dsh-packycode-api 1.1.4 → 1.1.5

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 1.1.5
+
+- Added `grok-4.7`, displayed as **Grok 4.7**, to the PackyCode `openai-responses` route at `https://cf.api.fan/v1`. [The official Grok 4.7 guide](https://docs.x.ai/developers/grok-4-7) declares a 500,000-token context, text/image input, text output, and `low` / `medium` / `high` / `xhigh` reasoning (default `high`, no off or max). There is no separate documented text-output cap; the numeric pi-ai ceiling is 500,000, bounded by remaining context per request. Only GPT Responses requests keep `prompt_cache_key`: the gateway's Grok route rejects this field with a misleading `Incorrect API key provided` error. Non-GPT Responses requests use pi-ai's `cacheRetention: 'none'` to omit it; the model, protocol, effort and plugin-owned credential stay the same.
+- Settings now has a model checkbox list with Select all / Select none. All models, including newly added catalog entries, are visible by default. The profile stores exclusions, and DSH's picker refreshes when they change. Hiding a model does not prevent an existing session or prepared turn from using it.
+- Fixed saving Auto web search on DSH 0.2 (including the reported macOS Intel installation): require `@deepseek-ai/schemastery` 3.18.4+, which declares volatile preference fields. The previous 3.18.2 dependency silently left them non-volatile, so DSH 0.2 refused the write. All RPC failures now carry Connection's required `code`, `message`, and empty `details`, preserving a safe error instead of `connection: invalid server-response failure`.
+- The live checker now reads only the plugin-owned `packycode-api/keys` credential record, selecting the active usable key or `--key-label LABEL`; legacy references and environment credentials never substitute for it. Invalid YAML produces a safe error without quoting secret-bearing source lines, and checks never modify the stored record.
+- Validation: 276 offline tests, both regenerated bundles and the versioned tarball; built settings UI checkbox/all/none/save-failure checks; the bundled DSH 0.2 Connection parser accepts the fixed failure. Built live gateway checks answered through DeepSeek Flash, GPT-6.1 Sol, GPT-6 Astra and Grok 4.7 and passed key rotation and secret-free projections. All four Grok efforts returned `ok` with a plugin-stored Grok-group key; xhigh first encountered a transient upstream 400 and succeeded on an identical retry. The user confirmed the local desktop build passed testing. The physical Intel desktop UI has not been retested.
+
 ## 1.1.4
 
 - **Carry the reviewed plan into the next CLI turn.** The plan previously existed only in `exit_plan_mode` arguments, which the delegated transcript dropped; a fresh CLI then saw only “Plan approved”. The latest complete plan and its matching review result are now recovered from durable native or adapter-generated PTC tool calls, so approval, revision, resume and fork keep their constraints. They are reserved before trimming older chat; an oversized plan/request fails explicitly rather than silently losing constraints. Unrelated tool arguments and arbitrary PTC programs are not forwarded.

package/README.en.md

@@ -25,6 +25,7 @@ The `PackyCode` model group ships with the plugin. No YAML edits and no separate
 | Capability | What it does |
 | --- | --- |
 | **Built-in model route** | Adds a `PackyCode` group to the model picker. No provider configuration and no `cordis.patch.yml` edits |
+| **Choose visible models** | All models are selected by default in Settings. Unchecking a model immediately hides it from the picker; existing sessions can keep using it |
 | **Keys used in order** | An exhausted or rejected key is disabled and the next usable key takes over; the failed step is retried on that key |
 | **Keys chosen by group** | Each key lists its PackyCode groups and the models they reach; when the active key's groups cannot reach the selected model (no `cc` group for Claude, say), that turn runs on a stored key whose groups can |
 | **Visible balance** | Settings lists each key's remaining, used, limit, reset period, and a usage bar, plus a total of those keys. The composer shows the active key's remaining balance |
@@ -44,7 +45,7 @@ Open the desktop application's **Plugins** page, click **Add plugin**, and enter
 dsh-packycode-api
 ```
 
-Choose the **official** install source, then click **Install**. To pin a version, enter `dsh-packycode-api@1.1.4`.
+Choose the **official** install source, then click **Install**. To pin a version, enter `dsh-packycode-api@1.1.5`.
 
 Then **manually restart the desktop application**. Refreshing the page does not reload the plugin inside the Host process.
 
@@ -56,14 +57,14 @@ Open **Settings → PackyCode**. Paste the API key under **Add a key**. A label
 
 ### 3. Select a model
 
-Choose a model from the `PackyCode` group. `deepseek-flash`, `gpt-6.1-sol`, and `gpt-6-astra` work once a key is stored. The three Claude models also need the Claude Code CLI on this device; see below.
+Choose a model from the `PackyCode` group. `deepseek-flash`, `gpt-6.1-sol`, `gpt-6-astra`, and `grok-4.7` use HTTP. The three Claude models also need the Claude Code CLI on this device; see below. Your key's groups must cover the selected model.
 
 <details>
 <summary>Verify the install / other profiles / a local checkout</summary>
 
 The **Plugins** page shows the installed state and version, and is also where you enable, disable, or uninstall.
 
-**For non-desktop profiles only:** `dsh plugin --profile <name> add dsh-packycode-api@1.1.4`. Do not use it for `desktop` — the CLI refuses it (`profile "desktop" is managed exclusively by the Electron application`).
+**For non-desktop profiles only:** `dsh plugin --profile <name> add dsh-packycode-api@1.1.5`. Do not use it for `desktop` — the CLI refuses it (`profile "desktop" is managed exclusively by the Electron application`).
 
 A local checkout can be linked with `dsh plugin --profile <name> add link:/path/to/dsh-packycode-api`.
 
@@ -73,6 +74,8 @@ A profile without a browser can still use the model route. It just has no settin
 
 ## Daily use
 
+**Choose visible models.** Under **Settings → PackyCode → Visible models**, check the models you want in the picker. All are selected by default, with Select all / Select none controls. The selection is saved in the current profile and applies immediately; unchecking a model does not interrupt an existing session. New catalog models are selected by default.
+
 **Switch keys.** Keys are used in the order they were added. **Use this key** picks the preferred key, effective from the next turn; **Rename** changes its label (at most 60 characters, empty names are refused); **Re-enable** puts a disabled key back after a top-up or replacement.
 
 **See groups.** Under **Accounts and keys**, each key lists its PackyCode groups (hover for the group's description) and which models they reach: ✓ yes, ◐ partly, ✕ no. The groups come from the gateway itself (its refusal of a model id it cannot route names the token's groups; nothing is billed), matched against PackyCode's public model-group table. Claude needs one of `cc` / `cc-sale` / `cc-expensive` / `claude-officially` (`claude-haiku-5-5` only `cc` and `claude-officially`); GPT needs `codex` / `codex-sale`; DeepSeek needs `deepseek-officially` / `deepseek-sale`.
@@ -138,12 +141,17 @@ Claude Code CLI → temporary local MCP web_search → selected PackyCode DeepSe
 | `deepseek-flash` | HTTP, chat/completions | Can be off; `low` / `high` / `max` | `deepseek-officially`, `deepseek-sale` |
 | `gpt-6.1-sol` | HTTP, Responses, images allowed | Cannot be off; `low` / `medium` / `high` / `xhigh` / `max` | `codex`, `codex-sale` |
 | `gpt-6-astra` | Same | Same | Same |
+| `grok-4.7` (Grok 4.7) | HTTP, Responses, text/image input; 500K context | Cannot be off; `low` / `medium` / `high` / `xhigh` | The Grok coverage read from the gateway in Settings |
 | `claude-opus-5-5` | Local Claude Code CLI | The picker offers the same levels; the CLI chooses the actual effort | A group the official CLI is allowed to use; see below |
 | `claude-sonnet-5-5` | Same | Same | Same |
 | `claude-haiku-5-5` | Same; session titles always use this model | Same | Same |
 
 A model in the list does not mean the current token group allows it. When changing groups, do not drop the group that serves the model you still want.
 
+Grok 4.7's context and reasoning levels follow the [official guide](https://docs.x.ai/developers/grok-4-7). There is no separate text-output limit; the plugin uses the context size as its numeric output ceiling, bounded by the remaining context per request.
+
+Only GPT Responses requests keep `prompt_cache_key`; other Responses models omit it by default. This gateway's Grok route reports a misleading `Incorrect API key provided` error when the field is present.
+
 <details>
 <summary>Protocol, group, and CLI constraints</summary>
 

package/README.md

@@ -25,6 +25,7 @@
 | 能力 | 使用体验 |
 | --- | --- |
 | **自带模型路由** | 安装后模型选择器出现 `PackyCode` 分组，不需要配置 provider，也不用改 `cordis.patch.yml` |
+| **自选显示的模型** | 设置页的模型列表默认全选；取消勾选后，切换列表立即隐藏该模型，已有会话仍可继续使用 |
 | **多 Key 按顺序使用** | 额度用尽或 Key 被拒绝时自动切到下一个可用 Key；失败的那一步由重试接手 |
 | **按分组选 Key** | 每个 Key 后面列出它所在的 PackyCode 分组和能用的模型；当前 Key 的分组用不了所选模型（例如没有 cc 分组却选了 Claude）时，这一轮自动改用分组合适的 Key |
 | **余额一眼可见** | 设置页列出每个 Key 的剩余、已用、额度、重置周期和用量条，并给出这些 Key 的合计；输入框右侧显示当前 Key 的剩余额度 |
@@ -48,7 +49,7 @@
 dsh-packycode-api
 ```
 
-在**安装源**中选择**官方源**，然后点击**安装**。需要固定版本时填入 `dsh-packycode-api@1.1.4`。
+在**安装源**中选择**官方源**，然后点击**安装**。需要固定版本时填入 `dsh-packycode-api@1.1.5`。
 
 完成后**手动重启桌面应用**。仅刷新页面不会重新加载 Host 里的插件。
 
@@ -60,14 +61,14 @@ dsh-packycode-api
 
 ### 3. 选择模型
 
-回到对话，在模型选择器里选 `PackyCode` 分组下的模型。`deepseek-flash`、`gpt-6.1-sol` 和 `gpt-6-astra` 添加 Key 后即可用。三个 Claude 模型还需要本机装有 Claude Code CLI，见下文。
+回到对话，在模型选择器里选 `PackyCode` 分组下的模型。`deepseek-flash`、`gpt-6.1-sol`、`gpt-6-astra` 和 `grok-4.7` 通过 HTTP 调用；三个 Claude 模型还需要本机装有 Claude Code CLI，见下文。Key 的分组必须覆盖所选模型。
 
 <details>
 <summary>检查安装 / 其它 profile / 本地目录</summary>
 
 桌面应用的**插件**页可以看到已安装状态与版本，也可以在那里启用、停用或卸载。
 
-**仅用于非 desktop profile：** `dsh plugin --profile <name> add dsh-packycode-api@1.1.4`。不要对 `desktop` 使用它 —— CLI 会直接拒绝（`profile "desktop" is managed exclusively by the Electron application`）。
+**仅用于非 desktop profile：** `dsh plugin --profile <name> add dsh-packycode-api@1.1.5`。不要对 `desktop` 使用它 —— CLI 会直接拒绝（`profile "desktop" is managed exclusively by the Electron application`）。
 
 本地开发可以用绝对路径：`dsh plugin --profile <name> add link:/path/to/dsh-packycode-api`。
 
@@ -77,6 +78,8 @@ dsh-packycode-api
 
 ## 日常使用
 
+**选择显示的模型。** 在 **设置 → PackyCode → 显示的模型** 中勾选要在切换列表里看到的模型，默认全选，也支持「全选」和「全不选」。选择保存在当前 profile，修改后立即生效；取消勾选不会中断已有会话。后续新增的模型默认勾选。
+
 **换 Key。** Key 按添加顺序使用。点「切到此 Key」指定优先使用的 Key，下一轮就生效；「重命名」改备注（最多 60 字，不能为空）；充值或更换后点「重新启用」。
 
 **看分组。** 「账户与 Key」里每个 Key 下面列出它所在的 PackyCode 分组（鼠标悬停可看分组说明），以及能用哪些模型：✓ 可用、◐ 部分可用、✕ 不可用。分组由网关自己报出（对一个不存在的模型 id 的拒绝里会写明「已选分组」，不产生费用），再对照 PackyCode 公开的模型分组表。Claude 需要 `cc` / `cc-sale` / `cc-expensive` / `claude-officially` 之一（`claude-haiku-5-5` 只在 `cc` 和 `claude-officially`）；GPT 需要 `codex` / `codex-sale`；DeepSeek 需要 `deepseek-officially` / `deepseek-sale`。
@@ -142,12 +145,17 @@ Claude Code CLI → 本机临时 MCP web_search → 插件选定的 DeepSeek/GPT
 | `deepseek-flash` | HTTP，chat/completions | 可关；`low` / `high` / `max` | `deepseek-officially`、`deepseek-sale` |
 | `gpt-6.1-sol` | HTTP，Responses，可带图 | 不能关；`low` / `medium` / `high` / `xhigh` / `max` | `codex`、`codex-sale` |
 | `gpt-6-astra` | 同上 | 同上 | 同上 |
+| `grok-4.7`（Grok 4.7） | HTTP，Responses，可带图；500k 上下文 | 不能关；`low` / `medium` / `high` / `xhigh` | 以设置页从网关读取的 Grok 分组覆盖为准 |
 | `claude-opus-5-5` | 本机 Claude Code CLI | 选择器档位同上，实际档位由 CLI 决定 | 能给官方 CLI 用的分组，比如cc分组 |
 | `claude-sonnet-5-5` | 同上 | 同上 | 同上 |
 | `claude-haiku-5-5` | 同上；会话标题也固定走它 | 同上 | 同上 |
 
 列表里看得到模型，不代表当前令牌分组一定放行。换分组时不要把对应分组一起去掉。
 
+Grok 4.7 的上下文与推理档位来自 [官方文档](https://docs.x.ai/developers/grok-4-7)。官方没有单独限制文字输出长度；插件将输出上限设为上下文大小，并按每次请求的剩余上下文收紧。
+
+Responses 请求只有 GPT 模型保留 `prompt_cache_key`，其他 Responses 模型默认省略。当前网关的 Grok 路由会将这个字段误报成 `Incorrect API key provided`。
+
 <details>
 <summary>协议、分组和 CLI 的具体约束</summary>
 

package/lib/client.js

@@ -84,6 +84,14 @@ window.__ModuleLoader__.load({
 			groupsMiss: "不可用",
 			groupsPartial: "部分",
 			groupsStale: "分组为上次读取的结果",
+			modelsTitle: "显示的模型",
+			modelsIntro: "切换模型时只显示已勾选的 PackyCode 模型，默认全选。修改后立即生效；已有会话仍可继续使用原模型。",
+			modelsChecking: "正在读取模型设置…",
+			modelsFailed: "模型设置读取或保存失败",
+			modelsAll: "全选",
+			modelsNone: "全不选",
+			modelsCount: "已选 {count} / {total}",
+			modelsEmpty: "未勾选任何模型，切换列表将隐藏 PackyCode 的模型。",
 			advanced: "高级：接口地址",
 			apiHost: "模型接口地址",
 			statusHost: "余额接口地址",
@@ -162,6 +170,14 @@ window.__ModuleLoader__.load({
 		};
 		const en = {
 			nav: "PackyCode",
+			modelsTitle: "Visible models",
+			modelsIntro: "Only selected PackyCode models appear when switching models. All are selected by default. Changes apply immediately; existing sessions can keep their current model.",
+			modelsChecking: "Reading model settings…",
+			modelsFailed: "Could not read or save model settings",
+			modelsAll: "Select all",
+			modelsNone: "Select none",
+			modelsCount: "{count} / {total} selected",
+			modelsEmpty: "No models selected. PackyCode models are hidden from the picker.",
 			intro: "Paste a PackyCode (PackyAPI) API key to use the built-in model route. Keys are used in order: an exhausted or rejected key hands over to the next one, and a key whose groups cannot reach the selected model is passed over for one whose groups can.",
 			accountsTitle: "Accounts and keys",
 			refresh: "Refresh",
@@ -364,6 +380,13 @@ window.__ModuleLoader__.load({
 .pkc-reach>span[data-state=no]{color:var(--dsw-alias-label-caption);text-decoration:line-through}
 .pkc-add{display:flex;flex-direction:column;gap:8px;padding-top:14px;border-top:.5px solid var(--dsw-alias-border-l2)}
 
+.pkc-models{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:8px;margin:0;padding:0;min-width:0;border:0}
+.pkc-model{display:flex;align-items:center;gap:10px;min-width:0;padding:10px 12px;border-radius:var(--dsw-radius-md,12px);background:var(--dsw-alias-interactive-bg-hover);cursor:pointer}
+.pkc-model>input{flex:none;width:16px;height:16px;margin:0;accent-color:var(--dsw-alias-state-business-primary)}
+.pkc-model>span{display:flex;flex-direction:column;min-width:0;gap:2px}
+.pkc-model b{font-size:13px;font-weight:500}
+.pkc-models:disabled .pkc-model{opacity:.5;cursor:not-allowed}
+
 .pkc-setting{display:grid;grid-template-columns:112px minmax(0,1fr);gap:6px 16px;align-items:start}
 .pkc-setting>.pkc-label{padding-top:5px}
 .pkc-setting>div{display:flex;flex-direction:column;gap:6px;min-width:0}
@@ -389,6 +412,7 @@ window.__ModuleLoader__.load({
 @media (max-width:640px){
   .pkc-stats{grid-template-columns:1fr}
   .pkc-setting{grid-template-columns:1fr}
+  .pkc-models{grid-template-columns:1fr}
   .pkc-setting>.pkc-label{padding-top:0}
 }
 `;
@@ -473,6 +497,7 @@ window.__ModuleLoader__.load({
 		const MODEL_FAMILIES = [
 			["DeepSeek", ["deepseek-flash"]],
 			["GPT", ["gpt-6.1-sol", "gpt-6-astra"]],
+			["Grok", ["grok-4.7"]],
 			["Claude", [
 				"claude-opus-5-5",
 				"claude-sonnet-5-5",
@@ -1006,6 +1031,95 @@ window.__ModuleLoader__.load({
 				]
 			});
 		}
+		function ModelsCard({ call, t }) {
+			const [state, setState] = react.useState();
+			const [busy, setBusy] = react.useState(false);
+			const [error, setError] = react.useState();
+			react.useEffect(() => {
+				let live = true;
+				call("models/status").then((value) => {
+					if (live) setState(value);
+				}).catch((failure) => {
+					if (live) setError(clearMessage(failure));
+				});
+				return () => {
+					live = false;
+				};
+			}, [call]);
+			const models = state?.models ?? [];
+			const selectedIds = models.filter((model) => model.selected).map((model) => model.id);
+			const disabled = busy || state?.writable !== true;
+			const update = (ids) => {
+				if (disabled) return;
+				setBusy(true);
+				setError(void 0);
+				call("models/update", { selectedIds: ids }).then(setState).catch((failure) => setError(clearMessage(failure))).finally(() => setBusy(false));
+			};
+			return /* @__PURE__ */ (0, react_jsx_runtime.jsxs)(Card, {
+				title: t("modelsTitle"),
+				aside: state !== void 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+					className: "pkc-meta",
+					children: fill(t("modelsCount"), {
+						count: selectedIds.length,
+						total: models.length
+					})
+				}),
+				children: [
+					/* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+						className: "pkc-note",
+						children: t("modelsIntro")
+					}),
+					state === void 0 && error === void 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+						className: "pkc-note",
+						role: "status",
+						children: t("modelsChecking")
+					}),
+					state !== void 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsxs)(react_jsx_runtime.Fragment, { children: [
+						/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
+							className: "pkc-actions",
+							children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)(Button, {
+								disabled: disabled || selectedIds.length === models.length,
+								onClick: () => update(models.map((model) => model.id)),
+								children: t("modelsAll")
+							}), /* @__PURE__ */ (0, react_jsx_runtime.jsx)(Button, {
+								disabled: disabled || selectedIds.length === 0,
+								onClick: () => update([]),
+								children: t("modelsNone")
+							})]
+						}),
+						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("fieldset", {
+							className: "pkc-models",
+							"aria-label": t("modelsTitle"),
+							disabled,
+							children: models.map((model) => /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("label", {
+								className: "pkc-model",
+								children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("input", {
+									type: "checkbox",
+									checked: model.selected,
+									onChange: (event) => update(event.target.checked ? [...selectedIds, model.id] : selectedIds.filter((id) => id !== model.id))
+								}), /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("span", { children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("b", { children: model.name }), /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+									className: "pkc-meta pkc-mono",
+									children: model.id
+								})] })]
+							}, model.id))
+						}),
+						selectedIds.length === 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+							className: "pkc-note",
+							children: t("modelsEmpty")
+						}),
+						state.writable !== true && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+							className: "pkc-note",
+							children: t("searchNotWritable")
+						})
+					] }),
+					error !== void 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+						className: "pkc-error",
+						role: "alert",
+						children: `${t("modelsFailed")}: ${error}`
+					})
+				]
+			});
+		}
 		/** Web search routing and backend, written through the host. */
 		function SearchCard({ call, t }) {
 			const [state, setState] = react.useState();
@@ -1469,6 +1583,10 @@ window.__ModuleLoader__.load({
 						call,
 						t
 					}),
+					/* @__PURE__ */ (0, react_jsx_runtime.jsx)(ModelsCard, {
+						call,
+						t
+					}),
 					/* @__PURE__ */ (0, react_jsx_runtime.jsx)(SearchCard, {
 						call,
 						t

package/lib/index.js

@@ -544,7 +544,8 @@ function createBalanceReader({ listKeys, getHosts, fetchImpl = ambientFetch, now
 * model does not support is refused before the request is sent: Claude Opus
 * 5.5 (platform.claude.com effort docs), GPT-6.1 Sol and GPT-6 Astra
 * `reasoning.effort` (developers.openai.com model pages), DeepSeek thinking
-* mode (`thinking` toggle plus `low|high|max` effort).
+* mode (`thinking` toggle plus `low|high|max` effort), and Grok 4.7
+* (docs.x.ai/developers/grok-4-7).
 *
 * @module dsh-packycode-api/catalog
 */
@@ -586,6 +587,11 @@ const ALWAYS_THINKING_LEVELS = Object.freeze({
 	xhigh: "xhigh",
 	max: "max"
 });
+/** Grok 4.7 supports low | medium | high | xhigh, with no off or max. */
+const GROK_LEVELS = Object.freeze({
+	...ALWAYS_THINKING_LEVELS,
+	max: null
+});
 const PACKYCODE_MODELS = Object.freeze([
 	Object.freeze({
 		id: "deepseek-flash",
@@ -632,6 +638,20 @@ const PACKYCODE_MODELS = Object.freeze([
 		maxTokens: 128e3,
 		thinkingLevelMap: ALWAYS_THINKING_LEVELS
 	}),
+	Object.freeze({
+		id: "grok-4.7",
+		name: "Grok 4.7",
+		api: "openai-responses",
+		provider: PROVIDER,
+		baseUrl: RESPONSES_BASE,
+		reasoning: true,
+		input: Object.freeze(["text", "image"]),
+		cost: NO_COST,
+		contextWindow: 5e5,
+		maxTokens: 5e5,
+		thinkingLevelMap: GROK_LEVELS,
+		compat: Object.freeze({ supportsLongCacheRetention: false })
+	}),
 	Object.freeze({
 		id: "claude-opus-5-5",
 		name: "Claude Opus 5.5",
@@ -4896,6 +4916,134 @@ var PackyCodeKeyRing = class {
 	}
 };
 //#endregion
+//#region src/preferences.js
+/**
+* Where the plugin's preferences are read from and written to, on both
+* settings generations DSH has shipped.
+*
+* - DSH 0.1.5 installs a settings *section*: the section hands back a live
+*   source and writes go through `settings.update(namespace, patch)`.
+* - DSH 0.2 has no sections: a preference is a *volatile* Config field of the
+*   plugin's own row, read through a live reference, written through
+*   `settings.update(rowId, patch)`, and announced by `loader/volatile-update`.
+*   Only volatile fields are writable there, so the host overrides stay
+*   read-only while web search and model visibility are editable.
+*
+* @module dsh-packycode-api/preferences
+*/
+/**
+* Mark a preference editable without restarting the plugin. DSH 0.2 stores
+* plugin preferences as volatile Config fields and writes only those. The
+* peer dependency requires the schema version that implements `volatile()`.
+*/
+const live = (schema) => schema.volatile();
+/** Read a Config field that may arrive as a volatile reference. */
+const fieldValue = (value) => value !== null && typeof value === "object" && typeof value.get === "function" ? value.get() : value;
+/** A preference target nothing can write to yet. */
+function unwritable(message) {
+	return {
+		writable: false,
+		set: async () => {
+			throw new Error(message);
+		}
+	};
+}
+/**
+* Connect the preferences to the settings service the host provides.
+* @param settingsCtx - the scope the `settings` inject handed over.
+* @param options - the plugin context and Config, the section namespace, the
+*   current source and how to replace it, what to do when the section changes,
+*   and the preference targets this fills in (host overrides, search, models).
+*/
+function connectSettings(settingsCtx, { ctx, Config, namespace, source, setSource, onChange, hostPreference, searchPreference, modelPreference }) {
+	const settings = settingsCtx.settings;
+	if (typeof settings?.installSection === "function") {
+		try {
+			settings.installSection(ctx, namespace, Config, source(), {
+				setSource: (current) => setSource(typeof current === "function" ? () => current() ?? {} : () => current ?? {}),
+				onChange
+			});
+			if (typeof settings.update === "function") {
+				const write = (patch) => settings.update(namespace, patch);
+				const target = {
+					writable: settings.writable !== false,
+					set: write
+				};
+				Object.assign(hostPreference, target);
+				Object.assign(searchPreference, target);
+				Object.assign(modelPreference, target);
+			}
+		} catch (error) {
+			ctx.logger?.warn?.("packycode-api: host overrides unavailable, defaults stand: %s", error.message);
+		}
+		return;
+	}
+	if (typeof settings?.update !== "function") return;
+	const rowId = ctx.fiber?.entry?.options?.id ?? namespace;
+	const target = {
+		writable: settings.writable !== false,
+		set: (patch) => settings.update(rowId, patch)
+	};
+	Object.assign(searchPreference, target);
+	Object.assign(modelPreference, target);
+	if (typeof settings.configure === "function") {
+		const scope = typeof settingsCtx.effect === "function" ? settingsCtx : ctx;
+		try {
+			scope.effect(() => settings.configure({ auto: false }, ctx.fiber), "packycode-api: settings page policy");
+		} catch (error) {
+			ctx.logger?.warn?.("packycode-api: could not hide the generated settings page: %s", error.message);
+		}
+	}
+}
+//#endregion
+//#region src/model-selection.js
+/** Profile preferences for the models advertised in PackyCode's picker. */
+/** Store exclusions so new catalog models are selected by default as well. */
+function readHiddenModels(preference) {
+	const value = fieldValue(preference?.hiddenModels);
+	if (!Array.isArray(value)) return [];
+	const hidden = new Set(value);
+	return PACKYCODE_MODEL_IDS.filter((id) => hidden.has(id));
+}
+function createModelSelectionController({ readPreference, writePreference, isWritable, onChange }) {
+	const hidden = () => readHiddenModels(readPreference());
+	let advertised = hidden().join(",");
+	const reconcile = () => {
+		const next = hidden().join(",");
+		if (next === advertised) return;
+		onChange?.();
+		advertised = next;
+	};
+	const status = () => {
+		const excluded = new Set(hidden());
+		return {
+			writable: isWritable() === true,
+			models: PACKYCODE_MODELS.map(({ id, name }) => ({
+				id,
+				name,
+				selected: !excluded.has(id)
+			}))
+		};
+	};
+	return Object.freeze({
+		status,
+		reconcile,
+		isVisible: (id) => !hidden().includes(id),
+		async update({ selectedIds } = {}) {
+			if (!Array.isArray(selectedIds) || selectedIds.some((id) => !PACKYCODE_MODEL_IDS.includes(id))) throw new Error("That PackyCode model selection is not supported");
+			if (isWritable() !== true) throw new Error("PackyCode settings are not writable in this profile");
+			const selected = new Set(selectedIds);
+			try {
+				await writePreference({ hiddenModels: PACKYCODE_MODEL_IDS.filter((id) => !selected.has(id)) });
+			} catch {
+				throw new Error("PackyCode could not save the model selection");
+			}
+			reconcile();
+			return status();
+		}
+	});
+}
+//#endregion
 //#region src/plugin-version.js
 /**
 * Version self-knowledge for the settings panel.
@@ -5218,85 +5366,6 @@ function createPackyCodePluginManager({ fetchImpl = ambientFetch, runCommand = s
 	});
 }
 //#endregion
-//#region src/preferences.js
-/**
-* Where the plugin's preferences are read from and written to, on both
-* settings generations DSH has shipped.
-*
-* - DSH 0.1.5 installs a settings *section*: the section hands back a live
-*   source and writes go through `settings.update(namespace, patch)`.
-* - DSH 0.2 has no sections: a preference is a *volatile* Config field of the
-*   plugin's own row, read through a live reference, written through
-*   `settings.update(rowId, patch)`, and announced by `loader/volatile-update`.
-*   Only volatile fields are writable there, so the host overrides stay
-*   read-only while the web search preference is editable.
-*
-* @module dsh-packycode-api/preferences
-*/
-/**
-* Mark a preference editable without restarting the plugin. DSH 0.2 stores
-* plugin preferences as volatile Config fields and writes only those; an older
-* schema library has no `volatile()` and keeps a plain field.
-*/
-const live = (schema) => typeof schema.volatile === "function" ? schema.volatile() : schema;
-/** Read a Config field that may arrive as a volatile reference. */
-const fieldValue = (value) => value !== null && typeof value === "object" && typeof value.get === "function" ? value.get() : value;
-/** A preference target nothing can write to yet. */
-function unwritable(message) {
-	return {
-		writable: false,
-		set: async () => {
-			throw new Error(message);
-		}
-	};
-}
-/**
-* Connect the preferences to the settings service the host provides.
-* @param settingsCtx - the scope the `settings` inject handed over.
-* @param options - the plugin context and Config, the section namespace, the
-*   current source and how to replace it, what to do when the section changes,
-*   and the two preference targets this fills in (host overrides, search).
-*/
-function connectSettings(settingsCtx, { ctx, Config, namespace, source, setSource, onChange, hostPreference, searchPreference }) {
-	const settings = settingsCtx.settings;
-	if (typeof settings?.installSection === "function") {
-		try {
-			settings.installSection(ctx, namespace, Config, source(), {
-				setSource: (current) => setSource(typeof current === "function" ? () => current() ?? {} : () => current ?? {}),
-				onChange
-			});
-			if (typeof settings.update === "function") {
-				const write = (patch) => settings.update(namespace, patch);
-				Object.assign(hostPreference, {
-					writable: true,
-					set: write
-				});
-				Object.assign(searchPreference, {
-					writable: true,
-					set: write
-				});
-			}
-		} catch (error) {
-			ctx.logger?.warn?.("packycode-api: host overrides unavailable, defaults stand: %s", error.message);
-		}
-		return;
-	}
-	if (typeof settings?.update !== "function") return;
-	const rowId = ctx.fiber?.entry?.options?.id ?? namespace;
-	Object.assign(searchPreference, {
-		writable: settings.writable !== false,
-		set: (patch) => settings.update(rowId, patch)
-	});
-	if (typeof settings.configure === "function") {
-		const scope = typeof settingsCtx.effect === "function" ? settingsCtx : ctx;
-		try {
-			scope.effect(() => settings.configure({ auto: false }, ctx.fiber), "packycode-api: settings page policy");
-		} catch (error) {
-			ctx.logger?.warn?.("packycode-api: could not hide the generated settings page: %s", error.message);
-		}
-	}
-}
-//#endregion
 //#region src/provider.js
 /**
 * The PackyCode pi-ai provider, built in code so the user configures no route.
@@ -5326,7 +5395,7 @@ function keyRingAuth() {
 }
 /** Build the route's pi-ai provider (unguarded; the plugin wraps its streams). */
 function createPackyCodeProvider() {
-	return createProvider({
+	const provider = createProvider({
 		id: PROVIDER,
 		name: DISPLAY_NAME,
 		baseUrl: DEFAULT_API_HOST,
@@ -5338,6 +5407,15 @@ function createPackyCodeProvider() {
 			"anthropic-messages": anthropicMessagesApi()
 		}
 	});
+	const requestOptions = (model, options) => model.api === "openai-responses" && !model.id.startsWith("gpt-") ? {
+		...options,
+		cacheRetention: "none"
+	} : options;
+	return Object.freeze({
+		...provider,
+		stream: (model, context, options) => provider.stream(model, context, requestOptions(model, options)),
+		streamSimple: (model, context, options) => provider.streamSimple(model, context, requestOptions(model, options))
+	});
 }
 /**
 * Observe a pi-ai event stream and hand a key-level failure to the plugin.
@@ -5418,7 +5496,7 @@ function guardKeyRotation(stream, { onKeyFailure, key } = {}) {
 //#region src/route.js
 /**
 * The HTTP model route: the pi-ai provider profile and the adapter that
-* serves the catalog's HTTP models (DeepSeek and GPT) with the ring's keys.
+* serves the catalog's HTTP models (DeepSeek, GPT and Grok) with the ring's keys.
 *
 * @module dsh-packycode-api/route
 */
@@ -5508,7 +5586,7 @@ function createPackyCodeProfile(provider) {
 *   supplies none, and the attachment store image input is read from.
 * @returns a `PiAiAdapter` serving the `packycode` route.
 */
-function createRouteAdapter({ ring, keys, fallbackSessionId, resolveAttachments }) {
+function createRouteAdapter({ ring, keys, fallbackSessionId, resolveAttachments, isModelVisible = () => true }) {
 	const raw = createPackyCodeProvider();
 	/**
 	* The gateway's Codex-group check refuses a Responses request that carries
@@ -5541,7 +5619,11 @@ function createRouteAdapter({ ring, keys, fallbackSessionId, resolveAttachments
 		streamSimple: guarded("streamSimple")
 	});
 	const profiles = /* @__PURE__ */ new Map([[PROVIDER, createPackyCodeProfile(provider)]]);
-	return new PiAiAdapter({
+	return new class extends PiAiAdapter {
+		async listModels(provider) {
+			return (await super.listModels(provider)).filter((model) => isModelVisible(model.id));
+		}
+	}({
 		profiles: () => profiles,
 		resolveApiKey: async () => {
 			const active = await keys.active();
@@ -5566,7 +5648,7 @@ function createRouteAdapter({ ring, keys, fallbackSessionId, resolveAttachments
 * Every reply carries only what this plugin owns: key labels and state, the
 * balance and group projections the host built, host overrides, whether this
 * device has the Claude Code CLI, the plugin version, and the web search
-* preference. Key material never crosses this boundary.
+* preference and model visibility. Key material never crosses this boundary.
 *
 * @module dsh-packycode-api/rpc
 */
@@ -5576,7 +5658,11 @@ const ok = (value) => ({
 });
 const failed = (message) => ({
 	ok: false,
-	error: { message }
+	error: {
+		code: "packycode/request-failed",
+		message,
+		details: {}
+	}
 });
 /** Only sentences this plugin authored may reach the browser. */
 const SAFE_MESSAGE = /^(?:PackyCode|That |Unknown |PackyCode's |add |the )[\s\S]{0,180}$/u;
@@ -5588,7 +5674,7 @@ const keyId = (payload) => String(payload?.id ?? "");
 *   web search controller (without one, its endpoints refuse).
 * @returns a handler for `connection.rpc.handle(CHANNEL, handler)`.
 */
-function createPackyCodeRpc({ ring, balance, groups, hosts, preference, claudeCli, pluginManager, search }) {
+function createPackyCodeRpc({ ring, balance, groups, hosts, preference, claudeCli, pluginManager, search, modelSelection }) {
 	const need = (service, message) => {
 		if (service === void 0) throw new Error(message);
 		return service;
@@ -5597,6 +5683,7 @@ function createPackyCodeRpc({ ring, balance, groups, hosts, preference, claudeCl
 	const manager = () => need(pluginManager, "PackyCode plugin version is unavailable");
 	const webSearch = () => need(search, "PackyCode web search is unavailable in this runtime");
 	const groupReader = () => need(groups, "PackyCode key groups are unavailable in this runtime");
+	const models = () => need(modelSelection, "PackyCode model selection is unavailable in this runtime");
 	const status = async () => ({
 		...await ring.list(),
 		hosts: hosts(),
@@ -5661,7 +5748,9 @@ function createPackyCodeRpc({ ring, balance, groups, hosts, preference, claudeCl
 		"search/update": (payload) => webSearch().update({
 			searchProvider: payload?.searchProvider,
 			searchBackend: payload?.searchBackend
-		})
+		}),
+		"models/status": () => models().status(),
+		"models/update": (payload) => models().update({ selectedIds: payload?.selectedIds })
 	};
 	return async (endpoint, payload, signal) => {
 		try {
@@ -6406,9 +6495,11 @@ const FOREIGN_ROUTERS = Object.freeze({
 });
 /** Normalize a stored preference; anything unknown reads as the default. */
 function readSearchChoice(value) {
+	const provider = fieldValue(value?.searchProvider);
+	const selectedBackend = fieldValue(value?.searchBackend);
 	return {
-		mode: SEARCH_MODES.includes(value?.searchProvider) ? value.searchProvider : SEARCH_MODE_DEFAULT,
-		backend: SEARCH_BACKENDS.includes(value?.searchBackend) ? value.searchBackend : DEFAULT_SEARCH_BACKEND
+		mode: SEARCH_MODES.includes(provider) ? provider : SEARCH_MODE_DEFAULT,
+		backend: SEARCH_BACKENDS.includes(selectedBackend) ? selectedBackend : DEFAULT_SEARCH_BACKEND
 	};
 }
 /** Only sentences this plugin wrote reach the browser. */
@@ -6592,7 +6683,9 @@ const Config = z.object({
 	*/
 	searchProvider: live(z.union([...SEARCH_MODES]).default(SEARCH_MODE_DEFAULT)),
 	/** Which PackyCode model runs a search: `deepseek` or `gpt`. */
-	searchBackend: live(z.union([...SEARCH_BACKENDS]).default(DEFAULT_SEARCH_BACKEND))
+	searchBackend: live(z.union([...SEARCH_BACKENDS]).default(DEFAULT_SEARCH_BACKEND)),
+	/** Only the picker is filtered; an existing session can keep its model. */
+	hiddenModels: live(z.array(z.string()).default([]))
 });
 function apply(ctx, config) {
 	const ring = new PackyCodeKeyRing(ctx.credentials);
@@ -6600,7 +6693,8 @@ function apply(ctx, config) {
 		apiHost: normalizeHost(config?.apiHost, DEFAULT_API_HOST),
 		statusHost: normalizeHost(config?.statusHost, DEFAULT_STATUS_HOST),
 		searchProvider: fieldValue(config?.searchProvider),
-		searchBackend: fieldValue(config?.searchBackend)
+		searchBackend: fieldValue(config?.searchBackend),
+		hiddenModels: fieldValue(config?.hiddenModels)
 	});
 	const hosts = () => {
 		const current = source() ?? {};
@@ -6646,6 +6740,17 @@ function apply(ctx, config) {
 	};
 	const fallbackSessionId = `${PLUGIN_ID}-${randomUUID()}`;
 	const attachments = () => ctx.get?.("attachments") ?? ctx.attachments;
+	const modelPreference = {
+		writable: false,
+		set: void 0
+	};
+	let refreshModels = () => {};
+	const modelSelection = createModelSelectionController({
+		readPreference: () => source() ?? {},
+		writePreference: (patch) => modelPreference.set(patch),
+		isWritable: () => modelPreference.writable === true && typeof modelPreference.set === "function",
+		onChange: () => refreshModels()
+	});
 	/**
 	* The Claude Code CLI runner. PackyCode serves its Claude models only to the
 	* official CLI, so CLI-backed models are run by that CLI itself — with this
@@ -6704,12 +6809,13 @@ function apply(ctx, config) {
 		const configured = config?.claudeCliMode;
 		return configured === void 0 || configured === "auto" ? claudeModeForSession(ctx, session) : configured;
 	};
-	ctx.llm.registerAdapter([PROVIDER], createClaudeCliAdapter({
+	const registration = ctx.llm.registerAdapter([PROVIDER], createClaudeCliAdapter({
 		inner: createRouteAdapter({
 			ring,
 			keys,
 			fallbackSessionId,
-			resolveAttachments: attachments
+			resolveAttachments: attachments,
+			isModelVisible: modelSelection.isVisible
 		}),
 		runner: claudeRunner,
 		resolveMode: () => {
@@ -6720,6 +6826,10 @@ function apply(ctx, config) {
 		resolveAttachments: attachments,
 		explainKey: (runKey) => keys.describe(runKey)
 	}));
+	refreshModels = () => {
+		if (typeof registration?.replace === "function") registration.replace([PROVIDER]);
+		else ctx.emit?.("llm/adapters-updated");
+	};
 	ctx.llm.registerConfigurableProviders([{
 		provider: PROVIDER,
 		displayName: DISPLAY_NAME,
@@ -6771,12 +6881,15 @@ function apply(ctx, config) {
 		onChange: () => {
 			balance.invalidate();
 			groups.invalidate();
+			modelSelection.reconcile();
 			search.reconcile();
 		},
 		hostPreference,
-		searchPreference
+		searchPreference,
+		modelPreference
 	}));
 	ctx.on?.("loader/volatile-update", () => {
+		modelSelection.reconcile();
 		search.reconcile();
 	});
 	/**
@@ -6798,7 +6911,8 @@ function apply(ctx, config) {
 		preference: hostPreference,
 		claudeCli,
 		pluginManager: createPackyCodePluginManager(),
-		search
+		search,
+		modelSelection
 	});
 	/**
 	* Connection registers a channel through `owner.webServer`, read on its own
@@ -6820,4 +6934,4 @@ function apply(ctx, config) {
 	});
 }
 //#endregion
-export { AUTO_CLAUDE_MODE, CHANNEL, CLAUDE_CLI_MODES, CLAUDE_INSTALL_COMMAND, CLAUDE_MISSING_MESSAGE, CLAUDE_NPM_PACKAGE, CLAUDE_TOOL_INSTRUCTIONS, CLI_BACKED_MODEL_IDS, CLI_IMAGE_LIMITS, Config, DEFAULT_API_HOST, DEFAULT_APPEND_SYSTEM_PROMPT, DEFAULT_SEARCH_BACKEND, DEFAULT_STATUS_HOST, DISPLAY_NAME, LEGACY_STATUS_HOSTS, PACKYCODE_AUTO_SEARCH_PROVIDER_ID, PACKYCODE_MODELS, PACKYCODE_MODEL_IDS, PACKYCODE_SEARCH_PROVIDER_ID, PLUGIN_ID, PROVIDER, PackyCodeKeyRing, SEARCH_BACKENDS, SEARCH_BACKEND_MODELS, SEARCH_MODES, SETTINGS_NAMESPACE, TITLE_MODEL_ID, TITLE_MODEL_ROUTES, accountHostOrder, apply, assertApiKey, buildClaudeArgs, buildClaudeEnvironment, buildClaudeInput, buildDelegatedContent, buildSearchRequest, capClaudeMode, catalogCoverage, classifyClientPolicy, classifyGatewayFailure, claudeBinaryCandidates, claudeModeFor, claudeModeForSession, cliSearchInstructions, createBalanceReader, createClaudeCliAdapter, createClaudeCliManager, createClaudeCodeTool, createClaudeRunner, createClaudeSearchBridge, createGroupReader, createKeyChooser, createPackyCodeAutoSearchProvider, createPackyCodeProfile, createPackyCodeProvider, createPackyCodeRpc, createPackyCodeSearchProvider, createProfileSearchComposition, createRouteAdapter, createSearchComposition, createSearchController, delegationInstructions, describeRunKey, explainCliClientPolicyFailure, explainCliGroupFailure, explainClientPolicyFailure, explainNpmFailure, findClaudeBinary, guardKeyRotation, inject, keyNote, locateClaudeBinary, locateNpm, name, normalizeFailureMessage, normalizeHost, npmCandidates, parseBillingSubscription, parseBillingUsage, parseClaudeResult, parseClaudeVersion, parseMessagesSearchResponse, parsePricing, parseResponsesSearchResponse, parseSelectedGroups, parseTokenUsage, pickKeyForModel, planModeForSession, planModeForToolExecution, readClaudeStreamEvents, readSearchChoice, renderAuxiliaryPrompt, renderDelegatedPrompt, resolveSpawnCommand, statusHostOrder, summarizeToolUse };
+export { AUTO_CLAUDE_MODE, CHANNEL, CLAUDE_CLI_MODES, CLAUDE_INSTALL_COMMAND, CLAUDE_MISSING_MESSAGE, CLAUDE_NPM_PACKAGE, CLAUDE_TOOL_INSTRUCTIONS, CLI_BACKED_MODEL_IDS, CLI_IMAGE_LIMITS, Config, DEFAULT_API_HOST, DEFAULT_APPEND_SYSTEM_PROMPT, DEFAULT_SEARCH_BACKEND, DEFAULT_STATUS_HOST, DISPLAY_NAME, LEGACY_STATUS_HOSTS, PACKYCODE_AUTO_SEARCH_PROVIDER_ID, PACKYCODE_MODELS, PACKYCODE_MODEL_IDS, PACKYCODE_SEARCH_PROVIDER_ID, PLUGIN_ID, PROVIDER, PackyCodeKeyRing, SEARCH_BACKENDS, SEARCH_BACKEND_MODELS, SEARCH_MODES, SETTINGS_NAMESPACE, TITLE_MODEL_ID, TITLE_MODEL_ROUTES, accountHostOrder, apply, assertApiKey, buildClaudeArgs, buildClaudeEnvironment, buildClaudeInput, buildDelegatedContent, buildSearchRequest, capClaudeMode, catalogCoverage, classifyClientPolicy, classifyGatewayFailure, claudeBinaryCandidates, claudeModeFor, claudeModeForSession, cliSearchInstructions, createBalanceReader, createClaudeCliAdapter, createClaudeCliManager, createClaudeCodeTool, createClaudeRunner, createClaudeSearchBridge, createGroupReader, createKeyChooser, createModelSelectionController, createPackyCodeAutoSearchProvider, createPackyCodeProfile, createPackyCodeProvider, createPackyCodeRpc, createPackyCodeSearchProvider, createProfileSearchComposition, createRouteAdapter, createSearchComposition, createSearchController, delegationInstructions, describeRunKey, explainCliClientPolicyFailure, explainCliGroupFailure, explainClientPolicyFailure, explainNpmFailure, findClaudeBinary, guardKeyRotation, inject, keyNote, locateClaudeBinary, locateNpm, name, normalizeFailureMessage, normalizeHost, npmCandidates, parseBillingSubscription, parseBillingUsage, parseClaudeResult, parseClaudeVersion, parseMessagesSearchResponse, parsePricing, parseResponsesSearchResponse, parseSelectedGroups, parseTokenUsage, pickKeyForModel, planModeForSession, planModeForToolExecution, readClaudeStreamEvents, readHiddenModels, readSearchChoice, renderAuxiliaryPrompt, renderDelegatedPrompt, resolveSpawnCommand, statusHostOrder, summarizeToolUse };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-packycode-api",
-  "version": "1.1.4",
+  "version": "1.1.5",
   "description": "Use a PackyCode (PackyAPI) API key in DeepSeek Harness through a built-in multi-protocol model route with key rotation and balance display",
   "type": "module",
   "main": "./lib/index.js",
@@ -76,7 +76,7 @@
     "@deepseek-ai/dsh-llm-pi-ai": ">=0.1.5-rc.1 <0.3.0-0",
     "@deepseek-ai/dsh-settings": ">=0.1.5-rc.1 <0.3.0-0",
     "@deepseek-ai/dsh-tools": ">=0.1.5-rc.1 <0.3.0-0",
-    "@deepseek-ai/schemastery": "^3.18.2",
+    "@deepseek-ai/schemastery": "^3.18.4",
     "@earendil-works/pi-ai": "0.85.1 || 0.86.0 || 0.86.1 || 0.87.0 || 0.87.1",
     "react": "^18.2.0"
   },
@@ -87,10 +87,11 @@
     "@deepseek-ai/dsh-llm-pi-ai": "0.1.5-rc.2",
     "@deepseek-ai/dsh-settings": "0.1.5-rc.2",
     "@deepseek-ai/dsh-tools": "0.1.5-rc.2",
-    "@deepseek-ai/schemastery": "3.18.2",
+    "@deepseek-ai/schemastery": "3.18.4",
     "@earendil-works/pi-ai": "0.85.1",
     "react": "18.3.1",
-    "tsdown": "0.22.2"
+    "tsdown": "0.22.2",
+    "yaml": "2.9.1"
   },
   "scripts": {
     "build": "tsdown --config tsdown.config.mjs",