@deepseek-ai/dsh-client-ui-tool 0.1.5-rc.2 → 0.1.6-alpha.2

package/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/client/ui-tool/README.md
-README.md: b8dd2a5e3c6743e496d585a2de238714f00e9f6b
-README.zh.md: 49e82c9fa70953d73171d466f36995ff2870c6b2
+README.md: 15dffa634660a5cf94081452481399821d09b25b
+README.zh.md: 6f01658e5fea4fefca9eded114971d3e88a13148

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-`dsh-client-ui-tool` is the client Tool presentation plugin of the dsh web client: it renders every tool call in the conversation. `ui-conversation` dispatches each ordered `tool-call` Conversation Node through the matching key of `conversation.chat.node`; this package renders its root and Code Dispatch children, then dispatches every atomic call through the keyed `tool.call.toolview` slot. Unregistered Tool names use the generic card. Business UI packages register only their wire Tool names and atomic views — they do not pair Session events, rebuild the transcript, or own root/subcall topology, because the Runtime remains authoritative for call/result pairing, lifecycle, and recursive `subCalls` projection.
+`dsh-client-ui-tool` is the client Tool presentation plugin of the dsh web client: it renders every tool call in the conversation. `ui-conversation` dispatches each ordered `tool-call` Conversation Node through the matching key of `conversation.chat.node`; this package renders its root and PTC dispatch children, then dispatches every atomic call through the keyed `tool.call.toolview` slot. Unregistered Tool names use the generic card. Business UI packages register only their wire Tool names and atomic views — they do not pair Session events, rebuild the transcript, or own root/subcall topology, because the Runtime remains authoritative for call/result pairing, lifecycle, and recursive `subCalls` projection.
 
 ## Table of Contents
 
@@ -39,11 +39,11 @@ ctx.slots.inject('tool.call.toolview', () =>
   }, BusinessToolRow))
 ```
 
-The owner payload is `ToolCallOwnerProps`: `callId`, `toolName`, the frozen `block`, optional `cwd` and `home`, the session-authorized `loadImage` loader (for a view whose result carries durable images), and plain `openFile`/`inspect` callbacks. A Code Dispatch block retains its event's `parentCallId`; a root Session call has no such field, so descendants route through the same keyed dispatch — a registered view such as `read_image` renders its card there, and unregistered descendants keep the generic flattened form. Path summaries relativize to the Session cwd first, then replace a leftover POSIX Host home with `~`; `filePath` and Host open keep the authored filesystem path. The registration receives the normal Session slot runtime share but no React node or Runtime service.
+The owner payload is `ToolCallOwnerProps`: `callId`, `toolName`, the frozen `block`, optional `cwd` and `home`, the session-authorized `loadImage` loader (for a view whose result carries durable images), and plain `openFile`/`inspect` callbacks. A PTC dispatch block retains its event's `parentCallId`; a root Session call has no such field, so descendants route through the same keyed dispatch — a registered view such as `read_image` renders its card there, and unregistered descendants keep the generic flattened form. Path summaries relativize to the Session cwd first, then replace a leftover POSIX Host home with `~`; `filePath` and Host open keep the authored filesystem path. The registration receives the normal Session slot runtime share but no React node or Runtime service.
 
 ### Built-in views
 
-This package owns the generic fallback and the built-in shell/pwsh, read, read_image, write/edit, running `str_replace_editor` `create`/`str_replace`, grep/glob, web, todo, question, and Code Dispatch presentations. Structured cards derive directly from first-party raw event fields; Host `presentCall` and `presentResult` values never enter the Client. Running and settled foreground standard `bash`/`pwsh` and `terminal_send` calls use terminal cards at the root and in Code Dispatch children, subject to the same argument, result, and error checks. Persistent `bash`/`pwsh` calls use terminal cards only while running. Shell output ending in a recognized spill-policy notice uses expandable generic output in shell rows and generic output in Details; a displaced or omitted exit marker cannot establish success. Settled persistent-shell results stay generic because reset and partial-output diagnostics do not always describe one process exit status; root persistent results are expandable, while background acknowledgements remain collapsed. A successful question row pairs call questions with result answers by their stable ids and shows readable question/answer lines when expanded. A cancelled or interrupted row shows its verdict and original questions without inventing answers. Unsupported, malformed, or ambiguous inputs fall back to flattened Tool input/result text. `ui-skill` demonstrates a business-owned registration for `skill`.
+This package owns the generic fallback and the built-in shell/pwsh, read, read_image, write/edit, running `str_replace_editor` `create`/`str_replace`, grep/glob, web, todo, question, and PTC dispatch presentations. Structured cards derive directly from first-party raw event fields; Host `presentCall` and `presentResult` values never enter the Client. Running and settled foreground standard `bash`/`pwsh` and `terminal_send` calls use terminal cards at the root and in PTC dispatch children, subject to the same argument, result, and error checks. Persistent `bash`/`pwsh` calls use terminal cards only while running. Shell output ending in a recognized spill-policy notice uses expandable generic output in shell rows and generic output in Details; a displaced or omitted exit marker cannot establish success. Settled persistent-shell results stay generic because reset and partial-output diagnostics do not always describe one process exit status; root persistent results are expandable, while background acknowledgements remain collapsed. A native or PTC dispatch failure carrying `AUTO_REVIEW_DENIED` shows the Auto review verdict in its collapsed row and one normalized not-executed reason when expanded; a missing or whitespace-only reason uses localized fallback text. A successful question row pairs call questions with result answers by their stable ids and shows readable question/answer lines when expanded. A cancelled or interrupted row shows its verdict and original questions without inventing answers. Unsupported, malformed, or ambiguous inputs fall back to flattened Tool input/result text. `ui-skill` demonstrates a business-owned registration for `skill`.
 
 -----
 
@@ -62,7 +62,11 @@ The package realizes one dispatch rule: atomic Tool views are keyed by wire Tool
 ### Cards
 
 
-Every card is read in place in the call tree; there is no second, full-height presentation of a selected call. Row renderers share one pure card model for each terminal, read, diff, search, and web card, and the image card's gallery renders through the tool-owned `tool.call.images` slot. These models validate raw call arguments, result content, failure state, persisted metadata, Code Dispatch `parentCallId`, and Session path facts. Unsupported or malformed inputs use flattened Tool result text. A file-path summary opens the file through the owner's `openFile`, which the chat view routes to the right Sidebar's text preview; `inspect` opens the trajectory view. Card-specific limits and fallback rules for the terminal, diff, read, search, and web cards remain in [the ui-primitives README](../ui-primitives/README.md); the image card's model in this package carries its own fallback rules.
+Every card is read in place in the call tree; there is no second, full-height presentation of a selected call. Row renderers share one pure card model for each terminal, read, diff, search, and web card, and the image card's gallery renders through the tool-owned `tool.call.images` slot. These models validate raw call arguments, result content, failure state, persisted metadata, PTC dispatch `parentCallId`, and Session path facts. Unsupported or malformed inputs use flattened Tool result text. A file-path summary opens the file through the owner's `openFile`, which the chat view routes to the right Sidebar's text preview; `inspect` opens the trajectory view. Card-specific limits and fallback rules for the terminal, diff, read, search, and web cards remain in [the ui-primitives README](../ui-primitives/README.md); the image card's model in this package carries its own fallback rules.
+
+Chat diff cards keep nine rows before folding, enough for a file header, one removed/added pair, and three context lines on either side. The collapsed row and expanded footer share the primitive's exact or coarse-replacement counts.
+
+An Auto denial takes precedence over keyed specialized views. Its generic row preserves the call identity, omits raw arguments, and normalizes the stored reason only for display: trim surrounding whitespace and collapse line separators to spaces, with localized fallback for an empty result. Session and SDK error details keep the original reason.
 
 The terminal model uses `hasSpillNotice` from the browser-safe `@deepseek-ai/dsh-spill-policy/notice` entry, not an independent UI pattern. The [spill-policy README](../../spill/spill-policy/README.md#shared-notice-ownership) owns notice formatting and recognition. This check conservatively selects generic output; matching text cannot authenticate its source, and replay leaves recorded result bytes untouched.
 </details>
@@ -77,6 +81,7 @@ These pages cover the conversation host, the view slots, and the card models.
 - [ui-conversation](../ui-conversation/README.md) — the chat surface dispatching `tool-call` nodes to this package.
 - [ui-primitives](../ui-primitives/README.md) — the output card atoms the built-in views compose.
 - [ui-skill](../ui-skill/README.md) — a business-owned registration for the `skill` tool.
+- [Auto review](../../experimental/auto-review/README.md) — the structured denial identity and user-visible reason owner.
 - [Conversation subsystem](../../../docs/subsystems/conversation.md) — how a business-owned feature registers a Conversation node.
 - [Slot system standard](../../../.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md) — the composition model behind the keyed slot.
 

package/README.zh.md

@@ -1,5 +1,5 @@
 ---
-description: "dsh Web 客户端的 Client 工具展示插件：整次调用树组合、keyed 按工具视图 slot 与内置原子工具卡片。"
+description: "dsh Web 客户端的 Client 工具展示插件：完整调用树的组合、按工具名称键控的视图 slot，以及内置原子工具卡片。"
 kind: "package-reference"
 ---
 
@@ -9,7 +9,7 @@ kind: "package-reference"
 
 ## 概述
 
-`dsh-client-ui-tool` 是 dsh Web 客户端的 Client 工具展示插件：它渲染对话中的每一次工具调用。`ui-conversation` 通过 `conversation.chat.node` 的匹配 key 分发每个已排序的 `tool-call` Conversation Node；本包渲染其中的 root 及其 Code Dispatch 子调用，并把每个原子调用通过 keyed slot `tool.call.toolview` 分发。没有注册的工具名称使用通用卡片。业务 UI 包只注册 wire 工具名称和原子视图——它们不配对会话事件、不重建 transcript，也不拥有 root/subcall 拓扑，因为运行时仍对 call/result 配对、生命周期与递归 `subCalls` 投影拥有最终决定权。
+`dsh-client-ui-tool` 是 dsh Web 客户端的 Client 工具展示插件：它渲染对话中的每一次工具调用。`ui-conversation` 通过 `conversation.chat.node` 的匹配 key 分发每个已排序的 `tool-call` Conversation Node；本包渲染其中的 root 及其 PTC dispatch 子调用，并把每个原子调用通过 keyed slot `tool.call.toolview` 分发。没有注册的工具名称使用通用卡片。业务 UI 包只注册 wire 工具名称和原子视图——它们不配对会话事件、不重建 transcript（文本记录），也不拥有 root/subcall 拓扑，因为运行时仍对 call/result 配对、生命周期与递归 `subCalls` 投影拥有最终决定权。
 
 ## 目录
 
@@ -39,11 +39,11 @@ ctx.slots.inject('tool.call.toolview', () =>
   }, BusinessToolRow))
 ```
 
-owner 载荷为 `ToolCallOwnerProps`：`callId`、`toolName`、冻结的 `block`、可选 `cwd` 与 `home`、会话授权的 `loadImage` loader（供结果携带持久图像的视图使用），以及普通的 `openFile`/`inspect` 回调。Code Dispatch block 保留事件的 `parentCallId`；root Session call 没有该字段，因此 descendant 走同一条按 key 分发——注册过视图的调用（如 `read_image`）在嵌套处也渲染其卡片，未注册的 descendant 保持 generic 压平形式。路径摘要先相对 Session cwd 缩短，再把剩余的 POSIX Host home 写成 `~`；`filePath` 与 Host 打开仍使用作者给出的文件系统路径。注册项会收到常规 Session slot runtime share，但不会收到 React node 或 runtime service。
+owner 载荷为 `ToolCallOwnerProps`：`callId`、`toolName`、冻结的 `block`、可选 `cwd` 与 `home`、会话授权的 `loadImage` loader（供结果携带持久图像的视图使用），以及普通的 `openFile`/`inspect` 回调。PTC dispatch 块保留事件的 `parentCallId`；根会话调用没有该字段，因此后代调用都走同一条按 key 分发路径：已注册视图的调用（如 `read_image`）也会在嵌套处渲染对应卡片，未注册的后代调用则保持通用压平形式。路径摘要先相对会话 cwd 缩短，再把剩余的 POSIX Host home 写成 `~`；`filePath` 与 Host 打开仍使用作者给出的文件系统路径。注册项会收到常规的会话 slot 运行时共享数据，但不会收到 React 节点或运行时服务。
 
 ### 内置视图
 
-本包拥有 generic fallback，以及 shell/pwsh、read、read_image、write/edit、running `str_replace_editor` `create`／`str_replace`、grep/glob、web、todo、question 与 Code Dispatch 的内置展示。结构化卡片直接从第一方原始 event 字段派生；Host `presentCall` 与 `presentResult` 值不会进入 Client。运行中与已完成的前台标准 `bash`/`pwsh` 和 `terminal_send` 调用，无论位于根还是 Code Dispatch 子调用中，都在通过相同的参数、结果和错误检查后使用 terminal 卡片。持久 `bash`/`pwsh` 调用仅在运行中使用 terminal 卡片。以已识别的 spill 策略提示结尾的 shell 输出，在 shell 行中使用可展开的 generic 输出，在 Details 中使用 generic 输出；位置被改变或被省略的退出标记无法证明成功。已完成的持久 shell 结果保持 generic 展示，因为 reset 与部分输出诊断不一定描述单个进程的退出状态；根调用的持久 shell 结果可展开，后台启动回执则保持折叠。成功的问题行按稳定 id 配对调用中的问题与结果中的回答，展开后显示可读的问答行。已取消或已中断的问题行显示其裁决与原始问题，不虚构回答。不受支持、格式错误或含糊的输入回退为压平的工具输入／结果文本。`ui-skill` 展示了业务包自行拥有的 `skill` 注册项。
+本包拥有 generic fallback，以及 shell/pwsh、read、read_image、write/edit、运行中的 `str_replace_editor` `create`／`str_replace`、grep/glob、web、todo、question 与 PTC dispatch 的内置展示。结构化卡片直接从第一方原始 event 字段派生；Host `presentCall` 与 `presentResult` 值不会进入 Client。运行中与已完成的前台标准 `bash`/`pwsh` 和 `terminal_send` 调用，无论位于根还是 PTC dispatch 子调用中，都在通过相同的参数、结果和错误检查后使用 terminal 卡片。持久 `bash`/`pwsh` 调用仅在运行中使用 terminal 卡片。以已识别的 spill 策略提示结尾的 shell 输出，在 shell 行中使用可展开的 generic 输出，在 Details 中使用 generic 输出；位置被改变或被省略的退出标记无法证明成功。已完成的持久 shell 结果保持 generic 展示，因为 reset 与部分输出诊断不一定描述单个进程的退出状态；根调用的持久 shell 结果可展开，后台启动回执则保持折叠。带有 `AUTO_REVIEW_DENIED` 的原生或 PTC dispatch 失败会在折叠行显示 Auto review 裁决，展开时显示一行归一化后的“未执行”原因；原因缺失或只有空白时使用本地化 fallback 文案。成功的问题行按稳定 id 配对调用中的问题与结果中的回答，展开后显示可读的问答行。已取消或已中断的问题行显示其裁决与原始问题，不虚构回答。不受支持、格式错误或含糊的输入回退为压平的工具输入／结果文本。`ui-skill` 展示了业务包自行拥有的 `skill` 注册项。
 
 -----
 
@@ -62,9 +62,13 @@ owner 载荷为 `ToolCallOwnerProps`：`callId`、`toolName`、冻结的 `block`
 ### 卡片
 
 
-每张卡片都在调用树里就地阅读；不存在选中调用的第二个全高展示面。行 renderer 为 terminal、read、diff、search 和 web 卡片各复用同一个纯 card model，image 卡片的图库经由工具自有 `tool.call.images` 槽位渲染。这些 model 校验原始调用参数、结果内容、失败状态、持久 metadata、Code Dispatch 的 `parentCallId` 与 Session 路径事实。不受支持或格式错误的输入使用压平的工具结果文本。文件路径摘要经属主的 `openFile` 打开文件，chat 视图把它路由到右侧 Sidebar 的文本预览；`inspect` 打开轨迹视图。terminal、diff、read、search 与 web 卡片的上限与 fallback 规则仍由 [ui-primitives README](../ui-primitives/README.zh.md) 负责；image 卡片的 fallback 规则由本包内的 card model 自行承载。
+每张卡片都直接在调用树中查看；选中调用后不会再显示第二个全高视图。行 renderer 为 terminal、read、diff、search 和 web 卡片各复用同一个纯 card model，image 卡片的图库经由工具自有 `tool.call.images` slot 渲染。这些 model 校验原始调用参数、结果内容、失败状态、持久 metadata、PTC dispatch 的 `parentCallId` 与会话路径信息。不受支持或格式错误的输入使用压平的工具结果文本。文件路径摘要经属主的 `openFile` 打开文件，chat 视图把它路由到右侧 Sidebar 的文本预览；`inspect` 打开轨迹视图。terminal、diff、read、search 与 web 卡片的上限与 fallback 规则仍由 [ui-primitives README](../ui-primitives/README.zh.md) 负责；image 卡片的 fallback 规则由本包内的 card model 自行承载。
 
-terminal model 使用浏览器安全入口 `@deepseek-ai/dsh-spill-policy/notice` 的 `hasSpillNotice`，而非独立的 UI 匹配规则。[spill-policy README](../../spill/spill-policy/README.zh.md#shared-notice-ownership) 负责通知的格式化与识别。该检查保守地选择通用输出；匹配文本不能认证其来源，回放也不改变已记录的结果字节。
+Chat diff 卡片在折叠前保留九行，足以容纳文件标题、一对删除与新增行及两侧各三行上下文。折叠工具行与展开卡片底部采用原语一致的精确或粗粒度替换统计。
+
+Auto 拒绝优先于按工具名选择的专门视图。其通用行保留调用身份、省略原始参数，并且只在显示时归一化存储的理由：去除首尾空白，把行分隔符折叠为空格，结果为空时使用本地化通用理由。Session 与 SDK 错误详情保留原始理由。
+
+terminal model 使用浏览器安全入口 `@deepseek-ai/dsh-spill-policy/notice` 的 `hasSpillNotice`，而非独立的 UI 匹配规则。[spill-policy README](../../spill/spill-policy/README.zh.md#shared-notice-ownership) 负责提示文本的格式化与识别。该检查保守地选择通用输出；匹配的文本无法证明其来源，回放也不改变已记录的结果字节。
 </details>
 
 -----
@@ -77,6 +81,7 @@ terminal model 使用浏览器安全入口 `@deepseek-ai/dsh-spill-policy/notice
 - [ui-conversation](../ui-conversation/README.zh.md)——把 `tool-call` 节点分派给本包的聊天界面。
 - [ui-primitives](../ui-primitives/README.zh.md)——内置视图所拼装的输出卡片原子组件。
 - [ui-skill](../ui-skill/README.zh.md)——`skill` 工具的业务自有注册。
+- [Auto review](../../experimental/auto-review/README.zh.md)——结构化拒绝身份与用户可见原因的 owner。
 - [Conversation 子系统](../../../docs/subsystems/conversation.zh.md)——业务自有功能如何注册 Conversation node。
 - [slot 系统标准](../../../.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.zh.md)——keyed slot 背后的组合模型。
 
@@ -100,7 +105,7 @@ terminal model 使用浏览器安全入口 `@deepseek-ai/dsh-spill-policy/notice
 
 - **Host 不把 `run_code` 暴露为 PTC mode 程序 binding**：生产事件只产生一层分发；递归的运行时/UI 约定支持嵌套。
 - **第一方工具视图集中在本包**：它们可以通过 keyed slot 独立迁移到各自所属的业务包。
-- **工具文案复用 `ui-conversation` locale namespace**：工具标题、行 chrome 与无 Cordis 的 primitive label 使用该字典；presenter model 保留 locale key 或数据，而不是已渲染文案。
+- **工具文案复用 `ui-conversation` locale namespace**：工具标题、行 chrome 与无 Cordis 的 primitive label 使用该字典；展示转换器模型保留 locale key 或数据，而不是已渲染文案。
 
 <a id="dev-note"></a>
 ### 开发备注
@@ -112,4 +117,4 @@ terminal model 使用浏览器安全入口 `@deepseek-ai/dsh-spill-policy/notice
 
 </details>
 
-**运行时不变式：** 不发布伴生入口。Tool composition 只存在于浏览器，不贡献事件或跨插件可变状态；slot 所有权由 ui-slots 校验。
+**运行时不变式：** 不发布伴生入口。工具组合只存在于浏览器，不贡献事件或跨插件可变状态；slot 所有权由 ui-slots 校验。

package/lib/client.js

@@ -60,6 +60,193 @@ window.__ModuleLoader__.load({
 			return text;
 		}
 		//#endregion
+		//#region lib/types/client/tool/models/tool-call-model.js
+		/** Locale key per generic row variant. */
+		const VARIANT_TITLE_KEYS = {
+			search: "tool.title.search",
+			read: "tool.title.read",
+			bash: "tool.title.bash",
+			write: "tool.title.write",
+			edit: "tool.title.edit",
+			code: "tool.title.code",
+			others: "tool.title.generic"
+		};
+		/**
+		* Known tool name -> variant.
+		*
+		* `cordis_define` is deliberately absent: ui-cordis registers a keyed
+		* `tool.call.toolview` entry for it, and a keyed hit REPLACES the generic row
+		* (this table is only reached through GenericToolCard, the dispatch fallback in
+		* ToolCallTree). An entry here would be unreachable, and a second title for the
+		* same call would be a second answer to a question the card already owns.
+		*/
+		const TOOL_VARIANTS = {
+			bash: "bash",
+			pwsh: "bash",
+			read: "read",
+			read_image: "read",
+			web_fetch: "read",
+			web_search: "search",
+			grep: "search",
+			glob: "search",
+			write: "write",
+			edit: "edit",
+			run_code: "code",
+			cordis_package_inspect: "read",
+			cordis_runtime_inspect: "read",
+			cordis_run: "others",
+			cordis_stop: "others",
+			cordis_undefine: "others"
+		};
+		/** Tool-owned titles that refine a generic row variant without replacing it. */
+		const TOOL_TITLE_KEYS = {
+			cordis_package_inspect: "tool.title.inspect",
+			cordis_runtime_inspect: "tool.title.inspect",
+			cordis_run: "tool.title.runCordis",
+			cordis_stop: "tool.title.stopCordis",
+			cordis_undefine: "tool.title.removeCordis",
+			pwsh: "tool.title.pwsh",
+			read_image: "tool.title.readImage"
+		};
+		/**
+		* Classify a tool name into its row variant.
+		* @param toolName - wire tool name.
+		* @returns matching variant, others when unknown.
+		*/
+		function classifyTool(toolName) {
+			return TOOL_VARIANTS[toolName] ?? "others";
+		}
+		function deriveAutoReviewDenial(block) {
+			if (!("kind" in block) || !block.isError) return null;
+			const error = block.error;
+			if (error?.name !== "AutoReviewDeniedError" || error.code !== "AUTO_REVIEW_DENIED") return null;
+			return { reason: typeof error.reason === "string" ? error.reason : null };
+		}
+		/**
+		* Flatten a settled result's content blocks to display text: text blocks
+		* verbatim, other block shapes as pretty JSON. Empty content on a failed call
+		* falls back to the structured error's `name: code` line.
+		* @param node - the settled result node.
+		* @returns the flattened result text (may be empty).
+		*/
+		function resultText(node) {
+			const parts = [];
+			for (const block of node.content) if (block.type === "text") parts.push(block.text);
+			else parts.push(JSON.stringify(block, null, 2));
+			if (parts.length === 0 && node.error !== void 0) parts.push(`${node.error.name}: ${node.error.code}`);
+			return parts.join("\n");
+		}
+		function parseArgs(argsRaw) {
+			try {
+				return JSON.parse(argsRaw);
+			} catch {
+				return;
+			}
+		}
+		function firstLine(text) {
+			const nl = text.indexOf("\n");
+			return nl === -1 ? text : text.slice(0, nl);
+		}
+		function pickString(args, keys) {
+			for (const key of keys) {
+				const v = args[key];
+				if (typeof v === "string" && v !== "") return v;
+			}
+		}
+		/** Summary key preference per variant (args-derived; result-derived summaries are a ledger item). */
+		const SUMMARY_KEYS = {
+			bash: ["description", "command"],
+			read: [
+				"path",
+				"file_path",
+				"url"
+			],
+			search: [
+				"query",
+				"pattern",
+				"url"
+			],
+			write: ["path", "file_path"],
+			edit: ["path", "file_path"],
+			code: ["description"],
+			others: []
+		};
+		function deriveSummary(variant, argsRaw) {
+			const parsed = parseArgs(argsRaw);
+			if (typeof parsed !== "object" || parsed === null) return firstLine(argsRaw);
+			const args = parsed;
+			if (variant === "search" && Array.isArray(args.queries)) {
+				const queries = args.queries.filter((query) => typeof query === "string" && query !== "");
+				if (queries.length > 0) return queries.map(firstLine).join(", ");
+			}
+			const picked = pickString(args, SUMMARY_KEYS[variant]);
+			if (picked !== void 0) return firstLine(picked);
+			for (const v of Object.values(args)) if (typeof v === "string" && v !== "") return firstLine(v);
+			return firstLine(argsRaw);
+		}
+		/** Path keys only — never `url` (web_fetch lands on the read variant). */
+		const FILE_PATH_KEYS = ["path", "file_path"];
+		/** File-tool variants whose summary may be an openable workspace path. */
+		const FILE_PATH_VARIANTS = new Set([
+			"read",
+			"write",
+			"edit"
+		]);
+		function deriveFilePath(variant, argsRaw) {
+			if (!FILE_PATH_VARIANTS.has(variant)) return void 0;
+			const parsed = parseArgs(argsRaw);
+			if (typeof parsed !== "object" || parsed === null) return void 0;
+			const picked = pickString(parsed, FILE_PATH_KEYS);
+			return picked === void 0 ? void 0 : firstLine(picked);
+		}
+		/**
+		* Format one argument payload when its generic input body becomes visible.
+		* @param variant - row presentation selected for the Tool name.
+		* @param argsRaw - original argument JSON or incomplete raw text.
+		* @returns display body, or null for empty input.
+		*/
+		function formatToolBody(variant, argsRaw) {
+			if (argsRaw === "") return null;
+			const parsed = parseArgs(argsRaw);
+			if (parsed === void 0) return argsRaw;
+			if (variant === "code" && typeof parsed === "object" && parsed !== null) {
+				const code = parsed.code;
+				if (typeof code === "string" && code !== "") return code;
+			}
+			return JSON.stringify(parsed, null, 2);
+		}
+		/**
+		* Derive the full row model from a frozen call slice.
+		* @param toolName - wire tool name (dispatch-supplied; survives windowless results).
+		* @param block - RunningToolCall or ToolResultNode off the snapshot caches.
+		* @param cwd - session workspace root; workspace-rooted path summaries display relative to it.
+		* @param home - host account home; a leftover POSIX home path displays as `~`.
+		* @returns the row model.
+		*/
+		function toolRowModel(toolName, block, cwd, home) {
+			const variant = classifyTool(toolName);
+			const done = "kind" in block;
+			const argsRaw = (done ? block.call?.argsRaw : block.argsRaw) ?? "";
+			const state = !done ? "running" : block.error?.code === "interrupted" ? "stopped" : block.isError ? "error" : "ok";
+			const base = argsRaw === "" ? block.callId : abbreviateHomePath(relativizeToCwd(deriveSummary(variant, argsRaw), cwd), home);
+			const toolTitleKey = TOOL_TITLE_KEYS[toolName];
+			const summary = variant === "others" && toolName !== "" && toolTitleKey === void 0 ? `${toolName} · ${base}` : base;
+			const output = done ? resultText(block) || null : null;
+			const errorSummary = state === "error" && output !== null ? firstLine(output) : null;
+			const bodyRaw = argsRaw === "" ? null : argsRaw;
+			return {
+				variant,
+				titleKey: toolTitleKey ?? VARIANT_TITLE_KEYS[variant],
+				summary,
+				filePath: deriveFilePath(variant, argsRaw),
+				bodyRaw,
+				output,
+				errorSummary,
+				autoReviewDenial: deriveAutoReviewDenial(block),
+				state
+			};
+		}
+		//#endregion
 		//#region lib/types/client/tool/models/raw-tool-call.js
 		const parsedCalls = /* @__PURE__ */ new WeakMap();
 		/**
@@ -445,7 +632,7 @@ window.__ModuleLoader__.load({
 		}
 		/**
 		* Recognize a final spill-policy notice in persisted text, including notice-only output.
-		* This identifies the text convention, not authenticated provenance of tool output.
+		* This identifies the text convention, not authenticated tool-output origin.
 		* @param text - complete recorded text result.
 		* @returns whether a complete notice occupies the end of the result.
 		*/
@@ -475,6 +662,7 @@ window.__ModuleLoader__.load({
 			return {
 				signal: (signal) => t("terminal.signal", { signal }),
 				exitCode: (code) => t("terminal.exitCode", { code }),
+				noExitCode: t("terminal.noExitCode"),
 				running: t("terminal.running"),
 				failed: t("terminal.failed"),
 				done: t("terminal.done"),
@@ -677,7 +865,7 @@ window.__ModuleLoader__.load({
 		}
 		/**
 		* Derive terminal props for supported shell and terminal-send calls, including
-		* nested Code Dispatch calls. Standard shell results parse their final status
+		* nested PTC dispatch calls. Standard shell results parse their final status
 		* marker; persistent shell results, spill previews, background calls, errors,
 		* and malformed input use the generic path. {@link isSettledPersistentShellCall} lets that generic
 		* persistent result remain expandable without inventing one process status.
@@ -791,183 +979,28 @@ window.__ModuleLoader__.load({
 			};
 		}
 		//#endregion
-		//#region lib/types/client/tool/models/tool-call-model.js
-		/** Locale key per generic row variant. */
-		const VARIANT_TITLE_KEYS = {
-			search: "tool.title.search",
-			read: "tool.title.read",
-			bash: "tool.title.bash",
-			write: "tool.title.write",
-			edit: "tool.title.edit",
-			code: "tool.title.code",
-			others: "tool.title.generic"
-		};
-		/**
-		* Known tool name -> variant.
-		*
-		* `cordis_define` is deliberately absent: ui-cordis registers a keyed
-		* `tool.call.toolview` entry for it, and a keyed hit REPLACES the generic row
-		* (this table is only reached through GenericToolCard, the dispatch fallback in
-		* ToolCallTree). An entry here would be unreachable, and a second title for the
-		* same call would be a second answer to a question the card already owns.
-		*/
-		const TOOL_VARIANTS = {
-			bash: "bash",
-			pwsh: "bash",
-			read: "read",
-			read_image: "read",
-			web_fetch: "read",
-			web_search: "search",
-			grep: "search",
-			glob: "search",
-			write: "write",
-			edit: "edit",
-			run_code: "code",
-			cordis_package_inspect: "read",
-			cordis_runtime_inspect: "read",
-			cordis_run: "others",
-			cordis_stop: "others",
-			cordis_undefine: "others"
-		};
-		/** Tool-owned titles that refine a generic row variant without replacing it. */
-		const TOOL_TITLE_KEYS = {
-			cordis_package_inspect: "tool.title.inspect",
-			cordis_runtime_inspect: "tool.title.inspect",
-			cordis_run: "tool.title.runCordis",
-			cordis_stop: "tool.title.stopCordis",
-			cordis_undefine: "tool.title.removeCordis",
-			pwsh: "tool.title.pwsh",
-			read_image: "tool.title.readImage"
-		};
-		/**
-		* Classify a tool name into its row variant.
-		* @param toolName - wire tool name.
-		* @returns matching variant, others when unknown.
-		*/
-		function classifyTool(toolName) {
-			return TOOL_VARIANTS[toolName] ?? "others";
-		}
-		/**
-		* Flatten a settled result's content blocks to display text: text blocks
-		* verbatim, other block shapes as pretty JSON. Empty content on a failed call
-		* falls back to the structured error's `name: code` line.
-		* @param node - the settled result node.
-		* @returns the flattened result text (may be empty).
-		*/
-		function resultText(node) {
-			const parts = [];
-			for (const block of node.content) if (block.type === "text") parts.push(block.text);
-			else parts.push(JSON.stringify(block, null, 2));
-			if (parts.length === 0 && node.error !== void 0) parts.push(`${node.error.name}: ${node.error.code}`);
-			return parts.join("\n");
-		}
-		function parseArgs(argsRaw) {
-			try {
-				return JSON.parse(argsRaw);
-			} catch {
-				return;
-			}
-		}
-		function firstLine(text) {
-			const nl = text.indexOf("\n");
-			return nl === -1 ? text : text.slice(0, nl);
-		}
-		function pickString(args, keys) {
-			for (const key of keys) {
-				const v = args[key];
-				if (typeof v === "string" && v !== "") return v;
-			}
-		}
-		/** Summary key preference per variant (args-derived; result-derived summaries are a ledger item). */
-		const SUMMARY_KEYS = {
-			bash: ["description", "command"],
-			read: [
-				"path",
-				"file_path",
-				"url"
-			],
-			search: [
-				"query",
-				"pattern",
-				"url"
-			],
-			write: ["path", "file_path"],
-			edit: ["path", "file_path"],
-			code: ["description"],
-			others: []
-		};
-		function deriveSummary(variant, argsRaw) {
-			const parsed = parseArgs(argsRaw);
-			if (typeof parsed !== "object" || parsed === null) return firstLine(argsRaw);
-			const args = parsed;
-			if (variant === "search" && Array.isArray(args.queries)) {
-				const queries = args.queries.filter((query) => typeof query === "string" && query !== "");
-				if (queries.length > 0) return queries.map(firstLine).join(", ");
-			}
-			const picked = pickString(args, SUMMARY_KEYS[variant]);
-			if (picked !== void 0) return firstLine(picked);
-			for (const v of Object.values(args)) if (typeof v === "string" && v !== "") return firstLine(v);
-			return firstLine(argsRaw);
-		}
-		/** Path keys only — never `url` (web_fetch lands on the read variant). */
-		const FILE_PATH_KEYS = ["path", "file_path"];
-		/** File-tool variants whose summary may be an openable workspace path. */
-		const FILE_PATH_VARIANTS = new Set([
-			"read",
-			"write",
-			"edit"
-		]);
-		function deriveFilePath(variant, argsRaw) {
-			if (!FILE_PATH_VARIANTS.has(variant)) return void 0;
-			const parsed = parseArgs(argsRaw);
-			if (typeof parsed !== "object" || parsed === null) return void 0;
-			const picked = pickString(parsed, FILE_PATH_KEYS);
-			return picked === void 0 ? void 0 : firstLine(picked);
-		}
+		//#region lib/types/client/tool/models/auto-review-denial.js
 		/**
-		* Format one argument payload when its generic input body becomes visible.
-		* @param variant - row presentation selected for the Tool name.
-		* @param argsRaw - original argument JSON or incomplete raw text.
-		* @returns display body, or null for empty input.
+		* Normalize only the user-visible copy; the durable error keeps the raw reason.
+		* @param reason - raw persisted reviewer reason, or null when none was recorded.
+		* @returns one display line, or null when the reason has no displayable text.
 		*/
-		function formatToolBody(variant, argsRaw) {
-			if (argsRaw === "") return null;
-			const parsed = parseArgs(argsRaw);
-			if (parsed === void 0) return argsRaw;
-			if (variant === "code" && typeof parsed === "object" && parsed !== null) {
-				const code = parsed.code;
-				if (typeof code === "string" && code !== "") return code;
-			}
-			return JSON.stringify(parsed, null, 2);
+		function normalizeAutoReviewReason(reason) {
+			if (reason === null) return null;
+			const normalized = reason.trim().replace(/[\r\n\u2028\u2029]+/gu, " ");
+			return normalized === "" ? null : normalized;
 		}
 		/**
-		* Derive the full row model from a frozen call slice.
-		* @param toolName - wire tool name (dispatch-supplied; survives windowless results).
-		* @param block - RunningToolCall or ToolResultNode off the snapshot caches.
-		* @param cwd - session workspace root; workspace-rooted path summaries display relative to it.
-		* @param home - host account home; a leftover POSIX home path displays as `~`.
-		* @returns the row model.
+		* Resolve the collapsed identity and the single expanded OUT line.
+		* @param denial - locale-neutral persisted denial facts.
+		* @param t - conversation-namespace translator.
+		* @returns localized summary and output text for the Tool row.
 		*/
-		function toolRowModel(toolName, block, cwd, home) {
-			const variant = classifyTool(toolName);
-			const done = "kind" in block;
-			const argsRaw = (done ? block.call?.argsRaw : block.argsRaw) ?? "";
-			const state = !done ? "running" : block.error?.code === "interrupted" ? "stopped" : block.isError ? "error" : "ok";
-			const base = argsRaw === "" ? block.callId : abbreviateHomePath(relativizeToCwd(deriveSummary(variant, argsRaw), cwd), home);
-			const toolTitleKey = TOOL_TITLE_KEYS[toolName];
-			const summary = variant === "others" && toolName !== "" && toolTitleKey === void 0 ? `${toolName} · ${base}` : base;
-			const output = done ? resultText(block) || null : null;
-			const errorSummary = state === "error" && output !== null ? firstLine(output) : null;
-			const bodyRaw = argsRaw === "" ? null : argsRaw;
+		function localizeAutoReviewDenial(denial, t) {
+			const reason = normalizeAutoReviewReason(denial.reason) ?? t("tool.autoReviewReasonFallback");
 			return {
-				variant,
-				titleKey: toolTitleKey ?? VARIANT_TITLE_KEYS[variant],
-				summary,
-				filePath: deriveFilePath(variant, argsRaw),
-				bodyRaw,
-				output,
-				errorSummary,
-				state
+				summary: t("tool.autoReviewRejected"),
+				output: t("tool.autoReviewNotExecuted", { reason })
 			};
 		}
 		//#endregion
@@ -1218,13 +1251,14 @@ window.__ModuleLoader__.load({
 			const searchBody = search ?? null;
 			const webBody = web ?? null;
 			const askQuestionBody = askQuestion ?? null;
+			const inputRaw = bodyRaw ?? null;
 			const outputText = output ?? null;
 			const card = askQuestionBody ?? terminalBody ?? diffBody ?? readBody ?? imageBody ?? searchBody ?? webBody;
-			const expandable = bodyRaw != null || outputText !== null || card !== null;
+			const expandable = inputRaw !== null || outputText !== null || card !== null;
 			const open = expanded && expandable;
-			const bodyText = (0, react.useMemo)(() => open && card === null && bodyRaw != null ? formatToolBody(variant, bodyRaw) : null, [
-				bodyRaw,
+			const bodyText = (0, react.useMemo)(() => open && card === null && inputRaw !== null ? formatToolBody(variant, inputRaw) : null, [
 				card,
+				inputRaw,
 				open,
 				variant
 			]);
@@ -1237,16 +1271,14 @@ window.__ModuleLoader__.load({
 				return `+${added} -${removed}`;
 			}, [diffBody]);
 			const suffix = failureLine === null ? summarySuffix ?? diffStat : null;
-			const fileLink = filePath !== void 0 && onOpenFile !== void 0 && failureLine === null;
 			const toggleExpand = () => {
 				setExpanded((v) => !v);
 			};
-			const openFile = (event) => {
+			const openFile = filePath !== void 0 && onOpenFile !== void 0 && failureLine === null ? (event) => {
 				event.stopPropagation();
-				if (filePath === void 0 || onOpenFile === void 0) return;
 				if (filePathLine === void 0) onOpenFile(filePath);
 				else onOpenFile(filePath, { line: filePathLine });
-			};
+			} : void 0;
 			const fileLinkKeyDown = (event) => {
 				if (event.key === "Enter" || event.key === " ") event.stopPropagation();
 			};
@@ -1276,7 +1308,7 @@ window.__ModuleLoader__.load({
 							className: ToolRow_module_css_default.sep,
 							"aria-hidden": true
 						}),
-						fileLink ? (0, react_jsx_runtime.jsx)("button", {
+						openFile !== void 0 ? (0, react_jsx_runtime.jsx)("button", {
 							type: "button",
 							className: ToolRow_module_css_default.fileLink,
 							onClick: openFile,
@@ -1301,7 +1333,7 @@ window.__ModuleLoader__.load({
 						}) : diffBody !== null ? (0, react_jsx_runtime.jsx)(_deepseek_ai_dsh_client_ui_primitives.DiffBlock, {
 							...diffBody.card,
 							labels: diffLabels,
-							maxLines: 8,
+							maxLines: 9,
 							className: ToolRow_module_css_default.diffBody
 						}) : readBody !== null ? (0, react_jsx_runtime.jsx)(_deepseek_ai_dsh_client_ui_primitives.ReadBlock, {
 							...readBody,
@@ -1399,6 +1431,7 @@ window.__ModuleLoader__.load({
 		};
 		function GenericToolCard({ toolName, block, cwd, home, openFile, inspect, t }) {
 			const model = toolRowModel(toolName, block, cwd, home);
+			const autoReview = model.autoReviewDenial === null ? null : localizeAutoReviewDenial(model.autoReviewDenial, t);
 			const terminal = terminalCardModel(block, cwd);
 			const read = readCardModel(block, cwd, home);
 			const diff = diffCardModel(block);
@@ -1413,9 +1446,9 @@ window.__ModuleLoader__.load({
 				icon: VARIANT_ICONS[model.variant],
 				title: t(model.titleKey),
 				summary: model.summary,
-				bodyRaw: singleFile ? null : model.bodyRaw,
-				output: model.output,
-				errorSummary: model.errorSummary,
+				bodyRaw: singleFile || autoReview !== null ? null : model.bodyRaw,
+				output: autoReview?.output ?? model.output,
+				errorSummary: autoReview?.summary ?? model.errorSummary,
 				terminal,
 				diff,
 				read,
@@ -1472,11 +1505,15 @@ window.__ModuleLoader__.load({
 				loadImage,
 				inspectCall
 			]);
+			const autoReviewDenied = (0, react.useMemo)(() => toolRowModel(toolName, block).autoReviewDenial !== null, [toolName, block]);
 			return (0, react_jsx_runtime.jsxs)("div", {
 				className: ToolCallTree_module_css_default.callRow,
 				"data-chat-anchor-key": `call:${callId}`,
 				"data-chat-call-id": callId,
-				children: [renderSlot("tool.call.toolview", owner, {
+				children: [autoReviewDenied ? (0, react_jsx_runtime.jsx)(GenericToolCard, {
+					...owner,
+					t
+				}) : renderSlot("tool.call.toolview", owner, {
 					entryKey: toolName,
 					fallback: (0, react_jsx_runtime.jsx)(GenericToolCard, {
 						...owner,

package/lib/types/client/tool/models/auto-review-denial.d.ts

@@ -0,0 +1,21 @@
+import type { TranslateNS } from '@deepseek-ai/dsh-client-ui-slots';
+import type { AutoReviewDenial } from './tool-call-model.ts';
+/** Localized copy that replaces ordinary failed-call output for an Auto denial. */
+export interface AutoReviewDenialPresentation {
+    summary: string;
+    output: string;
+}
+/**
+ * Normalize only the user-visible copy; the durable error keeps the raw reason.
+ * @param reason - raw persisted reviewer reason, or null when none was recorded.
+ * @returns one display line, or null when the reason has no displayable text.
+ */
+export declare function normalizeAutoReviewReason(reason: string | null): string | null;
+/**
+ * Resolve the collapsed identity and the single expanded OUT line.
+ * @param denial - locale-neutral persisted denial facts.
+ * @param t - conversation-namespace translator.
+ * @returns localized summary and output text for the Tool row.
+ */
+export declare function localizeAutoReviewDenial(denial: AutoReviewDenial, t: TranslateNS<'conversation'>): AutoReviewDenialPresentation;
+//# sourceMappingURL=auto-review-denial.d.ts.map

package/lib/types/client/tool/models/diff-card-model.d.ts

@@ -1,16 +1,8 @@
 /** Pure diff-card derivation from raw file-mutation calls and result metadata. @module */
 import type { DiffBlockProps } from '@deepseek-ai/dsh-client-ui-primitives';
 import type { ToolCallBlock } from './tool-call-model.ts';
-/**
- * Diff-body lines the chat row shows before collapsing the middle — half the
- * primitive's own default, which the details panel keeps. A chat row is a
- * summary surface inside the message flow: the flow must stay scannable across
- * many calls, while the details panel is the single-call reading surface. The
- * same split {@link CHAT_TERMINAL_MAX_LINES} draws for a terminal card, so the
- * two card kinds cap a long body at the same place in the flow. A design
- * constant of this UI's row geometry, not a deployment choice.
- */
-export declare const CHAT_DIFF_MAX_LINES = 8;
+/** Room for a path, one removed/added pair, and three context lines on each side. */
+export declare const CHAT_DIFF_MAX_LINES = 9;
 /**
  * The {@link DiffBlock} props this derivation owns. Picked off the primitive's
  * props so the two stay in step; `maxLines`/`className` belong to each render

package/lib/types/client/tool/models/terminal-card-model.d.ts

@@ -74,7 +74,7 @@ export declare function isSettledPersistentShellCall(block: ToolCallBlock): bool
 export declare function isSpilledShellCall(block: ToolCallBlock): boolean;
 /**
  * Derive terminal props for supported shell and terminal-send calls, including
- * nested Code Dispatch calls. Standard shell results parse their final status
+ * nested PTC dispatch calls. Standard shell results parse their final status
  * marker; persistent shell results, spill previews, background calls, errors,
  * and malformed input use the generic path. {@link isSettledPersistentShellCall} lets that generic
  * persistent result remain expandable without inventing one process status.

package/lib/types/client/tool/models/tool-call-model.d.ts

@@ -12,6 +12,11 @@ export type { ToolCallBlock } from '@deepseek-ai/dsh-client-ui-chat/client';
 export type ToolRowVariant = 'search' | 'read' | 'bash' | 'write' | 'edit' | 'code' | 'others';
 /** Row state semantic; colors self-supplied via StateDot (design gives none). */
 export type ToolRowState = 'running' | 'ok' | 'error' | 'stopped';
+/** Locale-neutral structured fact consumed only by the user-facing Tool row. */
+export interface AutoReviewDenial {
+    /** Raw persisted reviewer reason; display normalization happens at render time. */
+    reason: string | null;
+}
 type ToolTitleKey = Extract<LocaleKeysOf<'conversation'>, `tool.title.${string}`>;
 /** Locale key per generic row variant. */
 export declare const VARIANT_TITLE_KEYS: {
@@ -46,6 +51,8 @@ export interface ToolRowModel {
     output: string | null;
     /** First line of the result text on an error row; null for every other state. */
     errorSummary: string | null;
+    /** Structured Auto-review denial identity; null for every ordinary result. */
+    autoReviewDenial: AutoReviewDenial | null;
     state: ToolRowState;
 }
 /**

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-client-ui-tool",
   "description": "Client Tool call-tree renderer and keyed per-tool presentation slot",
-  "version": "0.1.5-rc.2",
+  "version": "0.1.6-alpha.2",
   "publishConfig": {
     "access": "public"
   },
@@ -46,28 +46,28 @@
     "react": "^18.2.0",
     "react-dom": "^18.2.0",
     "clsx": "^2.0.0",
-    "@deepseek-ai/dsh-agent": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-llm": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-spill-policy": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-system-prompt": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-session": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-tools": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-code-runtime-worker-thread": "^0.1.5-rc.2",
+    "@deepseek-ai/dsh-spill-policy": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-agent": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-llm": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-session": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-tools": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-spill": "^0.1.6-alpha.2",
     "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-client-connection": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-api-remotes": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-locale": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-ui-conversation": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-test-runtime": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-ui-primitives": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-ui-slots": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-ui-chat": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-ui-renderer": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-client-ui-session": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-util-workspace-path": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-attachment": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-spill": "^0.1.5-rc.2",
-    "@deepseek-ai/dsh-api-workspace-controller": "^0.1.5-rc.2"
+    "@deepseek-ai/dsh-api-remotes": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-connection": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-locale": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-test-runtime": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-ui-conversation": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-ui-primitives": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-ui-slots": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-api-workspace-controller": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-ui-chat": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-ui-session": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-util-workspace-path": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-attachment": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-ptc-runtime": "^0.1.6-alpha.2",
+    "@deepseek-ai/dsh-client-ui-renderer": "^0.1.6-alpha.2"
   },
   "files": [
     "lib/index.js",