保存前不会存储提供方。目录提供方使用已安装目录，不发起网络请求。

-密钥是只写的：页面拿到的永远是脱敏描述符，不是明文。写入的密钥存进 `$DSH_HOME/.credentials.yaml`，profile 里只记录引用它的变量名。
+## 选择模型

-## settings.yaml：进阶配置
+已配置的提供方会出现在模型选择器中。选择模型也会将其设为新会话的默认值。已发送过请求的会话会保留自身日志中记录的模型。

-文档位于 `$DSH_HOME/settings.yaml`（`$DSH_HOME` 默认是 `~/.dsh`）。模型页写的就是这个文件，你也可以直接编辑它——两个来源没有主次之分。
-
-```yaml
-llm-deepseek:
-  reasoningEffort: high
-
-llm-pi-ai:
-  providers:
-    # Catalog route: endpoint, protocol, and models come from pi-ai; you supply
-    # the credential.
-    openai:
-      apiKeyEnv: OPENAI_API_KEY
-
-    # Also a catalog route, moved to a private proxy, with its catalog narrowed
-    # to one model and that model's capacity corrected. Every unset field still
-    # comes from the catalog.
-    anthropic:
-      apiKeyEnv: ANTHROPIC_API_KEY
-      baseURL: https://proxy.example.com:8443
-      reasoning: high
-      models:
-        - id: claude-sonnet-4-5
-          contextWindow: 200000
-
-    # Catalog route with one model reshaped in place; the rest of the catalog
-    # keeps serving (a models list would replace it instead).
-    deepseek:
-      apiKeyEnv: DEEPSEEK_API_KEY
-      modelOverrides:
-        deepseek-v4-pro:
-          reasoningEfforts:
-            off:
-            high: high
-
-    # Hand-declared route: pi-ai ships nothing under this key, so the profile
-    # supplies the whole provider.
-    acme-gateway:
-      displayName: Acme Gateway
-      apiKeyEnv: ACME_GATEWAY_API_KEY
-      api: openai-completions
-      baseURL: https://gateway.acme.example/v1
-      # Reasoning dialect for an endpoint whose URL pi-ai cannot recognize.
-      compat:
-        thinkingFormat: deepseek
-      models:
-        - id: acme-large
-          name: Acme Large
-          contextWindow: 65536
-          maxTokens: 4096
-        - id: acme-think
-          name: Acme Think
-          # key = level offered in the picker, value = what goes on the wire;
-          # only off may leave the value empty (supported, send nothing).
-          reasoningEfforts:
-            off:
-            high: high
-            max: ultra
-```
-
-settings 段落**逐个提供方**地盖在 `cordis.yml` 的同名配置之上，所以你可以只覆盖某个路由的一个字段，其余保持组合里的样子。
-
-一份服务不了的 profile 会在**写入处**被拒绝：手工声明的路由必须给出 `api`、`baseURL` 和至少一个模型，缺了会带着路由名和模型名报错，而不是存下来再让整个命名空间静默失效。已经存好的文档被外部改坏时，settings 会保留上一次的好值并告警。
-
-## 模型目录
-
-`models` 是**替换**该路由的内置目录，不是往里追加；省略或留空则原样使用内置目录。每个条目会从同 `id` 的内置模型继承自己没写的字段，所以「收窄到两个模型」「更正一个容量」「加一个比内置目录更新的模型」都是一行编辑——但一旦声明了这份列表，该路由要继续服务的每个模型就都必须出现在其中，条目哪怕只写一个 `id` 也足够。
-
-就地重塑目录里的几个模型、保留其余，归 `modelOverrides` 管：它以目录模型 id 为键，接受与 `models` 条目相同的字段，目录的其余部分原样继续服务。覆盖若点名了目录没有描述的模型，或与 `models` 列表并存，或写在自定义提供方上，都会被拒绝，而不是被静默跳过。
-
-可配置的模型字段是 `id`、`name`、`contextWindow`、`maxTokens`、`reasoningEfforts` 与 `compat`。定价与输入模态没有消费方，随内置目录条目走。
-
-**按模型声明推理档位。** `reasoningEfforts` 列出模型提供的档位：每个键都会出现在输入框的档位选择器里，其值是分派在协议中实际发送的内容——`high: high` 原样透传名称，`max: ultra` 则为使用自有词汇的网关改名。没写的档位不会被提供。`off` 比较特殊：声明而不给值，选择器里会出现 Off，选中它时什么也不发送；完全不写，选择器不提供 Off，请求也不携带关闭开关——由提供方自己的默认行为决定。`reasoningEfforts: false` 声明一个不具备推理能力的模型，这也是从网关服务不了的目录模型上剥除推理的办法。不写这个字段，自定义模型不推理，目录模型保留目录给出的档位。
-
-**选定推理方言。** 档位如何在协议中传输——单独一个 `reasoning_effort`、DeepSeek 的 `thinking: {type}` 加档位，诸如此类——通常靠端点 URL 来猜，而私有网关的 URL 什么也说明不了，于是 DeepSeek 风格的网关只会收到 OpenAI 方言的请求。`compat.thinkingFormat` 用来显式指定方言，`compat.supportsReasoningEffort: false` 则让该参数不再发给拒绝它的端点；两者既可设在路由上（作为其模型的默认值），也可按模型设置，且仅适用于 `openai-completions` 路由。
-
-两处容量都没给出的模型，取路由级兜底 `defaultContextWindow`（262144）与 `defaultMaxTokens`（32768）。这两个数按定义就是猜测，所以它们是路由字段：网关服务的模型更小时改一次即可。
-
-模型 id 不是生命周期配置：请求一个该路由没有配置的模型，会在任何网络请求之前以 `UNKNOWN_MODEL` 失败。
-
-## 凭据
-
-使用 `apiKeyEnv`——它是一个**引用**，每次请求时解析，密钥本身不进配置文件。省略它会让路由不带认证，对内置目录路由意味着交给 pi-ai 自己的环境发现。给了引用却解析不到，请求会以 `MISSING_CREDENTIAL` 失败，而不是退回去用环境里碰巧存在的某个不相干的 key 计费。
-
-在 `dsh` 下，引用依次从继承环境、模型页的 `$DSH_HOME/.credentials.yaml` 存储、调用目录的 `.env` 和 `$DSH_HOME/.env` 解析。未挂载凭据服务时，引用只读取同名环境变量。一份凭据供该路由上的所有模型使用。
-
-## 让 agent（智能体）用上新提供方
-
-配好的路由会出现在 Web 的模型选择器里，随时可切。
-
-在那里切换同时也就选定了默认值：你选的模型会成为下一个新会话的起点，记录在 `settings.yaml` 的 `agent-default-model` 段里。没有另一个单独的手势。
-
-```yaml
-agent-default-model:
-  provider: acme-gateway
-  model: acme-large
-  reasoningEffort: high   # optional
-```
-
-会话跑过一轮后，其自身日志仍是模型选择的权威；默认值只适用于尚无请求记录的会话。这个段落之下的出厂兜底是 base 组合包的 `agent-default-model` 组合条目（`deepseek-official` / `deepseek-v4-flash`）。自行组装的 `cordis.yml` 会挂载并配置 `@deepseek-ai/dsh-agent-default-model`；直接入口与 Host 支撑的入口都读取同一服务。
-
-如果某个已存默认值指向的提供方后来被删掉了，输入框会显示**选择模型**并拒绝输入，而不是把消息发给一个没人服务的路由。
+如果已保存默认值指向已删除的提供方，输入框会显示**选择模型**，并在选择其他模型前阻止输入。

 ## 排错

- **`MISSING_CREDENTIAL`** — profile 里的 `apiKeyEnv` 指向的变量没有值。用模型页存一次密钥，或导出该环境变量。
- **`UNKNOWN_MODEL`** — 请求的模型不在该路由配置的目录里。把它加进 `models`，或改用目录里已有的 id。
- **`UNSUPPORTED_REASONING_EFFORT`** — 请求向模型要了一个它不提供的档位。从输入框为该模型列出的档位里挑一个，或把缺的那个声明进该模型的 `reasoningEfforts`。
- **`settings-rejected`** — 写入的 profile 服务不了，错误信息会点名具体的路由和模型。手工声明的路由检查 `api`、`baseURL`、`models` 是否齐全。
- **获取可用模型返回 401** — 端点拒绝了这次探测。检查密钥；若地址指向的是 Anthropic 风格网关，注意探测只读 OpenAI 兼容的 `GET /models`，此时手工填写模型即可。
+- **`MISSING_CREDENTIAL`**：通过模型页存储提供方密钥，或提供被引用的环境变量。
+- **`UNKNOWN_MODEL`**：选择已配置的模型，或向自定义提供方添加缺失的模型。
+- **获取可用模型返回 401**：检查密钥。模型发现会调用 OpenAI 兼容的 `GET /models` 端点；对于不提供该端点的服务，请手动输入模型。

-## 精确字段参考
+## 进阶配置

-每个插件当前支持的完整字段、类型与默认值见自动生成的[插件配置目录](../../config-catalog.md)。两个适配器各自的语义由它们的 README 负责：[`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) 与 [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md)。`cordis.yml` 本身的写法见[配置文件](./config.md)。
+自动生成的[插件配置目录](../../config-catalog.md)列出所有受支持的字段与默认值。[`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) 和 [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md) 参考文档负责直接 `settings.yaml` 配置、目录解析、推理控制、凭据与适配器错误。
@@ -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 docs/user/guide/python-sdk.md
-python-sdk.md: c6aee27e08b266ae3e54f7817cc5b9689ad8fba4
-python-sdk.zh.md: 0b0e37a6fff8ee11d4694163ecb7d22f93bcd550
+python-sdk.md: 3ef0e6595b0b5b7dddfe05e659c58556dcc48874
+python-sdk.zh.md: a46c79aa0c7cd3b6a286e1f64e01a8a81496c0f0
@@ -2,59 +2,29 @@

 English | [中文](python-sdk.zh.md)

-This tutorial installs the Python SDK, runs a checked-in Cordis composition without the Web UI, and uses the same API in your own program. It uses the compact [`minimal.cordis.yml`](../../../examples/jsonrpc-agent/minimal.cordis.yml) configuration as a complete example with a configurable system prompt, a two-tool catalog, persistent-shell behavior, and context compaction disabled.
+This tutorial is the programmatic alternative to the Web UI. It installs the published Python SDK, runs a checked-in agent composition, and shows how to call the same API from your own program.

 ## Prerequisites

 - Python 3.10 or newer
+- Git
 - Linux x64, Linux arm64, or macOS arm64
 - A DeepSeek-compatible API endpoint and credential
 - An isolated workspace that the agent may modify

 ## Install the SDK

-Choose either the public package or a source build. Both install the `deepseek-harness-sdk` distribution and expose the `deepseek_harness` Python module.
-
-### Install from PyPI
-
-Create a virtual environment and install the SDK with its same-version bundled runtime:
+Clone the repository for its runnable example, create a virtual environment, and install the SDK with its same-version bundled runtime:

 ```sh
+git clone https://github.com/deepseek-harness/deepseek-harness.git
+cd deepseek-harness
 python -m venv .venv
 . .venv/bin/activate
 python -m pip install deepseek-harness-sdk
 ```

-### Build from source
-
-A source build additionally requires Git, Node.js ^22.19 or >= 24, Corepack-enabled pnpm 11, and `uv`. The following commands build the runtime for the current supported host platform, build both wheels, and install them into the active virtual environment:
-
-```sh
-git clone https://github.com/deepseek-ai/deepseek-harness.git deepseek-harness
-cd deepseek-harness
-python -m pip install uv==0.11.23
-corepack enable
-pnpm install
-
-case "$(uname -s):$(uname -m)" in
-  Linux:x86_64) runtime_platform=linux-x64 ;;
-  Linux:aarch64|Linux:arm64) runtime_platform=linux-arm64 ;;
-  Darwin:arm64) runtime_platform=macos-arm64 ;;
-  *) echo "unsupported platform" >&2; exit 1 ;;
-esac
-
-pnpm exec tsx scripts/build-exe-for-python-sdk.ts --targets="node24-$runtime_platform"
-version="$(node -p "require('./package.json').version")"
-python scripts/build-python-release.py --package sdk --output-dir dist-python
-python scripts/build-python-release.py \
-  --package runtime \
-  --platform "$runtime_platform" \
-  --runtime-exe "dist-exe/dsh-jsonrpc-agent-pkg-$runtime_platform" \
-  --output-dir dist-python
-python -m pip install --find-links dist-python "deepseek-harness-sdk==$version"
-```
-
-The runtime wheel contains the JSON-RPC executable and every plugin used by the complete [`minimal.cordis.yml`](../../../examples/jsonrpc-agent/minimal.cordis.yml), so neither installation path needs Node.js after installation.
+The installed runtime needs no system Node.js. Repository contributors who need to build the runtime or wheels from source should use the [Python contributor workflows](../../../python/development.md).

 ## Run the checked-in example

@@ -67,7 +37,7 @@ export DEEPSEEK_API_KEY=sk-your-key-here
 # export DSH_SYSTEM_PROMPT='You are a helpful software engineer assistant.'
 ```

-Run one task from the repository checkout:
+Run one task against an isolated workspace and session directory:

 ```sh
 python examples/jsonrpc-agent/minimal.py \
@@ -77,11 +47,11 @@ python examples/jsonrpc-agent/minimal.py \
  "Inspect the repository and fix the failing tests."
 ```

-The script prints the final assistant response. The session root receives a JSONL session log containing the assembled model request and every tool call.
+The script prints the final assistant response. The session directory receives a JSONL log containing the assembled model requests and tool calls.

 ## Use the SDK in your own program

-The example is a thin wrapper around this SDK call:
+The checked-in example is a thin wrapper around this SDK call:

 ```python
 from pathlib import Path
@@ -108,9 +78,9 @@ with DeepSeekHarness(
 print(result.final_response)
 ```

-`DeepSeekHarness` starts the bundled JSON-RPC runtime lazily and reuses it until the context manager exits. Reusing the same harness and session id across calls also preserves the session-owned Bash process, including its working directory, exported variables, and shell functions.
+`DeepSeekHarness` starts the bundled runtime lazily and reuses it until the context manager exits. Reusing the same harness and session id preserves the session-owned Bash process, including its working directory, exported variables, and shell functions. Use a fresh session id for an independent task; reuse an id only when the next call should continue the same durable conversation.

-## Understand the example configuration
+## Understand the example composition

 | Property | Value |
 |---|---|
@@ -123,7 +93,7 @@ print(result.final_response)
 | Filesystem | Bare local backend; absolute editor paths may address any path visible to the runtime process |
 | Session persistence | Uncompressed JSONL under `DSH_SESSION_ROOT` |

-The configuration omits harness identity, workspace prompt text, skills, one-shot Bash, task tools, compaction, and every other model-facing plugin. Sandbox-policy facts are logged as runtime user context rather than appended to the system prompt. The editor requires absolute paths as an unconditional current contract, so the obsolete `requireAbsolutePath` option is absent.
+The composition omits harness identity, workspace prompt text, skills, one-shot Bash, task tools, compaction, and every other model-facing plugin. Sandbox-policy facts are logged as runtime user context rather than appended to the system prompt.

 ## Choose workspace and session IDs

@@ -131,4 +101,4 @@ The configuration omits harness identity, workspace prompt text, skills, one-sho

 The composition uses `danger-full-access`. Run it only inside a disposable checkout or container: Bash and the editor can modify any path allowed to the runtime process. The persistent PTY backend requires a POSIX terminal substrate, so this composition does not support Windows agents.

-For the complete SDK lifecycle and result contract, see the [Python SDK reference](../../../python/sdk/README.md). For Cordis composition syntax, see [Configuration](./config.md).
+The [`jsonrpc-agent` example reference](../../../examples/jsonrpc-agent/README.md) owns the exact composition. The [Python SDK reference](../../../python/sdk/README.md) covers lifecycle, results, notifications, runtime selection, and configuration; the [Cordis primer](../../cordis-primer.md) covers composition syntax.
@@ -2,59 +2,29 @@

 [English](python-sdk.md) | 中文

-本教程介绍如何安装 Python SDK、在不使用 Web UI 的情况下运行仓库内置 Cordis 组合，以及如何在自己的程序中调用同一套 API。教程使用精简且完整的 [`minimal.cordis.yml`](../../../examples/jsonrpc-agent/minimal.cordis.yml) 作为示例，其中包含可配置的系统提示词、双工具目录和持久 shell 行为，并关闭上下文压缩（context compaction）。
+本教程介绍 Web UI 之外的程序化使用方式：安装已发布的 Python SDK、运行仓库内置的 agent（智能体）组合，并在自己的程序中调用同一套 API。

 ## 前置要求

 - Python 3.10 或更高版本
+- Git
 - Linux x64、Linux arm64 或 macOS arm64
 - DeepSeek 兼容的 API 端点与凭据
 - agent 可以修改的隔离 workspace

 ## 安装 SDK

-可以选择安装公开包或从源码构建。两种方式都会安装 `deepseek-harness-sdk` 分发包，并提供 `deepseek_harness` Python 模块。
-
-### 从 PyPI 安装
-
-请创建虚拟环境，并安装 SDK 及其同版本内置运行时：
+克隆仓库以使用其中的可运行示例，创建虚拟环境，并安装 SDK 及其同版本内置运行时：

 ```sh
+git clone https://github.com/deepseek-harness/deepseek-harness.git
+cd deepseek-harness
 python -m venv .venv
 . .venv/bin/activate
 python -m pip install deepseek-harness-sdk
 ```

-### 从源码构建
-
-从源码构建还需要 Git、Node.js ^22.19 或 >= 24、通过 Corepack 启用的 pnpm 11，以及 `uv`。以下命令为当前受支持的宿主平台构建运行时和两个 wheel 包，并将它们安装进当前虚拟环境：
-
-```sh
-git clone https://github.com/deepseek-ai/deepseek-harness.git deepseek-harness
-cd deepseek-harness
-python -m pip install uv==0.11.23
-corepack enable
-pnpm install
-
-case "$(uname -s):$(uname -m)" in
-  Linux:x86_64) runtime_platform=linux-x64 ;;
-  Linux:aarch64|Linux:arm64) runtime_platform=linux-arm64 ;;
-  Darwin:arm64) runtime_platform=macos-arm64 ;;
-  *) echo "unsupported platform" >&2; exit 1 ;;
-esac
-
-pnpm exec tsx scripts/build-exe-for-python-sdk.ts --targets="node24-$runtime_platform"
-version="$(node -p "require('./package.json').version")"
-python scripts/build-python-release.py --package sdk --output-dir dist-python
-python scripts/build-python-release.py \
-  --package runtime \
-  --platform "$runtime_platform" \
-  --runtime-exe "dist-exe/dsh-jsonrpc-agent-pkg-$runtime_platform" \
-  --output-dir dist-python
-python -m pip install --find-links dist-python "deepseek-harness-sdk==$version"
-```
-
-运行时 wheel 包含 JSON-RPC 可执行文件，以及完整 [`minimal.cordis.yml`](../../../examples/jsonrpc-agent/minimal.cordis.yml) 使用的每个插件，因此两种安装方式完成后都不再需要 Node.js。
+安装后的运行时不需要系统提供 Node.js。需要从源码构建运行时或 wheel 包的仓库贡献者应使用 [Python 贡献者工作流](../../../python/development.md)。

 ## 运行仓库内置示例

@@ -67,7 +37,7 @@ export DEEPSEEK_API_KEY=sk-your-key-here
 # export DSH_SYSTEM_PROMPT='You are a helpful software engineer assistant.'
 ```

-从仓库 checkout 运行一个任务：
+针对隔离的 workspace 和会话目录运行一个任务：

 ```sh
 python examples/jsonrpc-agent/minimal.py \
@@ -77,11 +47,11 @@ python examples/jsonrpc-agent/minimal.py \
  "Inspect the repository and fix the failing tests."
 ```

-脚本会打印 assistant 的最终回复。会话根目录会收到 JSONL 会话日志，其中包含组装后的模型请求与每次工具调用。
+脚本会打印 assistant 的最终回复。会话目录会收到 JSONL 日志，其中包含组装后的模型请求与工具调用。

 ## 在自己的程序中使用 SDK

-该示例是以下 SDK 调用的轻量包装层：
+仓库内置示例是以下 SDK 调用的轻量包装：

 ```python
 from pathlib import Path
@@ -108,9 +78,9 @@ with DeepSeekHarness(
 print(result.final_response)
 ```

-`DeepSeekHarness` 会延迟启动内置 JSON-RPC 运行时，并持续复用，直至退出上下文管理器。在多次调用中复用同一个 harness 和 session id，还会保留该会话拥有的 Bash 进程，包括其工作目录、已导出的变量与 shell 函数。
+`DeepSeekHarness` 会延迟启动内置运行时，并持续复用，直至退出上下文管理器。复用同一个 harness 与 session id 会保留该会话拥有的 Bash 进程，包括其工作目录、已导出的变量与 shell 函数。独立任务应使用新的 session id；只有下一次调用需要延续同一段持久化对话时，才复用原有 id。

-## 了解示例配置
+## 了解示例组合

 | 属性 | 值 |
 |---|---|
@@ -123,7 +93,7 @@ print(result.final_response)
 | 文件系统 | 裸本地后端；编辑器使用绝对路径，可以访问运行时进程可见的任何路径 |
 | 会话持久化 | `DSH_SESSION_ROOT` 下未压缩的 JSONL |

-该配置省略了 harness 身份、workspace 提示词文本、skill（技能）、一次性 Bash、任务工具、上下文压缩和其他所有面向模型的插件。沙箱策略事实记录为运行时用户上下文，而不会追加到系统提示词中。编辑器无条件要求绝对路径，因此配置中没有已经废弃的 `requireAbsolutePath` 选项。
+该组合省略了 harness 身份、workspace 提示词文本、skill（技能）、一次性 Bash、任务工具、上下文压缩和其他所有面向模型的插件。沙箱策略事实记录为运行时用户上下文，而不会追加到系统提示词中。

 ## 选择 workspace 与 session id

@@ -131,4 +101,4 @@ print(result.final_response)

 该组合使用 `danger-full-access`。只能在可丢弃的 checkout 或容器内运行：Bash 与编辑器可以修改运行时进程有权访问的任何路径。持久 PTY 后端需要 POSIX 终端环境，因此该组合不支持 Windows agent。

-完整的 SDK 生命周期与结果约定见 [Python SDK 参考](../../../python/sdk/README.md)。Cordis 组合语法见[配置](./config.md)。
+准确的组合内容归 [`jsonrpc-agent` 示例参考](../../../examples/jsonrpc-agent/README.md)所有。[Python SDK 参考](../../../python/sdk/README.md)介绍生命周期、结果、通知、运行时选择和配置；[Cordis primer](../../cordis-primer.md)介绍组合语法。
@@ -1,6 +0,0 @@
-# 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 docs/user/guide/quickstart.md
-quickstart.md: e93e5a430f0cb345728581cd6fa3175ffd20b7d1
-quickstart.zh.md: 69cde830bb802ef19cc1204685395b957a0e02e3
@@ -1,62 +0,0 @@
-# Quick start
-
-English | [中文](quickstart.zh.md)
-
-This guide gets an agent running in five minutes.
-
-## Prerequisites
-
- [Node.js](https://nodejs.org/) ^22.19 or >= 24
- [pnpm](https://pnpm.io/) 11 through Corepack
- A [DeepSeek Platform](https://platform.deepseek.com/) API key
-
-```sh
-node -v
-corepack enable
-pnpm -v
-```
-
-## Step 1: install and configure the API key
-
-```sh
-git clone https://github.com/deepseek-ai/deepseek-harness.git
-cd deepseek-harness
-pnpm install
-```
-
-Create the gitignored repository-root `.env`:
-
-```sh
-DEEPSEEK_API_KEY=sk-your-key-here
-```
-
-## Step 2: run one Headless task
-
-Run a non-interactive task and print its final answer:
-
-```sh
-pnpm dsh --profile headless "summarize the architecture of this workspace"
-```
-
-`dsh --profile headless` creates and persists a fresh session, prints the final assistant answer, and exits. It starts no Web server or listening port, and a successful run leaves stderr empty.
-
-## Step 3: use the Web UI
-
-Start the browser interface:
-
-```sh
-pnpm dsh web
-```
-
-Open `http://127.0.0.1:3080`. The agent can read and write files, run commands, delegate subtasks, and track a plan. Try: `Create hello.js in the current directory, print "Hello from Harness!", and run it`.
-
-## What happened
-
-`dsh --profile headless` boots the `headless` profile: [`dsh-base`](../../../packages/bundle/base/cordis.patch.yml) and [`dsh-headless`](../../../packages/bundle/headless/cordis.patch.yml) compose over an empty root, then the runner drives the core Agent and Session services directly. `dsh web` instead composes `dsh-base` with [`dsh-web-app`](../../../packages/bundle/web-app/cordis.patch.yml), which owns the Host, HTTP, and browser layers. Both read the same default DeepSeek model route from `dsh-base`.
-
-## Next steps
-
- [Get started with the Python SDK](./python-sdk.md) — install the SDK and run a complete Cordis configuration without the Web UI
- [Configure models](./providers.md) — reach providers beyond DeepSeek, and custom gateways
- [Configuration](./config.md) — understand the `cordis.yml` format
- [Develop a plugin](../develop/basic/) — build your own tool or backend
@@ -1,62 +0,0 @@
-# 快速开始
-
-[English](quickstart.md) | 中文
-
-本指南带你在 5 分钟内跑起一个 agent（智能体）。
-
-## 环境准备
-
- [Node.js](https://nodejs.org/) ^22.19 或 >= 24
- 通过 Corepack 使用 [pnpm](https://pnpm.io/) 11
- [DeepSeek Platform](https://platform.deepseek.com/) API 密钥
-
-```sh
-node -v
-corepack enable
-pnpm -v
-```
-
-## 第一步：安装并配置 API 密钥
-
-```sh
-git clone https://github.com/deepseek-ai/deepseek-harness.git
-cd deepseek-harness
-pnpm install
-```
-
-在仓库根目录创建已被 Git 忽略的 `.env`：
-
-```sh
-DEEPSEEK_API_KEY=sk-your-key-here
-```
-
-## 第二步：运行一个 Headless 任务
-
-运行一个非交互式任务并打印最终回答：
-
-```sh
-pnpm dsh --profile headless "summarize the architecture of this workspace"
-```
-
-`dsh --profile headless` 创建并持久化一个新会话，打印最终助手回答，然后退出。它不会启动 Web 服务器或监听端口；成功运行时 stderr 为空。
-
-## 第三步：使用 Web UI
-
-启动浏览器界面：
-
-```sh
-pnpm dsh web
-```
-
-打开 `http://127.0.0.1:3080`。agent 可以读写文件、运行命令、分配子任务和跟踪计划。可以尝试：`Create hello.js in the current directory, print "Hello from Harness!", and run it`。
-
-## 运行原理
-
-`dsh --profile headless` 启动 `headless` profile：[`dsh-base`](../../../packages/bundle/base/cordis.patch.yml) 和 [`dsh-headless`](../../../packages/bundle/headless/cordis.patch.yml) 在空根之上组合，随后 runner 直接驱动 core Agent 与 Session 服务。`dsh web` 则由 `dsh-base` 与 [`dsh-web-app`](../../../packages/bundle/web-app/cordis.patch.yml) 组合，后者拥有 Host、HTTP 与浏览器层。二者都从 `dsh-base` 读取同一个默认 DeepSeek 模型路由。
-
-## 下一步
-
- [Python SDK 快速上手](./python-sdk.md) — 安装 SDK，并在不使用 Web UI 的情况下运行完整 Cordis 配置
- [配置模型](./providers.md) — 接入 DeepSeek 之外的提供方与自定义网关
- [配置文件](./config.md) — 了解 `cordis.yml` 的格式
- [开发插件](../develop/basic/) — 编写自己的工具或后端
@@ -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 examples/jsonrpc-agent/README.md
-README.md: 9eb37fd29442dc40c7a17cd266c225e6750a6886
-README.zh.md: f358d3c8b22017a10dff62ce2dedced2bfd6de6c
+README.md: 967f3f499962bf1fd1873fc16ac8fd8075b0df3b
+README.zh.md: f84ab95132e820cf0fcf45bff4ae30d9bccb55c1
@@ -35,4 +35,6 @@ Pass the config path through the Python SDK's `cordis` option or `DSH_CORDIS_CON
 - owner-scoped persistent `bash`
 - `str_replace_editor` with `view`, `create`, `str_replace`, and `insert`

-It composes the local PTY, bare `fs-local` backend, danger-full-access policy for persistent Bash, and uncompressed JSONL persistence needed by the bundled runtime. [`minimal.py`](minimal.py) runs it through the Python SDK and uses `DSH_MODEL` as its default model; the [Python SDK tutorial](../../docs/user/guide/python-sdk.md) covers setup, session management, and the security boundary.
+It composes the local PTY, bare `fs-local` backend, danger-full-access policy for persistent Bash, and uncompressed JSONL persistence needed by the bundled runtime. Bash and absolute editor paths can modify any path available to the runtime process, so run this variant only against a disposable checkout or container. The persistent PTY requires a POSIX terminal environment and is not a Windows agent interface.
+
+[`minimal.py`](minimal.py) runs the composition through the Python SDK and uses `DSH_MODEL` as its default model. The [Python SDK tutorial](../../docs/user/guide/python-sdk.md) covers installation, execution, workspace selection, and session identity; the [SDK reference](../../python/sdk/README.md) owns runtime lifecycle and result semantics.
@@ -35,4 +35,6 @@
 - 所有者作用域内持久化的 `bash`
 - 提供 `view`、`create`、`str_replace` 与 `insert` 的 `str_replace_editor`

-它组合了内置运行时所需的本地 PTY、裸 `fs-local` 后端、供持久 Bash 使用的 danger-full-access 策略，以及未压缩的 JSONL 持久化。[`minimal.py`](minimal.py) 通过 Python SDK 运行该配置，并把 `DSH_MODEL` 作为默认模型；[Python SDK 教程](../../docs/user/guide/python-sdk.md)以此配置介绍设置方式、会话管理与安全边界。
+它组合了内置运行时所需的本地 PTY、裸 `fs-local` 后端、供持久 Bash 使用的 danger-full-access 策略，以及未压缩的 JSONL 持久化。Bash 和编辑器绝对路径可以修改运行时进程有权访问的任何路径，因此只能针对可丢弃的 checkout 或容器运行该变体。持久 PTY 需要 POSIX 终端环境，因此不适用于 Windows agent 接口。
+
+[`minimal.py`](minimal.py)通过 Python SDK 运行该组合，并把 `DSH_MODEL` 作为默认模型。[Python SDK 教程](../../docs/user/guide/python-sdk.md)介绍安装、运行、workspace 选择与 session 标识；[SDK 参考](../../python/sdk/README.md)归属运行时生命周期与结果语义。
@@ -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 packages/boot/cmdline/README.md
-README.md: 2e8e58b23785fa78bd2663a459817669309a81be
-README.zh.md: c04d76905edb4afa6b18b36b8284b14990be6bdd
+README.md: 33125014539e801dbd2952a3b4513cafc80bdcee
+README.zh.md: 7ef49a1027d3c17817c9171e1166ed6feecd8559
@@ -15,15 +15,16 @@ An embedding host with no command line provides an empty list; that is the hones

 ## Ordinary providers and injected config

-Any app plugin may inject `cmdlineArgs`, parse it, and publish an ordinary app-owned service. `parseCmdline(ctx, program, plan)` is only a commander adapter; the caller owns the returned value and service:
+Any app plugin may inject `cmdlineArgs`, parse it, and publish an ordinary app-owned service. `parseCmdline(ctx, program)` is only a commander adapter; the program's own action owns validation and the published service:

 ```ts ignore
 export const name = 'web-startup'
 export const inject = ['cmdlineArgs']

 export function apply(ctx: Context): void {
-  const values = parseCmdline(ctx, webCommand(), planWebStartup)
-  if (values !== undefined) ctx.provide('webStartup', values)
+  const program = webCommand()
+  program.action(() => ctx.provide('webStartup', webValuesFrom(program)))
+  parseCmdline(ctx, program)
 }
 ```

@@ -45,7 +46,7 @@ Every row configured from those values uses ordinary service injection and direc
    port: !!js ctx.webStartup.port ?? 3080
 ```

-`parseCmdline` parses the immutable arguments and asks `plan` for the app-owned value. On `--help`, `--version`, a parse error, or a `program.error(...)` from the plan, it writes commander's text, requests exit, and returns `undefined`; the provider publishes nothing, so dependent rows never activate.
+`parseCmdline` refuses at load a program in which no command declares an action, routes every command's exit and output through the launcher (commander copies those settings into subcommands only at registration), and parses the immutable arguments; commander runs the invoked command's synchronous action on success. An action rejects an invalid invocation with `program.error(...)` — before publishing, since statements ahead of the rejection have already run. On `--help`, `--version`, a parse error, or that rejection, the helper writes commander's text and requests exit; the provider publishes nothing, so dependent rows never activate.

 ### How injection orders config

--- a/Show More
+++ b/Show More