@mars.liu/dsh-cybernetics 0.21.0 → 0.25.0

package/README.md

@@ -172,6 +172,8 @@ The settings card's「预置方案」dropdown — ten options: **auto-recommend*
 - **Vendor entries (data-driven, `status: 'ready'`)**: each vendor carries per-role model + reasoning-effort token (heterogeneous: OpenAI/Minimax five-level low/medium/high/xhigh/max, DeepSeek thinking switch, others model default), upgrade tier, availability fallback, per-role rationale, per-vendor note (⚠️ caveats — e.g. Qwen's 「verify 绝不用 Turbo」幻觉共振 warning, Kimi's K2-retirement avoidance, DeepSeek's 「成本不应成为降级 verify 的理由」) and VARIANTS (Claude 常规/高要求, Qwen A/B/C, DeepSeek 仅本家/verify 外置, Kimi 长期/最高验收质量, 火山 A/B, GLM 标准组合/重活命名角色). Selecting a preset applies its **default variant** (the first one); the outcome record discloses the variant applied and lists the remaining ones. Vendor-canonical model ids are applied verbatim — an id absent from this deployment's catalog shows the card's model-unavailable warning and the round's availability fallback (v0.8) keeps rounds alive.
 - **Auto-recommend (since v0.18.2 = a session-agent handoff, user ruling)**: selecting auto runs **NO independent LLM call and spawns NO agent** (the previous one guarded one-shot LLM call plus its route config field were removed — re-submitting the whole context to a second model call is a waste of both time and money). The plugin now probes the live catalog (`probeCatalogOptions`, the same directory smart selection reads), builds the handoff brief — embedding the catalog (the only selectable source), the cross-vendor principles (verify ≥ task; verify/task kept cross-generation/cross-family independent; verify must not be over-confident; cost cuts hit task/triage first and never verify; triage light), the current role config and every vendor preset as advisory reference — writes a `pending` record to the card, and hands the brief to the session agent through the plugin-registered `preset_recommend` tool (a steer/followup reminder is delivered to live session agents). The SESSION AGENT reads the catalog in its OWN context, answers for task/verify/triage, and calls the same tool again to submit; the plugin only validates (catalog-matched models only; per-role `reasoningEffort` validated against `ctx.llm.resolveModelInfo` and dropped to the model default when unsupported) and writes. Until the session agent answers, the card shows the pending note; an unusable answer (off-catalog / unparseable / zero picks) degrades to a written `degraded` record with the reason and is reported back to the session agent for a corrected re-submission — nothing is applied and no round is blocked. The tool survives the hard-gate allowlist alongside the cybernetics tool itself.
 - **Selecting is one-shot**: re-selecting the same entry does not re-fire (the handler guards on the last handled value; a value persisted across a restart is not re-applied at boot). Switch to「（未选择）」first to re-apply an entry.
+- **`/cybernetics use [id]` (v0.22.0, command channel)**: switch the role composition to any preset plan without opening the settings card. With no argument the command replies with a plain-text list of every applicable plan — all built-in registry ids plus the configured custom presets (`custom:<id>`) — and asks the user to confirm with a second `/cybernetics use <id>`. With an id it reuses the SAME apply pipeline as the dropdown (`handlePresetSelection`, six-field-bounded ops + the outcome record), so the reply and the card stay consistent; preset ids are case-preserved (custom ids are matched verbatim). Unlike the dropdown, a repeated `use <id>` DOES re-apply the same plan (the command keeps the one-shot volatile guard in sync and deliberately bypasses it), so no「（未选择）」detour is needed. The preset applied this way is profile-global — it affects every concurrent session.
+- **Editor-side preset picker (v0.24.1, popupSelect)**: the picker appears only after you express the `use` intent. Picking `/cybernetics` in the `/` menu completes the composer text to `/cybernetics` (no popup — keep typing `use ...`); pressing Enter on the bare `/cybernetics` token opens a searchable popup listing every applicable plan (the 12 built-in ids and the configured `custom:<id>` entries, grouped, fuzzy-filtered as you type, current plan highlighted); typing `/cybernetics use` and pressing Enter executes the plain-text listing and then opens the same popup over it. Picking a row runs `/cybernetics use <id>` through the same command transport (validation/apply/receipt stay server-authoritative; errors surface in the popup). This rides the host's own mechanism for commands with pickable values (`commandUi.decorate` + the public `popupFor`/`command/executed` faces, the same pattern as the official `/model` picker); hosts without the `commandUi` service keep the plain-text v0.22 behavior, and the typed `/cybernetics use <id>` path is untouched. Note: inline argument completion *inside the draft* (a dropdown right after typing `use `) is not possible with the host protocol — the slash trigger scan stops at the first whitespace (re-verified v0.25.0: the host composer publishes no draft-change event, the four `slash/input-*` scope events are plugin→shell bail-request channels only, and trigger-source outcomes are limited to `{claim}/{text}/{insert}` — nothing can observe the `/cybernetics use` draft before Enter). **Type `/cybernetics use`, then press Enter to open the preset picker** (the bare-enter path lands the plain-text listing first and the popup opens over it).
 
 ## Installation and Usage
 

package/README.zh-CN.md

@@ -172,6 +172,8 @@ goal 一经存在不再原地修改。`revise` 是唯一的改目标动词（必
 - **厂商方案（数据驱动，`status: 'ready'`）**：每厂商含逐角色模型 + 思考强度 token（异构：OpenAI/Minimax 五档 low/medium/high/xhigh/max、DeepSeek thinking 开关、其余模型默认）、可升级档、可用性 fallback、逐角色 rationale、厂商备注（⚠️ 注意事项——如 Qwen 的「verify 绝不用 Turbo（幻觉共振）」、Kimi 的避开退役 K2、DeepSeek 的「成本不应成为降级 verify 的理由」）与**多变体**（Claude 常规/高要求，Qwen A/B/C，DeepSeek 仅本家/verify 外置，Kimi 长期组合/最高验收质量，火山 A/B，GLM 标准组合/重活命名角色）。选择方案应用其**默认变体**（第一个）；结果记录披露所应用变体并列出其余变体。厂商原生模型 id 逐字应用——部署目录中不存在的 id 会显示卡片不可用警告，轮内可用性 fallback（v0.8）保证轮次存活。
 - **自动推荐（v0.18.2 起 = session agent 交办，用户裁定）**：选择 auto 时插件**不发起任何独立 LLM 调用、不新起任何子 agent**（v0.17.2 及之前的「一次一次性 LLM 调用 + 推荐所用模型配置项」已删除——另起一次调用等于把上下文重复提交一遍，时间与经济性都不合理）。现在的流程：插件探测实时目录（`probeCatalogOptions`，与智能选择同源），把推荐交办单——内嵌目录（唯一可选来源）、跨厂商通用原则（verify 档位不低于 task；verify/task 跨代际跨家族保持独立；verify 不能过度自信；省成本先压 task/triage、verify 最后动且成本不是降级 verify 的理由；triage 轻量）、当前角色配置与全部厂商方案（仅作参考）——经插件注册的 `preset_recommend` 工具交给 session agent，并在卡片写入 `pending` 记录、向在线 session agent 投递一条 steer/followup 提醒。session agent 在**自己的上下文中**读取目录、给出 task/verify/triage 的答案，再次调用该工具提交；插件只负责校验（逐字命中目录；逐角色 `reasoningEffort` 经 `ctx.llm.resolveModelInfo` 校验，不支持时降为模型默认并注明）与写入。session agent 未作答时卡片保持 pending；答案不可用（未命中目录/不可解析/零选择）时降级为带原因的 `degraded` 记录并回执给 session agent 修正重交——不应用任何更改、不阻塞任何轮次。该工具在硬门禁 allowlist 下与 cybernetics 工具一同保留。
 - **选择是一次性的**：重复选择同一项不会再次触发（处理器按最后处理值守卫；跨重启持久化的值不会在启动时重放）。要重复应用某项，先切「（未选择）」再选。
+- **`/cybernetics use [方案id]`（v0.22.0，命令通道）**：不开设置卡片，直接把角色组合切换为任意预置方案。无参数时命令回执纯文本清单——全部内置方案 id + 已配置的自定义方案（`custom:<id>`）——并提示用户再次输入 `/cybernetics use <id>` 确认；带 id 时复用与下拉框完全相同的应用管线（`handlePresetSelection`：六字段白名单 ops + 结果记录），回执与卡片保持一致；方案 id 大小写保留（自定义 id 逐字匹配）。与下拉框不同，重复输入同一条 `use <id>` 会**再次应用**（命令路径同步维护一次性守卫 `lastHandledPresetPlan` 并刻意绕过它），无需先切「（未选择）」。此方式应用的方案为 profile 全局生效——影响所有并发会话。
+- **编辑器侧方案选择器（v0.24.1，popupSelect）**：选择器只在你表达 `use` 意图之后出现。在 / 菜单点选 `\cybernetics` 只把编辑器文本补全为 `/cybernetics`（不弹层——继续输入 `use ...` 即可）；对裸 `/cybernetics` 回车弹出可搜索的方案选择器（12 个内置 id 与已配置的 `custom:<id>` 条目分组列出，输入即模糊过滤，当前方案高亮）；键入 `\cybernetics use` 回车则先落地纯文本清单，随后同一弹层在其上弹出。点选一项即经同一条命令通道提交 `/cybernetics use <id>`（校验/应用/回执仍以服务端为唯一权威，错误就地显示在弹层）。实现走宿主为「带可选值的命令」提供的原生机制（`commandUi.decorate` + 公开的 `popupFor`/`command/executed` 面，与官方 `/model` 选择器同一模式）；宿主无 commandUi 服务时保持 v0.22 纯文本行为，键入路径 `/cybernetics use <id>` 完全不动。说明：草稿内的参数级补全（输入 `use ` 后就地弹下拉）在宿主协议下不可实现——斜杠触发扫描遇空格即止（v0.25.0 复核：宿主 composer 不对外发射任何草稿变更事件，四个 `slash/input-*` 作用域事件均为插件→shell 的 bail 请求通道，触发源 outcome 仅 `{claim}/{text}/{insert}` 三种，均无法在回车前感知 `/cybernetics use` 草稿）。**请输入 `/cybernetics use` 后按 Enter 唤起方案选择器**（无参回车先落地纯文本清单，弹层随即在其上出现）。
 
 ## 安装与使用
 

package/docs/CHANGELOG.md

@@ -4,6 +4,65 @@
 > 当下的功能与使用方式以 [README.md](../README.md) 为准；协议细节见 [protocol.md](protocol.md)。
 > 约定：`src/` 改动需宿主重载生效；`lib/client.js` 改动需重启宿主（客户端模块图在宿主启动时构建）并刷新浏览器；`workflows/round.js` 改动热生效。
 
+## v0.25.0（2026-11-08）：「输入 `/cybernetics use` 未回车即弹方案选择器」调研结论——协议内不可行；弹层文案与文档明确「按 Enter 唤起」
+
+**背景（用户新诉求）**：v0.24.1 之后用户反馈：当前 `/cybernetics use` 必须**按 Enter** 才弹方案列表；希望输入到「/cybernetics use 」（以空格结尾、尚未回车）时就自动弹出。本轮做只读调研并尽力实现；若协议不支持则明确结论并在文档/弹层文案提示按 Enter。
+
+- **调研结论：协议内不可行**（宿主源码证据，本轮全量复核）：
+  1. **唯一的草稿观察器在遇空白时自杀**：斜杠触发扫描 `detectTrigger`（`@deepseek-ai/dsh-client-ui-input-trigger/lib/client.js` 约 776–810 行）从光标向左扫，`if (WHITESPACE.test(ch)) return null;`——只要光标与 `/` 之间存在任何空白，触发即死、菜单关闭；「/cybernetics use␣」这个草稿态不存在任何活的 `/` 触发。
+  2. **触发管线的回调全部依赖活触发**：`candidates(session, req)` / `header?` / `matchSpace?` 只有在 `track()`（同文件约 1038 行；由 conversation shell 在每次草稿变更时调用，`dsh-client-ui-conversation/lib/client.js` 约 15444 / 15642 行）检出活 hit 时才会被调用——草稿为「token 后带空白」时全部静默。`matchSpace` 更是只在「前导 token 敲完空格」这一瞬间被轮询一次（token = `/cybernetics`），此后继续输入 `use` 无任何回调。
+  3. **会话作用域事件通道是单向请求，不是通知**：`@deepseek-ai/dsh-client-ui-conversation/lib/types/client/contract/input.d.ts` 约 129–154 行——`slash/input-begin-command` / `slash/input-insert-reference` / `slash/input-consume-token` / `slash/input-insert-text` 四个事件全部 `@mode bail`，语义是「插件→shell 的草稿编辑请求」（shell 侧监听实现见 conversation `lib/client.js` 约 16200–16203 行 `actx.on(...)`）；用户打字**不发布**任何事件。`ctx.sessions.scope(sessionId)` 返回的 ClientContext（cordis Context）只暴露这些已声明 bail 事件的订阅，没有 on/subscribe/bus 之外的草稿面。
+  4. **触发源 outcome 无法开弹层**：`PickOutcome`（input.d.ts 约 53–60 行）仅 `{claim} | {insert} | {text} | 'handled' | undefined`——即使借 `registerSource` 造一个触发源，也只能在菜单活着时补全文本，无法经公开契约打开 popupSelect（`popupFor(actx)` 只被 `dispatch()/invoke()` 在真实开层时解析，`dsh-client-ui-commands/lib/types/client/contract.d.ts` 约 135–139 行）。
+  5. **无轮询面**：草稿文本只存在于 composer 输入机私有状态（`this.projection.detectText` / `this.rev`，conversation `lib/client.js` 输入机区域），不在 session scope 的任何公开 face/projection 上——定时轮询 scope 无从读到草稿。
+- **落地（零逻辑改动）**：`lib/client.js` 弹层搜索框占位文案（zh/en）加提示「输入 /cybernetics use 后按 Enter 唤起本列表」；README.md / README.zh-CN.md `use` 段落补全调研证据与显式指引；版本顺延 0.25.0（用户可见文案变更）。
+- **生效手段**：`lib/client.js` + `package.json` 改动需重启宿主并刷新浏览器。
+- **保留路径**：现状三条弹层触发（菜单点选=补全、裸回车=弹层、`use` 清单回执后弹层）全部不变；若宿主未来把 `matchEnter` 的 `line`（完整草稿）类观察能力或草稿变更事件开放为公开契约，可再评估。
+
+
+
+## v0.24.1（2026-11-08）：修复菜单点选后草稿无 token——经 `slash/input-insert-text` 作用域事件补全 `/cybernetics ` 文本
+
+**背景（v0.24.0 活体验证反馈）**：点选 `/` 菜单里的 `\cybernetics`（或列表选中后回车）后，编辑器**什么都没留下**——而点选 skills（如 `\browser-skill`）会留下高亮的完整 token。v0.24.0 的设计假设「菜单已把 token 放进草稿」被证伪。
+
+- **根因（宿主源码证据，dsh-client-ui-commands `lib/client.js`）**：菜单列的 `dispatch()` 对**装饰命令**走 `invoke()` → `popupFor().open()` 并返回 `"handled"`（约 L1523–1528）——宿主在这条路上**从不写 token**；token 的草稿写入只发生在 `dispatch`/`matchEnter` 返回 `{claim}` 时（input-trigger `settle()` → `execute()` → `slash/input-begin-command` → conversation shell `insertCommand`，约 L1364–1374 / L15703）。skills 无装饰，其源返回的是 `{text}`/`{insert}` 类 outcome，走 `slash/input-insert-text`/`insert-reference` 通道，所以留下高亮 token。装饰契约（contract.d.ts `CommandDecoration`）无 onComplete/取消回调，公开面上也没有任何草稿写回 API——v0.24.0 的 skip-open 只是不弹层，草稿停留在用户敲入的部分查询上。
+- **修复（`lib/client.js` menu 守卫）**：skip open 的同时，在插件已持有的会话 scope（`popupFor(actx)` 接受的同一个 actx）上发宿主自己的纯文本插入事件 `slash/input-insert-text`，用菜单段携带的 pick-time token span 做 CAS，替换为完整 `'/cybernetics '` 文本——与 skills 留 token 走的是同一条宿主通道。良性降级：shell 未挂载（监听缺失）、span CAS 落空（点选后草稿被编辑，shell 校验 `span.draftRev`）、`bail` 抛错——一律保持弹层关闭的旧行为，不炸菜单。
+- **不变项**：裸回车弹层（`via:'enter'` 透传）、`\cybernetics use` 清单回执弹层（`command/executed` 路径带 `via:'enter'` 合成段，绕过 menu 守卫）、键入路径与降级兜底全部原样。
+- **测试**：`test/v24-use-popup.mjs` (d3) 更新：menu 守卫断言「不弹层 **且** 恰发出一条 `slash/input-insert-text`（`/cybernetics ` + pick span）」；新增 bail-less scope 降级分支。全仓 16 套件 + commands-hint-probe 全绿；`relay-host-probe` 的 `dsh-user-approval stateOf` 失败仍为**改动前既有**（git stash 复验）。`node --check lib/client.js` 通过。
+- **生效手段**：`lib/client.js` + `package.json` 改动需重启宿主 + 刷新浏览器。
+- **待活体验证**：真实 GUI 中点选菜单项后编辑器是否留下高亮 `/cybernetics` token（span CAS 依赖点选与 settle 同步完成，协议上应必然成立；若宿主版本行为有差，需以真实草稿复验）。
+
+## v0.24.0（2026-11-08）：popupSelect 交互时机修正——菜单点选=补全文本、裸回车=弹层、`use` 无参回执后弹层
+
+**背景（用户活体验证 v0.23 后的三处反馈）**：①/ 菜单点选 `\cybernetics` 时立即弹方案选择器——太早，用户连 `use` 都没输；②方案列表应在表达 `use` 意图后才出现；③手动键入 `\cybernetics use` 回车后没有可操作的方案选择路径。
+
+- **契约复核（dsh-client-ui-commands，contract.d.ts + lib/client.js）**：①`CommandDecoration` 无法区分 menu-pick 与 bare-enter 两条触发——`dispatch()`（菜单列）与 `matchEnter()`（裸回车列）都汇入 `invoke()` 用同一份 ui spec，只有 TokenSegment 携带 `via:'menu'|'enter'`，且永不到达业务 spec（contract.d.ts L106–122）；②装饰只在**裸**调用触发——带空格的 `/cybernetics use` 行落回宿主 leadingInput claim（contract.d.ts L107–110；matchEnter 的 `if (bare)` 守卫）；③**没有**草稿写回 API——唯一能把文本留在输入框的宿主机制就是 claim，而它被装饰抢占。
+- **实现（`lib/client.js`）**：装饰保留（裸回车弹层为 v0.23 原生行为不变），在其上加两道公开契约边界的钩子：①`commandUi.popupFor(actx)` 包装——`invoke()` 正是经同一实例属性解析控制器，包装层对 `via:'menu'` 且命令为 `cybernetics` 的 open **不弹**（菜单点选已放进草稿的 token 文本 `/cybernetics` 原样保留 = 补全；同控制器的其它命令如 `/model` 的 popup 与一切 enter 路径原样透传；安装幂等）；②`ctx.on('command/executed')` 监听（官方 dsh-session-log-export 同款公开事件；仅提交方客户端收到）——收到 `cybernetics` 的**无参 `use` 清单回执**（精确前缀 `cybernetics 可用预置方案：`，服务端 `src/index.ts` use 分支）时，经公开的 `sessions.scope(sessionId)` + `popupFor(actx).open('cybernetics', spec, {sessionId}, {via:'enter', token:'/cybernetics use'})` 弹出同一选择器（选后 consume 的 CAS 落空属契约明示的良性路径；应用/状态/未知 id/其它命令回执一律不触发；scope 已消亡则静默跳过，纯文本回执即兜底）。
+- **交互形态（协议内可达的最优）**：菜单点选 → 编辑器补全 `cybernetics`（不弹层）；键入 Space 或裸回车 → 弹层（裸回车路径不变）；`\cybernetics use` 回车 → 服务端清单回执落地后弹层出现，点选即应用。草稿内 `use ` 之后的 inline 参数补全仍属协议不可达（v0.23 结论不变）。
+- **测试**：`test/v24-use-popup.mjs` 更新至 v0.24（新增 d3/d4/d4b 三组：menu 守卫只拦 `cybernetics`+`via:'menu'`、enter 与其它命令透传、重复 apply 不双重包装；清单回执触发弹层且应用/状态/错误/其它命令/畸形回执全部不触发、scope 消亡静默、子会话门禁；原有 a–f 全保留）。全仓 16 套件 + commands-hint-probe 全绿；`node --check lib/client.js` 通过。
+- **生效手段**：`lib/client.js` + `package.json` 改动需重启宿主 + 刷新浏览器；`src/` 未改动。
+- **待活体验证**：真实 GUI 中确认菜单点选后草稿保留 `/cybernetics` 文本（token 文本的精确拼写由宿主输入侧决定）；`\cybernetics use` 回车后弹层在清单回执节点之上正常出现且点选可用。
+
+## v0.23.0（2026-11-08）：`/cybernetics` 输入侧预置方案选择器——popupSelect 装饰（编辑器下拉选方案）
+
+**背景（用户新需求）**：v0.22 的 `use` 子命令只能靠纯文本回执选方案。用户希望像 @file 那样在编辑器输入 `\cybernetics use` 时弹出可点选的下拉列表。本轮先做只读调研，再按调研结论实现。
+
+- **调研结论（宿主源码证据）**：①斜杠触发扫描从光标向左**遇空白即止**（`@deepseek-ai/dsh-client-ui-input-trigger/lib/client.js` `detectTrigger`，约 763–810 行），因此 `use `（含空格）之后**不可能**由任何 `/` 触发源给出参数级补全——草稿内 inline 参数补全在宿主协议下不存在；②宿主自己为「带可选值的命令」提供的机制是挂在宿主命令上的 **popupSelect 装饰**（`@deepseek-ai/dsh-client-ui-commands/lib/types/client/contract.d.ts` `CommandDecoration`：「the decoration replaces only the bare menu-pick/enter with a popup whose onSelect typically submits a completed line back through command.execute」），`/model` 即官方先例（`dsh-client-ui-model-selection/lib/client.js` 约 2025–2045 行 `command.register` + `ui:{kind:'popupSelect'…}`）；③静态 `input.hint` 只是命令描述符上的一个字符串（`dsh-commands/lib/index.js` 157–166 行仅校验 `hint` 与 `attachments`），无 completion provider。
+- **实现（`lib/client.js` + `package.json`）**：客户端插件经 `ctx.inject(['commandUi'])` 对宿主命令 `/cybernetics` 做 `commandUi.decorate({name:'cybernetics', ui:{kind:'popupSelect'}})`：在 `/` 菜单点选（或裸回车）`/cybernetics` 时弹出可搜索方案选择器（fuzzy-label 搜索、内置/自定义分组、当前方案高亮「当前」角标）；`options` 复用与设置卡片同源的 12 个内置 id + ConfigForm 快照里 `customPresets` 解析出的 `custom:<id>` 行（`usePopupRows` 导出供离线测试）；`onSelect` 经与模式药丸同一条 `remote.commands.execute` 通道提交 `/cybernetics use <id>`——校验/应用管线/回执仍以服务端 `use` 分支为唯一权威，弹层内错误就地展示。`package.json dsh.client.inject` 补 `@deepseek-ai/dsh-client-ui-commands`。**守卫**：宿主无 commandUi 服务 / 无命令通道 / 子会话（available=false）时逐级降级；**键入路径完全不动**——`/cybernetics use <id>` 照旧 claim+submit，v0.22 纯文本清单兜底保留。
+- **与需求的偏差（诚实记录）**：宿主协议下「输入 `use ` 即在草稿内弹参数补全」不可实现（证据 ①）；本版实现的是宿主原生等价体验——输入 `/cybernetics` 触发弹层、搜索过滤、点选**直接应用**方案（而非仅补全草稿文本），效果上跳过了「补全后再回车」一步。
+- **测试**：新增 `test/v24-use-popup.mjs`（6 组：usePopupRows 12 内置 + custom 行 + active 标记 + 坏快照降级；apply 恰注册一个 popupSelect 装饰且 fuzzy-label + 本地化搜索文案；options 实时行；onSelect 经通道提交 `/cybernetics use <id>`、error/失败结果抛出给弹层；三类守卫降级；inject/导出回归）。`test/v12-mode-pill-running.mjs`、`test/v21-hint-location.mjs` inject 清单断言更新为含 `commandUi`（10 项）。全仓离线套件全绿（relay-host-probe 的 `dsh-user-approval stateOf` 失败为**改动前既有**，与本版无关，已用 git stash 复验）。
+- **生效手段**：`lib/client.js` + `package.json` 改动需重启宿主 + 刷新浏览器；`src/` 未改动。
+
+
+## v0.22.0（2026-11-08）：`/cybernetics use` 子命令——命令通道直接应用预置方案（快速切换角色组合）
+
+**背景（用户裁定：子命令名 `use`，早前方案的 `profile` 命名作废）**：预置方案此前只能经设置卡片下拉选择（volatile `presetPlan` + `loader/volatile-update` 一次性解析）；要在会话里快速切换 task/verify/triage 的模型与思考强度，得先打开卡片。本版把同一应用管线开放到 `/cybernetics` 命令通道。
+
+- **命令分支（`src/index.ts` 命令注册块）**：handler 新增 `use` 分支（子命令大小写不敏感，方案 id 大小写保留——自定义 id 逐字匹配）。**无参数**：回执纯文本清单（`PRESET_IDS` 全部 12 个内置 id 的 `presetChoiceLabel` + `customPresets` 已配置的自定义方案 `custom:<id>：名称`），并提示再次输入 `/cybernetics use <id>` 确认——命令通道只有 `{kind:'success'|'error', text}` 纯文本回执，无交互选择器。**带参数**：先同步校验（内置注册表 / `auto` / 自定义条目存在性，未知 id 直接 `error` 回执并列出全部可用 id，不写任何东西），随后以 `void handlePresetSelection(id)` fire-and-forget 走与下拉框完全相同的应用管线（六字段白名单 ops + 结果记录）。
+- **守卫同步与重复应用**：handler 同步维护 `lastHandledPresetPlan`——volatile 一次性守卫保持一致（此后 loader 带同值不会重复应用），同时命令路径刻意绕过该守卫：重复输入同一条 `use <id>` 会再次应用，无需先切「（未选择）」。命令路径**不写** volatile `presetPlan` 字段。`auto` 分支同样经 `handlePresetSelection('auto')`（pending 记录 + session agent 交办，零独立 LLM 调用）。
+- **命令引导**：动态 input hint 更新为 `[on|status|use]` / `[off|status|use]`（`profile` 命名全面移除）；status 用法行与命令 description 补 `use` 说明。
+- **测试**：新增 `test/v23-use-subcommand.mjs`（7 组：hint/用法文本只含 `use` 无 `profile`；无参数列出全部内置+自定义、零写入、确认提示；`use qwen`/`USE glm` 走 handlePresetSelection——恰 6 条角色字段 ops 且全部落在 ALLOWED_OP_PATHS 内 + ok 记录含变体；`custom:` 条目应用保存的组合并携带条目名；未知内置 id / 不存在的自定义 id → error + 清单 + 零写入；重复 `use` 再次应用且 volatile 字段未被命令路径触碰；on/status/未知文本回退不变）。`test/v09-session-mode.mjs` hint 断言更新为 `[on|status|use]` ↔ `[off|status|use]`。全仓 15 个离线套件全绿；`tsc --noEmit` 仅既有基线零新增。
+- **生效手段**：`src/` 改动宿主重载生效。风险：命令应用的方案与卡片写入同路径——**profile 全局生效**，影响所有并发会话；`auto` 分支会向在线顶层 session agent 投递交办消息。
+
 ## v0.21.0（2026-11-07）：轮次生效模型审计——round-cyb-*.json 记录 task/verify/triage 实际调用的 provider/model/effort，board 快照镜像 models 字段
 
 **背景（用户裁定，§7.12.1）**：历史全部 213 个 `round-cyb-*.json` 均无结构化 model/reasoningEffort 字段，board 快照只有 `{goals, savedAt, sessionId, version}`——「每个角色实际跑在什么模型上」跨轮不可审计。插件既有 taskAgentModel/verifyAgentModel/triageAgentModel 配置（v0.8.x 调用级回退、v0.15 思考强度），本轮把生效值落进轮审计与 board 快照。

package/lib/client.js

@@ -177,6 +177,18 @@ window.__ModuleLoader__.load({
 			'settings.preset.optVolcanoCodingPlan': '火山 Coding Plan',
 			'settings.preset.optMinimax': 'Minimax',
 			'settings.preset.optGlm': 'GLM',
+			'settings.preset.optBuiltinGlmLight': '轻量级GLM',
+			'settings.preset.optBuiltinDeepseekFast': 'deepseek 快速',
+			// v0.23.0: the /cybernetics popupSelect decoration (slash menu →
+			// preset picker; selecting one runs `/cybernetics use <id>`).
+			'popup.searchPlaceholder': '搜索预置方案…（输入 /cybernetics use 后按 Enter 唤起本列表）',
+			'popup.empty': '暂无预置方案。',
+			'popup.noResults': '没有匹配的预置方案。',
+			'popup.group.builtin': '内置方案',
+			'popup.group.custom': '自定义方案',
+			'popup.badge.current': '当前',
+			'popup.error.transport': '命令通道不可用，无法应用方案；请改用文本命令 /cybernetics use <id>。',
+			'popup.error.result': '应用失败：{message}',
 			// v0.17.1: session 范围提示（用户裁定：session agent 不在本功能范围内）。
 			'settings.preset.sessionScope': 'session agent 由用户自行管理：预置方案与自动推荐只应用 task/verify/triage 三个子 agent 角色，厂商方案中的 session 推荐仅作参考展示，不会写入任何配置。',
 			'settings.preset.applied': '已应用（{label}）：{picks}',
@@ -354,6 +366,17 @@ window.__ModuleLoader__.load({
 			'settings.preset.optVolcanoCodingPlan': 'Volcano Coding Plan',
 			'settings.preset.optMinimax': 'Minimax',
 			'settings.preset.optGlm': 'GLM',
+			'settings.preset.optBuiltinGlmLight': 'GLM (light)',
+			'settings.preset.optBuiltinDeepseekFast': 'deepseek (fast)',
+			// v0.23.0: /cybernetics popupSelect decoration copy (en mirror).
+			'popup.searchPlaceholder': 'Search preset plans… (type /cybernetics use, then press Enter)',
+			'popup.empty': 'No preset plans available.',
+			'popup.noResults': 'No matching preset plan.',
+			'popup.group.builtin': 'Built-in plans',
+			'popup.group.custom': 'Custom plans',
+			'popup.badge.current': 'current',
+			'popup.error.transport': 'Command transport unavailable — use the plain /cybernetics use <id> command instead.',
+			'popup.error.result': 'Applying failed: {message}',
 			// v0.17.1: session-scope callout (user ruling: the session agent is out of scope).
 			'settings.preset.sessionScope': 'The session agent is user-managed: preset plans and auto-recommend apply only the task/verify/triage sub-agent roles; a vendor\'s session suggestion is displayed for reference only and is never written to any config.',
 			'settings.preset.applied': 'Applied ({label}): {picks}',
@@ -1381,8 +1404,7 @@ window.__ModuleLoader__.load({
 		// event; the labels live in the locale dicts. The leading "(none)"
 		// option is the select's neutral value ('' = unset op).
 		const PRESET_CHOICES = [
-			{ id: 'auto', labelKey: 'settings.preset.optAuto' },
-			{ id: 'openai', labelKey: 'settings.preset.optOpenai' },
+			{ id: 'auto', labelKey: 'settings.preset.optAuto' },			{ id: 'openai', labelKey: 'settings.preset.optOpenai' },
 			{ id: 'claude', labelKey: 'settings.preset.optClaude' },
 			{ id: 'gemini', labelKey: 'settings.preset.optGemini' },
 			{ id: 'deepseek', labelKey: 'settings.preset.optDeepseek' },
@@ -1391,7 +1413,68 @@ window.__ModuleLoader__.load({
 			{ id: 'volcano-coding-plan', labelKey: 'settings.preset.optVolcanoCodingPlan' },
 			{ id: 'minimax', labelKey: 'settings.preset.optMinimax' },
 			{ id: 'glm', labelKey: 'settings.preset.optGlm' },
+			{ id: 'builtin-glm-light', labelKey: 'settings.preset.optBuiltinGlmLight' },
+			{ id: 'builtin-deepseek-fast', labelKey: 'settings.preset.optBuiltinDeepseekFast' },
 		];
+		/**
+		 * v0.23.0: popupSelect rows for the /cybernetics decoration — the
+		 * built-in registry ids (PRESET_CHOICES, same order as the settings
+		 * card dropdown) plus the user-saved custom presets parsed from the
+		 * live ConfigForm snapshot (`{status:'ready', value:{customPresets}}`
+		 * shape, identical to presetRow's reader). Custom ids get the
+		 * `custom:` selector prefix the server's use handler resolves. An
+		 * entry whose id equals the current `presetPlan` value is marked
+		 * `active` (the popup parks its highlight on it).
+		 *
+		 * Exported for the offline harness (test/v24-use-popup.mjs); the real
+		 * host path wraps it in the decoration's async options() provider.
+		 * @param {(key: string, params?: object) => string} t bound translator
+		 * @param {unknown} cfgSnap ConfigForm snapshot (or undefined)
+		 * @returns {Array<{id,label,detail?,group,active?,badge?}>}
+		 */
+		function usePopupRows(t, cfgSnap) {
+			const cfgReady = cfgSnap !== undefined && cfgSnap !== null && typeof cfgSnap === 'object'
+				&& cfgSnap.status === 'ready' && cfgSnap.value !== null && typeof cfgSnap.value === 'object';
+			const cfg = cfgReady ? cfgSnap.value : {};
+			const currentPlan = typeof cfg.presetPlan === 'string' ? cfg.presetPlan : '';
+			const groups = {
+				builtin: { name: 'builtin', label: t('popup.group.builtin') },
+				custom: { name: 'custom', label: t('popup.group.custom') },
+			};
+			const rows = PRESET_CHOICES.map((opt) => {
+				const id = opt.id;
+				return {
+					id,
+					label: t(opt.labelKey),
+					detail: '/' + 'cybernetics use ' + id,
+					group: groups.builtin,
+					...(currentPlan === id ? { active: true, badge: t('popup.badge.current') } : {}),
+				};
+			});
+			// Defensive parse of the customPresets field (SettingsCard's
+			// parseCustomPresetsList lives inside the card component body, so
+			// this mirrors the same degrade-to-empty semantics inline).
+			let list = [];
+			try {
+				const parsed = JSON.parse(cfg.customPresets);
+				if (Array.isArray(parsed)) {
+					list = parsed.filter((p) => p !== null && typeof p === 'object'
+						&& typeof p.id === 'string' && p.id !== ''
+						&& typeof p.name === 'string' && p.name.trim() !== '');
+				}
+			} catch { /* corrupt payload → built-ins only */ }
+			for (const entry of list) {
+				const id = 'custom:' + entry.id;
+				rows.push({
+					id,
+					label: entry.name,
+					detail: '/cybernetics use ' + id,
+					group: groups.custom,
+					...(currentPlan === id ? { active: true, badge: t('popup.badge.current') } : {}),
+				});
+			}
+			return rows;
+		}
 		/**
 		 * v0.17: parse the volatile presetRecommendation record the server
 		 * writes after a selection is resolved. Shape-tolerant: anything that
@@ -2598,7 +2681,15 @@ window.__ModuleLoader__.load({
 			// (remote.commands.execute(sessionId, line, attachments)). Guarded
 			// at runtime: absent → the pill renders disabled with a hint
 			// instead of throwing.
-			'remote.commands'];
+			'remote.commands',
+			// v0.23.0: the /cybernetics popupSelect decoration hangs off the
+			// client command surface (dsh-client-ui-commands). Guarded at
+			// runtime: a host without the service keeps the pre-v0.23 behavior
+			// (bare invocation = leading claim + typed arguments; the
+			// plain-text listing fallback). The namespace must ALSO appear in
+			// package.json dsh.client.inject, or the client runner refuses the
+			// read (inject-declared access guard).
+			'commandUi'];
 
 		function apply(ctx) {
 			ctx.effect(() => ctx.locale.register(NS, { zh, en }), 'dsh-cybernetics: dictionaries');
@@ -2816,6 +2907,199 @@ window.__ModuleLoader__.load({
 				} catch { /* namespace absent → undefined */ }
 				return undefined;
 			})();
+			// v0.24.0: the /cybernetics popupSelect interaction, retimed per user
+			// feedback on the live v0.23 GUI (three issues: the popup opened the
+			// instant the menu row was picked — before the user could even type
+			// "use"; and typing `/cybernetics use` + Enter gave no picker at all).
+			// Contract findings (dsh-client-ui-commands, contract.d.ts +
+			// lib/client.js):
+			//   - a CommandDecoration cannot distinguish its two trigger paths:
+			//     dispatch() (menu column) and matchEnter() (bare-enter column)
+			//     both route into invoke() with the same ui spec; only the
+			//     TokenSegment carries via:'menu'|'enter', and it never reaches
+			//     the business spec (contract.d.ts L106-122);
+			//   - a decoration fires on the BARE invocation only — a line like
+			//     `/cybernetics use` has a space, so matchEnter falls through to
+			//     the host leadingInput claim (contract.d.ts L107-110;
+			//     matchEnter `if (bare)` guard);
+			//   - there is NO draft-writeback API: the only host mechanism that
+			//     leaves text in the composer is the leadingInput claim, which a
+			//     decoration preempts.
+			// Design within those bounds:
+			//   1. menu-pick → completion, not popup: the decoration stays (so
+			//      bare Enter keeps the native popup), but we intercept at the
+			//      PUBLIC contract boundary commandUi.popupFor(actx) — the same
+			//      call invoke() uses — and wrap the per-session controller's
+			//      open(): a {via:'menu'} segment for 'cybernetics' opens
+			//      nothing, so the token text the menu already put into the
+			//      draft ("/cybernetics") stays as the completion, exactly like
+			//      the claim path leaves it. Other commands' popups (e.g. /model
+			//      contributions share the same per-session controller) pass
+			//      through untouched.
+			//   2. bare Enter → native popup (unchanged from v0.23): the picker
+			//      appears only after the user deliberately submitted the bare
+			//      command.
+			//   3. `/cybernetics use` + Enter → the host claim executes the line,
+			//      the server answers its plain-text listing receipt, and the
+			//      public `command/executed` event (same listener face the
+			//      official dsh-session-log-export uses) opens the SAME popup
+			//      through popupFor(actx).open() with a synthetic enter segment.
+			//      The consume CAS afterwards misses benignly (the draft is empty
+			//      — contract: a false CAS answer is benign and never retried).
+			//      Gated on the exact listing receipt, so `use <id>` applications,
+			//      status reports and unknown-id errors never open the picker.
+			// Guarded: a host without the commandUi service (or a failed
+			// registration) logs nothing and degrades to pre-v0.23 behavior;
+			// without popupFor or sessions.scope the listener is a no-op.
+			const popupSpec = {
+				kind: 'popupSelect',
+				searchMode: 'fuzzy-label',
+				searchLabels: () => ({
+					placeholder: t('popup.searchPlaceholder'),
+					empty: t('popup.empty'),
+					noResults: t('popup.noResults'),
+				}),
+				options: async () => usePopupRows(t, settingsForm && typeof settingsForm.getSnapshot === 'function' ? settingsForm.getSnapshot() : undefined),
+				onSelect: async (option, session) => {
+					if (typeof runCommand !== 'function') throw new Error(t('popup.error.transport'));
+					const outcome = await runCommand(session.sessionId, '/cybernetics use ' + option.id);
+					if (outcome && outcome.ok === false) {
+						throw new Error(t('popup.error.result', { message: outcome.error && outcome.error.message ? outcome.error.message : String(outcome.error ?? 'transport error') }));
+					}
+					const result = outcome && outcome.value ? outcome.value.result : undefined;
+					if (result && result.kind === 'error') {
+						throw new Error(t('popup.error.result', { message: result.text ?? 'command error' }));
+					}
+				},
+			};
+			// v0.24.0: marker prefix the server's no-id `use` listing receipt
+			// starts with (src/index.ts use branch). Matching the receipt — not
+			// the submitted line, which the event does not carry — keeps the
+			// gate exact and host-authoritative.
+			const USE_LISTING_PREFIX = 'cybernetics 可用预置方案：';
+			let commandUiRef;
+			// Open the preset picker over one session (issue-3 path). Best
+			// effort: a gone session scope, a missing sessions.scope face or a
+			// popupFor refusal just leaves the plain-text listing as-is.
+			const openPlanPicker = (sessionId) => {
+				const ui = commandUiRef;
+				if (!ui || typeof ui.popupFor !== 'function') return;
+				try {
+					if (ctx.sessions && typeof ctx.sessions.subagentAddress === 'function'
+						&& ctx.sessions.subagentAddress(sessionId) !== undefined) return;
+				} catch { /* catalog absent → stay open */ }
+				try {
+					const actx = ctx.sessions && typeof ctx.sessions.scope === 'function' ? ctx.sessions.scope(sessionId) : undefined;
+					if (!actx) return;
+					const controller = ui.popupFor(actx);
+					if (!controller || typeof controller.open !== 'function') return;
+					controller.open('cybernetics', popupSpec, { sessionId }, { via: 'enter', token: '/cybernetics use' });
+				} catch { /* scope gone → the text receipt stays the fallback */ }
+			};
+			try {
+				if (typeof ctx.inject === 'function') {
+					ctx.inject(['commandUi'], (scope) => {
+						const commandUi = scope.get('commandUi');
+						if (!commandUi || typeof commandUi.decorate !== 'function') return;
+						commandUiRef = commandUi;
+						scope.effect(() => commandUi.decorate({
+							name: 'cybernetics',
+							available: (session) => {
+								try {
+									if (ctx.sessions && typeof ctx.sessions.subagentAddress === 'function'
+										&& ctx.sessions.subagentAddress(session.sessionId) !== undefined) return false;
+								} catch { /* catalog absent → stay available */ }
+								return true;
+							},
+							ui: popupSpec,
+						}), 'dsh-cybernetics: /cybernetics use popup decoration');
+						// v0.24.0 issue 1: intercept the menu-pick popup at the
+						// public popupFor boundary. invoke() resolves the
+						// controller through this same instance property, so the
+						// wrapper sees every open with its TokenSegment. Only
+						// 'cybernetics' + {via:'menu'} is suppressed — every
+						// other command's popup (the controller is shared per
+						// session) and every enter-path open pass through.
+						try {
+							if (typeof commandUi.popupFor === 'function' && !commandUi.__cybMenuGuardInstalled) {
+								commandUi.__cybMenuGuardInstalled = true;
+								const popupForOriginal = commandUi.popupFor;
+								commandUi.popupFor = function (actx) {
+									const controller = popupForOriginal.call(commandUi, actx);
+									if (controller && typeof controller.open === 'function' && !controller.__cybMenuGuard) {
+										controller.__cybMenuGuard = true;
+										const openOriginal = controller.open;
+										controller.open = function (command, spec, context, segment) {
+											if (command === 'cybernetics' && segment && segment.via === 'menu') {
+												// v0.24.1 fix: a menu pick = completion
+												// intent, so open nothing — but DO write
+												// the token. Source evidence
+												// (dsh-client-ui-commands lib/client.js):
+												// dispatch() routes a decorated menu
+												// pick into invoke() and returns
+												// "handled" — the host NEVER inserts
+												// the token on this path (the
+												// leadingClaim writeback only happens
+												// when dispatch returns {claim}, which
+												// decorations preempt). The draft's
+												// only in-protocol writeback is the
+												// scoped `slash/input-insert-text`
+												// event on the session scope — the
+												// same channel the input-trigger
+												// pipeline uses for plain-text
+												// insert outcomes (the path skills
+												// like /browser-skill ride, which is
+												// why they leave a highlighted token).
+												// We own the session actx (popupFor
+												// accepted it), and the menu segment
+												// carries the pick-time token span,
+												// so replace that span with the full
+												// "/cybernetics " text, exactly like
+												// a text-insert pick outcome would.
+												// Benign degrades: the listener is
+												// absent (shell not mounted), the
+												// span CAS misses (draft edited since
+												// pick — the shell checks
+												// span.draftRev), or bail throws — in
+												// all cases nothing opens and we keep
+												// the pre-v0.24.1 behavior (empty
+												// draft) instead of crashing the menu.
+												try {
+													const span = segment.span;
+													if (actx && typeof actx.bail === 'function'
+														&& span && typeof span === 'object') {
+														actx.bail(actx, 'slash/input-insert-text', {
+															text: '/cybernetics ',
+															span,
+														});
+													}
+												} catch { /* insertion refused → no token, popup stays closed */ }
+												return undefined;
+											}
+											return openOriginal.call(controller, command, spec, context, segment);
+										};
+									}
+									return controller;
+								};
+							}
+						} catch { /* wrap failed → v0.23 menu behavior stays */ }
+					});
+				}
+			} catch { /* no commandUi → plain-text fallback stays */ }
+			// v0.24.0 issue 3: after `/cybernetics use` (no id) executes, the
+			// server's listing receipt IS the use intent — open the picker over
+			// it. The event fires on the submitting client only (host contract:
+			// other clients get the durable nodes, never this acknowledgment).
+			try {
+				if (typeof ctx.on === 'function') {
+					ctx.effect(() => ctx.on('command/executed', (sessionId, commandName, result) => {
+						if (commandName !== 'cybernetics') return;
+						if (!result || result.kind !== 'success') return;
+						if (typeof result.text !== 'string' || !result.text.startsWith(USE_LISTING_PREFIX)) return;
+						openPlanPicker(sessionId);
+					}), 'dsh-cybernetics: use-receipt preset picker');
+				}
+			} catch { /* no event face → the text receipt stays the fallback */ }
 			const modeIndicatorInject = (sessionId) => {
 				let mode = NO_MODE_FACE;
 				let goals = NO_MODE_FACE;
@@ -2861,6 +3145,7 @@ window.__ModuleLoader__.load({
 		// singleton) exported for the offline harness (test/v20-home-entry.mjs).
 		module.exports = {
 			name, inject, apply, countRunningGoals, countGoals, readHintLocation,
+			usePopupRows,
 			homeSessionOf, requestHome, consumeHomeRequest,
 		};
 		return module.exports;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mars.liu/dsh-cybernetics",
-  "version": "0.21.0",
+  "version": "0.25.0",
   "license": "MIT",
   "private": false,
   "files": [
@@ -35,7 +35,8 @@
         "@deepseek-ai/dsh-client-ui-conversation",
         "@deepseek-ai/dsh-client-ui-renderer",
         "@deepseek-ai/dsh-client-ui-session",
-        "@deepseek-ai/dsh-client-ui-settings"
+        "@deepseek-ai/dsh-client-ui-settings",
+        "@deepseek-ai/dsh-client-ui-commands"
       ],
       "platform": "web",
       "immediately": true

package/src/index.ts

@@ -36,7 +36,7 @@ import { startTeamRound, teamExecutorAvailable, teamExecutorUnavailableError } f
 import { computeSmartSelection, probeCatalogOptions, sessionRouteOf } from './modelSelection.ts'
 import type { SmartSelectionAudit } from './modelSelection.ts'
 import {
-  PRESET_AUTO_ID, PRESET_RECOMMEND_TOOL_NAME, applyRecommendationAnswer, buildRecommendationBrief,
+  PRESET_AUTO_ID, PRESET_IDS, PRESET_RECOMMEND_TOOL_NAME, applyRecommendationAnswer, buildRecommendationBrief,
   customPresetAsVendor, customPresetEntryId, formatRecommendationRecord, isCustomPresetId, parseCustomPresets,
   presetById, presetChoiceLabel, vendorPresetApplyOps,
 } from './modelPresets.ts'
@@ -1807,7 +1807,7 @@ export function apply(ctx: any, config: Partial<Config> = {}) {
     // recent mode change; a multi-session host may briefly show the other
     // session's hint until that session's own next /cybernetics invocation.
     const commandHint = (session: unknown): string =>
-      enabledFor(session) ? '[off|status]' : '[on|status]'
+      enabledFor(session) ? '[off|status|use]' : '[on|status|use]'
     let commandDisposer: (() => void) | undefined
     const handler = (invocation: any) => {
       const agent = invocation?.agent
@@ -1815,7 +1815,11 @@ export function apply(ctx: any, config: Partial<Config> = {}) {
       if (session === undefined || typeof session.append !== 'function') {
         return { kind: 'error' as const, text: 'cybernetics: 会话不可用，无法写入模式事件。' }
       }
-      const arg = (invocation.rawInput ?? '').trim().toLowerCase()
+      // Case-insensitive subcommand dispatch (v0.9.0); the `use` preset id
+      // keeps its original case — custom preset ids are user-chosen and
+      // case-sensitive (`custom:<id>` matches the customPresets entry verbatim).
+      const rawInput = (invocation.rawInput ?? '').trim()
+      const arg = rawInput.toLowerCase()
       const override = modeOverrideOf(ctx, session)
       const globalOn = allGoalsMode()
       if (arg === 'on' || arg === 'off') {
@@ -1840,6 +1844,59 @@ export function apply(ctx: any, config: Partial<Config> = {}) {
             : 'cybernetics 控制已对本会话关闭：不再注入控制 guidance，硬门禁放行，新输入回归 DSH 原生行为。/cybernetics on 可恢复。',
         }
       }
+      // --- `use` subcommand (v0.22.0): switch the role composition (task/
+      // verify/triage model + reasoning effort) to any preset plan — the
+      // built-in registry ids (PRESET_IDS) or a user-saved custom preset
+      // (`custom:<id>`). Reuses the SAME apply pipeline as the settings-card
+      // dropdown (handlePresetSelection, same closure) as fire-and-forget;
+      // lastHandledPresetPlan is kept in sync here so the one-shot volatile
+      // guard stays coherent (a later loader update with the same value is a
+      // no-op) while repeated invocations can re-apply the same plan.
+      if (arg === 'use' || arg.startsWith('use ')) {
+        const planArg = rawInput.slice(3).trim()
+        const listPlans = (): string[] => {
+          const lines = PRESET_IDS.map((id) => `- ${id}：${presetChoiceLabel(id)}`)
+          try {
+            for (const p of parseCustomPresets(readConfigField(config.customPresets, ''))) {
+              lines.push(`- custom:${p.id}：${p.name}（自定义方案）`)
+            }
+          } catch { /* readConfigField face absent → built-ins only */ }
+          return lines
+        }
+        if (planArg === '') {
+          // No argument: plain-text listing (the command channel has no
+          // picker UI); the user confirms with a second invocation.
+          return {
+            kind: 'success' as const,
+            text:
+              'cybernetics 可用预置方案：\n' + listPlans().join('\n') +
+              '\n再次输入 /cybernetics use <id> 应用其中一个方案。',
+          }
+        }
+        const isCustom = isCustomPresetId(planArg)
+        const customEntryExists = isCustom && (() => {
+          try {
+            return parseCustomPresets(readConfigField(config.customPresets, '')).some((p) => p.id === customPresetEntryId(planArg))
+          } catch { return false }
+        })()
+        const known = isCustom ? customEntryExists : (planArg === PRESET_AUTO_ID || presetById(planArg) !== undefined)
+        if (!known) {
+          return {
+            kind: 'error' as const,
+            text:
+              `cybernetics: 未知预置方案 "${planArg}"。可用 id：\n` + listPlans().join('\n') +
+              '\n输入 /cybernetics use <id> 应用其中一个方案。',
+          }
+        }
+        lastHandledPresetPlan = planArg
+        void handlePresetSelection(planArg)
+        return {
+          kind: 'success' as const,
+          text:
+            `cybernetics: 正在应用预置方案 "${planArg}"（${presetChoiceLabel(planArg)}）——` +
+            'task/verify/triage 的模型与思考强度将写入插件配置（全局生效，影响所有并发会话）。结果见设置卡片的结果记录。',
+        }
+      }
       // No argument (or unknown text) = status report.
       const effective = override === null ? globalOn : override
       const overrideText = override === null ? '未设置（遵循全局配置）' : override ? 'on' : 'off'
@@ -1852,7 +1909,7 @@ export function apply(ctx: any, config: Partial<Config> = {}) {
           `- 硬门禁 hardGate：${hardGate() ? (resolveGateMode(config, true) === 'allowlist' ? 'on（allowlist）' : 'on（denylist）') : 'off'}\n` +
           `- 新输入策略 inputPolicy：${readConfigField(config.inputPolicy, 'insert')}\n` +
           `- 轮完成通知策略 noticePolicy：${readConfigField(config.noticePolicy, 'insert')}\n` +
-          `用法：/cybernetics on | /cybernetics off | 无参数或 status = 显示状态`,
+          `用法：/cybernetics on | /cybernetics off | 无参数或 status = 显示状态 | /cybernetics use [方案id] = 应用预置方案（无参数列出全部可用方案）`,
       }
     }
     const registerCommand = (session: unknown): void => {
@@ -1861,7 +1918,7 @@ export function apply(ctx: any, config: Partial<Config> = {}) {
       } catch { /* a failed unregister must not block the re-register below */ }
       commandDisposer = commandCtx.commands.register({
         name: 'cybernetics',
-        description: 'Toggle cybernetics control loop (ALL-GOALS routing + hard gate) for THIS session; no argument shows status',
+        description: 'Toggle cybernetics control loop (ALL-GOALS routing + hard gate) for THIS session; no argument shows status; `use [id]` applies a preset plan (no id lists all)',
         input: { hint: commandHint(session) },
         handler,
       })

package/src/modelPresets.ts

@@ -113,6 +113,8 @@ export const PRESET_IDS = [
   'volcano-coding-plan',
   'minimax',
   'glm',
+  'builtin-glm-light',
+  'builtin-deepseek-fast',
 ] as const
 
 export type PresetId = (typeof PRESET_IDS)[number]
@@ -527,6 +529,50 @@ export const VENDOR_PRESETS: VendorPreset[] = [
     note: '命名角色（frontend 等）的 glm-5.3 max effort 只按需生效（智能选择命中难 subgoal 时），避免全量 max；verify 恒 glm-5.3 max，成本不构成降级理由。',
     sessionNote: PRESET_SESSION_NOTE,
   },
+  {
+    id: 'builtin-glm-light',
+    label: '轻量级GLM',
+    description: '用户自定义轻量 GLM 组合（provider 一律 zai-coding-cn）：task glm-5.3-flash / verify glm-5.3(effort medium) / triage glm-5.3-flash(effort minimal)。任务以 flash 为主、verify 只做中档强化，最小化单轮成本。',
+    status: 'ready',
+    roles: {
+      task: { provider: 'zai-coding-cn', model: 'glm-5.3-flash', rationale: '量最大的角色用 Flash：成本低、速度快。' },
+      verify: { provider: 'zai-coding-cn', model: 'glm-5.3', reasoningEffort: 'medium', rationale: 'verify 升到 glm-5.3 中档 effort，以档位差补偿同家族独立性。' },
+      triage: { provider: 'zai-coding-cn', model: 'glm-5.3-flash', reasoningEffort: 'minimal', rationale: '轻量分拣走 minimal effort，压成本与 wall-clock。' },
+    },
+    variants: [{
+      id: 'standard',
+      label: '标准组合',
+      roles: {
+        task: { provider: 'zai-coding-cn', model: 'glm-5.3-flash', rationale: 'Flash 执行主力。' },
+        verify: { provider: 'zai-coding-cn', model: 'glm-5.3', reasoningEffort: 'medium', rationale: 'verify glm-5.3 medium：轻量场景下的审计底线。' },
+        triage: { provider: 'zai-coding-cn', model: 'glm-5.3-flash', reasoningEffort: 'minimal', rationale: '轻量分拣 minimal。' },
+      },
+    }],
+    note: '源自用户自定义方案「轻量级GLM」的内置化副本（roles 照抄，id 固定为 builtin-glm-light）；provider zai-coding-cn 需部署侧具备对应渠道方可应用。',
+    sessionNote: PRESET_SESSION_NOTE,
+  },
+  {
+    id: 'builtin-deepseek-fast',
+    label: 'deepseek 快速',
+    description: '用户自定义 DeepSeek 快速组合：task deepseek-official/deepseek-flash / verify deepseek-official/deepseek-flash(effort high) / triage deepseek-account/deepseek-flash(effort low)。全 Flash 档拉满速度，verify 以 high effort 补偿同模型独立性。',
+    status: 'ready',
+    roles: {
+      task: { provider: 'deepseek-official', model: 'deepseek-flash', rationale: 'Flash 档执行主力：速度优先。' },
+      verify: { provider: 'deepseek-official', model: 'deepseek-flash', reasoningEffort: 'high', rationale: 'verify 同模型但开 high effort，以思考深度补偿独立性损失。' },
+      triage: { provider: 'deepseek-account', model: 'deepseek-flash', reasoningEffort: 'low', rationale: '轻量分拣 low 档（deepseek-account 为同款另一计费渠道）。' },
+    },
+    variants: [{
+      id: 'standard',
+      label: '标准组合',
+      roles: {
+        task: { provider: 'deepseek-official', model: 'deepseek-flash', rationale: 'Flash 执行主力。' },
+        verify: { provider: 'deepseek-official', model: 'deepseek-flash', reasoningEffort: 'high', rationale: 'verify high effort 审计。' },
+        triage: { provider: 'deepseek-account', model: 'deepseek-flash', reasoningEffort: 'low', rationale: '轻量分拣。' },
+      },
+    }],
+    note: '源自用户自定义方案「deepseek 快速」的内置化副本（roles 照抄，id 固定为 builtin-deepseek-fast）；triage 走 deepseek-account 渠道，需部署侧具备 deepseek-official / deepseek-account 两个 provider 方可应用。',
+    sessionNote: PRESET_SESSION_NOTE,
+  },
 ]
 
 // Normalize the mirror invariant: a READY preset's top-level `roles` IS its