From 5081697aafe3b54aa26c2f11dcce1324b8602ad0 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Tue, 28 Jul 2026 14:58:06 +0800 Subject: [PATCH 01/38] feat(web): render bash tool output as a terminal card The bash tool already declares the `card: 'terminal'` render intent for both its call and its result, and host/connection/runtime already deliver it to the browser as callView/resultView. The Web client ignored it: rows derived from raw args, and the details panel flattened every tool's content into one soft-wrapping `
`. Column-aligned output folded into
a paragraph and a long listing stretched the panel without bound.

`TerminalBlock` (ui-primitives) renders a command as a terminal surface:
a shortened-cwd prompt line, output at `white-space: pre` in a
horizontally scrolling box, a head/tail height cap with an expand
control, an exit-code/signal status pill, and a copy control for the raw
output. ANSI SGR runs are parsed with `anser` and resolved onto `--dsw-*`
theme tokens, with literal rgb kept for values the design system has no
token for. Geometry and fonts mirror CodeBlock; the clipboard write both
need moved into a package-internal `clipboard.ts`.

Both Web render sites for a bash call consume the intent through one
derivation (`terminal-card-model.ts`), so they cannot disagree about a
command, its cwd, or its exit status: the keyed BashRow carries the card
resident below its summary row, and the render-site fallback row keeps it
behind its existing expand control. Rows cap at 8 lines against the
panel's 16.

Inline output in the chat row reverses this package's stated
no-inline-output convention, on the owner's explicit decision; the Agent
Note records the reversal and its bound.

Tests: TerminalBlock/ansi/clipboard unit specs, ui-conversation wiring
specs at every render site, a built-client-graph snapshot covering both
chat-row shapes, and a real-browser e2e asserting the no-wrap layout and
the page's own Clipboard API.
---
 .../2026-07-28-web-terminal-card.i18n.yaml    |   6 +
 .../feature/2026-07-28-web-terminal-card.md   |  65 ++++
 .../2026-07-28-web-terminal-card.zh.md        |  65 ++++
 ...26-web-syntax-highlighting-shiki.i18n.yaml |   6 +-
 ...026-07-26-web-syntax-highlighting-shiki.md |   2 +-
 ...-07-26-web-syntax-highlighting-shiki.zh.md |   2 +-
 apps/web/tests/code-mode-fixture.snapshot.ts  |   6 +-
 apps/web/tests/navigation-panes.e2e.ts        |  46 ++-
 .../navigation-panes/details-open.expected.md |   7 +-
 .../terminal-card.expected.md                 |   3 +
 apps/web/tests/terminal-card.snapshot.ts      | 324 ++++++++++++++++
 .../client/connection/src/client/fixture.ts   |  73 +++-
 .../client/ui-conversation/README.i18n.yaml   |   4 +-
 packages/client/ui-conversation/README.md     |   2 +
 packages/client/ui-conversation/README.zh.md  |   2 +
 .../src/client/chat/GenericToolCard.tsx       |   2 +
 .../src/client/chat/ToolRow.module.css        |  12 +-
 .../src/client/chat/ToolRow.tsx               |  39 +-
 .../client/contract/terminal-card-model.ts    |  83 ++++
 .../src/client/contract/tool-call-model.ts    |   6 +-
 .../client/skeleton/DetailsPanel.module.css   |   6 +
 .../src/client/skeleton/DetailsPanel.tsx      |  79 ++--
 .../client/toolviews/bash-sample.module.css   |  16 +-
 .../src/client/toolviews/bash-sample.tsx      |  51 ++-
 .../tests/chat-tool-row.spec.tsx              |  21 +
 .../tests/terminal-card.spec.tsx              | 359 ++++++++++++++++++
 .../client/ui-primitives/README.i18n.yaml     |   6 +-
 packages/client/ui-primitives/README.md       |   7 +-
 packages/client/ui-primitives/README.zh.md    |   7 +-
 packages/client/ui-primitives/package.json    |   1 +
 packages/client/ui-primitives/src/Pill.tsx    |   4 +-
 .../src/TerminalBlock.module.css              | 101 +++++
 .../ui-primitives/src/TerminalBlock.tsx       | 170 +++++++++
 packages/client/ui-primitives/src/ansi.ts     | 153 ++++++++
 .../client/ui-primitives/src/clipboard.ts     |  48 +++
 packages/client/ui-primitives/src/index.ts    |   2 +
 .../ui-primitives/src/markdown/CodeBlock.tsx  |  40 +-
 .../client/ui-primitives/tests/ansi.spec.ts   | 188 +++++++++
 .../tests/terminal-block.spec.tsx             | 315 +++++++++++++++
 pnpm-lock.yaml                                |   8 +
 40 files changed, 2218 insertions(+), 119 deletions(-)
 create mode 100644 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml
 create mode 100644 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
 create mode 100644 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md
 create mode 100644 apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md
 create mode 100644 apps/web/tests/terminal-card.snapshot.ts
 create mode 100644 packages/client/ui-conversation/src/client/contract/terminal-card-model.ts
 create mode 100644 packages/client/ui-conversation/tests/terminal-card.spec.tsx
 create mode 100644 packages/client/ui-primitives/src/TerminalBlock.module.css
 create mode 100644 packages/client/ui-primitives/src/TerminalBlock.tsx
 create mode 100644 packages/client/ui-primitives/src/ansi.ts
 create mode 100644 packages/client/ui-primitives/src/clipboard.ts
 create mode 100644 packages/client/ui-primitives/tests/ansi.spec.ts
 create mode 100644 packages/client/ui-primitives/tests/terminal-block.spec.tsx

diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml
new file mode 100644
index 0000000000..347d5978c0
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
+2026-07-28-web-terminal-card.md: 76d5c47054378330da9e9eebb70571925e47f741
+2026-07-28-web-terminal-card.zh.md: 83d5e7f72d9b04358ce4fe1fd9295e5c97045031
diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
new file mode 100644
index 0000000000..76d5c47054
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
@@ -0,0 +1,65 @@
+# Agent Note: Web terminal card — the bash render intent reaches the browser
+
+Status: implemented
+
+English | [中文](2026-07-28-web-terminal-card.zh.md)
+
+## Problem
+
+The bash tool declares `card: 'terminal'` for both its call and its result ([render-intent union](../architecture/2026-07-02-tool-render-intent-union.md)): the call view carries the command, an optional model-authored description, and the working directory; the result view carries the output, exit code, and terminating signal. That view already reaches the browser — host, connection, and runtime deliver it onto `ConversationSnapshot` as `callView`/`resultView` — and the TUI already renders it as a `$`-prompt card with an exit line and a head/tail height cap.
+
+The Web client ignored it. `packages/client/ui-conversation/src/client/contract/tool-call-model.ts` derived every row from raw tool args, and `skeleton/DetailsPanel.tsx` flattened every tool's content blocks into one `
` with `white-space: pre-wrap; word-break: break-word`. Two defects followed from soft-wrapping and from having no height bound: multi-column output (`ls`, a table, box drawing) folded into a paragraph and lost the column alignment that is the whole point of that output, and a long single-column listing stretched the details panel to the length of the listing.
+
+## Decision
+
+`TerminalBlock` is a `ui-primitives` component that renders a shell command as a terminal surface, and both Web render sites for a bash call consume the terminal render intent through it: the chat tool row's expanded body and the details panel's Output section. `ui-conversation/src/client/contract/terminal-card-model.ts` is the single place that turns the snapshot's `callView`/`resultView` pair into the component's props, so the two sites cannot disagree about a command, its cwd, or its exit status. It returns null — the generic path — whenever neither side declares `card: 'terminal'`, including a `card` value this client version does not know, and whenever a settled call's result view is generic, which is how the bash tool's execution errors and background starts keep their existing rendering.
+
+The component's contract:
+
+- **Prompt line.** A shortened cwd label followed by the command verbatim. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`.
+- **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding.
+- **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends.
+- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters, and a carriage return reduces its line to the final redraw, which is what a terminal shows for progress output.
+- **Exit status and copy.** A non-zero exit code or a signal renders a status pill, matching the exit-status distinction the bash tool's own renderer draws; a clean exit renders none, and settled empty output renders a dimmed placeholder. The copy control copies the raw output text, not the rendered tree, so the prompt line and the pill stay out of the clipboard.
+
+Geometry, radius, and fonts mirror `CodeBlock`, so a terminal card and a fenced code block match visually; `white-space: pre` plus horizontal scroll is the deliberate divergence. The clipboard write both components need moved out of `CodeBlock` into a package-internal `src/clipboard.ts`, unexported so it stays an implementation detail of the two blocks.
+
+### Inline output in the chat row reverses a stated convention
+
+`chat/ToolRow.tsx` and `contract/tool-call-model.ts` asserted "no inline output ever — full results live in the details panel". Showing the terminal block in the row reverses that, on the owner's explicit decision.
+
+The reason the reversal holds: for a shell command the output *is* the result the user is reading, so routing it exclusively to a panel makes the common case a two-step interaction. A bounded, height-capped, non-wrapping terminal block in the row is what makes a bash-heavy transcript readable in one pass. The old rule's actual concern was a row whose height was unbounded by the length of the output, and the height cap plus expand control is what keeps that from returning.
+
+The remaining bound: the row caps at `CHAT_TERMINAL_MAX_LINES` (8), half the primitive's default, which the panel keeps — the message flow is a summary surface read across many calls, the panel is the single-call reading surface, so the panel stays the place for the full output. Only the terminal intent renders inline; a generic tool's content is still panel-only.
+
+## Alternatives considered
+
+**Render the terminal block only in the details panel.** This keeps the stated no-inline-output convention and needs no reversal to record. Rejected by the owner's explicit decision: a shell command's output is what the user came to read, and putting it one click away costs more than the convention buys. Recorded here as the owner's call, not as a conclusion derived from the codebase.
+
+**Reuse `CodeBlock` with a `console` language instead of a new primitive.** Rejected: `CodeBlock` soft-wraps, which is the defect being fixed, and it has no exit status, no cwd prompt line, no height cap, and no ANSI handling. Adding four terminal-specific concerns to the shared code-fence component would impose them on every markdown fence. The two components share their geometry and font tokens instead, which is the only part where one implementation is correct for both.
+
+**Hand-roll the SGR parser.** Rejected: an SGR parser is exactly the surface [prefer maintained dependencies over hand-rolling](../process/2026-07-26-dependencies-over-hand-rolling.md) says not to own — its edge cases (256-palette and truecolor forms, `reverse`, multi-parameter runs, unterminated sequences) each fail on output nobody produces in a test, so a hand-rolled version stays subtly wrong for a long time. Stated honestly against that policy's bar: `anser` does **not** delete existing owned code. It is a capability addition, which that note distinguishes from a net-deletion simplification; the health and boundary-fit halves of the bar are what it clears. What stays hand-rolled is the part `anser` does not cover: the theme-token color mapping, the non-CSI sanitizing, the carriage-return redraw, and the per-line span folding the height cap slices.
+
+## Consequences
+
+`anser` is a new runtime dependency of `packages/client/ui-primitives`, so every consumer of that package pays for it once. A bash row in the Web chat carries output, which is a deliberate density increase over a summary-only row; the cap is what keeps it bounded, and a tighter cap is a props change, not a redesign.
+
+`TerminalBlock` reads only the terminal view's fields, so it stays a pure function of what the render intent carries — no session lookups, replay-safe like the presenters that produce the view. A UI without the terminal capability still gets the bridge's fenced fallback; nothing about the tool's result shape changed.
+
+Inline rendering is licensed for the terminal intent alone. A future intent that wants it needs its own bound and its own decision, argued against the reason recorded here rather than against the panel-only convention on its own.
+
+## Testing
+
+`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, per-line carriage-return redraws, and CRLF preservation. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly.
+
+`packages/client/ui-conversation/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-conversation/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files.
+
+`apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 66 was named `bash` and turn 60 left as `fx-bash` so one fixture covers both shapes; that turn also carries what turn 60's three clean lines cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit recovered from the trailing marker.
+
+`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `details-open.expected.md` golden was refreshed for the panel's new terminal card. That refresh also absorbed a stale `Input json` line and its copy button, which the shiki `CodeBlock` change already on master left behind — verified as failing on a clean rebuilt tree before this change, so it is a correction carried along, not an effect of this one.
+
+## Related
+
+- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md) — the `card`-tagged vocabulary this consumes; the Web client is now a full consumer of the `terminal` arm rather than of args alone.
+- [Web client syntax highlighting](../process/2026-07-26-web-syntax-highlighting-shiki.md) — owns `CodeBlock` and its shiki arm, and records why tool output deliberately stays unhighlighted; ANSI color here is authored color, not guessed grammar.
+- [Web client architecture](../architecture/2026-07-19-gui-web-client-architecture.md) — the slot and snapshot layering the two render sites sit in.
diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md
new file mode 100644
index 0000000000..83d5e7f72d
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md
@@ -0,0 +1,65 @@
+# Agent Note: Web terminal card — the bash render intent reaches the browser
+
+Status: implemented
+
+[English](2026-07-28-web-terminal-card.md) | 中文
+
+## Problem
+
+bash 工具的调用与结果都声明 `card: 'terminal'`([渲染意图联合类型](../architecture/2026-07-02-tool-render-intent-union.md)):调用视图携带命令、一段可选的模型撰写描述以及工作目录,结果视图携带输出、退出码与终止信号。该视图早已抵达浏览器——host、connection 与 runtime 把它投递到 `ConversationSnapshot` 的 `callView`/`resultView` 上——TUI 也早已把它渲染为带 `$` 提示符的卡片,附退出行与首尾高度上限。
+
+Web client 却对它视而不见。`packages/client/ui-conversation/src/client/contract/tool-call-model.ts` 仅从原始工具参数推导每一行,`skeleton/DetailsPanel.tsx` 则把所有工具的内容块压平进一个 `
`,样式为 `white-space: pre-wrap; word-break: break-word`。软换行加上没有高度约束,带来两个缺陷:多列输出(`ls`、表格、制表符绘图)被折成一段文字,丢掉了这类输出赖以存在的列对齐;而单列的长列表会把详情面板拉长到与列表等长。
+
+## Decision
+
+`TerminalBlock` 是 `ui-primitives` 中把 shell 命令渲染为终端表面的组件,bash 调用在 Web 侧的两个渲染点都经由它消费 terminal 渲染意图:聊天工具行展开后的正文,以及详情面板的 Output 区。`ui-conversation/src/client/contract/terminal-card-model.ts` 是把快照上的 `callView`/`resultView` 这一对转换为该组件 props 的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧。当两侧都不声明 `card: 'terminal'` 时它返回 null,即走 generic 路径——包括本 client 版本不认识的 `card` 取值;当一个已落定调用的结果视图是 generic 时同样返回 null,这正是 bash 工具的执行错误与后台启动得以保持既有渲染的方式。
+
+该组件的契约:
+
+- **提示符行。** 一个缩短的 cwd 标签,其后原样跟随命令。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。
+- **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。
+- **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。
+- **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM;回车会把所在行归约为最后一次重绘,这正是终端对进度输出的呈现。
+- **退出状态与复制。** 非零退出码或信号渲染一枚状态徽章,与 bash 工具自身渲染器所作的退出状态区分一致;干净退出不渲染徽章,落定后的空输出渲染一处变暗的占位文字。复制控件复制的是原始输出文本而非渲染后的树,因此提示符行与徽章不会进入剪贴板。
+
+几何尺寸、圆角与字体沿用 `CodeBlock`,因此终端卡片与围栏代码块在视觉上一致;`white-space: pre` 加横向滚动是有意的分歧。两个组件都需要的剪贴板写入从 `CodeBlock` 中提取到包内部的 `src/clipboard.ts`,不对外导出,因此它仍是这两个块的实现细节。
+
+### 聊天行内嵌输出推翻了一条既有约定
+
+`chat/ToolRow.tsx` 与 `contract/tool-call-model.ts` 都断言过「绝不内嵌输出——完整结果在详情面板」。在行内显示终端块推翻了这一点,依据是 owner 的明确决定。
+
+这次推翻成立的理由:对 shell 命令而言,输出**就是**用户要读的结果,把它专门收进面板会让最常见的情形变成两步交互。行内一个有界、限高、不换行的终端块,正是让 bash 密集的 transcript 一遍读完的条件。旧规则真正担心的是行高不受输出长度约束,而高度上限加展开控件正是防止其复现的机制。
+
+余下的约束:行内上限为 `CHAT_TERMINAL_MAX_LINES`(8),是组件默认值的一半,而面板沿用默认值——消息流是跨多次调用阅读的摘要表面,面板才是单次调用的阅读表面,因此面板仍是查看完整输出的地方。只有 terminal 意图内嵌渲染;generic 工具的内容依旧只在面板中。
+
+## Alternatives considered
+
+**只在详情面板渲染终端块。** 这样保留既有的「不内嵌输出」约定,也不需要记录任何推翻。已被 owner 的明确决定否决:shell 命令的输出正是用户来读的东西,把它挪到一次点击之外,代价高于该约定带来的收益。此处记录的是 owner 的裁决,而非从代码库推导出的结论。
+
+**复用 `CodeBlock` 并传入 `console` 语言,而不新建组件。** 已否决:`CodeBlock` 会软换行,而软换行正是本次要修的缺陷,且它没有退出状态、没有 cwd 提示符行、没有高度上限、也不处理 ANSI。把四项终端专属关注点加进共享的代码围栏组件,等于把它们强加给每一个 markdown 围栏。两个组件改为共享几何与字体 token,那是唯一一处「一套实现对两者都正确」的部分。
+
+**手写 SGR 解析器。** 已否决:SGR 解析器恰是[优先采用维护良好的依赖而非手写](../process/2026-07-26-dependencies-over-hand-rolling.md)所指明不该自持的那类实现——它的边界情形(256 色板与 truecolor 形式、`reverse`、多参数分段、未终止的序列)各自只在没人会写进测试的输出上失效,因此手写版本会在很长时间内一直微妙地出错。对照那条策略的门槛如实陈述:`anser` **并未**删除任何既有自持代码。它是一次能力增补,而那条 Agent Note 把这与净删除式的简化区分开来;它清过的是健康度与边界契合这两半门槛。`anser` 未覆盖而仍由我们手写的部分是:主题 token 的颜色映射、非 CSI 序列的剥除、回车重绘,以及供高度上限切片的逐行 span 折叠。
+
+## Consequences
+
+`anser` 成为 `packages/client/ui-primitives` 的一项新运行时依赖,因此该包的每个消费方都为它支付一次。Web 聊天中的 bash 行现在承载输出,相比只有摘要的行,这是有意提高的信息密度;上限是维持其有界的机制,而调紧上限是改一个 prop,不是重新设计。
+
+`TerminalBlock` 只读取 terminal 视图携带的字段,因此它始终是渲染意图内容的纯函数——不查会话状态,与产出该视图的 presenter 一样可安全回放。不具备终端能力的 UI 仍从桥接层拿到围栏式回退;工具的结果形态未作任何改动。
+
+内嵌渲染的许可仅授予 terminal 意图。将来想要内嵌的意图需要有自己的边界与自己的决定,且需针对此处记录的理由来论证,而不是仅针对「只在面板」这条约定本身。
+
+## Testing
+
+`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层:基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、逐行的回车重绘,以及 CRLF 的保留。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件:cwd 缩短、运行中/空/已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关,以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出,另有对 `writeClipboard` 的直接固定。
+
+`packages/client/ui-conversation/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线:`terminalCardModel` 的推导及其每一处 null 分支、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片,以及面板 Output 区段(含 run_code 子派发与超出窗口的调用头)。该文件在没有门禁压力的情况下写成——`packages/client/ui-conversation/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中,因此覆盖率运行不会统计其中任何文件。
+
+`apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用:同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片,而其他任何声明 terminal 的工具名都落到渲染点兜底行上,其输出体受展开控制。fixture 第 66 轮改名为 `bash`、第 60 轮保留 `fx-bash`,于是一份 fixture 覆盖两种形态;该轮还承载第 60 轮三行干净输出无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd,以及从末尾标记还原出的非零退出码。
+
+`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景,断言 jsdom 无法计算的部分:把输出面板挤压到窄于内容宽度后,行仍保持单行且面板产生横向溢出;复制控件走的是页面自身的异步 Clipboard API,而非 `execCommand` 兜底路径。其 `details-open.expected.md` 基准已为面板的新终端卡片重新录制。该次录制同时吸收了一行陈旧的 `Input json` 及其复制按钮——那是 master 上已有的 shiki `CodeBlock` 改动留下的;在干净并重新构建的工作树上验证过它本就失败,因此那是被顺带修正的部分,而非本次改动的影响。
+
+## Related
+
+- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md)——本次消费的 `card` 标签词汇;Web client 现在是 `terminal` 分支的完整消费方,而不再只消费参数。
+- [Web client syntax highlighting](../process/2026-07-26-web-syntax-highlighting-shiki.md)——它拥有 `CodeBlock` 及其 shiki 分支,并记录了工具输出为何有意不做语法高亮;这里的 ANSI 颜色是作者指定的颜色,不是猜出来的语法。
+- [Web client architecture](../architecture/2026-07-19-gui-web-client-architecture.md)——两个渲染点所处的 slot 与快照分层。
diff --git a/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.i18n.yaml
index 9fd37bcedb..72cbbc368f 100644
--- a/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.i18n.yaml
+++ b/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.i18n.yaml
@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-26-web-syntax-highlighting-shiki.md: b329e35f1d0ce7b3de454758403a09f67056b5af
-2026-07-26-web-syntax-highlighting-shiki.zh.md: 8e9d1f0d0c38ce64bcb5da1262538da762f70b12
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.md
+2026-07-26-web-syntax-highlighting-shiki.md: 48a1e4c43f19693f90906f210f0ed85db3f31687
+2026-07-26-web-syntax-highlighting-shiki.zh.md: 780b66a309c841c542f873f376226b8da454e050
diff --git a/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.md b/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.md
index b329e35f1d..48a1e4c43f 100644
--- a/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.md
+++ b/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.md
@@ -17,7 +17,7 @@ The client rendered every code surface — markdown fences in assistant prose, t
 - **Dependency**: `shiki/core` + `@shikijs/langs`, composed via `createHighlighterCoreSync` with `createJavaScriptRegexEngine({ forgiving: true })` — no oniguruma WASM, no async init, bundle-friendly. Grammar allowlist: `typescript` (embeds JS), `shellscript`, `json` — the languages the harness actually renders; everything else falls back to a geometry-identical plain block, never an error. Prior art: the VitePress site already renders all documentation code through shiki, and TextMate grammars materially beat regex highlighters on TypeScript — the payload that matters here.
 - **Singleton**: `ui-primitives/src/markdown/highlight.ts` creates one `HighlighterCore` per document and exposes `highlightToHtml(code, lang)` (undefined = render plain). Engine + grammar construction is a ~120-175ms long task, so the module pre-warms the singleton in a deferred task at plugin boot (the lazy path stays as the correctness fallback), keeping the cost off the render path where a stream's finalize swap would jank. The alias table is a `Map`, not an object: fence info strings are assistant-authored, so a label like `constructor` must miss instead of resolving an inherited property and crashing shiki. The shared `CodeBlock` component owns both arms; its shiki arm injects the generated span tree via `dangerouslySetInnerHTML` — sanctioned because shiki emits a static span tree computed from the code text (no user HTML passes through, no scripts/handlers), shiki's own documented consumption path.
 - **Theming**: shiki's `createCssVariablesTheme` routes every token color through `--shiki-*` custom properties; the VALUES live in a new `ui-theme/styles/shiki.css` token sheet (light on `:root`, dark on `body[data-ds-dark-theme]` — the same cascade as every other sheet), imported by the shell's `base.css` chain. Component CSS stays tokens-only; no literal color ever enters JS or component sheets. Background/foreground alias the existing markdown code-block tokens so highlighted and plain blocks agree.
-- **Surfaces**: markdown fences (`MarkdownText`'s `pre` component routes single-string fences through `CodeBlock`), the `run_code` expanded program body (ToolRow's code variant, `lang="typescript"`), and the details panel's Input args (`lang="json"`). Output stays plain deliberately — tool output is arbitrary text, and guessing a grammar would mis-highlight more than it helps.
+- **Surfaces**: markdown fences (`MarkdownText`'s `pre` component routes single-string fences through `CodeBlock`), the `run_code` expanded program body (ToolRow's code variant, `lang="typescript"`), and the details panel's Input args (`lang="json"`). Tool output is never syntax-highlighted — it is arbitrary text, and guessing a grammar would mis-highlight more than it helps; a bash card's output carries only the color its own ANSI sequences declare, through [the terminal card](../feature/2026-07-28-web-terminal-card.md).
 
 ## Alternatives considered
 
diff --git a/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.zh.md b/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.zh.md
index 8e9d1f0d0c..780b66a309 100644
--- a/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.zh.md
+++ b/.agents/notes/implemented/process/2026-07-26-web-syntax-highlighting-shiki.zh.md
@@ -17,7 +17,7 @@ client 过去把每一处代码表面——assistant 正文里的 markdown 围
 - **依赖**:`shiki/core` + `@shikijs/langs`,经 `createHighlighterCoreSync` 搭配 `createJavaScriptRegexEngine({ forgiving: true })` 组装——不带 oniguruma WASM、没有异步初始化、对 bundle 友好。语法(grammar)白名单:`typescript`(内嵌 JS)、`shellscript`、`json`——即 harness 实际会渲染的那几种语言;其余一律回退到几何完全一致的纯文本块,绝不报错。先例:VitePress 站点已经通过 shiki 渲染全部文档代码;而在 TypeScript(正是此处要紧的载荷)上,TextMate 语法实质性优于正则高亮器。
 - **单例**:`ui-primitives/src/markdown/highlight.ts` 为每个 document 创建一个 `HighlighterCore`,并公开 `highlightToHtml(code, lang)`(undefined 即渲染为纯文本)。引擎加语法的构建是一次约 120-175ms 的长任务,因此模块在插件启动时用延迟任务预热单例(惰性路径保留为正确性兜底),把这笔开销挪出渲染路径——否则流式 finalize 交换的那一刻会卡顿。别名表用 `Map` 而非对象:fence 信息串由 assistant 撰写,诸如 `constructor` 这样的标签必须落空,而不是解析到继承属性并让 shiki 崩溃。共享的 `CodeBlock` 组件同时拥有两条分支;其 shiki 分支经 `dangerouslySetInnerHTML` 注入生成的 span 树——此用法获准,因为 shiki 输出的是从代码文本计算出的静态 span 树(不流经任何用户 HTML,没有脚本或事件处理器),这正是 shiki 自身文档载明的消费路径。
 - **主题化**:shiki 的 `createCssVariablesTheme` 让每一种 token 颜色都经由 `--shiki-*` 自定义属性路由;取值本身住在新增的 `ui-theme/styles/shiki.css` token 表里(亮色在 `:root`、暗色在 `body[data-ds-dark-theme]`——层叠方式与其余每张样式表相同),由壳的 `base.css` 导入链引入。组件 CSS 保持只用 token;任何字面颜色都不进入 JS 或组件样式表。背景/前景以别名指向既有的 markdown 代码块 token,使高亮块与纯文本块彼此一致。
-- **表面**:markdown 围栏代码块(`MarkdownText` 的 `pre` 组件把单字符串围栏路由到 `CodeBlock`)、`run_code` 展开后的程序正文(ToolRow 的 code 变体,`lang="typescript"`),以及 details 面板的 Input 参数(`lang="json"`)。输出有意保持纯文本——工具输出是任意文本,硬猜一种语法,带来的误高亮会多于帮助。
+- **表面**:markdown 围栏代码块(`MarkdownText` 的 `pre` 组件把单字符串围栏路由到 `CodeBlock`)、`run_code` 展开后的程序正文(ToolRow 的 code 变体,`lang="typescript"`),以及 details 面板的 Input 参数(`lang="json"`)。工具输出从不做语法高亮——它是任意文本,硬猜一种语法,带来的误高亮会多于帮助;bash 卡片的输出只承载其自身 ANSI 序列声明的颜色,经由[终端卡片](../feature/2026-07-28-web-terminal-card.md)渲染。
 
 ## 曾考虑的替代方案
 
diff --git a/apps/web/tests/code-mode-fixture.snapshot.ts b/apps/web/tests/code-mode-fixture.snapshot.ts
index f53777fff8..101859cc4a 100644
--- a/apps/web/tests/code-mode-fixture.snapshot.ts
+++ b/apps/web/tests/code-mode-fixture.snapshot.ts
@@ -213,9 +213,9 @@ it('trajectory and waterfall surface the run_code sub-calls with real timing', a
   }).toMatchInlineSnapshot(`
     {
       "subCells": [
-        "#51Subbash · {"command":"ls notes","description":"List notes"}+0.8s",
-        "#52Subread · {"path":"notes/demo.txt"}+0.8s",
-        "#53Subread · {"path":"notes/missing.txt"}+0.8s",
+        "#49Subbash · {"command":"ls notes","description":"List notes"}+0.8s",
+        "#50Subread · {"path":"notes/demo.txt"}+0.8s",
+        "#51Subread · {"path":"notes/missing.txt"}+0.8s",
       ],
     }
   `)
diff --git a/apps/web/tests/navigation-panes.e2e.ts b/apps/web/tests/navigation-panes.e2e.ts
index bbae7363df..b0e340da43 100644
--- a/apps/web/tests/navigation-panes.e2e.ts
+++ b/apps/web/tests/navigation-panes.e2e.ts
@@ -26,6 +26,7 @@ const SEED = join(SNAPSHOT_DIR, 'seed.jsonl')
 const TRAJECTORY_EXPECTED = join(SNAPSHOT_DIR, 'trajectory.expected.md')
 const WATERFALL_EXPECTED = join(SNAPSHOT_DIR, 'waterfall.expected.md')
 const DETAILS_EXPECTED = join(SNAPSHOT_DIR, 'details-open.expected.md')
+const TERMINAL_EXPECTED = join(SNAPSHOT_DIR, 'terminal-card.expected.md')
 const MODE = webSnapshotMode()
 const SEED_ID = 'navigation-panes-web-e2e'
 
@@ -170,9 +171,11 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
     await bashRow.click()
     await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 10_000 }).toBeNull()
     // The open panel shows the selected call's name, arguments, and durable
-    // result (NAVIGATION_OK appears in the chat row too, hence >= 2 total).
+    // result. The chat row carries its own terminal card, so NAVIGATION_OK
+    // appears there too — in the prompt line and in the output.
     await expect.poll(() => page.getByText('NAVIGATION_OK', { exact: false }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
-    // Golden of the open panel: tool name header, Input args, Output result.
+    // Golden of the open panel: tool name header, Input args, and the Output
+    // section's terminal card (prompt line + captured output).
     const snapshot = (await captureStableAria(page, '[class*="detailsCol"]', scaffold.workspaceCwd))
       .split(SEED_ID).join('{{seededId}}')
     await compareOrRefreshGolden(DETAILS_EXPECTED, snapshot, MODE)
@@ -180,11 +183,50 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
     await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 10_000 }).not.toBeNull()
   }, 60_000)
 
+  it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-terminal'))
+    await page.getByRole('tab', { name: 'Chat' }).click()
+    // The card is resident in the keyed bash row (no expand gesture): the
+    // recorded command's own output sits in the message flow, derived from the
+    // logged call/result presentations alone.
+    const card = page.locator('[data-sample="bash-global"] ~ [data-terminal], [data-sample="bash-global"] [data-terminal]').first()
+    await card.waitFor({ timeout: 15_000 })
+    // Real layout, not jsdom's stub (which computes no geometry at all):
+    // squeeze the output pane below its content width and the line must keep
+    // its single row and overflow sideways instead of folding. Soft-wrapping
+    // here is what shredded the column alignment this card exists to hold.
+    const layout = await card.locator('[class*="_output_"]').first().evaluate((node) => {
+      const pane = node as HTMLElement
+      const row = pane.querySelector('[class*="_line_"]')
+      if (row === null) throw new Error('output pane has no line')
+      const before = row.offsetHeight
+      const restore = pane.style.width
+      pane.style.width = '8px'
+      const squeezed = { wrapped: row.offsetHeight > before, scrollsSideways: pane.scrollWidth > pane.clientWidth }
+      pane.style.width = restore
+      return { whiteSpace: getComputedStyle(row).whiteSpace, overflowX: getComputedStyle(pane).overflowX, ...squeezed }
+    })
+    expect(layout).toEqual({ whiteSpace: 'pre', overflowX: 'auto', wrapped: false, scrollsSideways: true })
+    // Golden of the card at rest — captured before the copy click, whose
+    // confirmation label self-reverts on a timer and would not hold still.
+    const snapshot = (await captureStableAria(page, '[data-terminal]', scaffold.workspaceCwd))
+      .split(SEED_ID).join('{{seededId}}')
+    await compareOrRefreshGolden(TERMINAL_EXPECTED, snapshot, MODE)
+    // Copy writes the raw output through the browser's own clipboard, which in
+    // a real page is the async Clipboard API rather than the jsdom fallback.
+    await page.context().grantPermissions(['clipboard-read', 'clipboard-write'])
+    await card.locator('[class*="_copyButton_"]').first().click()
+    await expect.poll(() => card.locator('[class*="_copyButton_"]').first().textContent(), { timeout: 5_000 })
+      .toBe('复制成功')
+    expect(await page.evaluate(() => navigator.clipboard.readText())).toContain('NAVIGATION_OK')
+  }, 60_000)
+
   it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
     await assertFixtureInventory(SNAPSHOT_DIR, [
       'seed.jsonl', 'trajectory.expected.md', 'waterfall.expected.md', 'details-open.expected.md',
+      'terminal-card.expected.md',
     ])
   })
 })
diff --git a/apps/web/tests/snapshots/navigation-panes/details-open.expected.md b/apps/web/tests/snapshots/navigation-panes/details-open.expected.md
index d69a95eb2d..9eee71468d 100644
--- a/apps/web/tests/snapshots/navigation-panes/details-open.expected.md
+++ b/apps/web/tests/snapshots/navigation-panes/details-open.expected.md
@@ -1,5 +1,8 @@
 - text: bash
 - button "关闭详情"
-- text: Input
+- text: Input json
+- button "复制"
 - code: "{ \"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\" }"
-- text: Output NAVIGATION_OK
+- text: Output $ echo NAVIGATION_OK
+- button "复制"
+- text: NAVIGATION_OK
diff --git a/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md b/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md
new file mode 100644
index 0000000000..2b81725468
--- /dev/null
+++ b/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md
@@ -0,0 +1,3 @@
+- text: $ echo NAVIGATION_OK
+- button "复制"
+- text: NAVIGATION_OK
diff --git a/apps/web/tests/terminal-card.snapshot.ts b/apps/web/tests/terminal-card.snapshot.ts
new file mode 100644
index 0000000000..53215f4ba9
--- /dev/null
+++ b/apps/web/tests/terminal-card.snapshot.ts
@@ -0,0 +1,324 @@
+// @vitest-environment jsdom
+// Terminal card snapshot over the BUILT client graph (the code-mode-fixture
+// idiom: real bundles via AppWebEntry, keyless FixtureApiClient transport).
+// Opens the fixture history session and pins the `card: 'terminal'` render
+// intent at both of its conversation render sites, for both chat-row shapes:
+// turn 60's `fx-bash` on the render-site fallback row (expand-gated body) and
+// turn 66's `bash` on the keyed BashRow registration (resident body), plus the
+// details panel's Output section. Turn 66 carries what turn 60's three plain
+// lines cannot — SGR runs resolved to --dsw-* tokens, output past the chat
+// cap, a nested cwd, and a non-zero exit pill.
+import { readFileSync } from 'node:fs'
+import { join } from 'node:path'
+import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
+import { afterEach, beforeEach, expect, it, vi } from 'vitest'
+import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client'
+import { AppWebEntry } from '@deepseek-ai/dsh-client-web'
+
+const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
+  { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
+  { id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  {
+    id: '@deepseek-ai/dsh-client-ui-workspace',
+    dir: 'ui-workspace',
+    url: '/plugins/ui-workspace.js',
+    rev: 'fx',
+    inject: [
+      '@deepseek-ai/dsh-client-runtime',
+      '@deepseek-ai/dsh-client-ui-conversation',
+      '@deepseek-ai/dsh-client-ui-sidebar',
+    ],
+  },
+]
+
+const bundles = new Map(PLUGINS.map(plugin => [
+  plugin.url,
+  readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
+]))
+
+interface FixtureWindow extends Window {
+  __DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
+  __ModuleLoader__?: unknown
+}
+
+class ResizeObserverStub {
+  observe(): void {}
+  disconnect(): void {}
+  unobserve(): void {}
+}
+
+const win = window as FixtureWindow
+let unmount: (() => void) | undefined
+
+beforeEach(() => {
+  localStorage.clear()
+  document.title = 'DeepSeek Harness'
+  vi.stubGlobal('ResizeObserver', ResizeObserverStub)
+  vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
+    setTimeout(() => { callback(0) }, 0) as unknown as number)
+  vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
+})
+
+afterEach(() => {
+  act(() => { unmount?.() })
+  unmount = undefined
+  cleanup()
+  delete win.__DSH_BOOT__
+  delete win.__ModuleLoader__
+  document.body.innerHTML = ''
+  document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
+  document.title = ''
+  history.replaceState(null, '', '/')
+  vi.unstubAllGlobals()
+})
+
+/** Boot the complete built client graph against the populated fixture branch. */
+function boot(): void {
+  history.replaceState(null, '', '/?fixture')
+  const root = document.createElement('div')
+  root.id = 'root'
+  document.body.appendChild(root)
+  win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
+  act(() => {
+    const entry = new AppWebEntry(root, {
+      fetchBundle: (url) => {
+        const code = bundles.get(url)
+        return code === undefined ? Promise.reject(new Error(`missing built bundle ${url}`)) : Promise.resolve(code)
+      },
+      executeBundle: (code) => { (0, eval)(code) },
+    })
+    void entry.run()
+    unmount = () => { entry.dispose() }
+  })
+}
+
+/** Collapse decorative whitespace while preserving the text a user sees. */
+function visibleText(element: Element): string {
+  return (element.textContent ?? '').replace(/\s+/g, ' ').trim()
+}
+
+/**
+ * Read one terminal card's user-visible state. Output lines keep their interior
+ * whitespace: holding column alignment is what this card exists for, so
+ * collapsing runs of spaces would hide the behavior under test.
+ */
+function readCard(card: Element) {
+  const status = card.querySelector('[class*="_status_"]')
+  const expander = card.querySelector('button[aria-expanded]')
+  return {
+    prompt: `${card.querySelector('[class*="_cwd_"]')?.textContent ?? ''} ${card.querySelector('[class*="_command_"]')?.textContent ?? ''}`,
+    status: status === null ? null : status.textContent,
+    copy: card.querySelector('[class*="_copyButton_"]')?.textContent ?? null,
+    lines: [...card.querySelectorAll('[class*="_line_"]')].map(line => line.textContent),
+    expander: expander === null ? null : {
+      label: expander.getAttribute('aria-label'),
+      text: expander.textContent,
+      expanded: expander.getAttribute('aria-expanded'),
+    },
+    // Every color the ANSI parser emits resolves through a --dsw-* token, so
+    // the card follows the theme instead of painting literal terminal rgb.
+    colors: [...new Set([...card.querySelectorAll('span[style]')]
+      .map(span => span.getAttribute('style')))],
+  }
+}
+
+/** Open the fixture history session (the alpha log carrying both bash turns) and wait for its tail. */
+async function openFixtureSession(): Promise {
+  const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+  // Anchor on the expandable Workspace group row: the title and the blank
+  // session row can both read "fixture".
+  const group = (await within(tree).findAllByText('fixture'))
+    .map(el => el.closest('[role="treeitem"]'))
+    .find(el => el?.getAttribute('aria-expanded') !== null)
+  if (group === null || group === undefined) throw new Error('fixture Workspace group missing')
+  if (group.getAttribute('aria-expanded') === 'false') {
+    fireEvent.click(within(group).getByText('fixture'))
+    await waitFor(() => {
+      expect(group.getAttribute('aria-expanded')).toBe('true')
+    })
+  }
+  fireEvent.click(await within(tree).findByText('Fixture 历史会话'))
+  await waitFor(() => {
+    expect(document.querySelector('[data-sample="bash-global"]')).not.toBeNull()
+  }, { timeout: 10_000 })
+}
+
+/** The keyed BashRow of fixture turn 66 (the one carrying the ANSI sample). */
+function keyedBashRow(): Element {
+  const row = [...document.querySelectorAll('[data-sample="bash-global"]')]
+    .find(node => visibleText(node).includes('pnpm run check'))
+  if (row === undefined) throw new Error('keyed bash row for turn 66 missing')
+  return row
+}
+
+/** The turn-60 fallback row, which reaches the terminal card through GenericToolCard/ToolRow. */
+function fallbackBashRow(): Element {
+  const row = document.querySelector('[data-tool="fx-bash"]')
+  if (row === null) throw new Error('fx-bash fallback row missing')
+  return row
+}
+
+it('renders the keyed bash row with a resident terminal card', async () => {
+  boot()
+  await openFixtureSession()
+
+  const row = keyedBashRow()
+  const card = row.parentElement?.querySelector('[data-terminal]')
+  if (card === null || card === undefined) throw new Error('keyed bash row has no resident terminal card')
+  // The prompt shortens the nested cwd to its last segment, the exit pill
+  // recovers the trailing marker's code, ANSI runs land on theme tokens, and
+  // the chat cap (8) collapses the middle into a head/tail split with an
+  // expander between them.
+  expect(readCard(card)).toMatchInlineSnapshot(`
+    {
+      "colors": [
+        "font-weight: 700;",
+        "color: var(--dsw-alias-state-success-primary);",
+        "color: var(--dsw-alias-state-error-primary);",
+      ],
+      "copy": "复制",
+      "expander": {
+        "expanded": "false",
+        "label": "展开其余 14 行输出",
+        "text": "… 其余 14 行",
+      },
+      "lines": [
+        "Running 4 checks",
+        "✓ typecheck                                          1.82s",
+        "✓ lint                                               0.94s",
+        "✓ duplication                                        2.10s",
+        "markdown/Markdown.tsx       100%     100%        100%         -",
+        "",
+        "1 of 4 checks failed",
+        "[exit code: 1]",
+      ],
+      "prompt": "nested pnpm run check",
+      "status": "退出码 1",
+    }
+  `)
+})
+
+it('the fallback row reaches the same card through its expand control', async () => {
+  boot()
+  await openFixtureSession()
+
+  const row = fallbackBashRow()
+  expect(row.querySelector('[data-terminal]')).toBeNull()
+  const toggle = row.querySelector('button[aria-expanded]')
+  if (toggle === null) throw new Error('fallback row expand control missing')
+  fireEvent.click(toggle)
+  const card = await waitFor(() => {
+    const found = row.querySelector('[data-terminal]')
+    if (found === null) throw new Error('terminal card missing after expanding the fallback row')
+    return found
+  })
+  // Three plain lines under the cap: no ANSI spans, no exit pill, no expander.
+  expect(readCard(card)).toMatchInlineSnapshot(`
+    {
+      "colors": [],
+      "copy": "复制",
+      "expander": null,
+      "lines": [
+        "total 2",
+        "drwxr-xr-x fixture",
+        "-rw-r--r-- demo.txt",
+      ],
+      "prompt": "fixture ls -la",
+      "status": null,
+    }
+  `)
+})
+
+it('the chat card expands the collapsed middle in place, without opening the details panel', async () => {
+  boot()
+  await openFixtureSession()
+
+  const card = keyedBashRow().parentElement?.querySelector('[data-terminal]')
+  if (card === null || card === undefined) throw new Error('resident terminal card missing')
+  const expander = card.querySelector('button[aria-expanded]')
+  if (expander === null) throw new Error('height-cap expander missing')
+  const capped = card.querySelectorAll('[class*="_line_"]').length
+
+  fireEvent.click(expander)
+  await waitFor(() => {
+    expect(card.querySelector('button[aria-expanded]')?.getAttribute('aria-expanded')).toBe('true')
+  })
+  expect({
+    cappedLines: capped,
+    expandedLines: card.querySelectorAll('[class*="_line_"]').length,
+    expanderLabel: card.querySelector('button[aria-expanded]')?.getAttribute('aria-label'),
+    // The card sits outside the summary row's click target, so toggling it
+    // left the details panel shut.
+    detailsOpen: screen.queryByText('Input') !== null,
+  }).toMatchInlineSnapshot(`
+    {
+      "cappedLines": 8,
+      "detailsOpen": false,
+      "expandedLines": 22,
+      "expanderLabel": "收起输出",
+    }
+  `)
+})
+
+it('the details panel Output section renders the same call at full height', async () => {
+  boot()
+  await openFixtureSession()
+
+  fireEvent.click(keyedBashRow())
+  const label = await screen.findByText('Output')
+  const section = label.closest('section')
+  if (section === null) throw new Error('Output section missing')
+  const card = section.querySelector('[data-terminal]')
+  if (card === null) throw new Error('details panel Output is not a terminal card')
+
+  const chatLines = keyedBashRow().parentElement?.querySelectorAll('[class*="_line_"]').length ?? 0
+  expect({
+    ...readCard(card),
+    // The panel keeps the primitive's own allowance (16) against the chat
+    // row's 8, so it shows strictly more of the same output.
+    panelLines: card.querySelectorAll('[class*="_line_"]').length,
+    chatLines,
+  }).toMatchInlineSnapshot(`
+    {
+      "chatLines": 8,
+      "colors": [
+        "font-weight: 700;",
+        "color: var(--dsw-alias-state-success-primary);",
+        "color: var(--dsw-alias-state-error-primary);",
+        "color: var(--dsw-alias-label-tertiary);",
+      ],
+      "copy": "复制",
+      "expander": {
+        "expanded": "false",
+        "label": "展开其余 6 行输出",
+        "text": "… 其余 6 行",
+      },
+      "lines": [
+        "Running 4 checks",
+        "✓ typecheck                                          1.82s",
+        "✓ lint                                               0.94s",
+        "✓ duplication                                        2.10s",
+        "✗ unit                                               8.41s",
+        "",
+        "packages/client/ui-primitives/tests/terminal-block.spec.tsx",
+        "  FAIL caps output at the configured line budget",
+        "CodeBlock.tsx               98.4%    96.2%       100%         41-43",
+        "highlight.ts                100%     100%        100%         -",
+        "Pill.tsx                    100%     100%        100%         -",
+        "StateDot.tsx                100%     100%        100%         -",
+        "markdown/Markdown.tsx       100%     100%        100%         -",
+        "",
+        "1 of 4 checks failed",
+        "[exit code: 1]",
+      ],
+      "panelLines": 16,
+      "prompt": "nested pnpm run check",
+      "status": "退出码 1",
+    }
+  `)
+})
diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts
index 5c7befd8c9..401d3a76a4 100644
--- a/packages/client/connection/src/client/fixture.ts
+++ b/packages/client/connection/src/client/fixture.ts
@@ -46,6 +46,51 @@ const MARKDOWN_FIXTURE = [
 
 const USER_MARKDOWN_LITERAL = '用户字面量:# 不渲染 `code` [link](https://example.com)'
 
+/**
+ * SGR wrapper for the terminal output sample below: authoring the escapes as
+ * `\u001b` keeps literal control bytes out of this source file.
+ * @param code - the SGR parameter (an ANSI color or attribute number).
+ * @param body - the text the attribute applies to.
+ * @returns the body wrapped in the attribute and a reset.
+ */
+function sgr(code: number, body: string): string {
+  return `\u001b[${code}m${body}\u001b[0m`
+}
+
+/**
+ * Terminal output sample for fixture turn 66, authored to carry every feature
+ * the terminal card draws that turn 60's three plain lines cannot reach:
+ * basic-16 SGR foreground runs (green, red, bright-black) that must resolve to
+ * `--dsw-*` tokens, a bold run, column-aligned table rows that must scroll
+ * rather than fold, more than DEFAULT_TERMINAL_MAX_LINES (16) lines so the
+ * height cap collapses the middle, and the trailing `[exit code: N]` marker the
+ * bash tool appends, from which the exit pill is recovered.
+ */
+const TERMINAL_OUTPUT_FIXTURE = [
+  sgr(1, 'Running 4 checks'),
+  `${sgr(32, '\u2713')} typecheck                                          1.82s`,
+  `${sgr(32, '\u2713')} lint                                               0.94s`,
+  `${sgr(32, '\u2713')} duplication                                        2.10s`,
+  `${sgr(31, '\u2717')} unit                                               8.41s`,
+  '',
+  sgr(90, 'packages/client/ui-primitives/tests/terminal-block.spec.tsx'),
+  `  ${sgr(31, 'FAIL')} caps output at the configured line budget`,
+  '    expected 16 lines, received 24',
+  '',
+  'NAME                        LINES    BRANCHES    FUNCTIONS    UNCOVERED',
+  'TerminalBlock.tsx           100%     100%        100%         -',
+  'ansi.ts                     100%     100%        100%         -',
+  'clipboard.ts                100%     100%        100%         -',
+  'CodeBlock.tsx               98.4%    96.2%       100%         41-43',
+  'highlight.ts                100%     100%        100%         -',
+  'Pill.tsx                    100%     100%        100%         -',
+  'StateDot.tsx                100%     100%        100%         -',
+  'markdown/Markdown.tsx       100%     100%        100%         -',
+  '',
+  sgr(31, '1 of 4 checks failed'),
+  '[exit code: 1]',
+].join('\n')
+
 const DEEPSEEK_REASONING = {
   efforts: [
     { id: 'off', name: 'Off' },
@@ -124,7 +169,8 @@ function buildAlphaLog(): SessionEvent[] {
   }
   // Three view-sample turns (60-62) cover the built-in card types. The real filesystem names in
   // turns 62-63 also exercise their dedicated generic-row icon/title/path summaries. `echo` above
-  // stays presenter-less as the unknown fallback.
+  // stays presenter-less as the unknown fallback. Turn 66 is the second terminal sample, carrying
+  // what turn 60's three plain lines cannot (see TERMINAL_OUTPUT_FIXTURE) through the keyed row.
   const toolTurn = (turn: number, name: string, args: string, resultText: string): void => {
     const callId = `fx-call-${turn}`
     push({ type: 'turn/start', data: { turn, trigger: { kind: 'message', source: { kind: 'user' } } } })
@@ -201,6 +247,13 @@ function buildAlphaLog(): SessionEvent[] {
   const callIndex = events.length - 4
   const callTime = events[callIndex]?.time as number
   events.splice(callIndex + 1, 0, { type: 'todo/write', time: callTime + 400, data: { todos: fixtureTodos } })
+  // Turn 66: the terminal sample turn 60's three clean lines cannot cover —
+  // ANSI SGR coloring, output past the terminal card's height cap, a nested
+  // cwd whose prompt label is its last segment, and a non-zero exit recovered
+  // from the trailing marker the bash tool appends. Named `bash`, so it also
+  // covers the keyed toolview row (turn 60's `fx-bash` covers the render-site
+  // fallback row) — the two chat-row shapes the terminal card renders in.
+  toolTurn(66, 'bash', '{"command":"pnpm run check","cwd":"/tmp/fixture/deep/nested"}', TERMINAL_OUTPUT_FIXTURE)
   events.forEach((e, i) => { e.seq = i })
   return events as unknown as SessionEvent[]
 }
@@ -219,7 +272,11 @@ function presentCall(name: string, argsRaw: string): ToolCallView | undefined {
     return undefined
   }
   switch (name) {
+    // Both names present the same terminal card: `fx-bash` lands on the
+    // render-site fallback row, `bash` on the keyed BashRow registration, so
+    // the two chat-row shapes of one render intent are both reachable.
     case 'fx-bash':
+    case 'bash':
       return { card: 'terminal', title: str(args.command), cwd: str(args.cwd, '/tmp/fixture'), description: 'fixture 终端样本' }
     case 'fx-write':
       return {
@@ -235,12 +292,24 @@ function presentCall(name: string, argsRaw: string): ToolCallView | undefined {
   }
 }
 
+/**
+ * Recover the exit status from a trailing `[exit code: N]` marker, mirroring
+ * the real bash tool's `parseExitStatus` (this package must not depend on a
+ * tool package, so the marker contract is re-read rather than imported).
+ * @param text - the rendered result text.
+ * @returns the recovered exit code (0 when the marker is absent).
+ */
+function fixtureExitCode(text: string): number {
+  const marker = /\n\[exit code: (\d+)\]$/.exec(text)
+  return marker?.[1] === undefined ? 0 : Number(marker[1])
+}
+
 function presentResult(name: string, argsRaw: string, resultText: string): ToolResultView | undefined {
   const call = presentCall(name, argsRaw)
   if (call === undefined) return undefined
   switch (call.card) {
     case 'terminal':
-      return { card: 'terminal', output: resultText, exitCode: 0 }
+      return { card: 'terminal', output: resultText, exitCode: fixtureExitCode(resultText) }
     case 'diff':
       return { card: 'diff', diffs: call.diffs }
     case 'generic':
diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml
index c1a6828d5b..dd28591b01 100644
--- a/packages/client/ui-conversation/README.i18n.yaml
+++ b/packages/client/ui-conversation/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-conversation/README.md
-README.md: 56a445ccfa86e0b11cf5aefc37819a30746f0739
-README.zh.md: a7c160ecdd74074257c9d149630663dacd05c070
+README.md: 1c6912b05e259fa1f4a7096c3a2b82f9f67f5527
+README.zh.md: 157bfafd3a1157420acbb73861cd40d759228743
diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md
index 56a445ccfa..1c6912b05e 100644
--- a/packages/client/ui-conversation/README.md
+++ b/packages/client/ui-conversation/README.md
@@ -10,6 +10,8 @@ The view ring IS a slot: the conversation registration declares the `'conversati
 
 Generic tool rows classify the built-in bash, read, search, write, edit, and run_code names into dedicated visual variants. The filesystem variants render the edit icon and `Write · ` or `Edit · ` summary while retaining the shared row-to-details interaction. The code variant summarizes with the model-authored `description` and expands to the program itself; its logged sub-dispatches render as always-visible nested rows through the SAME keyed toolview hole (custom registrations and the GenericToolCard fallback apply to sub-rows unchanged), and the details panel resolves a selected sub-call id to its full logged args and complete output. Cordis lifecycle tools reuse those generic variants while presenting `Inspect`, `Mount temporary Plugin`, and `Unmount temporary Plugin` with a shared Cordis accent; mount keeps the code variant's expandable source rendering.
 
+A tool call declaring the `terminal` render intent renders its command output inline, at both conversation render sites, through ui-primitives' `TerminalBlock`. `contract/terminal-card-model.ts` is the single derivation from the snapshot's `callView`/`resultView` pair, so the sites cannot disagree about a command, its cwd, or its exit status; it yields null — the generic path — for any other card tag, including one this client version does not know. The keyed `BashRow` carries the card resident below its summary row and outside that row's click target, so copying or expanding the output does not open the details panel; the render-site fallback row keeps it behind its existing expand control. Rows cap at `CHAT_TERMINAL_MAX_LINES` (8) against the panel's 16, which is what keeps a summary surface bounded — the panel stays the single-call reading surface. Inline output is licensed for this intent alone; a generic tool's content remains panel-only ([decision](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)).
+
 Tool rows are slots too — the standalone tool ring (`ToolViewRegistry`/`ctx.toolviews`/outlet) is retired. The chat entry declares the keyed `'conversation.chat.toolview'` hole (session scope; the key space is runtime-open); its render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam (apply mounts ConversationService after the chat registration, so the service being present guarantees the slot is declared); session differentiation happens inside the component (`useSessions` reading `parentId` — the bash sample is the third-party-posture exemplar). Trajectory/waterfall toolview slots share this shape and land with their own render sites (RendersCheck rejects a declaration nobody renders).
 
 The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`/ 已完成 · ` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: -1` — above the queue rows — and is the durable plan strip: it selects `todos` off the session snapshot and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and collapses to a header of title plus `"/ tasks ·  in progress"` (status glyphs are the figma check / progress / dashed-pending set). The dock adapter owns the selection so the panel stays a pure function of its props; the persistent list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included.
diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md
index a7c160ecdd..157bfafd3a 100644
--- a/packages/client/ui-conversation/README.zh.md
+++ b/packages/client/ui-conversation/README.zh.md
@@ -10,6 +10,8 @@
 
 通用工具行把内置的 bash、read、search、write、edit 和 run_code 名称归入专用视觉变体。文件系统变体会渲染 edit 图标和 `Write · ` 或 `Edit · ` 摘要,同时保留共享的行到详情交互。code 变体以模型撰写的 `description` 作摘要,展开后显示程序本身;其已记录的子调用经由同一个键控 toolview 空位渲染为始终可见的嵌套行(自定义注册和 GenericToolCard fallback 原样适用于子行),details 面板则会根据选中的子调用 id 解析出其完整记录的参数与完整输出。Cordis 生命周期工具复用这些通用变体,同时以统一的 Cordis 强调色呈现 `Inspect`、`Mount temporary Plugin` 和 `Unmount temporary Plugin`;mount 行保留 code 变体的可展开源码渲染。
 
+声明 `terminal` 渲染意图的工具调用,会在两个对话渲染点上都通过 ui-primitives 的 `TerminalBlock` 内联渲染其命令输出。`contract/terminal-card-model.ts` 是从快照的 `callView`/`resultView` 对推导的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧;对任何其他 card 标签——包括当前客户端版本不认识的标签——它返回 null,落回通用路径。键控的 `BashRow` 把卡片常驻在摘要行下方、且位于该行点击目标之外,因此复制或展开输出不会打开详情面板;渲染点兜底行则保持其既有的展开控件。行的上限是 `CHAT_TERMINAL_MAX_LINES`(8),面板为 16,正是这一点让摘要面保持有界——面板仍是单次调用的阅读面。内联输出只对该意图开放;通用工具的内容仍然只在面板中呈现([决策](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md))。
+
 工具行同样是 slot:独立工具环(`ToolViewRegistry`/`ctx.toolviews`/outlet)已经退役。聊天配置项声明键控的 `'conversation.chat.toolview'` 空位(Session scope;key 空间在运行时开放);其渲染点逐行通过 `entryKey: toolName` 分发,并以 `GenericToolCard` 作为调用点 `fallback`。owner 载荷是统一的 `ToolRowOwnerProps`(`callId`/`toolName`/`block`/`openDetails`),`ToolRowProps` 则预先将其与 Session 标准工具包组合。注册方只是普通插件:`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`,以 `inject: ['slots', 'conversation']` 作为加载顺序 seam(apply 在聊天注册后挂载 ConversationService,因此服务存在即可保证 slot 已声明);Session 区分在组件内部完成(`useSessions` 读取 `parentId`,bash 示例是第三方姿态的范例)。Trajectory/waterfall 工具视图 slot 共享此形状,并随各自的渲染点落地(RendersCheck 会拒绝没有任何渲染方的声明)。
 
 todo 两个面就是在该形状上的两个注册项,都是普通注册方插件,`inject: ['slots', 'conversation']`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key,摘要该次调用「试图写入」的内容(从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`;模型 JSON 残缺或形状不对时回落到通用摘要;非 ok 执行状态保留通用状态点,使被取消的调用绝不读成一次已完成的更新)。`TodoDock` 以 `order: -1` 占用 `'conversation.input.dock'` 列表 slot(位于队列行之上),是常驻的计划条:它从会话快照中选取 `todos` 并渲染 `TodoPanel`,后者接收纯列表,在列表为空时自我隐藏,折叠时收成标题加 `"<已完成>/<总数> tasks ·  in progress"` 的表头(状态图标为 figma 的勾选/进行中/虚线未开始一组)。选取由 dock 适配器负责,因此面板保持为其 props 的纯函数;常驻列表放在此处而非行内,行才能保持单行。输入区 composer 链隐藏的一切(例如 ui-question 对 `conversation.composer` 的接管)也会隐藏整个 dock,包括这条计划条。
diff --git a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx
index 5cb2126f34..0bfde97019 100644
--- a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx
+++ b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx
@@ -9,6 +9,7 @@ import {
   IconApiOutline14, IconBrowseOutline16, IconCodeOutline16, IconEditOutline16, IconSearchOutline16, IconThinkOutline14,
 } from '@deepseek-ai/dsh-client-ui-primitives'
 import type { ToolRowOwnerProps } from '../contract/slots.ts'
+import { terminalCardModel } from '../contract/terminal-card-model.ts'
 import { toolRowModel, type ToolRowVariant } from '../contract/tool-call-model.ts'
 import { ToolRow } from './ToolRow.tsx'
 import { IconSparkle16 } from './IconSparkle16.tsx'
@@ -35,6 +36,7 @@ export function GenericToolCard({ toolName, block, openDetails }: ToolRowOwnerPr
       title={model.title}
       summary={model.summary}
       body={model.body}
+      terminal={terminalCardModel(block)}
       state={model.state}
       onOpenDetails={openDetails}
     />
diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.module.css b/packages/client/ui-conversation/src/client/chat/ToolRow.module.css
index 5d44a9260e..d238218d97 100644
--- a/packages/client/ui-conversation/src/client/chat/ToolRow.module.css
+++ b/packages/client/ui-conversation/src/client/chat/ToolRow.module.css
@@ -102,9 +102,13 @@ button.leading {
   color: var(--dsw-alias-label-tertiary);
 }
 
-/* The code variant's expanded body is the run_code program, rendered through
-   the shared CodeBlock (shiki-highlighted TypeScript); only indentation is
-   this row's concern. */
-.codeBody {
+/* The two block-shaped expanded bodies: the code variant's run_code program
+   through CodeBlock (shiki-highlighted TypeScript) and a terminal card's
+   command output through TerminalBlock. Both are drawn by the shared
+   primitive, so only the row's indentation is this file's concern — the margin
+   also replaces each primitive's own standalone vertical spacing with the
+   flow's row rhythm. */
+.codeBody,
+.terminalBody {
   margin: 4px 0 4px 22px;
 }
diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx
index a81c084b8e..91dcfe4a0a 100644
--- a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx
+++ b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx
@@ -1,13 +1,19 @@
 // ToolRow: the single-line tool summary row (figma component set 122:9479) —
 // 16px leading slot (state dot / tool icon, chevron when expanded) + title +
-// separator dot + FILL-truncated summary. Expanded body is indented gray text;
-// no inline output (full results live in the details panel). Expand state is
-// component-local view state; row click hands the selection off to the owner.
+// separator dot + FILL-truncated summary. The collapsed row is always one
+// line; the expanded body is indented gray text, the run_code program through
+// CodeBlock, or — for a call whose render intent is a terminal card — the
+// command's own output through TerminalBlock, capped at
+// CHAT_TERMINAL_MAX_LINES so the message flow stays scannable. The details
+// panel remains the full-height reading surface for the same call. Expand
+// state is component-local view state; row click hands the selection off to
+// the owner.
 
 import { useState, type KeyboardEvent, type MouseEvent, type ReactNode } from 'react'
 import clsx from 'clsx'
-import { CodeBlock, StateDot } from '@deepseek-ai/dsh-client-ui-primitives'
+import { CodeBlock, StateDot, TerminalBlock } from '@deepseek-ai/dsh-client-ui-primitives'
 import { IconChevronDownOutline14 } from '@deepseek-ai/dsh-client-ui-primitives'
+import { CHAT_TERMINAL_MAX_LINES, type TerminalCardModel } from '../contract/terminal-card-model.ts'
 import type { ToolRowState, ToolRowVariant } from '../contract/tool-call-model.ts'
 import css from './ToolRow.module.css'
 
@@ -19,8 +25,15 @@ export interface ToolRowProps {
   icon: ReactNode
   title: string
   summary: string
-  /** Expanded-body text; null = not expandable (leading slot never toggles). */
+  /** Expanded-body text; null = no text body (`terminal` is the other body source). */
   body: string | null
+  /**
+   * Terminal-card material for a call whose render intent is a terminal card
+   * (derived by `terminalCardModel`); it replaces the text body when present.
+   * Null or absent leaves the text body, and a row with neither is not
+   * expandable (its leading slot never toggles).
+   */
+  terminal?: TerminalCardModel | null | undefined
   state: ToolRowState
   /** Makes the row itself the expand control instead of only its leading icon. */
   expandOnRowClick?: boolean | undefined
@@ -46,12 +59,18 @@ export function ToolRow({
   title,
   summary,
   body,
+  terminal,
   state,
   expandOnRowClick = false,
   onOpenDetails,
 }: ToolRowProps) {
   const [expanded, setExpanded] = useState(false)
-  const expandable = body !== null
+  const terminalBody = terminal ?? null
+  const expandable = body !== null || terminalBody !== null
+  // The text arms take the empty string for a null body: a row expandable
+  // only through its terminal material renders the terminal body instead, so
+  // this substitution never shows.
+  const text = body ?? ''
   const open = expanded && expandable
   const rowExpands = expandable && expandOnRowClick
   const toggleExpand = () => {
@@ -99,9 +118,11 @@ export function ToolRow({
           
         )}
       
-      {open && (variant === 'code'
-        ? 
-        : 
{body}
)} + {open && (terminalBody !== null + ? + : variant === 'code' + ? + :
{text}
)} ) } diff --git a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts new file mode 100644 index 0000000000..a1b274e3f9 --- /dev/null +++ b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts @@ -0,0 +1,83 @@ +/** + * Pure derivation of the terminal-card props from a frozen call slice: the + * `card:'terminal'` render intent the bash tool declares arrives on the + * snapshot as `callView`/`resultView`, and this is the one place that turns + * that pair into what {@link TerminalBlock} draws. Both conversation render + * sites (the chat tool row's expanded body and the details panel's Output + * section) call this, so the command, cwd, output and exit status they show + * are derived once. + * @module + */ +import type { TerminalBlockProps } from '@deepseek-ai/dsh-client-ui-primitives' +import type { ToolCallBlock } from './tool-call-model.ts' + +/** + * Output lines the chat row's expanded terminal body 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. A design constant of this UI's row geometry, + * not a deployment choice, so it is fixed here rather than a plugin Config + * field. + */ +export const CHAT_TERMINAL_MAX_LINES = 8 + +/** + * The {@link TerminalBlock} props this derivation owns. Picked off the + * primitive's props so the two stay in step; `home` is absent because the web + * client has no home path for the session host (a cwd renders as its last + * path segment), and `maxLines`/`className` belong to each render site. + */ +export type TerminalCardModel = Pick< + TerminalBlockProps, + 'command' | 'cwd' | 'output' | 'exitCode' | 'signal' | 'running' +> + +/** + * Derive the terminal-card props for a tool call, or null when this call is + * not a terminal card and belongs on the generic path. + * + * The call side supplies the command and its working directory; the result + * side supplies the captured output and exit status. Three cases produce + * null, all of them the documented generic-card default: + * + * - Neither side declares `card:'terminal'` — including a `card` value this + * UI version does not know, which arrives over the wire and therefore + * cannot be trusted to be one of the compiled variants. + * - A settled call whose result view is not a terminal card: the result + * presentation decides how the settled call renders, and the bash tool + * returns a generic fenced card for an execution error or a background + * start, whose text and error styling the generic path preserves. + * + * Window truncation can drop the call head from a settled result (see + * `ToolResultNode.call`/`callView` in dsh-client-runtime), leaving a terminal + * result with no call side. That still renders: the command falls back to the + * result view's replacement title, then to an empty command (the prompt line + * draws bare), and the prompt shows no cwd. + * @param block - RunningToolCall or ToolResultNode off the snapshot caches. + * @returns the terminal-card props, or null for the generic path. + */ +export function terminalCardModel(block: ToolCallBlock): TerminalCardModel | null { + const call = block.callView?.card === 'terminal' ? block.callView : null + if (!('kind' in block)) { + // Running: the call view exists, the result view does not yet. + return call === null ? null : { + command: call.title, + cwd: call.cwd, + output: undefined, + exitCode: undefined, + signal: undefined, + running: true, + } + } + const result = block.resultView?.card === 'terminal' ? block.resultView : null + if (result === null) return null + return { + command: call?.title ?? result.title ?? '', + cwd: call?.cwd, + output: result.output, + exitCode: result.exitCode, + signal: result.signal, + running: false, + } +} diff --git a/packages/client/ui-conversation/src/client/contract/tool-call-model.ts b/packages/client/ui-conversation/src/client/contract/tool-call-model.ts index 5b725df00b..0b1afa8060 100644 --- a/packages/client/ui-conversation/src/client/contract/tool-call-model.ts +++ b/packages/client/ui-conversation/src/client/contract/tool-call-model.ts @@ -1,7 +1,9 @@ /** * Pure row-model derivation for tool summary rows: variant classification, - * one-line summary and expanded-body text from the frozen call slice. No - * inline output ever — full results live in the details panel. + * one-line summary and expanded-body text from the frozen call slice. This + * derivation reads the call ARGUMENTS only; a call whose render intent is a + * terminal card gets its expanded body from the views instead, through + * `terminalCardModel` in terminal-card-model.ts. */ // The block union's defining home is runtime (fold-product types); this // contract only forwards it (type-definition authority stays with the layer diff --git a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css index abdece3e25..ef4173735e 100644 --- a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css +++ b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css @@ -92,3 +92,9 @@ .code[data-error] { color: var(--dsw-alias-state-error-primary); } + +/* The terminal card sits directly under its section label, so it drops the + primitive's standalone vertical margin; the section owns the spacing. */ +.terminal { + margin: 0; +} diff --git a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx index 650a95f833..326e765044 100644 --- a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx @@ -1,47 +1,59 @@ // DetailsPanel, P-I minimal form: close button + the selected call's args and -// result rendered raw. The three-段 Switch / Prev-Next stepping / See-in- -// trajectory are deferred (ledger). Reads the selection from the shared chat +// result — args as JSON, the result raw except for a terminal-card call, whose +// Output section is the command's terminal card. The three-段 Switch / +// Prev-Next stepping / See-in-trajectory are deferred (ledger). Reads the +// selection from the shared chat // store (conversation writes, this panel reads — the cross-registration // share the store seat exists for) and derives the call material from the // session snapshot — no data of its own. -import { CodeBlock } from '@deepseek-ai/dsh-client-ui-primitives' +import { CodeBlock, TerminalBlock } from '@deepseek-ai/dsh-client-ui-primitives' import { shallowEqual } from '@deepseek-ai/dsh-client-runtime/client' -import type { ConversationSnapshot, ToolResultNode } from '@deepseek-ai/dsh-client-runtime/client' +import type { ConversationSnapshot, RunningToolCall, ToolResultNode } from '@deepseek-ai/dsh-client-runtime/client' import type { DetailsSlotProps } from '../contract/slots.ts' +import { terminalCardModel } from '../contract/terminal-card-model.ts' +import type { ToolCallBlock } from '../contract/tool-call-model.ts' import css from './DetailsPanel.module.css' /** Full props composed by reference from the contract (automatic shares & injected share). */ export type DetailsPanelProps = DetailsSlotProps -/** Selected call material: resolved result node, or the in-flight running call's args. */ +/** + * Selected call material: the call's display name and args plus the frozen + * block slice it came from. `block` is a snapshot-cached reference, so the + * wrapper stays shallow-equal across unrelated snapshot frames; the settled / + * running split is read off it with the `'kind' in block` discrimination + * instead of duplicated as flags. + */ interface CallMaterial { name: string argsRaw: string | null - result: ToolResultNode | null - running: boolean + block: ToolCallBlock +} + +/** Material of a settled result node (native call or run_code sub-dispatch). */ +function settledMaterial(node: ToolResultNode, callId: string): CallMaterial { + return { name: node.call?.name ?? callId, argsRaw: node.call?.argsRaw ?? null, block: node } +} + +/** Material of an in-flight call (native call or run_code sub-dispatch). */ +function runningMaterial(call: RunningToolCall): CallMaterial { + return { name: call.name, argsRaw: call.argsRaw, block: call } } function materialFor(s: ConversationSnapshot, callId: string): CallMaterial | null { for (const node of s.nodes) { - if (node.kind === 'tool-result' && node.callId === callId) { - return { name: node.call?.name ?? callId, argsRaw: node.call?.argsRaw ?? null, result: node, running: false } - } + if (node.kind === 'tool-result' && node.callId === callId) return settledMaterial(node, callId) } const open = s.runningCalls.find(c => c.callId === callId) - if (open !== undefined) { - return { name: open.name, argsRaw: open.argsRaw, result: null, running: true } - } + if (open !== undefined) return runningMaterial(open) // run_code sub-dispatches: the native call-block shapes, so a selected // sub-row resolves through the same material as a native call — the // settled ToolResultNode form, or the RunningToolCall form mid-flight. for (const subs of s.codeDispatches.values()) { for (const sub of subs) { if (sub.callId !== callId) continue - if ('kind' in sub) { - return { name: sub.call?.name ?? callId, argsRaw: sub.call?.argsRaw ?? null, result: sub, running: false } - } - return { name: sub.name, argsRaw: sub.argsRaw, result: null, running: true } + return 'kind' in sub ? settledMaterial(sub, callId) : runningMaterial(sub) } } return null @@ -95,15 +107,7 @@ export function DetailsPanel({ useSession, useStore, closeDetails }: DetailsPane )}
Output
- {/* materialFor invariant: result===null ⇔ running (a settled - material always carries its result node). */} - {material.result === null - ?
运行中…
- : ( -
-                        {renderResult(material.result)}
-                      
- )} +
)} @@ -112,6 +116,29 @@ export function DetailsPanel({ useSession, useStore, closeDetails }: DetailsPane ) } +/** + * The Output section's body for the selected call. A terminal-card call — a + * shell command's call/result views — renders through the shared TerminalBlock + * at the primitive's own full height allowance, so column-aligned output keeps + * its alignment and scrolls sideways instead of folding. Every other call, and + * a running call with no terminal card yet, keeps the flattened text form. + * @param props.material - the selected call's material from {@link materialFor}. + * @returns the Output section's body element. + */ +function OutputBody({ material }: { material: CallMaterial }) { + const terminal = terminalCardModel(material.block) + if (terminal !== null) return + // A settled call always carries the result node the flattened form needs; + // the running shape has no result to flatten. + if (!('kind' in material.block)) return
运行中…
+ const result = material.block + return ( +
+      {renderResult(result)}
+    
+ ) +} + /** Flatten result content blocks to display text (text blocks verbatim, others as JSON). */ function renderResult(node: ToolResultNode): string { const parts: string[] = [] diff --git a/packages/client/ui-conversation/src/client/toolviews/bash-sample.module.css b/packages/client/ui-conversation/src/client/toolviews/bash-sample.module.css index 9c42e69b59..450eb2301d 100644 --- a/packages/client/ui-conversation/src/client/toolviews/bash-sample.module.css +++ b/packages/client/ui-conversation/src/client/toolviews/bash-sample.module.css @@ -1,4 +1,18 @@ -/* Bash toolview: same geometry/tokens as ToolRow (figma Bash · description). */ +/* Bash toolview: same geometry/tokens as ToolRow (figma Bash · description), + plus the terminal card the row stacks under its summary line. */ + +/* Summary line over the terminal card; the summary row keeps its own 24px + height, so the card is a column around it rather than a change to it. */ +.card { + display: flex; + flex-direction: column; +} + +/* Row indentation matches ToolRow's expanded bodies (16px leading + 6px gap), + and replaces the primitive's standalone vertical margin with the flow's. */ +.terminal { + margin: 4px 0 4px 22px; +} .root { display: flex; diff --git a/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx b/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx index 616eee5943..49a5e6c2e4 100644 --- a/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx +++ b/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx @@ -3,10 +3,18 @@ // Product chrome matches ToolRow / Think (figma: Bash · {description}). // Child sessions keep a scoped badge so session-dimension differentiation stays // observable inside the component (no parallel registry). +// +// A bash call declares the terminal render intent, so this row also renders +// the command's own output through TerminalBlock. This row has no expand +// control (a click goes to the details panel), so its terminal body is +// resident rather than expand-gated as in ToolRow; the block's own height cap +// (CHAT_TERMINAL_MAX_LINES) and internal expander keep a long output from +// taking over the message flow. import type { Context } from 'cordis' -import { IconApiOutline14, StateDot } from '@deepseek-ai/dsh-client-ui-primitives' +import { IconApiOutline14, StateDot, TerminalBlock } from '@deepseek-ai/dsh-client-ui-primitives' import type { ToolRowProps } from '../contract/slots.ts' +import { CHAT_TERMINAL_MAX_LINES, terminalCardModel } from '../contract/terminal-card-model.ts' import { toolRowModel, type ToolRowState } from '../contract/tool-call-model.ts' import css from './bash-sample.module.css' @@ -29,26 +37,37 @@ function stateStatus(state: ToolRowState): string | null { } } -/** Bash row: icon + Bash · {description}, matching the shared ToolRow chrome. */ +/** + * Bash row: icon + Bash · {description} in the shared ToolRow chrome, with the + * command's terminal card below it. The summary row keeps its own click target + * (the details handoff); the terminal card sits outside that row, so its copy + * and expand controls do not open the details panel. + */ export function BashRow({ toolName, block, openDetails, sessionId, useSessions }: ToolRowProps) { const model = toolRowModel(toolName, block) + const terminal = terminalCardModel(block) const isChild = useSessions(list => list.byId[sessionId]?.parentId !== undefined) const status = stateStatus(model.state) return ( -
- {leadingFor(model.state)} - {status !== null && {status}} - {isChild && scoped} - {model.title} - - {model.summary} +
+
+ {leadingFor(model.state)} + {status !== null && {status}} + {isChild && scoped} + {model.title} + + {model.summary} +
+ {terminal !== null && ( + + )}
) } diff --git a/packages/client/ui-conversation/tests/chat-tool-row.spec.tsx b/packages/client/ui-conversation/tests/chat-tool-row.spec.tsx index 13a74548b4..4a5e80b224 100644 --- a/packages/client/ui-conversation/tests/chat-tool-row.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-tool-row.spec.tsx @@ -71,6 +71,11 @@ describe('tool-call-model', () => { expect(toolRowModel('bash', result({ call: null })).body).toBeNull() }) + it('a code row with an empty program falls back to the args JSON envelope', () => { + expect(toolRowModel('run_code', running({ name: 'run_code', argsRaw: '{"code":""}' })).body) + .toBe('{\n "code": ""\n}') + }) + it('gives Cordis lifecycle tools action titles over their generic variants', () => { expect(toolRowModel('cordis_inspect', running({ name: 'cordis_inspect', @@ -139,6 +144,22 @@ describe('ToolRow', () => { expect(view.queryByTestId('tool-icon')).not.toBeNull() }) + it('an expandOnRowClick row toggles from Enter and Space, ignoring other keys', () => { + const view = render() + const row = view.getByRole('button') + fireEvent.keyDown(row, { key: 'Tab' }) + expect(row.getAttribute('aria-expanded')).toBe('false') + fireEvent.keyDown(row, { key: 'Enter' }) + expect(row.getAttribute('aria-expanded')).toBe('true') + fireEvent.keyDown(row, { key: ' ' }) + expect(row.getAttribute('aria-expanded')).toBe('false') + }) + + it('a non-expandable expandOnRowClick row exposes no row button', () => { + const view = render() + expect(view.queryByRole('button')).toBeNull() + }) + it('row click hands off to onOpenDetails; the expand toggle does not', () => { const open = vi.fn() const view = render() diff --git a/packages/client/ui-conversation/tests/terminal-card.spec.tsx b/packages/client/ui-conversation/tests/terminal-card.spec.tsx new file mode 100644 index 0000000000..1ab75861b5 --- /dev/null +++ b/packages/client/ui-conversation/tests/terminal-card.spec.tsx @@ -0,0 +1,359 @@ +// @vitest-environment jsdom +// The terminal render intent on the web side: the pure terminalCardModel +// derivation over callView/resultView, and both conversation render sites that +// consume it — the chat tool row's expanded body (GenericToolCard / BashRow) +// and the details panel's Output section. + +import { afterEach, describe, expect, it, vi } from 'vitest' +import { cleanup, fireEvent, render } from '@testing-library/react' +import { bindSnapshotSelector } from '@deepseek-ai/dsh-client-web-react' +import { createSnapshotStore } from '@deepseek-ai/dsh-client-runtime/client' +import type { + ConversationSnapshot, RunningToolCall, SessionId, SessionListState, ToolResultNode, WorkspaceListState, +} from '@deepseek-ai/dsh-client-runtime/client' +import type { ToolCallView, ToolResultView } from '@deepseek-ai/dsh-client-connection/client' +import type { SelectionTarget, ToolRowOwnerProps, ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import { CHAT_TERMINAL_MAX_LINES, terminalCardModel } from '../src/client/contract/terminal-card-model.ts' +import { createChatStore } from '../src/client/stores.ts' +import { GenericToolCard } from '../src/client/chat/GenericToolCard.tsx' +import { DetailsPanel } from '../src/client/skeleton/DetailsPanel.tsx' +import { BashRow } from '../src/client/toolviews/bash-sample.tsx' + +afterEach(cleanup) + +/** + * Match an output line with its interior whitespace intact: the column + * alignment this card exists to preserve is exactly what the default + * whitespace-collapsing matcher would hide. + */ +const RAW = { normalizer: (text: string) => text } + +const SID = 's1' as SessionId + +const ARGS = '{"command":"ls -la","description":"List files"}' + +/** The bash tool's own call view for a foreground command. */ +const callTerminal = (over?: Partial>): ToolCallView => ({ + card: 'terminal', title: 'ls -la', description: 'List files', ...over, +}) + +/** The bash tool's own result view for a settled foreground command. */ +const resultTerminal = (over?: Partial>): ToolResultView => ({ + card: 'terminal', output: 'a.ts b.ts\nc.ts d.ts\n', exitCode: 0, ...over, +}) + +const running = (over?: Partial): RunningToolCall => ({ + callId: 'c1', name: 'bash', argsRaw: ARGS, + turn: 1, step: 1, time: 1_000, callView: callTerminal(), ...over, +}) + +const settled = (over?: Partial): ToolResultNode => ({ + kind: 'tool-result', seq: 10, time: 2_000, callId: 'c1', + call: { name: 'bash', argsRaw: ARGS }, + callTime: 1_000, + content: [{ type: 'text', text: 'a.ts b.ts\nc.ts d.ts\n' }], isError: false, + callView: callTerminal(), resultView: resultTerminal(), ...over, +}) + +describe('terminalCardModel', () => { + it('derives a running card from the call view alone', () => { + expect(terminalCardModel(running({ callView: callTerminal({ cwd: '/projects/app' }) }))).toEqual({ + command: 'ls -la', cwd: '/projects/app', output: undefined, + exitCode: undefined, signal: undefined, running: true, + }) + }) + + it('derives a settled card from both sides, carrying the exit status', () => { + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '/projects/app' }), + resultView: resultTerminal({ output: 'boom\n', exitCode: 2 }), + }))).toEqual({ + command: 'ls -la', cwd: '/projects/app', output: 'boom\n', + exitCode: 2, signal: undefined, running: false, + }) + expect(terminalCardModel(settled({ + resultView: { card: 'terminal', output: '', signal: 'SIGTERM' }, + }))?.signal).toBe('SIGTERM') + }) + + it('a window-truncated call side falls back to the result title, then to an empty command', () => { + // Truncation drops both the call head and its view (conversation.ts). + const truncated = { call: null, callView: null } + expect(terminalCardModel(settled({ + ...truncated, resultView: resultTerminal({ title: 'ls -la' }), + }))).toMatchObject({ command: 'ls -la', cwd: undefined, running: false }) + expect(terminalCardModel(settled(truncated))).toMatchObject({ command: '', cwd: undefined }) + }) + + it('returns null for every non-terminal call: no views, generic views, unknown cards', () => { + expect(terminalCardModel(running({ callView: null }))).toBeNull() + expect(terminalCardModel(settled({ callView: null, resultView: null }))).toBeNull() + expect(terminalCardModel(running({ callView: { card: 'generic', title: 'read x' } }))).toBeNull() + // A generic result settles a terminal call as a generic card (the bash + // tool's own execution-error and background paths). + expect(terminalCardModel(settled({ resultView: { card: 'generic' } }))).toBeNull() + // A card tag this UI version does not know arrives over the wire; the + // documented generic-card default takes it, not a crash. + const future = { card: 'chart', title: 'plot' } as unknown as ToolCallView + expect(terminalCardModel(running({ callView: future }))).toBeNull() + expect(terminalCardModel(settled({ + callView: future, resultView: { card: 'chart' } as unknown as ToolResultView, + }))).toBeNull() + }) +}) + +describe('chat row terminal body', () => { + const ownerProps = (block: RunningToolCall | ToolResultNode): ToolRowOwnerProps => ({ + callId: 'c1', toolName: 'bash', block, openDetails: vi.fn(), + }) + + it('the expanded body is the command output, capped tighter than the panel', () => { + expect(CHAT_TERMINAL_MAX_LINES).toBeLessThan(16) + const view = render() + // Collapsed: the one-line summary row only, no output. + expect(view.getByText('List files')).toBeTruthy() + expect(view.queryByText(/a\.ts/)).toBeNull() + fireEvent.click(view.container.querySelector('button')!) + expect(view.getByText('a.ts b.ts', RAW)).toBeTruthy() + expect(view.getByText('ls -la')).toBeTruthy() + // The args JSON body the generic path would have shown is gone. + expect(view.queryByText(/"command"/)).toBeNull() + }) + + it('the cap collapses a long output inside the row, expandable in place', () => { + const lines = Array.from({ length: CHAT_TERMINAL_MAX_LINES + 3 }, (_, i) => `line-${i}`) + const view = render() + fireEvent.click(view.container.querySelector('button')!) + expect(view.getByText('… 其余 3 行')).toBeTruthy() + expect(view.queryByText('line-5')).toBeNull() + fireEvent.click(view.getByRole('button', { name: '展开其余 3 行输出' })) + expect(view.getByText('line-5')).toBeTruthy() + }) + + it('a running terminal call expands to the prompt line with no output yet', () => { + const view = render() + fireEvent.click(view.container.querySelector('button')!) + expect(view.getByText('ls -la')).toBeTruthy() + expect(view.queryByText('复制')).toBeNull() + }) + + it('a non-terminal call keeps the args-JSON text body', () => { + const view = render() + fireEvent.click(view.container.querySelector('button')!) + expect(view.getByText(/"command"/)).toBeTruthy() + }) + + it('a terminal call with no args still expands, through its terminal body alone', () => { + // Empty args make the text body null; the terminal material carries the row. + const view = render() + fireEvent.click(view.container.querySelector('button')!) + expect(view.getByText('a.ts b.ts', RAW)).toBeTruthy() + }) +}) + +describe('BashRow terminal card', () => { + const list = () => createSnapshotStore({ + ids: [SID], + byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0 } }, + current: undefined, + phase: 'ready', + }) + + const rowProps = (block: RunningToolCall | ToolResultNode, openDetails = vi.fn()): ToolRowProps => ({ + callId: 'c1', toolName: 'bash', block, openDetails, + sessionId: SID, useSessions: bindSnapshotSelector(list()), + } as unknown as ToolRowProps) + + it('renders the command output under the summary row, without an expand gesture', () => { + const openDetails = vi.fn() + const view = render() + expect(view.getByText('List files')).toBeTruthy() + expect(view.getByText('a.ts b.ts', RAW)).toBeTruthy() + // The terminal card sits outside the row's click target: copying does not + // open the details panel. + fireEvent.click(view.getByText('复制')) + expect(openDetails).not.toHaveBeenCalled() + fireEvent.click(view.getByText('List files')) + expect(openDetails).toHaveBeenCalledTimes(1) + }) + + it('a non-terminal bash call (background start) renders the summary row alone', () => { + const view = render() + expect(view.getByText('List files')).toBeTruthy() + expect(view.queryByText(/a\.ts/)).toBeNull() + }) +}) + +describe('DetailsPanel Output section', () => { + function mount(snapshot: ConversationSnapshot, selection: SelectionTarget | null) { + localStorage.clear() + const chat = createChatStore().create() + if (selection !== null) chat.actions.select(selection) + const sessions = createSnapshotStore( + { ids: [], byId: {}, current: undefined, phase: 'ready' }) + const workspaces = createSnapshotStore({ + items: [], state: 'idle', phase: 'ready', error: null, + baselinesReady: true, recentWorkspaceId: undefined, + }) + return render( + snapshot, subscribe: () => () => {} })} + useSessions={bindSnapshotSelector(sessions)} + useWorkspaces={bindSnapshotSelector(workspaces)} + useInput={(() => { throw new Error('unused') })} + inputActions={{ setDraft: () => {}, submit: () => {} }} + useStore={bindSnapshotSelector(chat)} + actions={chat.actions} + closeDetails={vi.fn()} + />, + ) + } + + function snapshot(over: Partial = {}): ConversationSnapshot { + return { + sessionId: SID, nodes: [], foldDegraded: false, partial: null, runningCalls: [], codeDispatches: new Map(), + pending: [], queue: [], todos: [], running: false, composerPhase: 'active', removed: false, + openState: 'open', openError: null, hasMore: false, loadingOlder: false, + promptError: null, blank: false, lastAgentError: null, ...over, + } + } + + const target: SelectionTarget = { turnSeq: 10, callId: 'c1', toolName: 'bash' } + + it('renders the terminal card at full height, keeping the JSON Input section', () => { + const long = Array.from({ length: 20 }, (_, i) => `row-${i}`) + const view = mount(snapshot({ + nodes: [settled({ resultView: resultTerminal({ output: `${long.join('\n')}\n` }) })], + }), target) + expect(view.getByText(/"command"/)).toBeTruthy() + expect(view.getByText('ls -la')).toBeTruthy() + // The panel takes the primitive's own default cap (16), not the row's. + expect(view.getByText(`… 其余 ${20 - 16} 行`)).toBeTruthy() + expect(view.getByText('row-0')).toBeTruthy() + }) + + it('a running terminal call shows the prompt line, not the 运行中… placeholder', () => { + const view = mount(snapshot({ runningCalls: [running()] }), target) + expect(view.getByText('ls -la')).toBeTruthy() + expect(view.queryByText('运行中…')).toBeNull() + }) + + it('a running non-terminal call keeps the 运行中… placeholder', () => { + const view = mount(snapshot({ runningCalls: [running({ callView: null })] }), target) + expect(view.getByText('运行中…')).toBeTruthy() + }) + + it('a non-terminal result keeps the flattened pre with its error styling', () => { + const view = mount(snapshot({ + nodes: [settled({ + callView: null, resultView: null, isError: true, + content: [{ type: 'text', text: 'permission denied' }], + })], + }), target) + const pre = view.container.querySelector('pre[data-error]') + expect(pre?.textContent).toBe('permission denied') + }) + + it('a run_code sub-dispatch resolves to its own terminal card', () => { + const view = mount(snapshot({ + codeDispatches: new Map([['p1', [settled({ callId: 'c1' })]]]), + }), target) + expect(view.getByText('a.ts b.ts', RAW)).toBeTruthy() + }) + + it('a running run_code sub-dispatch resolves through the running material', () => { + const view = mount(snapshot({ + // The leading non-matching sub-call exercises the scan's skip. + codeDispatches: new Map([['p1', [running({ callId: 'other' }), running()]]]), + }), target) + expect(view.getByText('ls -la')).toBeTruthy() + }) + + it('a window-truncated call head titles the panel by callId and drops the Input section', () => { + const view = mount(snapshot({ + nodes: [settled({ call: null, callView: null, resultView: resultTerminal({ title: 'ls -la' }) })], + }), target) + expect(view.getByText('c1')).toBeTruthy() + expect(view.queryByText('Input')).toBeNull() + expect(view.getByText('Output')).toBeTruthy() + }) + + it('scans past other nodes and other calls before reporting the call out of window', () => { + const view = mount(snapshot({ + nodes: [ + { kind: 'assistant', seq: 1, time: 1_000, turn: 1, step: 1, blocks: [] }, + settled({ callId: 'elsewhere' }), + ], + runningCalls: [running({ callId: 'also-elsewhere' })], + }), target) + expect(view.getByText('该调用不在当前窗口内')).toBeTruthy() + }) + + it('no selection at all renders the guidance line and the default title', () => { + const view = mount(snapshot(), null) + expect(view.getByText('详情')).toBeTruthy() + expect(view.getByText('点击消息流中的工具行查看详情')).toBeTruthy() + }) + + it('a step selection without a callId renders the guidance line too', () => { + const view = mount(snapshot(), { turnSeq: 3, stepSeq: 1 }) + expect(view.getByText('点击消息流中的工具行查看详情')).toBeTruthy() + }) + + it('the close button reaches closeDetails', () => { + localStorage.clear() + const chat = createChatStore().create() + const closeDetails = vi.fn() + const snap = snapshot() + const view = render( + snap, subscribe: () => () => {} })} + useSessions={bindSnapshotSelector(createSnapshotStore( + { ids: [], byId: {}, current: undefined, phase: 'ready' }))} + useWorkspaces={bindSnapshotSelector(createSnapshotStore({ + items: [], state: 'idle', phase: 'ready', error: null, + baselinesReady: true, recentWorkspaceId: undefined, + }))} + useInput={(() => { throw new Error('unused') })} + inputActions={{ setDraft: () => {}, submit: () => {} }} + useStore={bindSnapshotSelector(chat)} + actions={chat.actions} + closeDetails={closeDetails} + />, + ) + fireEvent.click(view.getByRole('button', { name: '关闭详情' })) + expect(closeDetails).toHaveBeenCalledTimes(1) + }) + + it('a non-text result block renders as JSON, and an empty result falls back to its error', () => { + const nonText = mount(snapshot({ + nodes: [settled({ + callView: null, resultView: null, + content: [{ type: 'reasoning', text: 'why' }], + })], + }), target) + // Scope to the Output section: the Input section's CodeBlock renders a + //
 of its own, and it comes first in document order.
+    expect(nonText.getByText('Output').closest('section')?.querySelector('pre')?.textContent)
+      .toBe('{\n  "type": "reasoning",\n  "text": "why"\n}')
+    cleanup()
+    const empty = mount(snapshot({
+      nodes: [settled({
+        callView: null, resultView: null, content: [], isError: true,
+        error: { name: 'ToolError', code: 'interrupted' },
+      })],
+    }), target)
+    expect(empty.getByText('ToolError: interrupted')).toBeTruthy()
+  })
+})
diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml
index 6162494def..1eb8a05ba0 100644
--- a/packages/client/ui-primitives/README.i18n.yaml
+++ b/packages/client/ui-primitives/README.i18n.yaml
@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-README.md: 58e450451ab64f69762817dfb277b8a888e2177f
-README.zh.md: 6824f3efe4981adf9549941afa7e2f5db2ac005d
+#   pnpm run verify-translation-pairing --write packages/client/ui-primitives/README.md
+README.md: c9c70f29804ac4e6783486595460bf07499e1dff
+README.zh.md: 254fc5ba5aef553fd447338353a0c5311ddbd98a
diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md
index 58e450451a..c9c70f2980 100644
--- a/packages/client/ui-primitives/README.md
+++ b/packages/client/ui-primitives/README.md
@@ -2,12 +2,16 @@
 
 English | [中文](README.zh.md)
 
-Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/Input, markdown family (MessageText/MarkdownText/JsonBlock). Contract: api-contracts v3 §8.
+Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/Input, markdown family (MessageText/MarkdownText/JsonBlock), TerminalBlock. Contract: api-contracts v3 §8.
 
 ## Markdown rendering
 
 `MarkdownText` renders GFM from untrusted assistant output through React elements. It omits raw HTML, neutralizes relative and non-HTTP(S)/mailto links, opens HTTP(S) links with safe external-link attributes, and renders image alt text without loading remote resources; `MessageText` remains the literal-text primitive for user-authored content. Element spacing, tables, links, and inline code use the same `--dsw-alias-markdown-*` / `--dsw-font-markdown-*` tokens as deepsuite `@deepseek/md`. Fenced blocks render through `CodeBlock` (language banner, copy control, shiki for the registered grammars).
 
+## Terminal output
+
+`TerminalBlock` renders a shell command as a terminal surface: a prompt line (shortened `cwd` label plus the command), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md).
+
 ## Model Experience
 
 None, as the package renders pure React atoms in the browser; nothing here reaches a model request.
@@ -21,3 +25,4 @@ None; this package neither assembles nor sends a provider request.
 - **Glyph-level icons are redrawn approximations** — the fish logo (and the sparkle held by ui-conversation) come from font glyphs whose vector geometry is not exportable from the local design data; hand-authored recreations stand in until an exact export path exists.
 - **Pill and Input have no design source** — both atoms are self-defined; the sidebar search field and view-tab strip that resemble them are consumer-owned compositions, not these atoms.
 - **StateDot `Active` variant is a hidden placeholder in the design** — not implemented; the four shipped states (done/warning/ongoing/error) are the complete P-I surface.
+- **`TerminalBlock` is not a terminal emulator** — it renders settled or still-running command output, not an interactive session: SGR color and attributes are honored, while cursor movement, screen clearing, and alternate-screen sequences are stripped. Basic-16 magenta and cyan have no token equivalent and stay literal rgb.
diff --git a/packages/client/ui-primitives/README.zh.md b/packages/client/ui-primitives/README.zh.md
index 6824f3efe4..254fc5ba5a 100644
--- a/packages/client/ui-primitives/README.zh.md
+++ b/packages/client/ui-primitives/README.zh.md
@@ -2,12 +2,16 @@
 
 [English](README.md) | 中文
 
-纯 React 原子组件(零 cordis):StateDot、ic_ds_* 图标、Button/Pill/Menu/Modal/Input,以及 markdown 家族(MessageText/MarkdownText/JsonBlock)。契约:api-contracts v3 §8。
+纯 React 原子组件(零 cordis):StateDot、ic_ds_* 图标、Button/Pill/Menu/Modal/Input、markdown 家族(MessageText/MarkdownText/JsonBlock),以及 TerminalBlock。契约:api-contracts v3 §8。
 
 ## Markdown 渲染
 
 `MarkdownText` 通过 React 元素渲染来自不受信任 assistant 输出的 GFM。它会省略原始 HTML,使相对链接及非 HTTP(S)/mailto 链接失效,以安全的外部链接属性打开 HTTP(S) 链接,并只渲染图片 alt 文本而不加载远程资源;`MessageText` 仍是用户创作内容使用的字面文本原语。元素间距、表格、链接与行内代码使用与 deepsuite `@deepseek/md` 相同的 `--dsw-alias-markdown-*` / `--dsw-font-markdown-*` token。围栏代码块通过 `CodeBlock` 渲染(语言横幅、复制控件,以及对已注册语法使用 shiki)。
 
+## 终端输出
+
+`TerminalBlock` 将一条 shell 命令渲染为终端表层:提示行(缩短后的 `cwd` 标签加命令)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。
+
 ## 模型体验
 
 无。该包在浏览器中渲染纯 React 原子组件;这里没有任何内容进入模型请求。
@@ -21,3 +25,4 @@
 - **字形级图标是重新绘制的近似版本**:鱼形标志(以及 ui-conversation 持有的闪光图标)来自字体字形,而本地设计数据无法导出其矢量几何;在获得精确导出路径前,使用手工重建版本代替。
 - **Pill 与 Input 没有设计来源**:两个原子组件均自行定义;与其相似的侧边栏搜索字段和视图标签条由消费方组合,不是这些原子组件。
 - **StateDot 的 `Active` 变体是设计中的隐藏占位符**:尚未实现;已交付的四种状态(done/warning/ongoing/error)构成完整的 P-I 表层。
+- **`TerminalBlock` 不是终端模拟器**:它渲染已结束或仍在运行的命令输出,而不是交互式会话:SGR 颜色与属性会被遵循,而光标移动、清屏和备用屏幕序列会被剥离。基础 16 色中的洋红与青色没有对应 token,保持字面 rgb。
diff --git a/packages/client/ui-primitives/package.json b/packages/client/ui-primitives/package.json
index 9ce2bc8676..e629626129 100644
--- a/packages/client/ui-primitives/package.json
+++ b/packages/client/ui-primitives/package.json
@@ -21,6 +21,7 @@
   "license": "BSD-3-Clause",
   "dependencies": {
     "@shikijs/langs": "^4.3.1",
+    "anser": "^2.3.5",
     "clsx": "^2.0.0",
     "react": "^18.2.0",
     "react-dom": "^18.2.0",
diff --git a/packages/client/ui-primitives/src/Pill.tsx b/packages/client/ui-primitives/src/Pill.tsx
index 76b9301972..2c3c24c1ad 100644
--- a/packages/client/ui-primitives/src/Pill.tsx
+++ b/packages/client/ui-primitives/src/Pill.tsx
@@ -12,7 +12,9 @@ import css from './Pill.module.css'
  */
 export function Pill({ active = false, className, children, onClick, ...rest }: {
   active?: boolean
-  className?: string
+  // `| undefined` so a caller can forward an optional class straight through
+  // under exactOptionalPropertyTypes (a CSS-module lookup is string|undefined).
+  className?: string | undefined
   children?: ReactNode
 } & ButtonHTMLAttributes) {
   if (!onClick) {
diff --git a/packages/client/ui-primitives/src/TerminalBlock.module.css b/packages/client/ui-primitives/src/TerminalBlock.module.css
new file mode 100644
index 0000000000..8a4f4a5e60
--- /dev/null
+++ b/packages/client/ui-primitives/src/TerminalBlock.module.css
@@ -0,0 +1,101 @@
+/* Geometry mirrors CodeBlock (12px radius, code-block surface + banner rows,
+   markdown code-block font) so a terminal card and a fenced code block read as
+   one family. The one deliberate divergence: output keeps `white-space: pre`
+   and scrolls horizontally, because folding a column-aligned command's output
+   destroys its alignment. */
+
+.block {
+  --dsl-terminal-radius: 12px;
+  --dsl-terminal-line-height: 22px;
+
+  position: relative;
+  margin: 16px 0;
+  color: var(--dsw-alias-label-primary);
+  background: var(--dsw-alias-markdown-code-block);
+  border-radius: var(--dsl-terminal-radius);
+}
+
+.header {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  padding: 9px 14px;
+  background: var(--dsw-alias-markdown-code-block-banner);
+  border-top-left-radius: var(--dsl-terminal-radius);
+  border-top-right-radius: var(--dsl-terminal-radius);
+}
+
+/* The prompt row is the only element allowed to shrink; the status pill and
+   the copy control keep their intrinsic width. */
+.prompt {
+  display: flex;
+  align-items: baseline;
+  gap: 8px;
+  min-width: 0;
+  flex: 1;
+  font: var(--dsw-font-markdown-code-block);
+}
+
+.cwd {
+  flex: none;
+  color: var(--dsw-alias-label-tertiary);
+}
+
+.command {
+  min-width: 0;
+  color: var(--dsw-alias-label-primary);
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+
+.status {
+  flex: none;
+  color: var(--dsw-alias-state-error-primary);
+}
+
+.copyButton {
+  flex: none;
+  background-color: transparent;
+  border: none;
+  padding: 0;
+  margin: 0;
+  color: var(--dsw-alias-label-secondary);
+  cursor: pointer;
+  font: var(--dsw-font-xs-13);
+}
+
+.output {
+  padding: 12px 14px;
+  font: var(--dsw-font-markdown-code-block);
+  overflow-x: auto;
+  overflow-y: hidden;
+}
+
+/* No wrapping, no word-break: alignment is the payload of terminal output. */
+.line {
+  min-height: var(--dsl-terminal-line-height);
+  white-space: pre;
+}
+
+.expand {
+  display: block;
+  width: 100%;
+  padding: 0;
+  border: none;
+  background-color: transparent;
+  color: var(--dsw-alias-label-tertiary);
+  cursor: pointer;
+  font: inherit;
+  text-align: left;
+}
+
+.expand:hover {
+  color: var(--dsw-alias-label-secondary);
+}
+
+.empty {
+  padding: 12px 14px;
+  font: var(--dsw-font-markdown-code-block);
+  color: var(--dsw-alias-label-tertiary);
+}
diff --git a/packages/client/ui-primitives/src/TerminalBlock.tsx b/packages/client/ui-primitives/src/TerminalBlock.tsx
new file mode 100644
index 0000000000..e224e2b1de
--- /dev/null
+++ b/packages/client/ui-primitives/src/TerminalBlock.tsx
@@ -0,0 +1,170 @@
+// TerminalBlock: the terminal surface for a shell command and its output —
+// prompt line (shortened cwd + command), ANSI-colored output, settled exit
+// status, and a copy control for the raw output. Output never soft-wraps:
+// column-aligned output (ls, tables, box drawing) keeps its alignment and
+// scrolls horizontally instead of folding. Colors resolve through --dsw-*
+// tokens; ANSI parsing lives in ansi.ts.
+
+import { useCallback, useMemo, useState } from 'react'
+import clsx from 'clsx'
+import { parseAnsiLines, type AnsiLine } from './ansi.ts'
+import { writeClipboard } from './clipboard.ts'
+import { Pill } from './Pill.tsx'
+import css from './TerminalBlock.module.css'
+
+/**
+ * Output lines shown before the height cap collapses the middle. Matches the
+ * TUI transcript's default tool-output budget so both front ends cut a long
+ * command's output at the same place.
+ */
+export const DEFAULT_TERMINAL_MAX_LINES = 16
+
+export interface TerminalBlockProps {
+  /** The command line, rendered verbatim after the prompt label. */
+  command: string
+  /** Working directory for the prompt label; absent renders a plain `$`. */
+  cwd?: string | undefined
+  /** Absolute home directory, so a cwd equal to it collapses to `~`; absent disables that collapse. */
+  home?: string | undefined
+  /** The command's output text; may contain ANSI escape sequences. */
+  output?: string | undefined
+  /** Settled exit code; a non-zero value renders the status pill. */
+  exitCode?: number | undefined
+  /** Settled terminating signal name; any value renders the status pill, taking precedence over the exit code. */
+  signal?: string | undefined
+  /** The command is still running: the block shows the prompt line alone. */
+  running?: boolean | undefined
+  /** Height cap in output lines before the middle collapses (default {@link DEFAULT_TERMINAL_MAX_LINES}). */
+  maxLines?: number | undefined
+  /** Extra class merged onto the wrapper (callers position; this component draws). */
+  className?: string | undefined
+}
+
+/**
+ * Prompt label for a working directory: `~` for the home directory itself,
+ * otherwise the path's last segment (both separators accepted, trailing
+ * separators ignored), falling back to the path itself when it has no
+ * segment.
+ * @param cwd - the working directory path.
+ * @param home - absolute home directory, when the caller knows it.
+ * @returns the prompt label.
+ */
+function promptLabel(cwd: string, home: string | undefined): string {
+  const trimmed = cwd.replace(/[/\\]+$/, '')
+  if (home !== undefined && trimmed === home.replace(/[/\\]+$/, '')) return '~'
+  const segment = trimmed.split(/[/\\]/).pop()
+  return segment === undefined || segment === '' ? cwd : segment
+}
+
+/**
+ * Status pill text for a settled command, or undefined when the command
+ * settled cleanly (exit 0, no signal) and needs no pill — the same
+ * distinction the bash tool's own exit-status markers draw.
+ * @param exitCode - settled exit code, when known.
+ * @param signal - settled terminating signal name, when known.
+ * @returns the pill text, or undefined for a clean exit.
+ */
+function statusText(exitCode: number | undefined, signal: string | undefined): string | undefined {
+  if (signal !== undefined) return `信号 ${signal}`
+  if (exitCode !== undefined && exitCode !== 0) return `退出码 ${exitCode}`
+  return undefined
+}
+
+/**
+ * Render one parsed output line. Runs without SGR state render as bare text,
+ * so uncolored output carries no span wrappers.
+ * @param line - the line's styled runs.
+ * @returns the line's children.
+ */
+function renderLine(line: AnsiLine) {
+  return line.map((span, index) => span.style === undefined
+    ? span.text
+    : {span.text})
+}
+
+/**
+ * Render a shell command as a terminal surface.
+ * @param props - see {@link TerminalBlockProps}.
+ * @returns the terminal block element.
+ */
+export function TerminalBlock({
+  command,
+  cwd,
+  home,
+  output,
+  exitCode,
+  signal,
+  running = false,
+  maxLines = DEFAULT_TERMINAL_MAX_LINES,
+  className,
+}: TerminalBlockProps) {
+  const text = output ?? ''
+  // A command's output ends with a newline; that terminator is not an extra
+  // blank line to draw or to count against the height cap. The copy control
+  // still copies `text` untouched.
+  const lines = useMemo(() => parseAnsiLines(text.endsWith('\n') ? text.slice(0, -1) : text), [text])
+  const [expanded, setExpanded] = useState(false)
+  const [copied, setCopied] = useState(false)
+
+  const onCopy = useCallback(() => {
+    if (copied) return
+    // The raw output, never the rendered tree: the prompt line and the status
+    // pill are chrome the user did not run.
+    void writeClipboard(text).then((ok) => {
+      if (!ok) return
+      setCopied(true)
+      window.setTimeout(() => { setCopied(false) }, 1000)
+    })
+  }, [copied, text])
+
+  const onToggle = useCallback(() => { setExpanded(value => !value) }, [])
+
+  const status = statusText(exitCode, signal)
+  const empty = text.trim() === ''
+  const hidden = lines.length - maxLines
+  const capped = hidden > 0 && !expanded
+  // Same split arithmetic as the TUI transcript's collapsed tool card, so a
+  // command's head and tail slices agree between the two front ends.
+  const headLines = Math.ceil(maxLines / 2)
+  const tailLines = maxLines - headLines
+
+  return (
+    
+
+
+ {cwd === undefined ? '$' : promptLabel(cwd, home)} + {command} +
+ {status !== undefined && {status}} + {!running && !empty && ( + + )} +
+ {!running && (empty + ?
无输出
+ : ( +
+ {(capped ? lines.slice(0, headLines) : lines).map((line, index) => ( +
{renderLine(line)}
+ ))} + {hidden > 0 && ( + + )} + {capped && lines.slice(lines.length - tailLines).map((line, index) => ( +
{renderLine(line)}
+ ))} +
+ ))} +
+ ) +} diff --git a/packages/client/ui-primitives/src/ansi.ts b/packages/client/ui-primitives/src/ansi.ts new file mode 100644 index 0000000000..e4e2cc13e2 --- /dev/null +++ b/packages/client/ui-primitives/src/ansi.ts @@ -0,0 +1,153 @@ +// ANSI model behind TerminalBlock: anser splits the SGR runs, this module +// resolves each run's colors and decorations into a plain style record and +// folds the runs into per-line span arrays so a height cap can slice whole +// lines. Sequences anser does not turn into color (OSC, cursor movement, +// other C0 controls) are removed before parsing so they never reach the DOM +// as literal characters. + +import Anser from 'anser' +import type { CSSProperties } from 'react' + +/** + * The subset of one anser JSON chunk this module reads. anser's own types + * declare `fg`/`bg` as `string`, but its parser leaves them `null` for a run + * that sets no color, so the null is spelled out here. + */ +interface AnsiChunk { + /** Run text with its SGR codes already removed. */ + content: string + /** Foreground as an `r, g, b` triple, or null when the run sets none. */ + fg: string | null + /** Background as an `r, g, b` triple, or null when the run sets none. */ + bg: string | null + /** SGR attributes in effect for the run, in the order they were declared. */ + decorations: readonly string[] +} + +/** One run of terminal text; `style` is undefined for text that carries no SGR state. */ +export interface AnsiSpan { + /** The run's plain text, free of escape sequences and newlines. */ + text: string + /** Resolved inline style, or undefined when the run needs no wrapper. */ + style: CSSProperties | undefined +} + +/** The spans of one output line, in order. */ +export type AnsiLine = readonly AnsiSpan[] + +/** + * The 8/16 basic ANSI colors, keyed by the whitespace-free `r,g,b` triple + * anser emits for them, mapped onto the theme tokens that carry the same + * semantic. Black and white both resolve to the primary label color so text + * stays legible under either theme instead of matching the surface it sits + * on; bright black takes the tertiary label color (the muted-gray role). + * Magenta and cyan have no token equivalent in this design system and fall + * through to anser's literal rgb, as do all 256-palette and truecolor values. + */ +const TOKEN_BY_BASIC_RGB: Record = { + '0,0,0': 'var(--dsw-alias-label-primary)', + '255,255,255': 'var(--dsw-alias-label-primary)', + '85,85,85': 'var(--dsw-alias-label-tertiary)', + '187,0,0': 'var(--dsw-alias-state-error-primary)', + '255,85,85': 'var(--dsw-alias-state-error-secondary)', + '0,187,0': 'var(--dsw-alias-state-success-primary)', + '0,255,0': 'var(--dsw-alias-state-success-secondary)', + '187,187,0': 'var(--dsw-alias-state-warn-primary)', + '255,255,85': 'var(--dsw-alias-state-warn-secondary)', + '0,0,187': 'var(--dsw-alias-state-business-primary)', + '85,85,255': 'var(--dsw-static-blue-400)', +} + +/** + * CSS for each SGR attribute anser reports. `blink` is deliberately absent — + * animated text is not reproduced. `reverse` never arrives here: anser + * consumes it by swapping the run's foreground and background. Underline and + * strikethrough share `textDecoration`, so in a run declaring both, the + * later declaration wins. + */ +const STYLE_BY_DECORATION: Record = { + bold: { fontWeight: 700 }, + dim: { opacity: 0.7 }, + italic: { fontStyle: 'italic' }, + underline: { textDecoration: 'underline' }, + strikethrough: { textDecoration: 'line-through' }, + hidden: { visibility: 'hidden' }, +} + +/** OSC strings (window title, hyperlinks), with or without their terminator. */ +const OSC_SEQUENCE = /\u001b\][^\u0007\u001b]*(?:\u0007|\u001b\\)?/g + +/** Escape sequences other than CSI: charset selection, single-shift, reset. */ +const NON_CSI_ESCAPE = /\u001b(?!\[)[\u0020-\u002f]*[\u0030-\u007e]?/g + +/** C0 controls with no display meaning here; tab, newline and ESC survive for layout and anser's CSI split. */ +const INERT_CONTROL = /[\u0000-\u0008\u000b-\u001a\u001c-\u001f\u007f]/g + +/** + * Apply carriage-return redraws: within a line, only the text after the last + * `\r` survives, which is what a terminal shows for progress output. A `\r` + * that only terminates a CRLF line is dropped first so those lines keep + * their text. SGR codes preceding a dropped redraw are dropped with it. + * @param text - output text, already free of OSC and non-CSI escapes. + * @returns the text with each line reduced to its final redraw. + */ +function applyCarriageReturns(text: string): string { + return text.split('\n').map((raw) => { + const line = raw.replace(/\r+$/, '') + return line.slice(line.lastIndexOf('\r') + 1) + }).join('\n') +} + +/** + * Remove every escape sequence and control character that carries no color, + * leaving CSI sequences for anser and `\n`/`\t` for layout. + * @param text - raw command output. + * @returns text whose only remaining escapes are CSI sequences. + */ +function sanitize(text: string): string { + const escaped = text.replace(OSC_SEQUENCE, '').replace(NON_CSI_ESCAPE, '') + return applyCarriageReturns(escaped).replace(INERT_CONTROL, '') +} + +/** + * Resolve one run's colors and decorations. + * @param chunk - the anser chunk to style. + * @returns the run's inline style, or undefined when it carries no SGR state. + */ +function resolveStyle(chunk: AnsiChunk): CSSProperties | undefined { + const style: CSSProperties = {} + const background = chunk.bg === null ? undefined : `rgb(${chunk.bg})` + if (background !== undefined) style.backgroundColor = background + if (chunk.fg !== null) { + const literal = `rgb(${chunk.fg})` + // A run that paints its own background keeps anser's literal pair so the + // authored foreground/background contrast survives; a foreground-only run + // maps onto a theme token, which adapts to light and dark surfaces. + style.color = background === undefined + ? TOKEN_BY_BASIC_RGB[chunk.fg.replace(/\s+/g, '')] ?? literal + : literal + } + for (const decoration of chunk.decorations) Object.assign(style, STYLE_BY_DECORATION[decoration]) + return Object.keys(style).length === 0 ? undefined : style +} + +/** + * Parse command output into styled spans grouped by line. + * @param text - raw output text, which may contain ANSI escape sequences. + * @returns one entry per output line (always at least one, possibly empty). + */ +export function parseAnsiLines(text: string): AnsiLine[] { + let current: AnsiSpan[] = [] + const lines: AnsiSpan[][] = [current] + for (const chunk of Anser.ansiToJson(sanitize(text), { json: true, remove_empty: true })) { + const style = resolveStyle(chunk) + for (const [index, part] of chunk.content.split('\n').entries()) { + if (index > 0) { + current = [] + lines.push(current) + } + if (part !== '') current.push({ text: part, style }) + } + } + return lines +} diff --git a/packages/client/ui-primitives/src/clipboard.ts b/packages/client/ui-primitives/src/clipboard.ts new file mode 100644 index 0000000000..c01e802f31 --- /dev/null +++ b/packages/client/ui-primitives/src/clipboard.ts @@ -0,0 +1,48 @@ +// Package-internal clipboard write, shared by every copy control in this +// package (CodeBlock's code copy, TerminalBlock's output copy). Not part of the +// public surface: consumers get the components, not the host detection. + +/** + * Write text to the host clipboard, preferring the async Clipboard API and + * falling back to `execCommand('copy')` on hosts (jsdom, insecure contexts) + * that omit it. + * @param text - the exact text to place on the clipboard. + * @returns true only when the host accepted the write. + */ +export async function writeClipboard(text: string): Promise { + // lib.dom types clipboard non-optional, but insecure contexts omit it — + // that runtime gap is exactly what this guard detects. + /* eslint-disable-next-line @typescript-eslint/no-unnecessary-condition */ + if (navigator.clipboard?.writeText) { + try { + await navigator.clipboard.writeText(text) + return true + } catch { + // Denied permissions / iframe policy — do not claim success. + return false + } + } + // jsdom and older hosts: best-effort execCommand path when present. + // execCommand('copy') is the only clipboard fallback where the async API + // is missing; deprecated but deliberately retained. + /* eslint-disable @typescript-eslint/no-deprecated */ + const exec = typeof document.execCommand === 'function' + ? document.execCommand.bind(document) + : undefined + if (exec === undefined) return false + const el = document.createElement('textarea') + el.value = text + el.setAttribute('readonly', '') + el.style.position = 'fixed' + el.style.left = '-9999px' + document.body.appendChild(el) + el.select() + try { + return exec('copy') + } catch { + return false + } finally { + el.remove() + } + /* eslint-enable @typescript-eslint/no-deprecated */ +} diff --git a/packages/client/ui-primitives/src/index.ts b/packages/client/ui-primitives/src/index.ts index 330a3145bf..dca6374fb8 100644 --- a/packages/client/ui-primitives/src/index.ts +++ b/packages/client/ui-primitives/src/index.ts @@ -17,6 +17,8 @@ export { FishLogo } from './FishLogo.tsx' export { BrandWordmark } from './BrandWordmark.tsx' export { Tooltip } from './Tooltip.tsx' export type { TooltipSide } from './Tooltip.tsx' +export { TerminalBlock, DEFAULT_TERMINAL_MAX_LINES } from './TerminalBlock.tsx' +export type { TerminalBlockProps } from './TerminalBlock.tsx' export { CodeBlock } from './markdown/CodeBlock.tsx' export { JsonBlock } from './markdown/JsonBlock.tsx' export { MarkdownText } from './markdown/MarkdownText.tsx' diff --git a/packages/client/ui-primitives/src/markdown/CodeBlock.tsx b/packages/client/ui-primitives/src/markdown/CodeBlock.tsx index de6a478af4..9c7e968053 100644 --- a/packages/client/ui-primitives/src/markdown/CodeBlock.tsx +++ b/packages/client/ui-primitives/src/markdown/CodeBlock.tsx @@ -6,6 +6,7 @@ import { useCallback, useMemo, useRef, useState } from 'react' import clsx from 'clsx' +import { writeClipboard } from '../clipboard.ts' import { highlightToHtml } from './highlight.ts' import css from './CodeBlock.module.css' @@ -18,45 +19,6 @@ export interface CodeBlockProps { className?: string | undefined } -/** @returns true only when the host accepted the write. */ -async function writeClipboard(text: string): Promise { - // lib.dom types clipboard non-optional, but insecure contexts omit it — - // that runtime gap is exactly what this guard detects. - /* eslint-disable-next-line @typescript-eslint/no-unnecessary-condition */ - if (navigator.clipboard?.writeText) { - try { - await navigator.clipboard.writeText(text) - return true - } catch { - // Denied permissions / iframe policy — do not claim success. - return false - } - } - // jsdom and older hosts: best-effort execCommand path when present. - // execCommand('copy') is the only clipboard fallback where the async API - // is missing; deprecated but deliberately retained. - /* eslint-disable @typescript-eslint/no-deprecated */ - const exec = typeof document.execCommand === 'function' - ? document.execCommand.bind(document) - : undefined - if (exec === undefined) return false - const el = document.createElement('textarea') - el.value = text - el.setAttribute('readonly', '') - el.style.position = 'fixed' - el.style.left = '-9999px' - document.body.appendChild(el) - el.select() - try { - return exec('copy') - } catch { - return false - } finally { - el.remove() - } - /* eslint-enable @typescript-eslint/no-deprecated */ -} - export function CodeBlock({ code, lang, className }: CodeBlockProps) { const trimmed = code.endsWith('\n') ? code.slice(0, -1) : code const html = useMemo(() => highlightToHtml(trimmed, lang), [trimmed, lang]) diff --git a/packages/client/ui-primitives/tests/ansi.spec.ts b/packages/client/ui-primitives/tests/ansi.spec.ts new file mode 100644 index 0000000000..57a29d4f33 --- /dev/null +++ b/packages/client/ui-primitives/tests/ansi.spec.ts @@ -0,0 +1,188 @@ +// parseAnsiLines, the ANSI model behind TerminalBlock: anser's SGR runs +// resolved into inline styles and folded into per-line span arrays, with every +// escape and control character that carries no color removed first. The DOM +// side of the same model (which runs get a span wrapper) is in +// terminal-block.spec.tsx. + +import { describe, expect, it } from 'vitest' +import { parseAnsiLines } from '../src/ansi.ts' + +const ESC = '\u001b' + +/** Paint `text` with the SGR `codes`, then reset. */ +function sgr(codes: string, text: string): string { + return `${ESC}[${codes}m${text}${ESC}[0m` +} + +/** The single span of a single-line, single-run parse. */ +function onlySpan(text: string) { + const lines = parseAnsiLines(text) + expect(lines).toHaveLength(1) + expect(lines[0]).toHaveLength(1) + return lines[0]![0]! +} + +describe('parseAnsiLines: text without SGR state', () => { + it('leaves plain text as one unstyled span', () => { + expect(parseAnsiLines('hello')).toEqual([[{ text: 'hello', style: undefined }]]) + }) + + it('returns exactly one empty line for empty input', () => { + expect(parseAnsiLines('')).toEqual([[]]) + }) + + it('splits a multi-line run and drops the empty line between two blocks', () => { + expect(parseAnsiLines('a\n\nb')).toEqual([ + [{ text: 'a', style: undefined }], + [], + [{ text: 'b', style: undefined }], + ]) + }) + + it('keeps tabs, which the terminal surface needs for column layout', () => { + expect(onlySpan('a\tb')).toEqual({ text: 'a\tb', style: undefined }) + }) +}) + +describe('parseAnsiLines: basic colors mapped onto theme tokens', () => { + it.each<[string, string, string]>([ + ['30', 'black', 'var(--dsw-alias-label-primary)'], + ['37', 'white', 'var(--dsw-alias-label-primary)'], + ['90', 'bright black', 'var(--dsw-alias-label-tertiary)'], + ['31', 'red', 'var(--dsw-alias-state-error-primary)'], + ['91', 'bright red', 'var(--dsw-alias-state-error-secondary)'], + ['32', 'green', 'var(--dsw-alias-state-success-primary)'], + ['92', 'bright green', 'var(--dsw-alias-state-success-secondary)'], + ['33', 'yellow', 'var(--dsw-alias-state-warn-primary)'], + ['93', 'bright yellow', 'var(--dsw-alias-state-warn-secondary)'], + ['34', 'blue', 'var(--dsw-alias-state-business-primary)'], + ['94', 'bright blue', 'var(--dsw-static-blue-400)'], + ])('SGR %s (%s) resolves to %s', (code, _name, token) => { + expect(onlySpan(sgr(code, 'x'))).toEqual({ text: 'x', style: { color: token } }) + }) +}) + +describe('parseAnsiLines: colors with no token equivalent', () => { + it.each<[string, string, string]>([ + ['35', 'magenta', 'rgb(187, 0, 187)'], + ['36', 'cyan', 'rgb(0, 187, 187)'], + ['38;5;208', '256-palette orange', 'rgb(255, 135, 0)'], + ['38;2;10;20;30', 'truecolor', 'rgb(10, 20, 30)'], + ])('SGR %s (%s) falls through to %s', (code, _name, literal) => { + expect(onlySpan(sgr(code, 'x')).style).toEqual({ color: literal }) + }) +}) + +describe('parseAnsiLines: backgrounds', () => { + it('sets backgroundColor for a background-only run', () => { + expect(onlySpan(sgr('44', 'x')).style).toEqual({ backgroundColor: 'rgb(0, 0, 187)' }) + }) + + it('keeps the literal foreground when the run paints its own background', () => { + expect(onlySpan(sgr('41;37', 'x')).style).toEqual({ + backgroundColor: 'rgb(187, 0, 0)', + color: 'rgb(255,255,255)', + }) + }) + + it('renders reverse video as the swapped pair anser reports', () => { + expect(onlySpan(sgr('31;7', 'x')).style).toEqual({ + backgroundColor: 'rgb(187, 0, 0)', + color: 'rgb(0, 0, 0)', + }) + }) +}) + +describe('parseAnsiLines: decorations', () => { + it.each<[string, string, Record]>([ + ['1', 'bold', { fontWeight: 700 }], + ['2', 'dim', { opacity: 0.7 }], + ['3', 'italic', { fontStyle: 'italic' }], + ['4', 'underline', { textDecoration: 'underline' }], + ['9', 'strikethrough', { textDecoration: 'line-through' }], + ['8', 'hidden', { visibility: 'hidden' }], + ])('SGR %s (%s) resolves to %o', (code, _name, style) => { + expect(onlySpan(sgr(code, 'x')).style).toEqual(style) + }) + + it('lets the later textDecoration win when a run declares underline and strikethrough', () => { + expect(onlySpan(sgr('4;9', 'x')).style).toEqual({ textDecoration: 'line-through' }) + expect(onlySpan(sgr('9;4', 'x')).style).toEqual({ textDecoration: 'underline' }) + }) + + it('combines a color with several decorations in one style', () => { + expect(onlySpan(sgr('1;3;31', 'x')).style).toEqual({ + color: 'var(--dsw-alias-state-error-primary)', + fontWeight: 700, + fontStyle: 'italic', + }) + }) + + it('reproduces no animation for blink, leaving the run unstyled', () => { + expect(onlySpan(sgr('5', 'x'))).toEqual({ text: 'x', style: undefined }) + }) +}) + +describe('parseAnsiLines: sequences that carry no color', () => { + it('removes an OSC string with its BEL terminator', () => { + expect(onlySpan(`a${ESC}]0;window title\u0007b`)).toEqual({ text: 'ab', style: undefined }) + }) + + it('removes an OSC string terminated by ST', () => { + expect(onlySpan(`a${ESC}]8;;https://example.com${ESC}\\b`)).toEqual({ text: 'ab', style: undefined }) + }) + + it('removes non-CSI escapes such as charset selection and reset', () => { + expect(onlySpan(`x${ESC}(By${ESC}cz`)).toEqual({ text: 'xyz', style: undefined }) + }) + + it('removes inert C0 controls', () => { + expect(onlySpan('\u0000ab\u001fc\u007f')).toEqual({ text: 'abc', style: undefined }) + }) + + it('keeps CSI sequences that only move the cursor out of the text', () => { + expect(onlySpan(`${ESC}[2K${ESC}[1Adone`)).toEqual({ text: 'done', style: undefined }) + }) +}) + +describe('parseAnsiLines: carriage returns', () => { + it('keeps only the last redraw of a line', () => { + expect(onlySpan('10%\r55%\r100%')).toEqual({ text: '100%', style: undefined }) + }) + + it('drops the SGR codes that preceded a discarded redraw', () => { + expect(onlySpan(`${ESC}[31mgone\rkept`)).toEqual({ text: 'kept', style: undefined }) + }) + + it('preserves both lines of a CRLF pair instead of treating it as a redraw', () => { + expect(parseAnsiLines('a\r\r\nb\r\n')).toEqual([ + [{ text: 'a', style: undefined }], + [{ text: 'b', style: undefined }], + [], + ]) + }) + + it('applies the redraw per line, not across the whole text', () => { + expect(parseAnsiLines('one\rtwo\nthree')).toEqual([ + [{ text: 'two', style: undefined }], + [{ text: 'three', style: undefined }], + ]) + }) +}) + +describe('parseAnsiLines: runs spanning lines', () => { + it('carries one run\'s style onto every line it covers', () => { + expect(parseAnsiLines(sgr('32', 'first\nsecond'))).toEqual([ + [{ text: 'first', style: { color: 'var(--dsw-alias-state-success-primary)' } }], + [{ text: 'second', style: { color: 'var(--dsw-alias-state-success-primary)' } }], + ]) + }) + + it('keeps several runs of one line in order', () => { + expect(parseAnsiLines(`plain${sgr('31', 'red')}tail`)).toEqual([[ + { text: 'plain', style: undefined }, + { text: 'red', style: { color: 'var(--dsw-alias-state-error-primary)' } }, + { text: 'tail', style: undefined }, + ]]) + }) +}) diff --git a/packages/client/ui-primitives/tests/terminal-block.spec.tsx b/packages/client/ui-primitives/tests/terminal-block.spec.tsx new file mode 100644 index 0000000000..87e153a741 --- /dev/null +++ b/packages/client/ui-primitives/tests/terminal-block.spec.tsx @@ -0,0 +1,315 @@ +// @vitest-environment jsdom +// TerminalBlock: the prompt label's cwd shortening, the running/empty/settled +// arms, the exit-status pill, the head/tail height cap and its expand control, +// and the copy control writing the raw output on both the accepted and the +// refused clipboard paths. writeClipboard's own return contract is pinned here +// too, since it is the seam both copy controls in this package share; the +// resolution of ANSI runs into styles is pinned in ansi.spec.ts, so only its +// DOM consequence (which runs get a span wrapper) is asserted here. + +import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' +import { act, cleanup, fireEvent, render, screen } from '@testing-library/react' +import { DEFAULT_TERMINAL_MAX_LINES, TerminalBlock } from '../src/index.ts' +import { writeClipboard } from '../src/clipboard.ts' + +const ESC = '\u001b' + +afterEach(cleanup) + +beforeEach(() => { + vi.useRealTimers() +}) + +/** The rendered output rows, one string per visible line (CSS-module class prefix). */ +function outputLines(container: HTMLElement): string[] { + return [...container.querySelectorAll('[class^="_line_"]')].map(row => row.textContent ?? '') +} + +/** `count` numbered output lines, without the terminating newline. */ +function body(count: number): string { + return Array.from({ length: count }, (_value, index) => `line ${index + 1}`).join('\n') +} + +describe('TerminalBlock prompt label', () => { + it('collapses the home directory itself to ~', () => { + render() + expect(screen.getByText('~')).toBeTruthy() + }) + + it('shows only the last segment below home', () => { + render() + expect(screen.getByText('Documents')).toBeTruthy() + }) + + it('ignores trailing separators on both the cwd and home', () => { + const view = render() + expect(view.getByText('~')).toBeTruthy() + view.rerender() + expect(view.getByText('~')).toBeTruthy() + }) + + it('drops trailing separators before taking the last segment', () => { + render() + expect(screen.getByText('Documents')).toBeTruthy() + }) + + it('takes the last segment when no home is known', () => { + render() + expect(screen.getByText('Projects')).toBeTruthy() + }) + + it('collapses a backslash home path to ~', () => { + render() + expect(screen.getByText('~')).toBeTruthy() + }) + + it('falls back to the raw path when it has no segment', () => { + render() + expect(screen.getByText('/')).toBeTruthy() + }) + + it('renders a plain $ with no cwd', () => { + render() + expect(screen.getByText('$')).toBeTruthy() + }) + + it('renders the command verbatim after the label', () => { + render() + expect(screen.getByText('git log --oneline | head -3')).toBeTruthy() + }) +}) + +describe('TerminalBlock states', () => { + it('running shows the command line only: no output, no placeholder, no copy', () => { + const view = render() + expect(view.getByText('sleep 5')).toBeTruthy() + expect(view.queryByText('partial')).toBeNull() + expect(view.queryByText('无输出')).toBeNull() + expect(view.queryByRole('button')).toBeNull() + expect(view.container.firstElementChild?.getAttribute('data-running')).toBe('') + }) + + it('running still shows a settled-looking status pill when one is supplied', () => { + render() + expect(screen.getByText('信号 SIGINT')).toBeTruthy() + }) + + it('settled with whitespace-only output shows the dimmed placeholder', () => { + const view = render() + expect(view.getByText('无输出')).toBeTruthy() + expect(view.queryByRole('button', { name: '复制' })).toBeNull() + }) + + it('settled with absent output shows the placeholder', () => { + render() + expect(screen.getByText('无输出')).toBeTruthy() + }) + + it('settled with an empty string shows the placeholder', () => { + render() + expect(screen.getByText('无输出')).toBeTruthy() + }) + + it('merges className onto the wrapper', () => { + const view = render() + expect(view.container.firstElementChild?.classList.contains('x')).toBe(true) + expect(view.container.firstElementChild?.hasAttribute('data-running')).toBe(false) + }) + + it('drops the output text terminator instead of drawing a blank line', () => { + const view = render() + expect(outputLines(view.container)).toEqual(['a', 'b']) + }) + + it('keeps a genuinely blank final line when the output ends with two newlines', () => { + const view = render() + expect(outputLines(view.container)).toEqual(['a', 'b', '']) + }) + + it('renders ANSI runs as styled spans and plain text bare', () => { + const view = render() + const span = view.container.querySelector('span[style]') + expect(span?.textContent).toBe('bad') + expect(span?.getAttribute('style')).toContain('--dsw-alias-state-error-primary') + expect(outputLines(view.container)).toEqual(['bad ok']) + }) + + it('renders uncolored output with no span wrappers at all', () => { + const view = render() + expect(view.container.querySelectorAll('[class^="_line_"] span')).toHaveLength(0) + }) +}) + +describe('TerminalBlock status pill', () => { + it('renders no pill for a clean exit', () => { + const view = render() + expect(view.queryByText(/退出码|信号/u)).toBeNull() + }) + + it('renders no pill while the exit status is unknown', () => { + const view = render() + expect(view.queryByText(/退出码|信号/u)).toBeNull() + }) + + it('renders the exit-code pill for a non-zero exit', () => { + render() + expect(screen.getByText('退出码 1')).toBeTruthy() + }) + + it('renders the signal pill, which outranks the exit code', () => { + render() + expect(screen.getByText('信号 SIGKILL')).toBeTruthy() + expect(screen.queryByText(/退出码/u)).toBeNull() + }) +}) + +describe('TerminalBlock height cap', () => { + it('renders every line and no expand control under the cap', () => { + const view = render() + expect(outputLines(view.container)).toHaveLength(4) + expect(view.container.querySelector('[aria-expanded]')).toBeNull() + }) + + it('does not count the output terminator against the cap', () => { + const view = render() + expect(outputLines(view.container)).toHaveLength(4) + expect(view.container.querySelector('[aria-expanded]')).toBeNull() + }) + + it('slices head and tail over the cap and expands on click', () => { + const view = render() + // maxLines 4: head = ceil(4/2) = 2, tail = 4 - 2 = 2, 6 hidden. + expect(outputLines(view.container)).toEqual(['line 1', 'line 2', 'line 9', 'line 10']) + const toggle = view.getByRole('button', { name: '展开其余 6 行输出' }) + expect(toggle.getAttribute('aria-expanded')).toBe('false') + expect(toggle.textContent).toBe('… 其余 6 行') + + fireEvent.click(toggle) + expect(outputLines(view.container)).toHaveLength(10) + const collapse = view.getByRole('button', { name: '收起输出' }) + expect(collapse.getAttribute('aria-expanded')).toBe('true') + expect(collapse.textContent).toBe('收起') + + fireEvent.click(collapse) + expect(outputLines(view.container)).toEqual(['line 1', 'line 2', 'line 9', 'line 10']) + }) + + it('renders the head slice alone when the cap leaves no tail', () => { + const view = render() + expect(outputLines(view.container)).toEqual(['line 1']) + expect(view.getByRole('button', { name: '展开其余 4 行输出' })).toBeTruthy() + }) + + it('caps at the documented default when maxLines is absent', () => { + const view = render() + expect(outputLines(view.container)).toHaveLength(DEFAULT_TERMINAL_MAX_LINES) + expect(view.getByRole('button', { name: '展开其余 1 行输出' })).toBeTruthy() + }) +}) + +describe('TerminalBlock copy', () => { + it('copies the raw output, never the prompt line or the pill', async () => { + vi.useFakeTimers() + const writeText = vi.fn().mockResolvedValue(undefined) + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: { writeText } }) + const output = `${ESC}[31mbad${ESC}[39m\n` + render() + fireEvent.click(screen.getByRole('button', { name: '复制' })) + // Escape codes, the newline terminator, and nothing of the chrome around them. + expect(writeText).toHaveBeenCalledWith(output) + await act(async () => { + await Promise.resolve() + }) + expect(screen.getByRole('button', { name: '复制成功' })).toBeTruthy() + // While the ok label is showing, further clicks are no-ops. + fireEvent.click(screen.getByRole('button', { name: '复制成功' })) + expect(writeText).toHaveBeenCalledTimes(1) + await vi.advanceTimersByTimeAsync(1000) + expect(screen.getByRole('button', { name: '复制' })).toBeTruthy() + }) + + it('copies the whole output while the height cap hides its middle', async () => { + const writeText = vi.fn().mockResolvedValue(undefined) + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: { writeText } }) + const output = `${body(10)}\n` + render() + fireEvent.click(screen.getByRole('button', { name: '复制' })) + expect(writeText).toHaveBeenCalledWith(output) + expect(await screen.findByRole('button', { name: '复制成功' })).toBeTruthy() + }) + + it('does not claim success when the host refuses the write', async () => { + Object.defineProperty(navigator, 'clipboard', { + configurable: true, + value: { writeText: vi.fn().mockRejectedValue(new Error('denied')) }, + }) + render() + fireEvent.click(screen.getByRole('button', { name: '复制' })) + await act(async () => { + await Promise.resolve() + }) + expect(screen.getByRole('button', { name: '复制' })).toBeTruthy() + expect(screen.queryByRole('button', { name: '复制成功' })).toBeNull() + }) +}) + +describe('writeClipboard', () => { + it('reports true after the async Clipboard API accepts the exact text', async () => { + const writeText = vi.fn().mockResolvedValue(undefined) + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: { writeText } }) + await expect(writeClipboard('payload')).resolves.toBe(true) + expect(writeText).toHaveBeenCalledWith('payload') + }) + + it('reports false when the Clipboard API rejects', async () => { + Object.defineProperty(navigator, 'clipboard', { + configurable: true, + value: { writeText: vi.fn().mockRejectedValue(new Error('denied')) }, + }) + await expect(writeClipboard('payload')).resolves.toBe(false) + }) + + it('selects a detached textarea for the execCommand fallback and removes it after', async () => { + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: undefined }) + let selected: string | undefined + const exec = vi.fn(() => { + selected = document.querySelector('textarea[readonly]')?.value + return true + }) + Object.defineProperty(document, 'execCommand', { configurable: true, value: exec }) + await expect(writeClipboard('payload')).resolves.toBe(true) + expect(exec).toHaveBeenCalledWith('copy') + expect(selected).toBe('payload') + expect(document.querySelector('textarea')).toBeNull() + }) + + it('reports execCommand\'s own refusal verbatim', async () => { + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: undefined }) + Object.defineProperty(document, 'execCommand', { configurable: true, value: vi.fn(() => false) }) + await expect(writeClipboard('payload')).resolves.toBe(false) + }) + + it('reports false and still removes the textarea when execCommand throws', async () => { + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: undefined }) + Object.defineProperty(document, 'execCommand', { + configurable: true, + value: () => { + throw new Error('denied') + }, + }) + await expect(writeClipboard('payload')).resolves.toBe(false) + expect(document.querySelector('textarea')).toBeNull() + }) + + it('reports false on a host with neither clipboard path', async () => { + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: undefined }) + Object.defineProperty(document, 'execCommand', { configurable: true, value: undefined }) + await expect(writeClipboard('payload')).resolves.toBe(false) + }) + + it('reports false when navigator.clipboard exists without writeText', async () => { + Object.defineProperty(navigator, 'clipboard', { configurable: true, value: {} }) + Object.defineProperty(document, 'execCommand', { configurable: true, value: undefined }) + await expect(writeClipboard('payload')).resolves.toBe(false) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b9538051cd..53791fe2fd 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1075,6 +1075,9 @@ importers: '@shikijs/langs': specifier: ^4.3.1 version: 4.3.1 + anser: + specifier: ^2.3.5 + version: 2.3.5 clsx: specifier: ^2.0.0 version: 2.1.1 @@ -7856,6 +7859,9 @@ packages: resolution: {integrity: sha512-OyacJsaeuLUvGWOynNqYc6sx88XvyoG39wMT8SYqL3l9wwaorDW/LPRbUPfhzw0bWsUWzNCZTnFYOrWFBKsUaw==} engines: {node: '>= 14.0.0'} + anser@2.3.5: + resolution: {integrity: sha512-vcZjxvvVoxTeR5XBNJB38oTu/7eDCZlwdz32N1eNgpyPF7j/Z7Idf+CUwQOkKKpJ7RJyjxgLHCM7vdIK0iCNMQ==} + ansi-regex@5.0.1: resolution: {integrity: sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==} engines: {node: '>=8'} @@ -12840,6 +12846,8 @@ snapshots: '@algolia/requester-fetch': 5.55.2 '@algolia/requester-node-http': 5.55.2 + anser@2.3.5: {} + ansi-regex@5.0.1: {} ansi-regex@6.2.2: {} From f4c243c75fa2590ddba00273d4c0b12a393a5e5a Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Tue, 28 Jul 2026 16:41:04 +0800 Subject: [PATCH 02/38] feat(web): state the run state on the terminal card's prompt line MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The terminal card showed no run state: a running command and a settled command that produced no output rendered the same prompt line, so whether a command was still running had to be inferred from the absence of output. Lead the prompt line with a StateDot in three of its states — the spinning ring while running, red for the same exit status that renders the status pill, green for a clean settle. That is the same indicator a tool row's leading icon carries, so a row and its own card cannot disagree about one command; the row/card agreement is pinned in the ui-conversation spec. StateDot is aria-hidden, so a visually hidden text label rides beside it, which is what the refreshed aria goldens now record. The e2e adds what jsdom cannot compute: the dot's color resolves to the green success token through the real theme stylesheet, and the dot precedes the prompt label in document order. --- .../2026-07-28-web-terminal-card.i18n.yaml | 4 +- .../feature/2026-07-28-web-terminal-card.md | 8 +-- .../2026-07-28-web-terminal-card.zh.md | 8 +-- apps/web/tests/navigation-panes.e2e.ts | 28 ++++++++++ .../navigation-panes/details-open.expected.md | 2 +- .../terminal-card.expected.md | 2 +- apps/web/tests/terminal-card.snapshot.ts | 13 ++++- .../client/ui-conversation/README.i18n.yaml | 4 +- packages/client/ui-conversation/README.md | 2 +- packages/client/ui-conversation/README.zh.md | 2 +- .../tests/terminal-card.spec.tsx | 22 ++++++++ .../client/ui-primitives/README.i18n.yaml | 4 +- packages/client/ui-primitives/README.md | 2 +- packages/client/ui-primitives/README.zh.md | 2 +- .../client/ui-primitives/src/StateDot.tsx | 4 +- .../src/TerminalBlock.module.css | 17 ++++++ .../ui-primitives/src/TerminalBlock.tsx | 33 +++++++++++- .../tests/terminal-block.spec.tsx | 54 ++++++++++++++++++- 18 files changed, 184 insertions(+), 27 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml index 347d5978c0..98cbad4ffc 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md -2026-07-28-web-terminal-card.md: 76d5c47054378330da9e9eebb70571925e47f741 -2026-07-28-web-terminal-card.zh.md: 83d5e7f72d9b04358ce4fe1fd9295e5c97045031 +2026-07-28-web-terminal-card.md: 7dbe688b58e78a8f67fe14809b86a6bfd4f7ce36 +2026-07-28-web-terminal-card.zh.md: 1e8c847e2955605be1a55b45d84fb449ea2a46fd diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md index 76d5c47054..7dbe688b58 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md @@ -16,7 +16,7 @@ The Web client ignored it. `packages/client/ui-conversation/src/client/contract/ The component's contract: -- **Prompt line.** A shortened cwd label followed by the command verbatim. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. +- **Prompt line.** A run-state dot, then a shortened cwd label, then the command verbatim. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. The dot is `StateDot` in three of its four states: the spinning ring while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. It leads the line because the first question a reader has about a shell command is whether it is still running, and without the dot that had to be inferred from the absence of output — which a settled command producing no output also looks like. `StateDot` is `aria-hidden`, so a visually hidden text label rides beside it. - **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding. - **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends. - **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters, and a carriage return reduces its line to the final redraw, which is what a terminal shows for progress output. @@ -50,13 +50,13 @@ Inline rendering is licensed for the terminal intent alone. A future intent that ## Testing -`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, per-line carriage-return redraws, and CRLF preservation. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly. +`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, per-line carriage-return redraws, and CRLF preservation. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, the run-state dot across all three reachable states plus its position ahead of the prompt label, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly. -`packages/client/ui-conversation/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-conversation/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files. +`packages/client/ui-conversation/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card and its agreement with its own summary row's state dot, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-conversation/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files. `apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 66 was named `bash` and turn 60 left as `fx-bash` so one fixture covers both shapes; that turn also carries what turn 60's three clean lines cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit recovered from the trailing marker. -`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `details-open.expected.md` golden was refreshed for the panel's new terminal card. That refresh also absorbed a stale `Input json` line and its copy button, which the shiki `CodeBlock` change already on master left behind — verified as failing on a clean rebuilt tree before this change, so it is a correction carried along, not an effect of this one. +`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, the run-state dot resolves to the green success token rather than to a literal color (a `--dsw-*` var has no computed value at all without the real theme stylesheet), and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `details-open.expected.md` golden was refreshed for the panel's new terminal card. That refresh also absorbed a stale `Input json` line and its copy button, which the shiki `CodeBlock` change already on master left behind — verified as failing on a clean rebuilt tree before this change, so it is a correction carried along, not an effect of this one. ## Related diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md index 83d5e7f72d..1e8c847e29 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md @@ -16,7 +16,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c 该组件的契约: -- **提示符行。** 一个缩短的 cwd 标签,其后原样跟随命令。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。 +- **提示符行。** 一枚运行状态点,其后是缩短的 cwd 标签,再原样跟随命令。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。状态点是 `StateDot` 四种状态中的三种:运行期间为旋转圆环,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。它位于行首,因为读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有该状态点时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。`StateDot` 是 `aria-hidden`,因此其旁伴随一处视觉隐藏的文本标签。 - **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。 - **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。 - **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM;回车会把所在行归约为最后一次重绘,这正是终端对进度输出的呈现。 @@ -50,13 +50,13 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c ## Testing -`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层:基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、逐行的回车重绘,以及 CRLF 的保留。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件:cwd 缩短、运行中/空/已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关,以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出,另有对 `writeClipboard` 的直接固定。 +`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层:基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、逐行的回车重绘,以及 CRLF 的保留。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件:cwd 缩短、运行中/空/已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关、运行状态点全部三种可达状态及其位于提示符标签之前的位置,以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出,另有对 `writeClipboard` 的直接固定。 -`packages/client/ui-conversation/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线:`terminalCardModel` 的推导及其每一处 null 分支、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片,以及面板 Output 区段(含 run_code 子派发与超出窗口的调用头)。该文件在没有门禁压力的情况下写成——`packages/client/ui-conversation/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中,因此覆盖率运行不会统计其中任何文件。 +`packages/client/ui-conversation/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线:`terminalCardModel` 的推导及其每一处 null 分支、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片及其与自身摘要行状态点的一致性,以及面板 Output 区段(含 run_code 子派发与超出窗口的调用头)。该文件在没有门禁压力的情况下写成——`packages/client/ui-conversation/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中,因此覆盖率运行不会统计其中任何文件。 `apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用:同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片,而其他任何声明 terminal 的工具名都落到渲染点兜底行上,其输出体受展开控制。fixture 第 66 轮改名为 `bash`、第 60 轮保留 `fx-bash`,于是一份 fixture 覆盖两种形态;该轮还承载第 60 轮三行干净输出无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd,以及从末尾标记还原出的非零退出码。 -`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景,断言 jsdom 无法计算的部分:把输出面板挤压到窄于内容宽度后,行仍保持单行且面板产生横向溢出;复制控件走的是页面自身的异步 Clipboard API,而非 `execCommand` 兜底路径。其 `details-open.expected.md` 基准已为面板的新终端卡片重新录制。该次录制同时吸收了一行陈旧的 `Input json` 及其复制按钮——那是 master 上已有的 shiki `CodeBlock` 改动留下的;在干净并重新构建的工作树上验证过它本就失败,因此那是被顺带修正的部分,而非本次改动的影响。 +`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景,断言 jsdom 无法计算的部分:把输出面板挤压到窄于内容宽度后,行仍保持单行且面板产生横向溢出;运行状态点解析为绿色的 success token,而不是字面颜色(没有真实主题样式表时,`--dsw-*` 变量根本不产生计算值);复制控件走的是页面自身的异步 Clipboard API,而非 `execCommand` 兜底路径。其 `details-open.expected.md` 基准已为面板的新终端卡片重新录制。该次录制同时吸收了一行陈旧的 `Input json` 及其复制按钮——那是 master 上已有的 shiki `CodeBlock` 改动留下的;在干净并重新构建的工作树上验证过它本就失败,因此那是被顺带修正的部分,而非本次改动的影响。 ## Related diff --git a/apps/web/tests/navigation-panes.e2e.ts b/apps/web/tests/navigation-panes.e2e.ts index b0e340da43..1e022489ee 100644 --- a/apps/web/tests/navigation-panes.e2e.ts +++ b/apps/web/tests/navigation-panes.e2e.ts @@ -207,6 +207,34 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { return { whiteSpace: getComputedStyle(row).whiteSpace, overflowX: getComputedStyle(pane).overflowX, ...squeezed } }) expect(layout).toEqual({ whiteSpace: 'pre', overflowX: 'auto', wrapped: false, scrollsSideways: true }) + // The run-state dot's color is the whole point of it and is the one thing + // jsdom cannot report: --dsw-* tokens resolve only against the real theme + // stylesheet. This command settled cleanly, so the dot must be the green + // success token — a red one here would read as a failed command. + const dot = await card.locator('[class*="_runState_"][data-state]').first().evaluate((node) => { + // The token lives on body, so the probe must sit in the same cascade. + const probe = document.createElement('span') + probe.style.color = 'var(--dsw-alias-state-success-primary)' + document.body.appendChild(probe) + const success = getComputedStyle(probe).color + probe.remove() + return { + state: node.getAttribute('data-state'), + color: getComputedStyle(node as HTMLElement).color, + success, + label: node.parentElement?.querySelector('[class*="_runStateLabel_"]')?.textContent ?? null, + // The dot precedes the prompt label in document order, which is what + // puts it to the left of the `$`. + beforePrompt: node.compareDocumentPosition(node.parentElement!.querySelector('[class*="_cwd_"]')!) + === Node.DOCUMENT_POSITION_FOLLOWING, + } + }) + expect(dot.state).toBe('done') + expect(dot.label).toBe('已完成') + expect(dot.beforePrompt).toBe(true) + // Resolved through the theme token, not a literal hex in the component. + expect(dot.success).toMatch(/^rgb/) + expect(dot.color).toBe(dot.success) // Golden of the card at rest — captured before the copy click, whose // confirmation label self-reverts on a timer and would not hold still. const snapshot = (await captureStableAria(page, '[data-terminal]', scaffold.workspaceCwd)) diff --git a/apps/web/tests/snapshots/navigation-panes/details-open.expected.md b/apps/web/tests/snapshots/navigation-panes/details-open.expected.md index 9eee71468d..d0a753994a 100644 --- a/apps/web/tests/snapshots/navigation-panes/details-open.expected.md +++ b/apps/web/tests/snapshots/navigation-panes/details-open.expected.md @@ -3,6 +3,6 @@ - text: Input json - button "复制" - code: "{ \"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\" }" -- text: Output $ echo NAVIGATION_OK +- text: Output 已完成 $ echo NAVIGATION_OK - button "复制" - text: NAVIGATION_OK diff --git a/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md b/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md index 2b81725468..abeffe93a8 100644 --- a/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md +++ b/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md @@ -1,3 +1,3 @@ -- text: $ echo NAVIGATION_OK +- text: 已完成 $ echo NAVIGATION_OK - button "复制" - text: NAVIGATION_OK diff --git a/apps/web/tests/terminal-card.snapshot.ts b/apps/web/tests/terminal-card.snapshot.ts index 53215f4ba9..80cc4fd2b4 100644 --- a/apps/web/tests/terminal-card.snapshot.ts +++ b/apps/web/tests/terminal-card.snapshot.ts @@ -120,9 +120,14 @@ function readCard(card: Element) { text: expander.textContent, expanded: expander.getAttribute('aria-expanded'), }, + // The run-state dot at the head of the prompt line, by its StateDot state. + runState: card.querySelector('[class*="_runState_"][data-state]')?.getAttribute('data-state') ?? null, + runStateLabel: card.querySelector('[class*="_runStateLabel_"]')?.textContent ?? null, // Every color the ANSI parser emits resolves through a --dsw-* token, so // the card follows the theme instead of painting literal terminal rgb. - colors: [...new Set([...card.querySelectorAll('span[style]')] + // Scoped to the output lines: the run-state dot is an inline-styled span + // too, and its geometry is not an ANSI-resolved color. + colors: [...new Set([...card.querySelectorAll('[class*="_line_"] span[style]')] .map(span => span.getAttribute('style')))], } } @@ -198,6 +203,8 @@ it('renders the keyed bash row with a resident terminal card', async () => { "[exit code: 1]", ], "prompt": "nested pnpm run check", + "runState": "error", + "runStateLabel": "失败", "status": "退出码 1", } `) @@ -229,6 +236,8 @@ it('the fallback row reaches the same card through its expand control', async () "-rw-r--r-- demo.txt", ], "prompt": "fixture ls -la", + "runState": "done", + "runStateLabel": "已完成", "status": null, } `) @@ -318,6 +327,8 @@ it('the details panel Output section renders the same call at full height', asyn ], "panelLines": 16, "prompt": "nested pnpm run check", + "runState": "error", + "runStateLabel": "失败", "status": "退出码 1", } `) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index dd28591b01..677029cf5f 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/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-conversation/README.md -README.md: 1c6912b05e259fa1f4a7096c3a2b82f9f67f5527 -README.zh.md: 157bfafd3a1157420acbb73861cd40d759228743 +README.md: 39d185014c658f490f0a3672ea3d7c99f30d8df2 +README.zh.md: 6b63631287bf420af0985a743f068f27b9c97873 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index 1c6912b05e..39d185014c 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -10,7 +10,7 @@ The view ring IS a slot: the conversation registration declares the `'conversati Generic tool rows classify the built-in bash, read, search, write, edit, and run_code names into dedicated visual variants. The filesystem variants render the edit icon and `Write · ` or `Edit · ` summary while retaining the shared row-to-details interaction. The code variant summarizes with the model-authored `description` and expands to the program itself; its logged sub-dispatches render as always-visible nested rows through the SAME keyed toolview hole (custom registrations and the GenericToolCard fallback apply to sub-rows unchanged), and the details panel resolves a selected sub-call id to its full logged args and complete output. Cordis lifecycle tools reuse those generic variants while presenting `Inspect`, `Mount temporary Plugin`, and `Unmount temporary Plugin` with a shared Cordis accent; mount keeps the code variant's expandable source rendering. -A tool call declaring the `terminal` render intent renders its command output inline, at both conversation render sites, through ui-primitives' `TerminalBlock`. `contract/terminal-card-model.ts` is the single derivation from the snapshot's `callView`/`resultView` pair, so the sites cannot disagree about a command, its cwd, or its exit status; it yields null — the generic path — for any other card tag, including one this client version does not know. The keyed `BashRow` carries the card resident below its summary row and outside that row's click target, so copying or expanding the output does not open the details panel; the render-site fallback row keeps it behind its existing expand control. Rows cap at `CHAT_TERMINAL_MAX_LINES` (8) against the panel's 16, which is what keeps a summary surface bounded — the panel stays the single-call reading surface. Inline output is licensed for this intent alone; a generic tool's content remains panel-only ([decision](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)). +A tool call declaring the `terminal` render intent renders its command output inline, at both conversation render sites, through ui-primitives' `TerminalBlock`. `contract/terminal-card-model.ts` is the single derivation from the snapshot's `callView`/`resultView` pair, so the sites cannot disagree about a command, its cwd, or its exit status; it yields null — the generic path — for any other card tag, including one this client version does not know. Both sites therefore also show the card's run-state dot, which is the same `StateDot` semantic a tool row's leading icon carries, so a row and its own card always agree about one command's state. The keyed `BashRow` carries the card resident below its summary row and outside that row's click target, so copying or expanding the output does not open the details panel; the render-site fallback row keeps it behind its existing expand control. Rows cap at `CHAT_TERMINAL_MAX_LINES` (8) against the panel's 16, which is what keeps a summary surface bounded — the panel stays the single-call reading surface. Inline output is licensed for this intent alone; a generic tool's content remains panel-only ([decision](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)). Tool rows are slots too — the standalone tool ring (`ToolViewRegistry`/`ctx.toolviews`/outlet) is retired. The chat entry declares the keyed `'conversation.chat.toolview'` hole (session scope; the key space is runtime-open); its render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam (apply mounts ConversationService after the chat registration, so the service being present guarantees the slot is declared); session differentiation happens inside the component (`useSessions` reading `parentId` — the bash sample is the third-party-posture exemplar). Trajectory/waterfall toolview slots share this shape and land with their own render sites (RendersCheck rejects a declaration nobody renders). diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index 157bfafd3a..6b63631287 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -10,7 +10,7 @@ 通用工具行把内置的 bash、read、search、write、edit 和 run_code 名称归入专用视觉变体。文件系统变体会渲染 edit 图标和 `Write · ` 或 `Edit · ` 摘要,同时保留共享的行到详情交互。code 变体以模型撰写的 `description` 作摘要,展开后显示程序本身;其已记录的子调用经由同一个键控 toolview 空位渲染为始终可见的嵌套行(自定义注册和 GenericToolCard fallback 原样适用于子行),details 面板则会根据选中的子调用 id 解析出其完整记录的参数与完整输出。Cordis 生命周期工具复用这些通用变体,同时以统一的 Cordis 强调色呈现 `Inspect`、`Mount temporary Plugin` 和 `Unmount temporary Plugin`;mount 行保留 code 变体的可展开源码渲染。 -声明 `terminal` 渲染意图的工具调用,会在两个对话渲染点上都通过 ui-primitives 的 `TerminalBlock` 内联渲染其命令输出。`contract/terminal-card-model.ts` 是从快照的 `callView`/`resultView` 对推导的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧;对任何其他 card 标签——包括当前客户端版本不认识的标签——它返回 null,落回通用路径。键控的 `BashRow` 把卡片常驻在摘要行下方、且位于该行点击目标之外,因此复制或展开输出不会打开详情面板;渲染点兜底行则保持其既有的展开控件。行的上限是 `CHAT_TERMINAL_MAX_LINES`(8),面板为 16,正是这一点让摘要面保持有界——面板仍是单次调用的阅读面。内联输出只对该意图开放;通用工具的内容仍然只在面板中呈现([决策](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md))。 +声明 `terminal` 渲染意图的工具调用,会在两个对话渲染点上都通过 ui-primitives 的 `TerminalBlock` 内联渲染其命令输出。`contract/terminal-card-model.ts` 是从快照的 `callView`/`resultView` 对推导的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧;对任何其他 card 标签——包括当前客户端版本不认识的标签——它返回 null,落回通用路径。因此两个渲染点也都显示卡片的运行状态点,它与工具行行首图标承载同一套 `StateDot` 语义,所以一行与其自身的卡片对同一条命令的状态总是一致。键控的 `BashRow` 把卡片常驻在摘要行下方、且位于该行点击目标之外,因此复制或展开输出不会打开详情面板;渲染点兜底行则保持其既有的展开控件。行的上限是 `CHAT_TERMINAL_MAX_LINES`(8),面板为 16,正是这一点让摘要面保持有界——面板仍是单次调用的阅读面。内联输出只对该意图开放;通用工具的内容仍然只在面板中呈现([决策](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md))。 工具行同样是 slot:独立工具环(`ToolViewRegistry`/`ctx.toolviews`/outlet)已经退役。聊天配置项声明键控的 `'conversation.chat.toolview'` 空位(Session scope;key 空间在运行时开放);其渲染点逐行通过 `entryKey: toolName` 分发,并以 `GenericToolCard` 作为调用点 `fallback`。owner 载荷是统一的 `ToolRowOwnerProps`(`callId`/`toolName`/`block`/`openDetails`),`ToolRowProps` 则预先将其与 Session 标准工具包组合。注册方只是普通插件:`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`,以 `inject: ['slots', 'conversation']` 作为加载顺序 seam(apply 在聊天注册后挂载 ConversationService,因此服务存在即可保证 slot 已声明);Session 区分在组件内部完成(`useSessions` 读取 `parentId`,bash 示例是第三方姿态的范例)。Trajectory/waterfall 工具视图 slot 共享此形状,并随各自的渲染点落地(RendersCheck 会拒绝没有任何渲染方的声明)。 diff --git a/packages/client/ui-conversation/tests/terminal-card.spec.tsx b/packages/client/ui-conversation/tests/terminal-card.spec.tsx index 1ab75861b5..49fcf48d4c 100644 --- a/packages/client/ui-conversation/tests/terminal-card.spec.tsx +++ b/packages/client/ui-conversation/tests/terminal-card.spec.tsx @@ -28,6 +28,11 @@ afterEach(cleanup) */ const RAW = { normalizer: (text: string) => text } +/** The rendered card's run-state dot state, so a render site cannot silently drop it. */ +function runStateOf(container: HTMLElement): string | null { + return container.querySelector('[data-terminal] [data-state]')?.getAttribute('data-state') ?? null +} + const SID = 's1' as SessionId const ARGS = '{"command":"ls -la","description":"List files"}' @@ -137,6 +142,9 @@ describe('chat row terminal body', () => { fireEvent.click(view.container.querySelector('button')!) expect(view.getByText('ls -la')).toBeTruthy() expect(view.queryByText('复制')).toBeNull() + // The card states its own run state: a running command reads as running + // even though it has no output yet to distinguish it from an empty settle. + expect(runStateOf(view.container)).toBe('ongoing') }) it('a non-terminal call keeps the args-JSON text body', () => { @@ -183,6 +191,19 @@ describe('BashRow terminal card', () => { expect(openDetails).toHaveBeenCalledTimes(1) }) + // The row's leading StateDot and the card's run-state dot describe the same + // command, so a running row whose card claimed 'done' would be a contradiction + // the reader sees on one line. + it('agrees with the summary row about the run state', () => { + const runningView = render() + expect(runningView.container.querySelector('[data-variant="bash"]')?.getAttribute('data-state')).toBe('running') + expect(runStateOf(runningView.container)).toBe('ongoing') + cleanup() + const settledView = render() + expect(settledView.container.querySelector('[data-variant="bash"]')?.getAttribute('data-state')).toBe('ok') + expect(runStateOf(settledView.container)).toBe('done') + }) + it('a non-terminal bash call (background start) renders the summary row alone', () => { const view = render( { const view = mount(snapshot({ runningCalls: [running()] }), target) expect(view.getByText('ls -la')).toBeTruthy() expect(view.queryByText('运行中…')).toBeNull() + expect(runStateOf(view.container)).toBe('ongoing') }) it('a running non-terminal call keeps the 运行中… placeholder', () => { diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml index 1eb8a05ba0..78281969f3 100644 --- a/packages/client/ui-primitives/README.i18n.yaml +++ b/packages/client/ui-primitives/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-primitives/README.md -README.md: c9c70f29804ac4e6783486595460bf07499e1dff -README.zh.md: 254fc5ba5aef553fd447338353a0c5311ddbd98a +README.md: b0387debbecb713b1e4af2b1497e81ddda083a51 +README.zh.md: d04a34951422c9cdd02421759a4e29672b1f7a54 diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md index c9c70f2980..b0387debbe 100644 --- a/packages/client/ui-primitives/README.md +++ b/packages/client/ui-primitives/README.md @@ -10,7 +10,7 @@ Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/ ## Terminal output -`TerminalBlock` renders a shell command as a terminal surface: a prompt line (shortened `cwd` label plus the command), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). +`TerminalBlock` renders a shell command as a terminal surface: a prompt line (a run-state `StateDot` ahead of the shortened `cwd` label, then the command), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. The dot reaches three of `StateDot`'s states — the spinning ring while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries a visually hidden text label because `StateDot` is `aria-hidden`. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). ## Model Experience diff --git a/packages/client/ui-primitives/README.zh.md b/packages/client/ui-primitives/README.zh.md index 254fc5ba5a..d04a349514 100644 --- a/packages/client/ui-primitives/README.zh.md +++ b/packages/client/ui-primitives/README.zh.md @@ -10,7 +10,7 @@ ## 终端输出 -`TerminalBlock` 将一条 shell 命令渲染为终端表层:提示行(缩短后的 `cwd` 标签加命令)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 +`TerminalBlock` 将一条 shell 命令渲染为终端表层:提示行(缩短后的 `cwd` 标签之前是一枚运行状态 `StateDot`,其后是命令)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。该状态点用到 `StateDot` 的三种状态——`running` 期间为旋转圆环,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它同时携带一处视觉隐藏的文本标签。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 ## 模型体验 diff --git a/packages/client/ui-primitives/src/StateDot.tsx b/packages/client/ui-primitives/src/StateDot.tsx index c4117673ba..6bc4cdba5c 100644 --- a/packages/client/ui-primitives/src/StateDot.tsx +++ b/packages/client/ui-primitives/src/StateDot.tsx @@ -19,8 +19,8 @@ export type StateDotState = 'done' | 'warning' | 'ongoing' | 'error' */ export function StateDot({ state, size = 10, className }: { state: StateDotState - size?: number - className?: string + size?: number | undefined + className?: string | undefined }) { const gradientId = useId() if (state === 'ongoing') { diff --git a/packages/client/ui-primitives/src/TerminalBlock.module.css b/packages/client/ui-primitives/src/TerminalBlock.module.css index 8a4f4a5e60..6d470ec634 100644 --- a/packages/client/ui-primitives/src/TerminalBlock.module.css +++ b/packages/client/ui-primitives/src/TerminalBlock.module.css @@ -36,6 +36,23 @@ font: var(--dsw-font-markdown-code-block); } +/* The dot sits on the prompt row's baseline box, which is a code-font line, so + it is centered against that line's box rather than sitting on the baseline. */ +.runState { + flex: none; + align-self: center; +} + +/* The dot is aria-hidden; this is its text label for assistive technology. */ +.runStateLabel { + position: absolute; + width: 1px; + height: 1px; + overflow: hidden; + clip-path: inset(50%); + white-space: nowrap; +} + .cwd { flex: none; color: var(--dsw-alias-label-tertiary); diff --git a/packages/client/ui-primitives/src/TerminalBlock.tsx b/packages/client/ui-primitives/src/TerminalBlock.tsx index e224e2b1de..5431f3c443 100644 --- a/packages/client/ui-primitives/src/TerminalBlock.tsx +++ b/packages/client/ui-primitives/src/TerminalBlock.tsx @@ -1,6 +1,6 @@ // TerminalBlock: the terminal surface for a shell command and its output — -// prompt line (shortened cwd + command), ANSI-colored output, settled exit -// status, and a copy control for the raw output. Output never soft-wraps: +// prompt line (run-state dot + shortened cwd + command), ANSI-colored output, +// settled exit status, and a copy control for the raw output. Output never soft-wraps: // column-aligned output (ls, tables, box drawing) keeps its alignment and // scrolls horizontally instead of folding. Colors resolve through --dsw-* // tokens; ANSI parsing lives in ansi.ts. @@ -10,6 +10,7 @@ import clsx from 'clsx' import { parseAnsiLines, type AnsiLine } from './ansi.ts' import { writeClipboard } from './clipboard.ts' import { Pill } from './Pill.tsx' +import { StateDot, type StateDotState } from './StateDot.tsx' import css from './TerminalBlock.module.css' /** @@ -70,6 +71,31 @@ function statusText(exitCode: number | undefined, signal: string | undefined): s return undefined } +/** + * Run-state indicator for the command, shown at the head of the prompt line so + * the card states whether the command is still running without the reader + * having to infer it from the presence of output. Three of {@link StateDotState}'s + * four states are reachable: the spinning ring while running (the same + * indicator a running tool row's leading icon uses, so the row and its card + * never disagree), green for a clean settle, red for a signal or a non-zero + * exit — the same status distinction {@link statusText} draws for the pill. A + * settled command whose exit status never reached the view counts as a clean + * settle: the view says it finished and says nothing went wrong. + * @param running - the command has not settled. + * @param exitCode - settled exit code, when known. + * @param signal - settled terminating signal name, when known. + * @returns the dot's state and its text label, since the dot is aria-hidden. + */ +function runState( + running: boolean, + exitCode: number | undefined, + signal: string | undefined, +): { state: StateDotState; label: string } { + if (running) return { state: 'ongoing', label: '运行中' } + if (statusText(exitCode, signal) !== undefined) return { state: 'error', label: '失败' } + return { state: 'done', label: '已完成' } +} + /** * Render one parsed output line. Runs without SGR state render as bare text, * so uncolored output carries no span wrappers. @@ -120,6 +146,7 @@ export function TerminalBlock({ const onToggle = useCallback(() => { setExpanded(value => !value) }, []) const status = statusText(exitCode, signal) + const state = runState(running, exitCode, signal) const empty = text.trim() === '' const hidden = lines.length - maxLines const capped = hidden > 0 && !expanded @@ -132,6 +159,8 @@ export function TerminalBlock({
+ + {state.label} {cwd === undefined ? '$' : promptLabel(cwd, home)} {command}
diff --git a/packages/client/ui-primitives/tests/terminal-block.spec.tsx b/packages/client/ui-primitives/tests/terminal-block.spec.tsx index 87e153a741..fd928f48d5 100644 --- a/packages/client/ui-primitives/tests/terminal-block.spec.tsx +++ b/packages/client/ui-primitives/tests/terminal-block.spec.tsx @@ -1,6 +1,6 @@ // @vitest-environment jsdom // TerminalBlock: the prompt label's cwd shortening, the running/empty/settled -// arms, the exit-status pill, the head/tail height cap and its expand control, +// arms, the prompt line's run-state dot, the exit-status pill, the head/tail height cap and its expand control, // and the copy control writing the raw output on both the accepted and the // refused clipboard paths. writeClipboard's own return contract is pinned here // too, since it is the seam both copy controls in this package share; the @@ -25,6 +25,15 @@ function outputLines(container: HTMLElement): string[] { return [...container.querySelectorAll('[class^="_line_"]')].map(row => row.textContent ?? '') } +/** The prompt line's run-state dot: its StateDot state plus the hidden text label beside it. */ +function runStateOf(container: HTMLElement): { state: string | null; label: string | undefined } { + const dot = container.querySelector('[class*="_runState_"][data-state]') + return { + state: dot?.getAttribute('data-state') ?? null, + label: container.querySelector('[class^="_runStateLabel_"]')?.textContent ?? undefined, + } +} + /** `count` numbered output lines, without the terminating newline. */ function body(count: number): string { return Array.from({ length: count }, (_value, index) => `line ${index + 1}`).join('\n') @@ -128,7 +137,8 @@ describe('TerminalBlock states', () => { it('renders ANSI runs as styled spans and plain text bare', () => { const view = render() - const span = view.container.querySelector('span[style]') + // Scoped to a line: the prompt line's run-state dot is a styled span too. + const span = view.container.querySelector('[class^="_line_"] span[style]') expect(span?.textContent).toBe('bad') expect(span?.getAttribute('style')).toContain('--dsw-alias-state-error-primary') expect(outputLines(view.container)).toEqual(['bad ok']) @@ -163,6 +173,46 @@ describe('TerminalBlock status pill', () => { }) }) +describe('TerminalBlock run-state dot', () => { + it('shows the spinning ring and its running label while the command runs', () => { + const view = render() + expect(runStateOf(view.container)).toEqual({ state: 'ongoing', label: '运行中' }) + }) + + it('shows the done dot for a clean settled exit', () => { + const view = render() + expect(runStateOf(view.container)).toEqual({ state: 'done', label: '已完成' }) + }) + + it('counts a settled command with no exit status as a clean settle', () => { + const view = render() + expect(runStateOf(view.container)).toEqual({ state: 'done', label: '已完成' }) + }) + + it('shows the error dot for a non-zero exit', () => { + const view = render() + expect(runStateOf(view.container)).toEqual({ state: 'error', label: '失败' }) + }) + + it('shows the error dot for a signal, whatever the exit code says', () => { + const view = render() + expect(runStateOf(view.container)).toEqual({ state: 'error', label: '失败' }) + }) + + // The dot precedes the prompt label, which is what makes it read as the + // state OF this command rather than of the card's chrome. + it('places the dot ahead of the prompt label and the command', () => { + const view = render() + const prompt = view.container.querySelector('[class^="_prompt_"]') + expect([...prompt!.children].map(node => node.textContent)).toEqual(['', '已完成', 'app', 'ls']) + }) + + it('keeps the running dot even while a settled-looking status pill is supplied', () => { + const view = render() + expect(runStateOf(view.container)).toEqual({ state: 'ongoing', label: '运行中' }) + }) +}) + describe('TerminalBlock height cap', () => { it('renders every line and no expand control under the cap', () => { const view = render() From 9d2f7f43625904605a5ed5d9cf3c417db5db122a Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Tue, 28 Jul 2026 17:08:40 +0800 Subject: [PATCH 03/38] docs(web): describe the running dot as the chase master now renders Master replaced StateDot's ongoing ring with a pixel-art chase, so the prompt line's run-state description named an indicator that no longer exists. Same fix in the note, both READMEs, and the test name. --- .../feature/2026-07-28-web-terminal-card.i18n.yaml | 4 ++-- .../notes/implemented/feature/2026-07-28-web-terminal-card.md | 2 +- .../implemented/feature/2026-07-28-web-terminal-card.zh.md | 2 +- packages/client/ui-primitives/README.i18n.yaml | 4 ++-- packages/client/ui-primitives/README.md | 2 +- packages/client/ui-primitives/README.zh.md | 2 +- packages/client/ui-primitives/src/TerminalBlock.tsx | 2 +- packages/client/ui-primitives/tests/terminal-block.spec.tsx | 2 +- 8 files changed, 10 insertions(+), 10 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml index 98cbad4ffc..9739ef195a 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md -2026-07-28-web-terminal-card.md: 7dbe688b58e78a8f67fe14809b86a6bfd4f7ce36 -2026-07-28-web-terminal-card.zh.md: 1e8c847e2955605be1a55b45d84fb449ea2a46fd +2026-07-28-web-terminal-card.md: 0c10e867afe6a9cc7085206709ae94df54bc4ed0 +2026-07-28-web-terminal-card.zh.md: e680f34bc5852430e00a5970389be0280b086f3b diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md index 7dbe688b58..0c10e867af 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md @@ -16,7 +16,7 @@ The Web client ignored it. `packages/client/ui-conversation/src/client/contract/ The component's contract: -- **Prompt line.** A run-state dot, then a shortened cwd label, then the command verbatim. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. The dot is `StateDot` in three of its four states: the spinning ring while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. It leads the line because the first question a reader has about a shell command is whether it is still running, and without the dot that had to be inferred from the absence of output — which a settled command producing no output also looks like. `StateDot` is `aria-hidden`, so a visually hidden text label rides beside it. +- **Prompt line.** A run-state dot, then a shortened cwd label, then the command verbatim. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. The dot is `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. It leads the line because the first question a reader has about a shell command is whether it is still running, and without the dot that had to be inferred from the absence of output — which a settled command producing no output also looks like. `StateDot` is `aria-hidden`, so a visually hidden text label rides beside it. - **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding. - **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends. - **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters, and a carriage return reduces its line to the final redraw, which is what a terminal shows for progress output. diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md index 1e8c847e29..e680f34bc5 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md @@ -16,7 +16,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c 该组件的契约: -- **提示符行。** 一枚运行状态点,其后是缩短的 cwd 标签,再原样跟随命令。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。状态点是 `StateDot` 四种状态中的三种:运行期间为旋转圆环,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。它位于行首,因为读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有该状态点时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。`StateDot` 是 `aria-hidden`,因此其旁伴随一处视觉隐藏的文本标签。 +- **提示符行。** 一枚运行状态点,其后是缩短的 cwd 标签,再原样跟随命令。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。状态点是 `StateDot` 四种状态中的三种:运行期间为追逐动画,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。它位于行首,因为读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有该状态点时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。`StateDot` 是 `aria-hidden`,因此其旁伴随一处视觉隐藏的文本标签。 - **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。 - **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。 - **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM;回车会把所在行归约为最后一次重绘,这正是终端对进度输出的呈现。 diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml index 78281969f3..495831a377 100644 --- a/packages/client/ui-primitives/README.i18n.yaml +++ b/packages/client/ui-primitives/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-primitives/README.md -README.md: b0387debbecb713b1e4af2b1497e81ddda083a51 -README.zh.md: d04a34951422c9cdd02421759a4e29672b1f7a54 +README.md: bc880333157f5cb790cbaf854b01aaf8ea6c1cc9 +README.zh.md: 6593e4518d09eaccee7e55874b1162943c5eb3bd diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md index b0387debbe..bc88033315 100644 --- a/packages/client/ui-primitives/README.md +++ b/packages/client/ui-primitives/README.md @@ -10,7 +10,7 @@ Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/ ## Terminal output -`TerminalBlock` renders a shell command as a terminal surface: a prompt line (a run-state `StateDot` ahead of the shortened `cwd` label, then the command), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. The dot reaches three of `StateDot`'s states — the spinning ring while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries a visually hidden text label because `StateDot` is `aria-hidden`. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). +`TerminalBlock` renders a shell command as a terminal surface: a prompt line (a run-state `StateDot` ahead of the shortened `cwd` label, then the command), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. The dot reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries a visually hidden text label because `StateDot` is `aria-hidden`. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). ## Model Experience diff --git a/packages/client/ui-primitives/README.zh.md b/packages/client/ui-primitives/README.zh.md index d04a349514..6593e4518d 100644 --- a/packages/client/ui-primitives/README.zh.md +++ b/packages/client/ui-primitives/README.zh.md @@ -10,7 +10,7 @@ ## 终端输出 -`TerminalBlock` 将一条 shell 命令渲染为终端表层:提示行(缩短后的 `cwd` 标签之前是一枚运行状态 `StateDot`,其后是命令)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。该状态点用到 `StateDot` 的三种状态——`running` 期间为旋转圆环,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它同时携带一处视觉隐藏的文本标签。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 +`TerminalBlock` 将一条 shell 命令渲染为终端表层:提示行(缩短后的 `cwd` 标签之前是一枚运行状态 `StateDot`,其后是命令)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。该状态点用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它同时携带一处视觉隐藏的文本标签。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 ## 模型体验 diff --git a/packages/client/ui-primitives/src/TerminalBlock.tsx b/packages/client/ui-primitives/src/TerminalBlock.tsx index 5431f3c443..c5278dd7df 100644 --- a/packages/client/ui-primitives/src/TerminalBlock.tsx +++ b/packages/client/ui-primitives/src/TerminalBlock.tsx @@ -75,7 +75,7 @@ function statusText(exitCode: number | undefined, signal: string | undefined): s * Run-state indicator for the command, shown at the head of the prompt line so * the card states whether the command is still running without the reader * having to infer it from the presence of output. Three of {@link StateDotState}'s - * four states are reachable: the spinning ring while running (the same + * four states are reachable: the running chase (the same * indicator a running tool row's leading icon uses, so the row and its card * never disagree), green for a clean settle, red for a signal or a non-zero * exit — the same status distinction {@link statusText} draws for the pill. A diff --git a/packages/client/ui-primitives/tests/terminal-block.spec.tsx b/packages/client/ui-primitives/tests/terminal-block.spec.tsx index fd928f48d5..486aac1197 100644 --- a/packages/client/ui-primitives/tests/terminal-block.spec.tsx +++ b/packages/client/ui-primitives/tests/terminal-block.spec.tsx @@ -174,7 +174,7 @@ describe('TerminalBlock status pill', () => { }) describe('TerminalBlock run-state dot', () => { - it('shows the spinning ring and its running label while the command runs', () => { + it('shows the running chase and its running label while the command runs', () => { const view = render() expect(runStateOf(view.container)).toEqual({ state: 'ongoing', label: '运行中' }) }) From a00678a44452df0dd341eabe4ad47804470ebcb0 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Tue, 28 Jul 2026 18:48:57 +0800 Subject: [PATCH 04/38] feat(web): give a multi-line command one prompt row per line MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A `command` carrying two shell commands on two lines rendered as one row: `.command` had `white-space: nowrap`, so the two collapsed into a single ellipsized line that read as one command with stray arguments. Render one prompt row per command line, and move the run-state dot out of flow into a gutter reserved to the left of the card surface, so it neither indents its command nor depends on the command's text metrics to line up. The dot stays exactly one per card, on the first row. The exit status the view carries is the whole call's and bash reports no per-command status, so a dot per line would assert, of a line that succeeded inside a failing call, that the line itself failed. The single visually hidden label keeps the same scope, since one label per row would read to assistive technology as several distinct outcomes. Fixture turn 60's command becomes two lines, so the built-bundle snapshot pins the layout and its dot distribution (`dotsPerPromptRow: [1, 0]`), and the e2e adds that the dot starts left of the card surface — geometry jsdom cannot compute. Both READMEs now also record that this package's user-facing copy is inline Chinese, since zero-cordis atoms have no route to `ctx.locale`; extracting it belongs to the repo-wide localization work. --- .../2026-07-28-web-terminal-card.i18n.yaml | 4 +- .../feature/2026-07-28-web-terminal-card.md | 9 +++-- .../2026-07-28-web-terminal-card.zh.md | 9 +++-- apps/web/tests/navigation-panes.e2e.ts | 9 ++++- apps/web/tests/terminal-card.snapshot.ts | 32 ++++++++++++++-- .../client/connection/src/client/fixture.ts | 4 +- .../tests/terminal-card.spec.tsx | 11 ++++++ .../client/ui-primitives/README.i18n.yaml | 4 +- packages/client/ui-primitives/README.md | 3 +- packages/client/ui-primitives/README.zh.md | 3 +- .../src/TerminalBlock.module.css | 37 ++++++++++++++----- .../ui-primitives/src/TerminalBlock.tsx | 21 +++++++++-- .../tests/terminal-block.spec.tsx | 29 ++++++++++++++- 13 files changed, 140 insertions(+), 35 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml index 9739ef195a..ca4d5e62e1 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md -2026-07-28-web-terminal-card.md: 0c10e867afe6a9cc7085206709ae94df54bc4ed0 -2026-07-28-web-terminal-card.zh.md: e680f34bc5852430e00a5970389be0280b086f3b +2026-07-28-web-terminal-card.md: 7a4672e110cb4333df8d7a29a772de8bf2717d84 +2026-07-28-web-terminal-card.zh.md: df49ef45e000a464715635ca32e42848994fc7ff diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md index 0c10e867af..7a4672e110 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md @@ -16,7 +16,8 @@ The Web client ignored it. `packages/client/ui-conversation/src/client/contract/ The component's contract: -- **Prompt line.** A run-state dot, then a shortened cwd label, then the command verbatim. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. The dot is `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. It leads the line because the first question a reader has about a shell command is whether it is still running, and without the dot that had to be inferred from the absence of output — which a settled command producing no output also looks like. `StateDot` is `aria-hidden`, so a visually hidden text label rides beside it. +- **Prompt lines, one per command line.** Each line of the command gets its own row: label, then that line verbatim. A `command` carrying two shell commands on two lines therefore reads as the two commands it is, instead of collapsing into one ellipsized row. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. A trailing newline is a terminator, not an empty final command. +- **One run-state dot for the call, on the first row.** `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. The dot exists because the first question a reader has about a shell command is whether it is still running, and without it that had to be inferred from the absence of output — which a settled command producing no output also looks like. It sits out of flow in a gutter reserved to the left of the card surface, so it neither indents its command nor depends on the command's own text metrics to line up with it. Exactly one dot, whatever the line count: the exit status the view carries is the whole call's, and bash reports no per-command status, so a dot per line would assert of a line that succeeded inside a failing call that the line itself failed. The single visually hidden text label carries the same scope, since `StateDot` is `aria-hidden` and one label per row would read to assistive technology as several distinct outcomes. - **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding. - **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends. - **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters, and a carriage return reduces its line to the final redraw, which is what a terminal shows for progress output. @@ -50,13 +51,13 @@ Inline rendering is licensed for the terminal intent alone. A future intent that ## Testing -`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, per-line carriage-return redraws, and CRLF preservation. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, the run-state dot across all three reachable states plus its position ahead of the prompt label, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly. +`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, per-line carriage-return redraws, and CRLF preservation. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, the run-state dot across all three reachable states plus its position ahead of the prompt label, the one-row-per-command-line prompt and its single dot on the first row, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly. `packages/client/ui-conversation/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card and its agreement with its own summary row's state dot, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-conversation/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files. -`apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 66 was named `bash` and turn 60 left as `fx-bash` so one fixture covers both shapes; that turn also carries what turn 60's three clean lines cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit recovered from the trailing marker. +`apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 66 was named `bash` and turn 60 left as `fx-bash` so one fixture covers both shapes, and turn 60's command was made two lines so the built-bundle snapshot pins the per-line prompt and its single dot (`dotsPerPromptRow: [1, 0]`); that turn also carries what turn 60's three clean lines cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit recovered from the trailing marker. -`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, the run-state dot resolves to the green success token rather than to a literal color (a `--dsw-*` var has no computed value at all without the real theme stylesheet), and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `details-open.expected.md` golden was refreshed for the panel's new terminal card. That refresh also absorbed a stale `Input json` line and its copy button, which the shiki `CodeBlock` change already on master left behind — verified as failing on a clean rebuilt tree before this change, so it is a correction carried along, not an effect of this one. +`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, the run-state dot resolves to the green success token rather than to a literal color (a `--dsw-*` var has no computed value at all without the real theme stylesheet) and starts to the left of the card surface itself, and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `details-open.expected.md` golden was refreshed for the panel's new terminal card. That refresh also absorbed a stale `Input json` line and its copy button, which the shiki `CodeBlock` change already on master left behind — verified as failing on a clean rebuilt tree before this change, so it is a correction carried along, not an effect of this one. ## Related diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md index e680f34bc5..df49ef45e0 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md @@ -16,7 +16,8 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c 该组件的契约: -- **提示符行。** 一枚运行状态点,其后是缩短的 cwd 标签,再原样跟随命令。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。状态点是 `StateDot` 四种状态中的三种:运行期间为追逐动画,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。它位于行首,因为读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有该状态点时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。`StateDot` 是 `aria-hidden`,因此其旁伴随一处视觉隐藏的文本标签。 +- **提示符行,每条命令行一行。** 命令的每一行各占一行:标签,其后原样跟随该行。因此一个在两行上承载两条 shell 命令的 `command` 就读作它本身的两条命令,而不是被压成一行并省略号截断。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。末尾换行是终止符,不是一条空的末命令。 +- **整次调用一枚运行状态点,位于第一行。** 它是 `StateDot` 四种状态中的三种:运行期间为追逐动画,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。该状态点存在的理由是:读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有它时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。它以脱离文档流的方式落在卡片表面左侧预留的落区里,因此既不会缩进其命令,也不依赖命令自身的文本度量来与之对齐。无论有多少行,都只有一枚:视图携带的退出状态属于整次调用,而 bash 不报告逐条命令的状态,因此每行一枚状态点就等于在断言——一条在失败调用中其实成功了的命令行自身失败了。那一处视觉隐藏的文本标签具有相同的作用域,因为 `StateDot` 是 `aria-hidden`,而每行一个标签会被辅助技术读成好几个各自独立的结果。 - **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。 - **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。 - **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM;回车会把所在行归约为最后一次重绘,这正是终端对进度输出的呈现。 @@ -50,13 +51,13 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c ## Testing -`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层:基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、逐行的回车重绘,以及 CRLF 的保留。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件:cwd 缩短、运行中/空/已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关、运行状态点全部三种可达状态及其位于提示符标签之前的位置,以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出,另有对 `writeClipboard` 的直接固定。 +`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层:基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、逐行的回车重绘,以及 CRLF 的保留。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件:cwd 缩短、运行中/空/已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关、运行状态点全部三种可达状态及其位于提示符标签之前的位置、每条命令行一行的提示区及其位于第一行的单枚状态点,以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出,另有对 `writeClipboard` 的直接固定。 `packages/client/ui-conversation/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线:`terminalCardModel` 的推导及其每一处 null 分支、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片及其与自身摘要行状态点的一致性,以及面板 Output 区段(含 run_code 子派发与超出窗口的调用头)。该文件在没有门禁压力的情况下写成——`packages/client/ui-conversation/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中,因此覆盖率运行不会统计其中任何文件。 -`apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用:同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片,而其他任何声明 terminal 的工具名都落到渲染点兜底行上,其输出体受展开控制。fixture 第 66 轮改名为 `bash`、第 60 轮保留 `fx-bash`,于是一份 fixture 覆盖两种形态;该轮还承载第 60 轮三行干净输出无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd,以及从末尾标记还原出的非零退出码。 +`apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用:同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片,而其他任何声明 terminal 的工具名都落到渲染点兜底行上,其输出体受展开控制。fixture 第 66 轮改名为 `bash`、第 60 轮保留 `fx-bash`,于是一份 fixture 覆盖两种形态,并把第 60 轮的命令改为两行,使构建产物快照钉住逐行提示区及其单枚状态点(`dotsPerPromptRow: [1, 0]`);该轮还承载第 60 轮三行干净输出无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd,以及从末尾标记还原出的非零退出码。 -`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景,断言 jsdom 无法计算的部分:把输出面板挤压到窄于内容宽度后,行仍保持单行且面板产生横向溢出;运行状态点解析为绿色的 success token,而不是字面颜色(没有真实主题样式表时,`--dsw-*` 变量根本不产生计算值);复制控件走的是页面自身的异步 Clipboard API,而非 `execCommand` 兜底路径。其 `details-open.expected.md` 基准已为面板的新终端卡片重新录制。该次录制同时吸收了一行陈旧的 `Input json` 及其复制按钮——那是 master 上已有的 shiki `CodeBlock` 改动留下的;在干净并重新构建的工作树上验证过它本就失败,因此那是被顺带修正的部分,而非本次改动的影响。 +`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景,断言 jsdom 无法计算的部分:把输出面板挤压到窄于内容宽度后,行仍保持单行且面板产生横向溢出;运行状态点解析为绿色的 success token,而不是字面颜色(没有真实主题样式表时,`--dsw-*` 变量根本不产生计算值),且其起点位于卡片表面本身的左侧;复制控件走的是页面自身的异步 Clipboard API,而非 `execCommand` 兜底路径。其 `details-open.expected.md` 基准已为面板的新终端卡片重新录制。该次录制同时吸收了一行陈旧的 `Input json` 及其复制按钮——那是 master 上已有的 shiki `CodeBlock` 改动留下的;在干净并重新构建的工作树上验证过它本就失败,因此那是被顺带修正的部分,而非本次改动的影响。 ## Related diff --git a/apps/web/tests/navigation-panes.e2e.ts b/apps/web/tests/navigation-panes.e2e.ts index 1e022489ee..2883371bdb 100644 --- a/apps/web/tests/navigation-panes.e2e.ts +++ b/apps/web/tests/navigation-panes.e2e.ts @@ -222,16 +222,23 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { state: node.getAttribute('data-state'), color: getComputedStyle(node as HTMLElement).color, success, - label: node.parentElement?.querySelector('[class*="_runStateLabel_"]')?.textContent ?? null, + // One label per card (the state is the call's), so it hangs off the + // prompt column rather than the row the dot sits in. + label: node.closest('[class*="_prompt_"]')?.querySelector('[class*="_runStateLabel_"]')?.textContent ?? null, // The dot precedes the prompt label in document order, which is what // puts it to the left of the `$`. beforePrompt: node.compareDocumentPosition(node.parentElement!.querySelector('[class*="_cwd_"]')!) === Node.DOCUMENT_POSITION_FOLLOWING, + // The dot is out of flow in the card's left gutter, so it starts to the + // left of the card surface itself — the geometry jsdom cannot compute. + leftOfCard: (node as HTMLElement).getBoundingClientRect().left + < node.closest('[data-terminal]')!.getBoundingClientRect().left, } }) expect(dot.state).toBe('done') expect(dot.label).toBe('已完成') expect(dot.beforePrompt).toBe(true) + expect(dot.leftOfCard).toBe(true) // Resolved through the theme token, not a literal hex in the component. expect(dot.success).toMatch(/^rgb/) expect(dot.color).toBe(dot.success) diff --git a/apps/web/tests/terminal-card.snapshot.ts b/apps/web/tests/terminal-card.snapshot.ts index 80cc4fd2b4..b6e53d972f 100644 --- a/apps/web/tests/terminal-card.snapshot.ts +++ b/apps/web/tests/terminal-card.snapshot.ts @@ -111,7 +111,14 @@ function readCard(card: Element) { const status = card.querySelector('[class*="_status_"]') const expander = card.querySelector('button[aria-expanded]') return { - prompt: `${card.querySelector('[class*="_cwd_"]')?.textContent ?? ''} ${card.querySelector('[class*="_command_"]')?.textContent ?? ''}`, + // One entry per command line: a multi-line command is one row per line. + prompt: [...card.querySelectorAll('[class*="_promptLine_"]')].map(row => + `${row.querySelector('[class*="_cwd_"]')?.textContent ?? ''} ${row.querySelector('[class*="_command_"]')?.textContent ?? ''}`), + // Dots per prompt row: exactly one, on the first row — the exit status the + // view carries is the whole call's, so a dot per line would assert a + // per-line outcome bash does not report. + dotsPerPromptRow: [...card.querySelectorAll('[class*="_promptLine_"]')].map(row => + row.querySelectorAll('[data-state]').length), status: status === null ? null : status.textContent, copy: card.querySelector('[class*="_copyButton_"]')?.textContent ?? null, lines: [...card.querySelectorAll('[class*="_line_"]')].map(line => line.textContent), @@ -187,6 +194,9 @@ it('renders the keyed bash row with a resident terminal card', async () => { "color: var(--dsw-alias-state-error-primary);", ], "copy": "复制", + "dotsPerPromptRow": [ + 1, + ], "expander": { "expanded": "false", "label": "展开其余 14 行输出", @@ -202,7 +212,9 @@ it('renders the keyed bash row with a resident terminal card', async () => { "1 of 4 checks failed", "[exit code: 1]", ], - "prompt": "nested pnpm run check", + "prompt": [ + "nested pnpm run check", + ], "runState": "error", "runStateLabel": "失败", "status": "退出码 1", @@ -229,13 +241,20 @@ it('the fallback row reaches the same card through its expand control', async () { "colors": [], "copy": "复制", + "dotsPerPromptRow": [ + 1, + 0, + ], "expander": null, "lines": [ "total 2", "drwxr-xr-x fixture", "-rw-r--r-- demo.txt", ], - "prompt": "fixture ls -la", + "prompt": [ + "fixture ls -la", + "fixture echo done", + ], "runState": "done", "runStateLabel": "已完成", "status": null, @@ -302,6 +321,9 @@ it('the details panel Output section renders the same call at full height', asyn "color: var(--dsw-alias-label-tertiary);", ], "copy": "复制", + "dotsPerPromptRow": [ + 1, + ], "expander": { "expanded": "false", "label": "展开其余 6 行输出", @@ -326,7 +348,9 @@ it('the details panel Output section renders the same call at full height', asyn "[exit code: 1]", ], "panelLines": 16, - "prompt": "nested pnpm run check", + "prompt": [ + "nested pnpm run check", + ], "runState": "error", "runStateLabel": "失败", "status": "退出码 1", diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 401d3a76a4..55907be48a 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -185,7 +185,9 @@ function buildAlphaLog(): SessionEvent[] { push({ type: 'step/end', data: { turn, step: 0 } }) push({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } }) } - toolTurn(60, 'fx-bash', '{"command":"ls -la","cwd":"/tmp/fixture"}', 'total 2\ndrwxr-xr-x fixture\n-rw-r--r-- demo.txt') + // A two-line command, so the fixture covers the terminal card's one-row-per- + // command-line prompt (and that the card still marks the call exactly once). + toolTurn(60, 'fx-bash', '{"command":"ls -la\\necho done","cwd":"/tmp/fixture"}', 'total 2\ndrwxr-xr-x fixture\n-rw-r--r-- demo.txt') toolTurn(61, 'fx-write', '{"path":"notes/demo.txt","content":"hello fixture\\n"}', 'wrote notes/demo.txt') toolTurn(62, 'edit', '{"file_path":"notes/demo.txt","old_string":"hello","new_string":"hello fixture"}', '已编辑') toolTurn(63, 'write', '{"file_path":"notes/new-demo.txt","content":"hello fixture\\n"}', '已写入') diff --git a/packages/client/ui-conversation/tests/terminal-card.spec.tsx b/packages/client/ui-conversation/tests/terminal-card.spec.tsx index 49fcf48d4c..e6ff5e7eed 100644 --- a/packages/client/ui-conversation/tests/terminal-card.spec.tsx +++ b/packages/client/ui-conversation/tests/terminal-card.spec.tsx @@ -137,6 +137,17 @@ describe('chat row terminal body', () => { expect(view.getByText('line-5')).toBeTruthy() }) + it('renders a multi-line command as one prompt row per line', () => { + const view = render() + fireEvent.click(view.container.querySelector('button')!) + const rows = view.container.querySelectorAll('[class^="_promptLine_"]') + expect([...rows].map(row => row.textContent)).toEqual(['$ls -la', '$echo done']) + // Still one dot for the call, on the first row. + expect(view.container.querySelectorAll('[data-terminal] [data-state]')).toHaveLength(1) + }) + it('a running terminal call expands to the prompt line with no output yet', () => { const view = render() fireEvent.click(view.container.querySelector('button')!) diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml index 495831a377..753c33fdea 100644 --- a/packages/client/ui-primitives/README.i18n.yaml +++ b/packages/client/ui-primitives/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-primitives/README.md -README.md: bc880333157f5cb790cbaf854b01aaf8ea6c1cc9 -README.zh.md: 6593e4518d09eaccee7e55874b1162943c5eb3bd +README.md: 9e5384f84c3714d327b7b4ceaba8fb0a2cd67e7b +README.zh.md: 9f2a362e4a1e03bffde1d7b218bf94ed41ffd168 diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md index bc88033315..9e5384f84c 100644 --- a/packages/client/ui-primitives/README.md +++ b/packages/client/ui-primitives/README.md @@ -10,7 +10,7 @@ Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/ ## Terminal output -`TerminalBlock` renders a shell command as a terminal surface: a prompt line (a run-state `StateDot` ahead of the shortened `cwd` label, then the command), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. The dot reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries a visually hidden text label because `StateDot` is `aria-hidden`. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). +`TerminalBlock` renders a shell command as a terminal surface: one prompt row per line of the command (the shortened `cwd` label, then that line), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. A run-state `StateDot` marks the call once, on the first row, out of flow in a gutter to the left of the card surface. It reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries one visually hidden text label because `StateDot` is `aria-hidden`. One dot regardless of line count is deliberate: the exit status is the whole call's, so a dot per line would claim a per-line outcome the view does not carry. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). ## Model Experience @@ -25,4 +25,5 @@ None; this package neither assembles nor sends a provider request. - **Glyph-level icons are redrawn approximations** — the fish logo (and the sparkle held by ui-conversation) come from font glyphs whose vector geometry is not exportable from the local design data; hand-authored recreations stand in until an exact export path exists. - **Pill and Input have no design source** — both atoms are self-defined; the sidebar search field and view-tab strip that resemble them are consumer-owned compositions, not these atoms. - **StateDot `Active` variant is a hidden placeholder in the design** — not implemented; the four shipped states (done/warning/ongoing/error) are the complete P-I surface. +- **This package's user-facing copy is inline Chinese, not localized** — the atoms are zero-cordis and so cannot reach `ctx.locale`; `TerminalBlock`'s exit-code and signal pills, its copy and expand controls, and `CodeBlock`'s copy control are all hardcoded. This matches the repo-wide state the locale package records (only the Settings surface is translated); extracting these into the `zh`/`en` dictionaries needs a localization channel for zero-cordis atoms and belongs to that repo-wide extraction. - **`TerminalBlock` is not a terminal emulator** — it renders settled or still-running command output, not an interactive session: SGR color and attributes are honored, while cursor movement, screen clearing, and alternate-screen sequences are stripped. Basic-16 magenta and cyan have no token equivalent and stay literal rgb. diff --git a/packages/client/ui-primitives/README.zh.md b/packages/client/ui-primitives/README.zh.md index 6593e4518d..9f2a362e4a 100644 --- a/packages/client/ui-primitives/README.zh.md +++ b/packages/client/ui-primitives/README.zh.md @@ -10,7 +10,7 @@ ## 终端输出 -`TerminalBlock` 将一条 shell 命令渲染为终端表层:提示行(缩短后的 `cwd` 标签之前是一枚运行状态 `StateDot`,其后是命令)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。该状态点用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它同时携带一处视觉隐藏的文本标签。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 +`TerminalBlock` 将一条 shell 命令渲染为终端表层:命令的每一行各占一个提示行(缩短后的 `cwd` 标签,其后是该行)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。一枚运行状态 `StateDot` 为整次调用标记一次,位于第一行,以脱离文档流的方式落在卡片表面左侧的落区中。它用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它携带一处视觉隐藏的文本标签。无论多少行都只有一枚状态点是有意为之:退出状态属于整次调用,因此每行一枚就会声称一个视图并不携带的逐行结果。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 ## 模型体验 @@ -25,4 +25,5 @@ - **字形级图标是重新绘制的近似版本**:鱼形标志(以及 ui-conversation 持有的闪光图标)来自字体字形,而本地设计数据无法导出其矢量几何;在获得精确导出路径前,使用手工重建版本代替。 - **Pill 与 Input 没有设计来源**:两个原子组件均自行定义;与其相似的侧边栏搜索字段和视图标签条由消费方组合,不是这些原子组件。 - **StateDot 的 `Active` 变体是设计中的隐藏占位符**:尚未实现;已交付的四种状态(done/warning/ongoing/error)构成完整的 P-I 表层。 +- **本包面向用户的文案是内联中文,未做本地化**:这些原子组件是 zero-cordis 的,因此拿不到 `ctx.locale`;`TerminalBlock` 的退出码与信号胶囊、它的复制与展开控件,以及 `CodeBlock` 的复制控件全部硬编码。这与 locale 包记录的全仓现状一致(只有 Settings 表面做了翻译);把它们抽取进 `zh`/`en` 字典需要为 zero-cordis 原子组件提供一条本地化通道,属于那次全仓抽取的范围。 - **`TerminalBlock` 不是终端模拟器**:它渲染已结束或仍在运行的命令输出,而不是交互式会话:SGR 颜色与属性会被遵循,而光标移动、清屏和备用屏幕序列会被剥离。基础 16 色中的洋红与青色没有对应 token,保持字面 rgb。 diff --git a/packages/client/ui-primitives/src/TerminalBlock.module.css b/packages/client/ui-primitives/src/TerminalBlock.module.css index 6d470ec634..aec2971921 100644 --- a/packages/client/ui-primitives/src/TerminalBlock.module.css +++ b/packages/client/ui-primitives/src/TerminalBlock.module.css @@ -7,17 +7,23 @@ .block { --dsl-terminal-radius: 12px; --dsl-terminal-line-height: 22px; + /* Reserved strip to the left of the card for the per-line run-state dots. + The dots sit outside the card surface, so a reader scans command state + down one column without the dots competing with the commands themselves. */ + --dsl-terminal-gutter: 30px; position: relative; - margin: 16px 0; + margin: 16px 0 16px var(--dsl-terminal-gutter); color: var(--dsw-alias-label-primary); background: var(--dsw-alias-markdown-code-block); border-radius: var(--dsl-terminal-radius); } +/* Top-aligned: the status pill and copy control stay on the first prompt row + however many command lines the card carries. */ .header { display: flex; - align-items: center; + align-items: flex-start; gap: 12px; padding: 9px 14px; background: var(--dsw-alias-markdown-code-block-banner); @@ -25,22 +31,33 @@ border-top-right-radius: var(--dsl-terminal-radius); } -/* The prompt row is the only element allowed to shrink; the status pill and - the copy control keep their intrinsic width. */ +/* One row per command line. The prompt column is the only element allowed to + shrink; the status pill and the copy control keep their intrinsic width. */ .prompt { display: flex; - align-items: baseline; - gap: 8px; + flex-direction: column; min-width: 0; flex: 1; font: var(--dsw-font-markdown-code-block); } -/* The dot sits on the prompt row's baseline box, which is a code-font line, so - it is centered against that line's box rather than sitting on the baseline. */ +.promptLine { + position: relative; + display: flex; + align-items: baseline; + gap: 8px; + min-width: 0; + line-height: var(--dsl-terminal-line-height); +} + +/* Out of flow in the gutter, so a dot neither indents its command nor depends + on the command's own text metrics to line up with it. Centered against the + row's line box rather than sitting on the code font's baseline. */ .runState { - flex: none; - align-self: center; + position: absolute; + left: calc(-1 * var(--dsl-terminal-gutter)); + top: 50%; + transform: translateY(-50%); } /* The dot is aria-hidden; this is its text label for assistive technology. */ diff --git a/packages/client/ui-primitives/src/TerminalBlock.tsx b/packages/client/ui-primitives/src/TerminalBlock.tsx index c5278dd7df..3ae7ca7113 100644 --- a/packages/client/ui-primitives/src/TerminalBlock.tsx +++ b/packages/client/ui-primitives/src/TerminalBlock.tsx @@ -147,6 +147,13 @@ export function TerminalBlock({ const status = statusText(exitCode, signal) const state = runState(running, exitCode, signal) + // A multi-line command gets one prompt row per line, so a two-command shell + // snippet reads as the two commands it is instead of collapsing into one + // ellipsized row. A trailing newline is a terminator, not an empty command. + const commandLines = useMemo(() => { + const body = command.endsWith('\n') ? command.slice(0, -1) : command + return body.split('\n') + }, [command]) const empty = text.trim() === '' const hidden = lines.length - maxLines const capped = hidden > 0 && !expanded @@ -159,10 +166,18 @@ export function TerminalBlock({
- {state.label} - {cwd === undefined ? '$' : promptLabel(cwd, home)} - {command} + {commandLines.map((line, index) => ( +
+ {/* One dot for the card, on the first row: the exit status the + view carries is the whole call's, and bash reports no + per-command status, so a dot per row would assert a + per-line outcome nothing here knows. */} + {index === 0 && } + {cwd === undefined ? '$' : promptLabel(cwd, home)} + {line} +
+ ))}
{status !== undefined && {status}} {!running && !empty && ( diff --git a/packages/client/ui-primitives/tests/terminal-block.spec.tsx b/packages/client/ui-primitives/tests/terminal-block.spec.tsx index 486aac1197..dd9af07b8e 100644 --- a/packages/client/ui-primitives/tests/terminal-block.spec.tsx +++ b/packages/client/ui-primitives/tests/terminal-block.spec.tsx @@ -34,6 +34,11 @@ function runStateOf(container: HTMLElement): { state: string | null; label: stri } } +/** The prompt rows as `
{open && (terminalBody !== null - ? + ? : variant === 'code' ? :
{text}
)} diff --git a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts index bf832e2961..a1439c6bc1 100644 --- a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts +++ b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts @@ -28,10 +28,21 @@ export const CHAT_TERMINAL_MAX_LINES = 8 * client has no home path for the session host (a cwd renders as its last * path segment), and `maxLines`/`className` belong to each render site. */ -export type TerminalCardModel = Pick< - TerminalBlockProps, - 'command' | 'cwd' | 'output' | 'exitCode' | 'signal' | 'running' -> +export interface TerminalCardModel { + /** + * The props {@link TerminalBlock} draws. Held as a nested object so a render + * site spreads exactly the primitive's own surface and can never leak a + * neighbouring field into it. + */ + card: Pick + /** + * The call view's model-authored description, which the contract defines as + * rendering ABOVE the card (the card itself has no description slot). Absent + * when the presenter supplied none, or when the window dropped the call side; + * a row then keeps its args-derived summary. + */ + description: string | undefined +} /** * Resolve a terminal view's working directory the way the render-intent @@ -47,8 +58,41 @@ export type TerminalCardModel = Pick< */ function resolveTerminalCwd(viewCwd: string | undefined, sessionCwd: string | undefined): string | undefined { if (viewCwd === undefined || viewCwd === '') return sessionCwd - if (sessionCwd === undefined || sessionCwd === '') return viewCwd - return resolveToolPath(sessionCwd, viewCwd) + if (sessionCwd === undefined || sessionCwd === '') return normalizeSegments(viewCwd) + return normalizeSegments(resolveToolPath(sessionCwd, viewCwd)) +} + +/** + * Collapse `.` and `..` segments so the prompt label names the directory the + * command actually ran in. The bash executor resolves the workdir before + * running, so a joined `/w/app/..` must display as `w`, not as `..`. Separators + * are preserved as authored (a Windows path keeps its backslashes) because this + * value is only ever displayed; a `..` that would climb past the root is + * dropped, which is what a filesystem does with it. + * @param path - a joined or absolute path, possibly carrying `.`/`..` segments. + * @returns the same path with those segments resolved. + */ +function normalizeSegments(path: string): string { + if (!/(?:^|[/\\])\.\.?(?:[/\\]|$)/.test(path)) return path + const backslashed = path.includes('\\') && !path.includes('/') + const separator = backslashed ? '\\' : '/' + const leading = /^[/\\]/.test(path) ? separator : '' + const drive = /^[A-Za-z]:/.exec(path)?.[0] ?? '' + const kept: string[] = [] + for (const segment of path.slice(drive.length).split(/[/\\]/)) { + if (segment === '' || segment === '.') continue + if (segment === '..') { + // Nothing to climb from: at a root the segment is dropped, matching the + // filesystem; on a relative path the `..` has to stay, since it is still + // meaningful against a cwd this function cannot see. + if (kept.length > 0 && kept[kept.length - 1] !== '..') kept.pop() + else if (leading === '' && drive === '') kept.push(segment) + continue + } + kept.push(segment) + } + const body = kept.join(separator) + return drive === '' ? `${leading}${body}` : `${drive}${leading === '' ? separator : leading}${body}` } /** @@ -82,25 +126,31 @@ export function terminalCardModel(block: ToolCallBlock, sessionCwd?: string): Te if (!('kind' in block)) { // Running: the call view exists, the result view does not yet. return call === null ? null : { - command: call.title, - cwd: resolveTerminalCwd(call.cwd, sessionCwd), - output: undefined, - exitCode: undefined, - signal: undefined, - running: true, + description: call.description, + card: { + command: call.title, + cwd: resolveTerminalCwd(call.cwd, sessionCwd), + output: undefined, + exitCode: undefined, + signal: undefined, + running: true, + }, } } const result = block.resultView?.card === 'terminal' ? block.resultView : null if (result === null) return null return { - // The result's title REPLACES the pending one when the tool supplies it - // (the presentation contract's replacement-title rule); the call title is - // what a result without one keeps. - command: result.title ?? call?.title ?? '', - cwd: resolveTerminalCwd(call?.cwd, sessionCwd), - output: result.output, - exitCode: result.exitCode, - signal: result.signal, - running: false, + description: call?.description, + card: { + // The result's title REPLACES the pending one when the tool supplies it + // (the presentation contract's replacement-title rule); the call title is + // what a result without one keeps. + command: result.title ?? call?.title ?? '', + cwd: resolveTerminalCwd(call?.cwd, sessionCwd), + output: result.output, + exitCode: result.exitCode, + signal: result.signal, + running: false, + }, } } diff --git a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx index a7add10328..630334eae7 100644 --- a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx @@ -135,7 +135,7 @@ export function DetailsPanel({ useSession, useSessions, sessionId, useStore, clo */ function OutputBody({ material, cwd }: { material: CallMaterial; cwd: string | undefined }) { const terminal = terminalCardModel(material.block, cwd) - if (terminal !== null) return + if (terminal !== null) return // A settled call always carries the result node the flattened form needs; // the running shape has no result to flatten. if (!('kind' in material.block)) return
运行中…
diff --git a/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx b/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx index 6800e79180..1e6e9183fc 100644 --- a/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx +++ b/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx @@ -64,10 +64,12 @@ export function BashRow({ toolName, block, sessionId, useSessions }: ToolRowProp {isChild && scoped} {model.title} - {model.summary} + {/* The terminal presenter's description is the contractual + above-card summary; it outranks the args-derived one. */} + {terminal?.description ?? model.summary}
{terminal !== null && ( - + )}
) diff --git a/packages/client/ui-conversation/tests/terminal-card.spec.tsx b/packages/client/ui-conversation/tests/terminal-card.spec.tsx index 0b3ba5e849..7df9de7f36 100644 --- a/packages/client/ui-conversation/tests/terminal-card.spec.tsx +++ b/packages/client/ui-conversation/tests/terminal-card.spec.tsx @@ -63,8 +63,11 @@ const settled = (over?: Partial): ToolResultNode => ({ describe('terminalCardModel', () => { it('derives a running card from the call view alone', () => { expect(terminalCardModel(running({ callView: callTerminal({ cwd: '/projects/app' }) }))).toEqual({ - command: 'ls -la', cwd: '/projects/app', output: undefined, - exitCode: undefined, signal: undefined, running: true, + description: 'List files', + card: { + command: 'ls -la', cwd: '/projects/app', output: undefined, + exitCode: undefined, signal: undefined, running: true, + }, }) }) @@ -73,12 +76,15 @@ describe('terminalCardModel', () => { callView: callTerminal({ cwd: '/projects/app' }), resultView: resultTerminal({ output: 'boom\n', exitCode: 2 }), }))).toEqual({ - command: 'ls -la', cwd: '/projects/app', output: 'boom\n', - exitCode: 2, signal: undefined, running: false, + description: 'List files', + card: { + command: 'ls -la', cwd: '/projects/app', output: 'boom\n', + exitCode: 2, signal: undefined, running: false, + }, }) expect(terminalCardModel(settled({ resultView: { card: 'terminal', output: '', signal: 'SIGTERM' }, - }))?.signal).toBe('SIGTERM') + }))?.card.signal).toBe('SIGTERM') }) it('takes the result view\'s replacement title over the pending one', () => { @@ -87,30 +93,75 @@ describe('terminalCardModel', () => { expect(terminalCardModel(settled({ callView: callTerminal({ title: 'pnpm run check' }), resultView: resultTerminal({ title: 'pnpm run check --filter web' }), - }))?.command).toBe('pnpm run check --filter web') + }))?.card.command).toBe('pnpm run check --filter web') // Without one, the call's title is what the card keeps. - expect(terminalCardModel(settled())?.command).toBe('ls -la') + expect(terminalCardModel(settled())?.card.command).toBe('ls -la') }) it('resolves the cwd against the session workspace the way the bridge must', () => { // Omitted workdir — the common bash call — IS the session workspace. - expect(terminalCardModel(settled(), '/w/app')?.cwd).toBe('/w/app') + expect(terminalCardModel(settled(), '/w/app')?.card.cwd).toBe('/w/app') // A relative workdir joins under it. expect(terminalCardModel(settled({ callView: callTerminal({ cwd: 'packages/ui' }), - }), '/w/app')?.cwd).toBe('/w/app/packages/ui') + }), '/w/app')?.card.cwd).toBe('/w/app/packages/ui') // An absolute one is used as-is. expect(terminalCardModel(settled({ callView: callTerminal({ cwd: '/srv/other' }), - }), '/w/app')?.cwd).toBe('/srv/other') + }), '/w/app')?.card.cwd).toBe('/srv/other') // With no session cwd there is nothing to resolve against: a relative path // stays as authored and an omitted one stays absent (a bare `$` prompt). expect(terminalCardModel(settled({ callView: callTerminal({ cwd: 'packages/ui' }), - }))?.cwd).toBe('packages/ui') - expect(terminalCardModel(settled())?.cwd).toBeUndefined() + }))?.card.cwd).toBe('packages/ui') + expect(terminalCardModel(settled())?.card.cwd).toBeUndefined() // The running arm resolves identically. - expect(terminalCardModel(running(), '/w/app')?.cwd).toBe('/w/app') + expect(terminalCardModel(running(), '/w/app')?.card.cwd).toBe('/w/app') + }) + + it('normalizes a relative workdir so the label names the directory actually used', () => { + // The bash executor resolves the workdir before running, so `..` against + // /w/app runs in /w — the card must say `w`, not `..`. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '..' }), + }), '/w/app')?.card.cwd).toBe('/w') + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '.' }), + }), '/w/app')?.card.cwd).toBe('/w/app') + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '../sibling' }), + }), '/w/app')?.card.cwd).toBe('/w/sibling') + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: './nested/../other' }), + }), '/w/app')?.card.cwd).toBe('/w/app/other') + // A `..` that would climb past the root is dropped, as a filesystem does. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '../../..' }), + }), '/w')?.card.cwd).toBe('/') + // An absolute path carrying segments normalizes too. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '/srv/./app/../other' }), + }), '/w/app')?.card.cwd).toBe('/srv/other') + // A Windows path keeps its separators. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: 'C:\\ws\\app\\..' }), + }), '/w')?.card.cwd).toBe('C:\\ws') + // Without a session cwd a relative `..` has nothing to resolve against, so + // it survives as authored rather than being silently dropped. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '../elsewhere' }), + }))?.card.cwd).toBe('../elsewhere') + }) + + it('carries the call view\'s description, which the contract renders above the card', () => { + expect(terminalCardModel(settled())?.description).toBe('List files') + expect(terminalCardModel(running())?.description).toBe('List files') + // A presenter that supplies none, and a window-truncated call side, both + // leave it absent so the row keeps its args-derived summary. + expect(terminalCardModel(settled({ + callView: { card: 'terminal', title: 'ls' }, + }))?.description).toBeUndefined() + expect(terminalCardModel(settled({ call: null, callView: null }))?.description).toBeUndefined() }) it('a window-truncated call side falls back to the result title, then to an empty command', () => { @@ -118,8 +169,8 @@ describe('terminalCardModel', () => { const truncated = { call: null, callView: null } expect(terminalCardModel(settled({ ...truncated, resultView: resultTerminal({ title: 'ls -la' }), - }))).toMatchObject({ command: 'ls -la', cwd: undefined, running: false }) - expect(terminalCardModel(settled(truncated))).toMatchObject({ command: '', cwd: undefined }) + }))?.card).toMatchObject({ command: 'ls -la', cwd: undefined, running: false }) + expect(terminalCardModel(settled(truncated))?.card).toMatchObject({ command: '', cwd: undefined }) }) it('returns null for every non-terminal call: no views, generic views, unknown cards', () => { @@ -244,6 +295,23 @@ describe('BashRow terminal card', () => { expect(runStateOf(settledView.container)).toBe('done') }) + it('shows the terminal presenter\'s description instead of the args summary', () => { + // `terminal_send`-style presenters author a description the args do not + // repeat; the contract puts it above the card, which is this row's summary. + const view = render() + expect(view.getByText('Terminal 3')).toBeTruthy() + expect(view.queryByText('List files')).toBeNull() + }) + + it('keeps the args-derived summary when the presenter authored no description', () => { + const view = render() + expect(view.getByText('List files')).toBeTruthy() + }) + it('a non-terminal bash call (background start) renders the summary row alone', () => { const view = render( { expect(pre?.textContent).toBe('permission denied') }) - it('a run_code sub-dispatch resolves to its own terminal card', () => { + // The panel resolves a sub-dispatch through the same material as a native + // call, so a sub-call that DID carry terminal views would render the card. + // The shipped wire cannot produce that yet: `session.ts` folds + // `tool/code-dispatch(-start)` with `callView: null`/`resultView: null`, and + // the host's `viewFor` only presents top-level `tool/call`/`tool/result`. This + // pins the resolution path with views injected directly, and the arm below + // pins what the shipped path actually shows today. + it('a run_code sub-dispatch resolves to its own terminal card once views reach it', () => { const view = mount(snapshot({ codeDispatches: new Map([['p1', [settled({ callId: 'c1' })]]]), }), target) expect(view.getByText('a.ts b.ts', RAW)).toBeTruthy() }) + it('a sub-dispatch as the wire actually delivers it (no views) keeps the flattened form', () => { + const view = mount(snapshot({ + codeDispatches: new Map([['p1', [settled({ callId: 'c1', callView: null, resultView: null })]]]), + }), target) + // No terminal card: the generic path renders the result text in the Output + // section's
 (the Input section has its own, hence the scoping).
+    expect(view.container.querySelector('[data-terminal]')).toBeNull()
+    const output = view.getByText('Output').closest('section')
+    expect(output?.querySelector('pre')?.textContent).toContain('a.ts  b.ts')
+  })
+
   it('a running run_code sub-dispatch resolves through the running material', () => {
     const view = mount(snapshot({
       // The leading non-matching sub-call exercises the scan's skip.

From 0f70886e0c3dfc4afe0f1d3f18e0a6cc892e2b60 Mon Sep 17 00:00:00 2001
From: Chinesezjc 
Date: Wed, 29 Jul 2026 12:10:34 +0800
Subject: [PATCH 11/38] fix(web): label only the first prompt row with the
 working directory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A multi-line command repeated the cwd label on every prompt row, which
states something the view does not know: it carries ONE working directory —
where the call started — and a `cd` in the command moves later lines
elsewhere. `cd ~` then `ls` rendered both rows labelled with the session
workspace while `ls` actually listed the home directory.

The label now appears on the first row only, and later rows keep a bare `$`
so they still read as prompts. Same reasoning as the run-state dot: neither
a per-line directory nor a per-line exit status exists to report.

The built-bundle snapshot records the effect on fixture turn 60's two-line
command (`fixture echo done` becomes `$ echo done`).
---
 .../feature/2026-07-28-web-terminal-card.i18n.yaml     |  4 ++--
 .../feature/2026-07-28-web-terminal-card.md            |  2 +-
 .../feature/2026-07-28-web-terminal-card.zh.md         |  2 +-
 apps/web/tests/terminal-card.snapshot.ts               |  2 +-
 packages/client/ui-primitives/README.i18n.yaml         |  4 ++--
 packages/client/ui-primitives/README.md                |  2 +-
 packages/client/ui-primitives/README.zh.md             |  2 +-
 packages/client/ui-primitives/src/TerminalBlock.tsx    | 10 +++++++++-
 .../client/ui-primitives/tests/terminal-block.spec.tsx |  8 ++++++++
 9 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml
index 022c4f84ed..0f5c43ff36 100644
--- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
-2026-07-28-web-terminal-card.md: 8e4701b49373af3495c6f424c4ae2777f5bfcb75
-2026-07-28-web-terminal-card.zh.md: 07341ca942864281390f3820db88388fd61cef0e
+2026-07-28-web-terminal-card.md: 4bf5ee4e7899dceacbc56aced3289647ee42cd82
+2026-07-28-web-terminal-card.zh.md: a7baf5a84364994e938f7c12c368c8202832544a
diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
index 8e4701b493..4bf5ee4e78 100644
--- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
+++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
@@ -16,7 +16,7 @@ The Web client ignored it. `packages/client/ui-conversation/src/client/contract/
 
 The component's contract:
 
-- **Prompt lines, one per command line.** Each line of the command gets its own row: label, then that line verbatim. A `command` carrying two shell commands on two lines therefore reads as the two commands it is, instead of collapsing into one ellipsized row. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. A trailing newline is a terminator, not an empty final command.
+- **Prompt lines, one per command line.** Each line of the command gets its own row: label, then that line verbatim. A `command` carrying two shell commands on two lines therefore reads as the two commands it is, instead of collapsing into one ellipsized row. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. A trailing newline is a terminator, not an empty final command. Only the FIRST row carries the label: the view knows one working directory — where the call started — and a later line may run somewhere else entirely, since a `cd` in the command is enough to move it. Repeating the label down the rows would state a directory per line that nothing here knows, which is the same reason the run-state dot appears once. Later rows keep a bare `$` so they still read as prompts.
 - **One run-state dot for the call, on the first row.** `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. The dot exists because the first question a reader has about a shell command is whether it is still running, and without it that had to be inferred from the absence of output — which a settled command producing no output also looks like. It sits out of flow in a gutter reserved to the left of the card surface, so it neither indents its command nor depends on the command's own text metrics to line up with it. Exactly one dot, whatever the line count: the exit status the view carries is the whole call's, and bash reports no per-command status, so a dot per line would assert of a line that succeeded inside a failing call that the line itself failed. The single visually hidden text label carries the same scope, since `StateDot` is `aria-hidden` and one label per row would read to assistive technology as several distinct outcomes.
 - **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding.
 - **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends.
diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md
index 07341ca942..a7baf5a843 100644
--- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md
+++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md
@@ -16,7 +16,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c
 
 该组件的契约:
 
-- **提示符行,每条命令行一行。** 命令的每一行各占一行:标签,其后原样跟随该行。因此一个在两行上承载两条 shell 命令的 `command` 就读作它本身的两条命令,而不是被压成一行并省略号截断。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。末尾换行是终止符,不是一条空的末命令。
+- **提示符行,每条命令行一行。** 命令的每一行各占一行:标签,其后原样跟随该行。因此一个在两行上承载两条 shell 命令的 `command` 就读作它本身的两条命令,而不是被压成一行并省略号截断。标签取 cwd 的最后一段路径,当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`,因此由调用方提供绝对家目录,不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。末尾换行是终止符,不是一条空的末命令。只有**第一行**携带该标签:视图只知道一个工作目录——调用开始处的那个——而后面的行完全可能在别处运行,命令里一个 `cd` 就足以改变它。把标签在各行重复,等于陈述一个此处无人知晓的逐行目录,这与运行状态点只出现一次是同一个理由。其余行保留一个裸 `$`,因此它们仍读作提示符。
 - **整次调用一枚运行状态点,位于第一行。** 它是 `StateDot` 四种状态中的三种:运行期间为追逐动画,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。该状态点存在的理由是:读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有它时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。它以脱离文档流的方式落在卡片表面左侧预留的落区里,因此既不会缩进其命令,也不依赖命令自身的文本度量来与之对齐。无论有多少行,都只有一枚:视图携带的退出状态属于整次调用,而 bash 不报告逐条命令的状态,因此每行一枚状态点就等于在断言——一条在失败调用中其实成功了的命令行自身失败了。那一处视觉隐藏的文本标签具有相同的作用域,因为 `StateDot` 是 `aria-hidden`,而每行一个标签会被辅助技术读成好几个各自独立的结果。
 - **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。
 - **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。
diff --git a/apps/web/tests/terminal-card.snapshot.ts b/apps/web/tests/terminal-card.snapshot.ts
index 0154a3d7fd..82d94b251d 100644
--- a/apps/web/tests/terminal-card.snapshot.ts
+++ b/apps/web/tests/terminal-card.snapshot.ts
@@ -264,7 +264,7 @@ it('the fallback row reaches the same card through its expand control', async ()
       ],
       "prompt": [
         "fixture ls -la",
-        "fixture echo done",
+        "$ echo done",
       ],
       "runState": "done",
       "runStateLabel": "已完成",
diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml
index 772851ea82..ad22a9f734 100644
--- a/packages/client/ui-primitives/README.i18n.yaml
+++ b/packages/client/ui-primitives/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-primitives/README.md
-README.md: 5d71aa920707462f953ed4eb5572b0530b8d0ed2
-README.zh.md: 7c59ed3d3bacbac06a0123e6ff93023a1bcbd028
+README.md: 4222aac4fa1d9c89a3d3c702ee8391fba1eef178
+README.zh.md: e7a5b5ad57048bc59872963b0068c6f88fc772f8
diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md
index 5d71aa9207..4222aac4fa 100644
--- a/packages/client/ui-primitives/README.md
+++ b/packages/client/ui-primitives/README.md
@@ -10,7 +10,7 @@ Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/
 
 ## Terminal output
 
-`TerminalBlock` renders a shell command as a terminal surface: one prompt row per line of the command (the shortened `cwd` label, then that line), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. A run-state `StateDot` marks the call once, on the first row, out of flow in a gutter to the left of the card surface. It reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries one visually hidden text label because `StateDot` is `aria-hidden`. One dot regardless of line count is deliberate: the exit status is the whole call's, so a dot per line would claim a per-line outcome the view does not carry. Command text is `white-space: pre`, so repeated spaces, tabs, and an indented continuation render verbatim while the row stays single-line and ellipsizes. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; carriage-return redraws and backspace overwrites resolve as a terminal performs them before inert controls are stripped; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md).
+`TerminalBlock` renders a shell command as a terminal surface: one prompt row per line of the command (the shortened `cwd` label on the first row only, since the view knows one working directory and a `cd` moves later lines elsewhere, then that line), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. A run-state `StateDot` marks the call once, on the first row, out of flow in a gutter to the left of the card surface. It reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries one visually hidden text label because `StateDot` is `aria-hidden`. One dot regardless of line count is deliberate: the exit status is the whole call's, so a dot per line would claim a per-line outcome the view does not carry. Command text is `white-space: pre`, so repeated spaces, tabs, and an indented continuation render verbatim while the row stays single-line and ellipsizes. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; carriage-return redraws and backspace overwrites resolve as a terminal performs them before inert controls are stripped; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md).
 
 ## Model Experience
 
diff --git a/packages/client/ui-primitives/README.zh.md b/packages/client/ui-primitives/README.zh.md
index 7c59ed3d3b..e7a5b5ad57 100644
--- a/packages/client/ui-primitives/README.zh.md
+++ b/packages/client/ui-primitives/README.zh.md
@@ -10,7 +10,7 @@
 
 ## 终端输出
 
-`TerminalBlock` 将一条 shell 命令渲染为终端表层:命令的每一行各占一个提示行(缩短后的 `cwd` 标签,其后是该行)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。一枚运行状态 `StateDot` 为整次调用标记一次,位于第一行,以脱离文档流的方式落在卡片表面左侧的落区中。它用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它携带一处视觉隐藏的文本标签。无论多少行都只有一枚状态点是有意为之:退出状态属于整次调用,因此每行一枚就会声称一个视图并不携带的逐行结果。命令文本使用 `white-space: pre`,因此重复空格、制表符与缩进续行都原样呈现,同时该行仍保持单行并以省略号截断。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;回车重绘与退格覆盖会按终端的行为先行结算,之后才剥除无显示意义的控制符;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。
+`TerminalBlock` 将一条 shell 命令渲染为终端表层:命令的每一行各占一个提示行(缩短后的 `cwd` 标签只出现在第一行,因为视图只知道一个工作目录,而一个 `cd` 就会让后面的行去到别处,标签之后是该行)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。一枚运行状态 `StateDot` 为整次调用标记一次,位于第一行,以脱离文档流的方式落在卡片表面左侧的落区中。它用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它携带一处视觉隐藏的文本标签。无论多少行都只有一枚状态点是有意为之:退出状态属于整次调用,因此每行一枚就会声称一个视图并不携带的逐行结果。命令文本使用 `white-space: pre`,因此重复空格、制表符与缩进续行都原样呈现,同时该行仍保持单行并以省略号截断。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;回车重绘与退格覆盖会按终端的行为先行结算,之后才剥除无显示意义的控制符;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。
 
 ## 模型体验
 
diff --git a/packages/client/ui-primitives/src/TerminalBlock.tsx b/packages/client/ui-primitives/src/TerminalBlock.tsx
index 3ae7ca7113..0932f4a7f0 100644
--- a/packages/client/ui-primitives/src/TerminalBlock.tsx
+++ b/packages/client/ui-primitives/src/TerminalBlock.tsx
@@ -174,7 +174,15 @@ export function TerminalBlock({
                   per-command status, so a dot per row would assert a
                   per-line outcome nothing here knows. */}
               {index === 0 && }
-              {cwd === undefined ? '$' : promptLabel(cwd, home)}
+              {/* The cwd labels the CALL, so only its first row carries it. The
+                  view knows one working directory — where the call started —
+                  and a later line may well run somewhere else (a `cd` in the
+                  command is enough), so repeating the label down the rows would
+                  assert a directory per line that nothing here knows. Later
+                  rows keep a bare `$` to stay aligned as prompts. */}
+              
+                {index > 0 || cwd === undefined ? '$' : promptLabel(cwd, home)}
+              
               {line}
             
))} diff --git a/packages/client/ui-primitives/tests/terminal-block.spec.tsx b/packages/client/ui-primitives/tests/terminal-block.spec.tsx index 74352f6fba..d1162fcb7f 100644 --- a/packages/client/ui-primitives/tests/terminal-block.spec.tsx +++ b/packages/client/ui-primitives/tests/terminal-block.spec.tsx @@ -212,6 +212,14 @@ describe('TerminalBlock run-state dot', () => { expect([...row!.children].map(node => node.textContent)).toEqual(['', 'app', 'ls']) }) + // The cwd labels the call, not each line: a `cd` in the command moves later + // lines elsewhere, so repeating the label would state a directory per line + // that the view does not know. + it('labels only the first row with the cwd, leaving later rows a bare $', () => { + const view = render() + expect(promptRows(view.container)).toEqual(['appcd ~', '$ls']) + }) + it('gives a multi-line command one row per line', () => { const view = render() expect(promptRows(view.container)).toEqual(['$echo one', '$echo two']) From bbe1481a9ecd4b4d85dc4954b343696b534c4d49 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Wed, 29 Jul 2026 13:10:44 +0800 Subject: [PATCH 12/38] fix(web): keep escapes, UNC roots, and truncated cwd honest MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Four review findings. Two are defects the previous two rounds introduced, which the existing tests did not catch: A backspace erased raw bytes, so one landing after an SGR reset ate part of the escape: `\x1b[31mabc\x1b[0m\b\bXY` left `\x1b[` and repainted the rest of the line with whatever the remainder parsed as. Backspaces now resolve over VISIBLE characters — a CSI sequence is one indivisible unit a backspace steps over on its way to the last printed character, so the surviving text keeps the color its run authored. The cwd normalizer popped a UNC share root: `\\server\share` with a `..` became `/server`, losing the separators too. A UNC path's server and share are its root, and Windows cannot climb above a share, so they are split off and the remainder collapses against that root. The other two are gaps the earlier fixes left: The render-site fallback row still passed the args-derived summary, so any terminal-declaring tool without its own keyed row (`terminal_send`) lost the contract's above-card description. It now prefers the description exactly as BashRow does. A settled call read `call?.cwd`, which cannot tell "the call omitted a cwd" from "the paging window dropped the call head". The second case has no cwd anywhere and the original call may have used an explicit workdir, so it now draws a bare `$` instead of naming the session workspace. --- .../2026-07-28-web-terminal-card.i18n.yaml | 4 +- .../feature/2026-07-28-web-terminal-card.md | 4 +- .../2026-07-28-web-terminal-card.zh.md | 4 +- .../src/client/chat/GenericToolCard.tsx | 7 ++- .../client/contract/terminal-card-model.ts | 53 +++++++++++++++---- .../tests/terminal-card.spec.tsx | 36 +++++++++++++ packages/client/ui-primitives/src/ansi.ts | 49 ++++++++++++++--- .../client/ui-primitives/tests/ansi.spec.ts | 18 +++++++ 8 files changed, 150 insertions(+), 25 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml index 0f5c43ff36..0d805c8de0 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md -2026-07-28-web-terminal-card.md: 4bf5ee4e7899dceacbc56aced3289647ee42cd82 -2026-07-28-web-terminal-card.zh.md: a7baf5a84364994e938f7c12c368c8202832544a +2026-07-28-web-terminal-card.md: 87cb40331bca6a1bfcdd4e8ecd9bbe69c6572be0 +2026-07-28-web-terminal-card.zh.md: ab5a35d6f76427cf1e0338d8491bd3485cb41302 diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md index 4bf5ee4e78..87cb40331b 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md @@ -12,7 +12,7 @@ The Web client ignored it. `packages/client/ui-conversation/src/client/contract/ ## Decision -`TerminalBlock` is a `ui-primitives` component that renders a shell command as a terminal surface, and both Web render sites for a bash call consume the terminal render intent through it: the chat tool row's expanded body and the details panel's Output section. `ui-conversation/src/client/contract/terminal-card-model.ts` is the single place that turns the snapshot's `callView`/`resultView` pair into the component's props, so the two sites cannot disagree about a command, its cwd, or its exit status. It returns null — the generic path — whenever neither side declares `card: 'terminal'`, including a `card` value this client version does not know, and whenever a settled call's result view is generic, which is how the bash tool's execution errors and background starts keep their existing rendering. Two duties the render-intent contract assigns to the UI bridge land here rather than in the tool: a settled result's `title` REPLACES the pending one, and the working directory resolves against the session workspace — an absolute view cwd is used as-is, a relative one joins under the workspace, and an omitted one IS the workspace, which is the common case for a bash call with no `workdir`. A pure presenter cannot see the session cwd, which is why the resolution belongs at this seam; each render site supplies the cwd off the session list row. The resolved path also normalizes its `.`/`..` segments, because the bash executor resolves the workdir before running: a `..` against `/w/app` runs in `/w`, so the prompt label has to read `w` rather than `..`. The call view's `description` rides the same derivation, since the contract renders it above the card and it must outrank the row's args-derived summary. +`TerminalBlock` is a `ui-primitives` component that renders a shell command as a terminal surface, and both Web render sites for a bash call consume the terminal render intent through it: the chat tool row's expanded body and the details panel's Output section. `ui-conversation/src/client/contract/terminal-card-model.ts` is the single place that turns the snapshot's `callView`/`resultView` pair into the component's props, so the two sites cannot disagree about a command, its cwd, or its exit status. It returns null — the generic path — whenever neither side declares `card: 'terminal'`, including a `card` value this client version does not know, and whenever a settled call's result view is generic, which is how the bash tool's execution errors and background starts keep their existing rendering. Two duties the render-intent contract assigns to the UI bridge land here rather than in the tool: a settled result's `title` REPLACES the pending one, and the working directory resolves against the session workspace — an absolute view cwd is used as-is, a relative one joins under the workspace, and an omitted one IS the workspace, which is the common case for a bash call with no `workdir`. A pure presenter cannot see the session cwd, which is why the resolution belongs at this seam; each render site supplies the cwd off the session list row. Only a PRESENT call view can mean "omitted, so use the workspace": when the paging window drops the call head there is no cwd anywhere — the result view carries none — and the original call may have used an explicit workdir, so the prompt draws a bare `$` rather than naming a directory it cannot know. The resolved path also normalizes its `.`/`..` segments, because the bash executor resolves the workdir before running: a `..` against `/w/app` runs in `/w`, so the prompt label has to read `w` rather than `..`. A UNC path's `server` and `share` are part of its root rather than poppable segments, since Windows cannot climb above a share. The call view's `description` rides the same derivation, since the contract renders it above the card and it must outrank the row's args-derived summary. The component's contract: @@ -20,7 +20,7 @@ The component's contract: - **One run-state dot for the call, on the first row.** `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. The dot exists because the first question a reader has about a shell command is whether it is still running, and without it that had to be inferred from the absence of output — which a settled command producing no output also looks like. It sits out of flow in a gutter reserved to the left of the card surface, so it neither indents its command nor depends on the command's own text metrics to line up with it. Exactly one dot, whatever the line count: the exit status the view carries is the whole call's, and bash reports no per-command status, so a dot per line would assert of a line that succeeded inside a failing call that the line itself failed. The single visually hidden text label carries the same scope, since `StateDot` is `aria-hidden` and one label per row would read to assistive technology as several distinct outcomes. - **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding. - **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends. -- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Two cursor movements resolve before that strip, because their effect on the visible text has to land before the characters expressing them are dropped: a carriage return reduces its line to the final redraw, and a backspace overwrites the character before it, so `abc` followed by two backspaces and `XY` reads `aXY` as a terminal draws it. Both are per-line, so neither reaches across a newline. +- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Two cursor movements resolve before that strip, because their effect on the visible text has to land before the characters expressing them are dropped: a carriage return reduces its line to the final redraw, and a backspace overwrites the character before it, so `abc` followed by two backspaces and `XY` reads `aXY` as a terminal draws it. Both are per-line, so neither reaches across a newline. A backspace steps over CSI sequences rather than erasing their bytes: a sequence moves no cursor, and eating part of one would corrupt it and repaint everything after with whatever the mangled remainder parses as, so it walks back to the last PRINTED character and drops that instead — the surviving text keeps the color its run authored. - **Exit status and copy.** A non-zero exit code or a signal renders a status pill, matching the exit-status distinction the bash tool's own renderer draws; a clean exit renders none, and settled empty output renders a dimmed placeholder. The copy control copies the raw output text, not the rendered tree, so the prompt line and the pill stay out of the clipboard. Geometry, radius, and fonts mirror `CodeBlock`, so a terminal card and a fenced code block match visually; `white-space: pre` plus horizontal scroll is the deliberate divergence. The clipboard write both components need moved out of `CodeBlock` into a package-internal `src/clipboard.ts`, unexported so it stays an implementation detail of the two blocks. diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md index a7baf5a843..ab5a35d6f7 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md @@ -12,7 +12,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c ## Decision -`TerminalBlock` 是 `ui-primitives` 中把 shell 命令渲染为终端表面的组件,bash 调用在 Web 侧的两个渲染点都经由它消费 terminal 渲染意图:聊天工具行展开后的正文,以及详情面板的 Output 区。`ui-conversation/src/client/contract/terminal-card-model.ts` 是把快照上的 `callView`/`resultView` 这一对转换为该组件 props 的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧。当两侧都不声明 `card: 'terminal'` 时它返回 null,即走 generic 路径——包括本 client 版本不认识的 `card` 取值;当一个已落定调用的结果视图是 generic 时同样返回 null,这正是 bash 工具的执行错误与后台启动得以保持既有渲染的方式。渲染意图契约交给 UI 桥接层的两项职责也落在这里,而不在工具侧:已落定结果的 `title` **替换**待定标题;工作目录针对会话 workspace 解析——视图给出的绝对路径原样使用,相对路径在 workspace 之下拼接,省略则**就是** workspace,而这正是不带 `workdir` 的 bash 调用的常见情形。纯 presenter 看不到会话 cwd,因此该解析属于这道接缝;两个渲染点各自从会话列表行取出 cwd 传入。解析后的路径还会归一化其 `.`/`..` 段,因为 bash 执行器在运行前就已解析 workdir:相对 `/w/app` 的 `..` 实际运行在 `/w`,因此提示标签必须读作 `w` 而不是 `..`。调用视图的 `description` 走同一处推导,因为契约把它渲染在卡片上方,且它必须优先于该行由参数推导出的摘要。 +`TerminalBlock` 是 `ui-primitives` 中把 shell 命令渲染为终端表面的组件,bash 调用在 Web 侧的两个渲染点都经由它消费 terminal 渲染意图:聊天工具行展开后的正文,以及详情面板的 Output 区。`ui-conversation/src/client/contract/terminal-card-model.ts` 是把快照上的 `callView`/`resultView` 这一对转换为该组件 props 的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧。当两侧都不声明 `card: 'terminal'` 时它返回 null,即走 generic 路径——包括本 client 版本不认识的 `card` 取值;当一个已落定调用的结果视图是 generic 时同样返回 null,这正是 bash 工具的执行错误与后台启动得以保持既有渲染的方式。渲染意图契约交给 UI 桥接层的两项职责也落在这里,而不在工具侧:已落定结果的 `title` **替换**待定标题;工作目录针对会话 workspace 解析——视图给出的绝对路径原样使用,相对路径在 workspace 之下拼接,省略则**就是** workspace,而这正是不带 `workdir` 的 bash 调用的常见情形。纯 presenter 看不到会话 cwd,因此该解析属于这道接缝;两个渲染点各自从会话列表行取出 cwd 传入。只有**存在**的调用视图才能表示「省略了 cwd,因此取 workspace」:当分页窗口丢掉调用头时,任何地方都不再有 cwd——结果视图并不携带它——而原调用完全可能使用过一个显式 workdir,因此提示行绘制一个裸 `$`,而不是命名一个它无法知晓的目录。解析后的路径还会归一化其 `.`/`..` 段,因为 bash 执行器在运行前就已解析 workdir:相对 `/w/app` 的 `..` 实际运行在 `/w`,因此提示标签必须读作 `w` 而不是 `..`。UNC 路径的 `server` 与 `share` 属于其根,而非可弹出的路径段,因为 Windows 无法越过一个共享向上。调用视图的 `description` 走同一处推导,因为契约把它渲染在卡片上方,且它必须优先于该行由参数推导出的摘要。 该组件的契约: @@ -20,7 +20,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c - **整次调用一枚运行状态点,位于第一行。** 它是 `StateDot` 四种状态中的三种:运行期间为追逐动画,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。该状态点存在的理由是:读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有它时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。它以脱离文档流的方式落在卡片表面左侧预留的落区里,因此既不会缩进其命令,也不依赖命令自身的文本度量来与之对齐。无论有多少行,都只有一枚:视图携带的退出状态属于整次调用,而 bash 不报告逐条命令的状态,因此每行一枚状态点就等于在断言——一条在失败调用中其实成功了的命令行自身失败了。那一处视觉隐藏的文本标签具有相同的作用域,因为 `StateDot` 是 `aria-hidden`,而每行一个标签会被辅助技术读成好几个各自独立的结果。 - **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。 - **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。 -- **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM。两种光标移动在该剥除之前先行结算,因为它们对可见文本的作用必须先落地,之后才能丢弃表达它们的那些字符:回车把所在行归约为最后一次重绘,退格覆盖它前面的字符——于是 `abc` 后接两个退格再接 `XY` 读作 `aXY`,与终端的绘制一致。两者都按行结算,因此都不会跨越换行。 +- **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM。两种光标移动在该剥除之前先行结算,因为它们对可见文本的作用必须先落地,之后才能丢弃表达它们的那些字符:回车把所在行归约为最后一次重绘,退格覆盖它前面的字符——于是 `abc` 后接两个退格再接 `XY` 读作 `aXY`,与终端的绘制一致。两者都按行结算,因此都不会跨越换行。退格会跨过 CSI 序列,而不是擦掉它的字节:序列本身不移动光标,吃掉它的一部分会破坏该序列,并让其后的一切按被损坏的残余重新着色,因此退格回退到最后一个**已打印**字符并删除它——存活下来的文本保留其所在分段所声明的颜色。 - **退出状态与复制。** 非零退出码或信号渲染一枚状态徽章,与 bash 工具自身渲染器所作的退出状态区分一致;干净退出不渲染徽章,落定后的空输出渲染一处变暗的占位文字。复制控件复制的是原始输出文本而非渲染后的树,因此提示符行与徽章不会进入剪贴板。 几何尺寸、圆角与字体沿用 `CodeBlock`,因此终端卡片与围栏代码块在视觉上一致;`white-space: pre` 加横向滚动是有意的分歧。两个组件都需要的剪贴板写入从 `CodeBlock` 中提取到包内部的 `src/clipboard.ts`,不对外导出,因此它仍是这两个块的实现细节。 diff --git a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx index 5b93d66e32..ce55d84f57 100644 --- a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx +++ b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx @@ -28,6 +28,7 @@ const VARIANT_ICONS: Record = { export function GenericToolCard({ toolName, block, cwd, openFile }: ToolRowOwnerProps) { const model = toolRowModel(toolName, block, cwd) + const terminal = terminalCardModel(block, cwd) const singleFile = model.filePath !== undefined return ( 0 && kept[kept.length - 1] !== '..') kept.pop() - else if (leading === '' && drive === '') kept.push(segment) + else if (!rooted) kept.push(segment) continue } kept.push(segment) } - const body = kept.join(separator) - return drive === '' ? `${leading}${body}` : `${drive}${leading === '' ? separator : leading}${body}` + return kept.join(separator) } /** @@ -146,7 +174,12 @@ export function terminalCardModel(block: ToolCallBlock, sessionCwd?: string): Te // (the presentation contract's replacement-title rule); the call title is // what a result without one keeps. command: result.title ?? call?.title ?? '', - cwd: resolveTerminalCwd(call?.cwd, sessionCwd), + // Only a PRESENT call view can mean "omitted the cwd, so use the + // workspace". When the window dropped the call head there is no cwd + // anywhere — the result view carries none — and the original call may + // well have used an explicit workdir, so the prompt draws a bare `$` + // rather than naming a directory this card cannot know. + cwd: call === null ? undefined : resolveTerminalCwd(call.cwd, sessionCwd), output: result.output, exitCode: result.exitCode, signal: result.signal, diff --git a/packages/client/ui-conversation/tests/terminal-card.spec.tsx b/packages/client/ui-conversation/tests/terminal-card.spec.tsx index 7df9de7f36..dd096c6e91 100644 --- a/packages/client/ui-conversation/tests/terminal-card.spec.tsx +++ b/packages/client/ui-conversation/tests/terminal-card.spec.tsx @@ -153,6 +153,32 @@ describe('terminalCardModel', () => { }))?.card.cwd).toBe('../elsewhere') }) + it('keeps a UNC server and share as an unpoppable root', () => { + // Windows cannot climb above a share, so `..` from the share root stays put. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '..' }), + }), '\\\\server\\share')?.card.cwd).toBe('\\\\server\\share') + // Below the share it pops normally, keeping the UNC separators. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '..' }), + }), '\\\\server\\share\\app')?.card.cwd).toBe('\\\\server\\share') + // Several `..` cannot escape the root either. + expect(terminalCardModel(settled({ + callView: callTerminal({ cwd: '../../..' }), + }), '\\\\server\\share\\app')?.card.cwd).toBe('\\\\server\\share') + }) + + it('draws a bare $ when the window dropped the call head, rather than guessing', () => { + // A truncated call carries no cwd anywhere: the result view has none, and + // the original call may have used an explicit workdir. Falling back to the + // session workspace here would name a directory the card cannot know. + expect(terminalCardModel(settled({ + call: null, callView: null, resultView: resultTerminal({ title: 'ls -la' }), + }), '/w/app')?.card.cwd).toBeUndefined() + // A present call view that omits its cwd still means the workspace. + expect(terminalCardModel(settled(), '/w/app')?.card.cwd).toBe('/w/app') + }) + it('carries the call view\'s description, which the contract renders above the card', () => { expect(terminalCardModel(settled())?.description).toBe('List files') expect(terminalCardModel(running())?.description).toBe('List files') @@ -231,6 +257,16 @@ describe('chat row terminal body', () => { expect(view.container.querySelectorAll('[data-terminal] [data-state]')).toHaveLength(1) }) + it('the fallback row shows the presenter description, not the args summary', () => { + // Any terminal-declaring tool without its own keyed row lands here, so the + // contract's above-card description has to win at this render site as well. + const view = render() + expect(view.getByText('Terminal 3')).toBeTruthy() + expect(view.queryByText('List files')).toBeNull() + }) + it('a running terminal call expands to the prompt line with no output yet', () => { const view = render() fireEvent.click(view.container.querySelector('button')!) diff --git a/packages/client/ui-primitives/src/ansi.ts b/packages/client/ui-primitives/src/ansi.ts index bf05d0d2c8..115d3faffc 100644 --- a/packages/client/ui-primitives/src/ansi.ts +++ b/packages/client/ui-primitives/src/ansi.ts @@ -114,14 +114,49 @@ function applyCarriageReturns(text: string): string { */ function applyBackspaces(text: string): string { if (!text.includes('\u0008')) return text - return text.split('\n').map((line) => { - const kept: string[] = [] - for (const char of line) { - if (char === '\u0008') kept.pop() - else kept.push(char) + return text.split('\n').map(applyBackspacesToLine).join('\n') +} + +/** + * One line's backspaces, resolved over VISIBLE characters only. A CSI sequence + * moves no cursor, so it must survive intact: erasing its bytes would corrupt + * the sequence and repaint the rest of the output with whatever the mangled + * remainder parses as. The sequences are therefore held as indivisible units + * that a backspace steps over on its way to the last printed character, and a + * unit already erased stays erased so a run's own color still applies to what + * remains of it. + * @param line - one output line, still carrying its CSI sequences. + * @returns the line with each backspace applied to the character before it. + */ +function applyBackspacesToLine(line: string): string { + if (!line.includes('\u0008')) return line + const units: { text: string; visible: boolean }[] = [] + // Same shape anser splits on: CSI ... final byte. Matched here so a sequence + // is one unit rather than a run of erasable characters. + const csi = /\u001b\[[\u0030-\u003f]*[\u0020-\u002f]*[\u0040-\u007e]/g + let at = 0 + for (const match of line.matchAll(csi)) { + for (const char of line.slice(at, match.index)) units.push({ text: char, visible: true }) + units.push({ text: match[0], visible: false }) + at = match.index + match[0].length + } + for (const char of line.slice(at)) units.push({ text: char, visible: true }) + + const kept: { text: string; visible: boolean }[] = [] + for (const unit of units) { + if (unit.visible && unit.text === '\u0008') { + // Walk back past any escapes to the last printed character and drop it, + // keeping those escapes so the surviving text stays styled as authored. + for (let index = kept.length - 1; index >= 0; index--) { + if (kept[index]?.visible !== true) continue + kept.splice(index, 1) + break + } + continue } - return kept.join('') - }).join('\n') + kept.push(unit) + } + return kept.map(unit => unit.text).join('') } /** diff --git a/packages/client/ui-primitives/tests/ansi.spec.ts b/packages/client/ui-primitives/tests/ansi.spec.ts index 0fd4f6391e..76af75a565 100644 --- a/packages/client/ui-primitives/tests/ansi.spec.ts +++ b/packages/client/ui-primitives/tests/ansi.spec.ts @@ -184,6 +184,24 @@ describe('parseAnsiLines: backspaces', () => { ]) }) + it('steps over an SGR sequence instead of erasing its bytes', () => { + // `abc` reset then two backspaces then `XY`: erasing the reset's bytes would + // corrupt it and repaint the rest of the line with whatever the remainder + // parses as. The visible result is `aXY`, still red, with the reset intact. + expect(parseAnsiLines(`${sgr('31', 'abc')}${BS}${BS}XY`)).toEqual([[ + { text: 'a', style: { color: 'var(--dsw-alias-state-error-primary)' } }, + { text: 'XY', style: undefined }, + ]]) + }) + + it('erases across a style boundary without dropping the styles between', () => { + // The backspace reaches back past the reset to the last printed character. + expect(parseAnsiLines(`${sgr('32', 'ok')}${ESC}[31m${BS}bad`)).toEqual([[ + { text: 'o', style: { color: 'var(--dsw-alias-state-success-primary)' } }, + { text: 'bad', style: { color: 'var(--dsw-alias-state-error-primary)' } }, + ]]) + }) + it('applies the overwrite after a carriage-return redraw, not before', () => { // The redraw wins first; the backspace then erases inside what survived. expect(onlySpan(`old\rnew${BS}`)).toEqual({ text: 'ne', style: undefined }) From f378873b22e8142c8625f42664f5cc3eee93cca4 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Wed, 29 Jul 2026 14:39:21 +0800 Subject: [PATCH 13/38] fix(web): replay cursor movements the way a terminal paints them MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Carriage return and backspace only MOVE the cursor; neither erases. Both of my earlier approximations were wrong, and I checked each case against a real terminal rather than reasoning about it: `100%\rOK` shows `OK0%`, not `OK` — the redraw is shorter than the frame beneath it, so the tail stands. `abc\b` still shows `abc`, not `ab` — a trailing backspace has nothing to overwrite. `\x1b[31mgone\rkept` paints `kept` RED, because a carriage return does not reset the graphic state, which one of my own tests had asserted the opposite of. Both now replay into a per-line column buffer with SGR state stamped per column, as a terminal stores it per cell. That gives the partial-overwrite case its real result too: red `bad`, three backspaces, then `ok` shows `okd` with the `d` still red, since `ok` reached only two of the three cells. The presenter description now also renders at every site. An expanded row draws it itself — the collapsed summary is hidden while open, so otherwise the description was visible only collapsed, the opposite of "above the card" — and the details panel draws it above the card as well. Three of my own tests encoded the wrong semantics and were corrected with their behavior, and the emit loop's gap-filling arm was removed as unreachable: `\r` and backspace only move left, so no column can be unwritten. --- .../2026-07-28-web-terminal-card.i18n.yaml | 4 +- .../feature/2026-07-28-web-terminal-card.md | 4 +- .../2026-07-28-web-terminal-card.zh.md | 4 +- .../src/client/chat/ToolRow.module.css | 8 ++ .../src/client/chat/ToolRow.tsx | 6 + .../client/skeleton/DetailsPanel.module.css | 8 ++ .../src/client/skeleton/DetailsPanel.tsx | 13 +- .../tests/terminal-card.spec.tsx | 24 ++++ .../client/ui-primitives/README.i18n.yaml | 4 +- packages/client/ui-primitives/README.md | 2 +- packages/client/ui-primitives/README.zh.md | 2 +- packages/client/ui-primitives/src/ansi.ts | 136 +++++++++--------- .../client/ui-primitives/tests/ansi.spec.ts | 52 +++++-- 13 files changed, 182 insertions(+), 85 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml index 0d805c8de0..6927b58937 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md -2026-07-28-web-terminal-card.md: 87cb40331bca6a1bfcdd4e8ecd9bbe69c6572be0 -2026-07-28-web-terminal-card.zh.md: ab5a35d6f76427cf1e0338d8491bd3485cb41302 +2026-07-28-web-terminal-card.md: 284c91cc936c1e757f20f0d0d8afbe4b4c0afc42 +2026-07-28-web-terminal-card.zh.md: 3ffcf232942eed883f44da583c68455715d347ce diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md index 87cb40331b..284c91cc93 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md @@ -12,7 +12,7 @@ The Web client ignored it. `packages/client/ui-conversation/src/client/contract/ ## Decision -`TerminalBlock` is a `ui-primitives` component that renders a shell command as a terminal surface, and both Web render sites for a bash call consume the terminal render intent through it: the chat tool row's expanded body and the details panel's Output section. `ui-conversation/src/client/contract/terminal-card-model.ts` is the single place that turns the snapshot's `callView`/`resultView` pair into the component's props, so the two sites cannot disagree about a command, its cwd, or its exit status. It returns null — the generic path — whenever neither side declares `card: 'terminal'`, including a `card` value this client version does not know, and whenever a settled call's result view is generic, which is how the bash tool's execution errors and background starts keep their existing rendering. Two duties the render-intent contract assigns to the UI bridge land here rather than in the tool: a settled result's `title` REPLACES the pending one, and the working directory resolves against the session workspace — an absolute view cwd is used as-is, a relative one joins under the workspace, and an omitted one IS the workspace, which is the common case for a bash call with no `workdir`. A pure presenter cannot see the session cwd, which is why the resolution belongs at this seam; each render site supplies the cwd off the session list row. Only a PRESENT call view can mean "omitted, so use the workspace": when the paging window drops the call head there is no cwd anywhere — the result view carries none — and the original call may have used an explicit workdir, so the prompt draws a bare `$` rather than naming a directory it cannot know. The resolved path also normalizes its `.`/`..` segments, because the bash executor resolves the workdir before running: a `..` against `/w/app` runs in `/w`, so the prompt label has to read `w` rather than `..`. A UNC path's `server` and `share` are part of its root rather than poppable segments, since Windows cannot climb above a share. The call view's `description` rides the same derivation, since the contract renders it above the card and it must outrank the row's args-derived summary. +`TerminalBlock` is a `ui-primitives` component that renders a shell command as a terminal surface, and both Web render sites for a bash call consume the terminal render intent through it: the chat tool row's expanded body and the details panel's Output section. `ui-conversation/src/client/contract/terminal-card-model.ts` is the single place that turns the snapshot's `callView`/`resultView` pair into the component's props, so the two sites cannot disagree about a command, its cwd, or its exit status. It returns null — the generic path — whenever neither side declares `card: 'terminal'`, including a `card` value this client version does not know, and whenever a settled call's result view is generic, which is how the bash tool's execution errors and background starts keep their existing rendering. Two duties the render-intent contract assigns to the UI bridge land here rather than in the tool: a settled result's `title` REPLACES the pending one, and the working directory resolves against the session workspace — an absolute view cwd is used as-is, a relative one joins under the workspace, and an omitted one IS the workspace, which is the common case for a bash call with no `workdir`. A pure presenter cannot see the session cwd, which is why the resolution belongs at this seam; each render site supplies the cwd off the session list row. Only a PRESENT call view can mean "omitted, so use the workspace": when the paging window drops the call head there is no cwd anywhere — the result view carries none — and the original call may have used an explicit workdir, so the prompt draws a bare `$` rather than naming a directory it cannot know. The resolved path also normalizes its `.`/`..` segments, because the bash executor resolves the workdir before running: a `..` against `/w/app` runs in `/w`, so the prompt label has to read `w` rather than `..`. A UNC path's `server` and `share` are part of its root rather than poppable segments, since Windows cannot climb above a share. The call view's `description` rides the same derivation, since the contract renders it above the card and it must outrank the row's args-derived summary. All three render sites draw it: both chat-row shapes and the details panel. An expanded row draws it itself, because the collapsed summary is hidden while a row is open — without that the description would only ever be visible collapsed, which is the opposite of what "above the card" means. The component's contract: @@ -20,7 +20,7 @@ The component's contract: - **One run-state dot for the call, on the first row.** `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. The dot exists because the first question a reader has about a shell command is whether it is still running, and without it that had to be inferred from the absence of output — which a settled command producing no output also looks like. It sits out of flow in a gutter reserved to the left of the card surface, so it neither indents its command nor depends on the command's own text metrics to line up with it. Exactly one dot, whatever the line count: the exit status the view carries is the whole call's, and bash reports no per-command status, so a dot per line would assert of a line that succeeded inside a failing call that the line itself failed. The single visually hidden text label carries the same scope, since `StateDot` is `aria-hidden` and one label per row would read to assistive technology as several distinct outcomes. - **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding. - **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends. -- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Two cursor movements resolve before that strip, because their effect on the visible text has to land before the characters expressing them are dropped: a carriage return reduces its line to the final redraw, and a backspace overwrites the character before it, so `abc` followed by two backspaces and `XY` reads `aXY` as a terminal draws it. Both are per-line, so neither reaches across a newline. A backspace steps over CSI sequences rather than erasing their bytes: a sequence moves no cursor, and eating part of one would corrupt it and repaint everything after with whatever the mangled remainder parses as, so it walks back to the last PRINTED character and drops that instead — the surviving text keeps the color its run authored. +- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Cursor movements resolve before that strip, into a per-line column buffer rather than by string surgery, because carriage return and backspace only MOVE the cursor — neither erases anything, so what a reader sees is whatever each column last had written to it. `100%` then a carriage return and `OK` shows `OK0%`, since the redraw is shorter than the frame beneath it; a trailing `abc` plus a backspace still shows `abc`, since nothing overwrote the `c`; `abc` plus two backspaces and `XY` shows `aXY`. Each of these was checked against a real terminal, because the earlier truncate-and-delete approximations looked right and were not. SGR state is stamped per column as a terminal stores it per cell, so a partial overwrite keeps each surviving character's own color: red `bad`, three backspaces, then `ok` shows `okd` with the `d` still red. A CSI sequence occupies no column and changes only the state later writes are stamped with, which is also why a carriage return does not reset color. - **Exit status and copy.** A non-zero exit code or a signal renders a status pill, matching the exit-status distinction the bash tool's own renderer draws; a clean exit renders none, and settled empty output renders a dimmed placeholder. The copy control copies the raw output text, not the rendered tree, so the prompt line and the pill stay out of the clipboard. Geometry, radius, and fonts mirror `CodeBlock`, so a terminal card and a fenced code block match visually; `white-space: pre` plus horizontal scroll is the deliberate divergence. The clipboard write both components need moved out of `CodeBlock` into a package-internal `src/clipboard.ts`, unexported so it stays an implementation detail of the two blocks. diff --git a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md index ab5a35d6f7..3ffcf23294 100644 --- a/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md @@ -12,7 +12,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c ## Decision -`TerminalBlock` 是 `ui-primitives` 中把 shell 命令渲染为终端表面的组件,bash 调用在 Web 侧的两个渲染点都经由它消费 terminal 渲染意图:聊天工具行展开后的正文,以及详情面板的 Output 区。`ui-conversation/src/client/contract/terminal-card-model.ts` 是把快照上的 `callView`/`resultView` 这一对转换为该组件 props 的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧。当两侧都不声明 `card: 'terminal'` 时它返回 null,即走 generic 路径——包括本 client 版本不认识的 `card` 取值;当一个已落定调用的结果视图是 generic 时同样返回 null,这正是 bash 工具的执行错误与后台启动得以保持既有渲染的方式。渲染意图契约交给 UI 桥接层的两项职责也落在这里,而不在工具侧:已落定结果的 `title` **替换**待定标题;工作目录针对会话 workspace 解析——视图给出的绝对路径原样使用,相对路径在 workspace 之下拼接,省略则**就是** workspace,而这正是不带 `workdir` 的 bash 调用的常见情形。纯 presenter 看不到会话 cwd,因此该解析属于这道接缝;两个渲染点各自从会话列表行取出 cwd 传入。只有**存在**的调用视图才能表示「省略了 cwd,因此取 workspace」:当分页窗口丢掉调用头时,任何地方都不再有 cwd——结果视图并不携带它——而原调用完全可能使用过一个显式 workdir,因此提示行绘制一个裸 `$`,而不是命名一个它无法知晓的目录。解析后的路径还会归一化其 `.`/`..` 段,因为 bash 执行器在运行前就已解析 workdir:相对 `/w/app` 的 `..` 实际运行在 `/w`,因此提示标签必须读作 `w` 而不是 `..`。UNC 路径的 `server` 与 `share` 属于其根,而非可弹出的路径段,因为 Windows 无法越过一个共享向上。调用视图的 `description` 走同一处推导,因为契约把它渲染在卡片上方,且它必须优先于该行由参数推导出的摘要。 +`TerminalBlock` 是 `ui-primitives` 中把 shell 命令渲染为终端表面的组件,bash 调用在 Web 侧的两个渲染点都经由它消费 terminal 渲染意图:聊天工具行展开后的正文,以及详情面板的 Output 区。`ui-conversation/src/client/contract/terminal-card-model.ts` 是把快照上的 `callView`/`resultView` 这一对转换为该组件 props 的唯一位置,因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧。当两侧都不声明 `card: 'terminal'` 时它返回 null,即走 generic 路径——包括本 client 版本不认识的 `card` 取值;当一个已落定调用的结果视图是 generic 时同样返回 null,这正是 bash 工具的执行错误与后台启动得以保持既有渲染的方式。渲染意图契约交给 UI 桥接层的两项职责也落在这里,而不在工具侧:已落定结果的 `title` **替换**待定标题;工作目录针对会话 workspace 解析——视图给出的绝对路径原样使用,相对路径在 workspace 之下拼接,省略则**就是** workspace,而这正是不带 `workdir` 的 bash 调用的常见情形。纯 presenter 看不到会话 cwd,因此该解析属于这道接缝;两个渲染点各自从会话列表行取出 cwd 传入。只有**存在**的调用视图才能表示「省略了 cwd,因此取 workspace」:当分页窗口丢掉调用头时,任何地方都不再有 cwd——结果视图并不携带它——而原调用完全可能使用过一个显式 workdir,因此提示行绘制一个裸 `$`,而不是命名一个它无法知晓的目录。解析后的路径还会归一化其 `.`/`..` 段,因为 bash 执行器在运行前就已解析 workdir:相对 `/w/app` 的 `..` 实际运行在 `/w`,因此提示标签必须读作 `w` 而不是 `..`。UNC 路径的 `server` 与 `share` 属于其根,而非可弹出的路径段,因为 Windows 无法越过一个共享向上。调用视图的 `description` 走同一处推导,因为契约把它渲染在卡片上方,且它必须优先于该行由参数推导出的摘要。三个渲染点都会绘制它:两种聊天行形态与详情面板。展开后的行自行绘制它,因为一行处于展开态时其折叠摘要是隐藏的——否则该描述将只在折叠时可见,这与「位于卡片上方」的含义正好相反。 该组件的契约: @@ -20,7 +20,7 @@ Web client 却对它视而不见。`packages/client/ui-conversation/src/client/c - **整次调用一枚运行状态点,位于第一行。** 它是 `StateDot` 四种状态中的三种:运行期间为追逐动画,与渲染状态徽章相同的退出状态为红色,干净落定为绿色——与工具行行首图标使用同一个指示器,因此一行与其自身的卡片不可能对同一条命令产生分歧。该状态点存在的理由是:读者对一条 shell 命令的第一个问题就是它是否仍在运行;没有它时,这一点只能从「没有输出」推断,而一条落定后无输出的命令看起来也一样。它以脱离文档流的方式落在卡片表面左侧预留的落区里,因此既不会缩进其命令,也不依赖命令自身的文本度量来与之对齐。无论有多少行,都只有一枚:视图携带的退出状态属于整次调用,而 bash 不报告逐条命令的状态,因此每行一枚状态点就等于在断言——一条在失败调用中其实成功了的命令行自身失败了。那一处视觉隐藏的文本标签具有相同的作用域,因为 `StateDot` 是 `aria-hidden`,而每行一个标签会被辅助技术读成好几个各自独立的结果。 - **不软换行。** 输出行使用 `white-space: pre`,置于横向滚动的容器内。列对齐得以保留;长行滚动,而非折行。 - **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`(16)行时,显示 `ceil(max/2)` 行首部加余下的尾部行数,中间是一个按钮,报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行,因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片(`packages/ui/tui/src/components/transcript.ts`)完全一致,因此同一条命令的首尾切片在两个前端之间吻合。 -- **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM。两种光标移动在该剥除之前先行结算,因为它们对可见文本的作用必须先落地,之后才能丢弃表达它们的那些字符:回车把所在行归约为最后一次重绘,退格覆盖它前面的字符——于是 `abc` 后接两个退格再接 `XY` 读作 `aXY`,与终端的绘制一致。两者都按行结算,因此都不会跨越换行。退格会跨过 CSI 序列,而不是擦掉它的字节:序列本身不移动光标,吃掉它的一部分会破坏该序列,并让其后的一切按被损坏的残余重新着色,因此退格回退到最后一个**已打印**字符并删除它——存活下来的文本保留其所在分段所声明的颜色。 +- **ANSI 颜色。** `anser` 切分 SGR 分段;`ui-primitives/src/ansi.ts` 把每段解析为内联样式,渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token,使作者指定的颜色在两种主题下都可读;自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb,以保住它意图中的对比度,256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列(OSC 串、非 CSI 转义、无显示意义的 C0 控制符)在解析前被剥除,因此绝不会以字面字符抵达 DOM。光标移动在该剥除之前先行结算,且落在逐行的列缓冲里而不是靠字符串手术,因为回车与退格**只移动**光标——两者都不擦除任何东西,所以读者看到的就是每一列最后被写入的内容。`100%` 后接回车再接 `OK` 显示为 `OK0%`,因为这次重绘比它下面的帧更短;末尾 `abc` 加一个退格仍显示 `abc`,因为没有任何东西覆盖过那个 `c`;`abc` 加两个退格再接 `XY` 显示 `aXY`。这些用例都对照真实终端核实过,因为先前「截断加删除」的近似看起来是对的,实际并不对。SGR 状态按列打戳,与终端按单元格存储颜色的方式一致,因此部分覆盖会保留每个存活字符自身的颜色:红色 `bad`、三个退格、再写 `ok`,显示为 `okd` 且那个 `d` 仍是红的。CSI 序列不占列,只改变后续写入被打上的状态——这也正是回车不会重置颜色的原因。 - **退出状态与复制。** 非零退出码或信号渲染一枚状态徽章,与 bash 工具自身渲染器所作的退出状态区分一致;干净退出不渲染徽章,落定后的空输出渲染一处变暗的占位文字。复制控件复制的是原始输出文本而非渲染后的树,因此提示符行与徽章不会进入剪贴板。 几何尺寸、圆角与字体沿用 `CodeBlock`,因此终端卡片与围栏代码块在视觉上一致;`white-space: pre` 加横向滚动是有意的分歧。两个组件都需要的剪贴板写入从 `CodeBlock` 中提取到包内部的 `src/clipboard.ts`,不对外导出,因此它仍是这两个块的实现细节。 diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.module.css b/packages/client/ui-conversation/src/client/chat/ToolRow.module.css index bf1e238e23..0c1f674262 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.module.css +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.module.css @@ -182,6 +182,14 @@ button.leading { also replaces each primitive's own standalone vertical spacing with the flow's row rhythm. */ .codeBody, +/* Indented to the terminal body's own column, so the description reads as the + card's heading rather than as another summary row. */ +.terminalDescription { + margin: 4px 0 0 22px; + color: var(--dsw-alias-label-secondary); + font: var(--dsw-font-xs-13); +} + .terminalBody { margin: 4px 0 4px 22px; } diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx index 30ef595397..d4fae4f6c5 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx @@ -156,6 +156,12 @@ export function ToolRow({ )}
+ {/* The terminal presenter's description belongs ABOVE the card per the + render-intent contract, so an expanded terminal row keeps showing it + even though the collapsed summary is hidden while open. */} + {open && terminalBody?.description !== undefined && ( +
{terminalBody.description}
+ )} {open && (terminalBody !== null ? : variant === 'code' diff --git a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css index ef4173735e..0ddc58e30b 100644 --- a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css +++ b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.module.css @@ -95,6 +95,14 @@ /* The terminal card sits directly under its section label, so it drops the primitive's standalone vertical margin; the section owns the spacing. */ +/* Above the card, which is where the render-intent contract puts a terminal + call's description; the panel has no summary row to carry it. */ +.terminalDescription { + margin: 0 0 6px; + color: var(--dsw-alias-label-secondary); + font: var(--dsw-font-xs-13); +} + .terminal { margin: 0; } diff --git a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx index 630334eae7..9fc5a04ff6 100644 --- a/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/DetailsPanel.tsx @@ -135,7 +135,18 @@ export function DetailsPanel({ useSession, useSessions, sessionId, useStore, clo */ function OutputBody({ material, cwd }: { material: CallMaterial; cwd: string | undefined }) { const terminal = terminalCardModel(material.block, cwd) - if (terminal !== null) return + if (terminal !== null) { + // The contract renders the presenter's description above the card, and the + // panel has no summary row to carry it, so it is drawn here. + return ( + <> + {terminal.description !== undefined && ( +
{terminal.description}
+ )} + + + ) + } // A settled call always carries the result node the flattened form needs; // the running shape has no result to flatten. if (!('kind' in material.block)) return
运行中…
diff --git a/packages/client/ui-conversation/tests/terminal-card.spec.tsx b/packages/client/ui-conversation/tests/terminal-card.spec.tsx index dd096c6e91..3ac9ad2f1c 100644 --- a/packages/client/ui-conversation/tests/terminal-card.spec.tsx +++ b/packages/client/ui-conversation/tests/terminal-card.spec.tsx @@ -267,6 +267,19 @@ describe('chat row terminal body', () => { expect(view.queryByText('List files')).toBeNull() }) + it('keeps the presenter description visible once the terminal card is expanded', () => { + // The contract puts the description ABOVE the card. The collapsed summary is + // hidden while a row is open, so an expanded terminal row has to draw it + // itself or the description would only ever be visible collapsed. + const view = render() + expect(view.getByText('Terminal 3')).toBeTruthy() + fireEvent.click(view.container.querySelector('button')!) + expect(view.container.querySelector('[data-terminal]')).not.toBeNull() + expect(view.getByText('Terminal 3')).toBeTruthy() + }) + it('a running terminal call expands to the prompt line with no output yet', () => { const view = render() fireEvent.click(view.container.querySelector('button')!) @@ -421,6 +434,17 @@ describe('DetailsPanel Output section', () => { expect(second.getByRole('button', { name: '展开其余 4 行输出' })).toBeTruthy() }) + it('renders the presenter description above the card', () => { + const view = mount(snapshot({ + nodes: [settled({ callView: callTerminal({ description: 'Terminal 3' }) })], + }), target) + const description = view.getByText('Terminal 3') + const card = view.container.querySelector('[data-terminal]') + expect(card).not.toBeNull() + // Above, not below: document order is what places it as the card's heading. + expect(description.compareDocumentPosition(card!) & Node.DOCUMENT_POSITION_FOLLOWING).toBeTruthy() + }) + it('resolves the prompt cwd against the session workspace', () => { const view = mount(snapshot({ nodes: [settled()] }), target, '/w/app') // No workdir in the call view: the prompt label is the workspace basename. diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml index ad22a9f734..3e81b076a4 100644 --- a/packages/client/ui-primitives/README.i18n.yaml +++ b/packages/client/ui-primitives/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-primitives/README.md -README.md: 4222aac4fa1d9c89a3d3c702ee8391fba1eef178 -README.zh.md: e7a5b5ad57048bc59872963b0068c6f88fc772f8 +README.md: 3e77cb1955972db602b4e751a52a45cf5f5f349d +README.zh.md: 19e02c3e466afcbddd0d19ad6644887d3a53ca10 diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md index 4222aac4fa..3e77cb1955 100644 --- a/packages/client/ui-primitives/README.md +++ b/packages/client/ui-primitives/README.md @@ -10,7 +10,7 @@ Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/ ## Terminal output -`TerminalBlock` renders a shell command as a terminal surface: one prompt row per line of the command (the shortened `cwd` label on the first row only, since the view knows one working directory and a `cd` moves later lines elsewhere, then that line), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. A run-state `StateDot` marks the call once, on the first row, out of flow in a gutter to the left of the card surface. It reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries one visually hidden text label because `StateDot` is `aria-hidden`. One dot regardless of line count is deliberate: the exit status is the whole call's, so a dot per line would claim a per-line outcome the view does not carry. Command text is `white-space: pre`, so repeated spaces, tabs, and an indented continuation render verbatim while the row stays single-line and ellipsizes. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; carriage-return redraws and backspace overwrites resolve as a terminal performs them before inert controls are stripped; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). +`TerminalBlock` renders a shell command as a terminal surface: one prompt row per line of the command (the shortened `cwd` label on the first row only, since the view knows one working directory and a `cd` moves later lines elsewhere, then that line), the command's output, a status pill for a non-zero exit code or a terminating signal, and a copy control that writes the raw `output` prop. A run-state `StateDot` marks the call once, on the first row, out of flow in a gutter to the left of the card surface. It reaches three of `StateDot`'s states — the chase while `running`, red for the same exit status that renders the pill, green otherwise — so a card states whether its command is still running rather than leaving that to be inferred from the presence of output; it carries one visually hidden text label because `StateDot` is `aria-hidden`. One dot regardless of line count is deliberate: the exit status is the whole call's, so a dot per line would claim a per-line outcome the view does not carry. Command text is `white-space: pre`, so repeated spaces, tabs, and an indented continuation render verbatim while the row stays single-line and ellipsizes. ANSI escape sequences are parsed with the `anser` runtime dependency into React spans; carriage return and backspace replay into a per-line column buffer before inert controls are stripped, since both only move the cursor (so `100%` + CR + `OK` shows `OK0%`), with SGR state stamped per column as a terminal stores it per cell; basic-16 foreground colors map onto `--dsw-*` tokens, while 256-palette and truecolor values pass through as literal rgb. Output keeps `white-space: pre` with horizontal scrolling, so column-aligned output holds its alignment instead of soft-wrapping, and collapses to a head slice plus a tail slice past `maxLines` (default 16, the TUI transcript's split arithmetic) behind an expand button. Rationale: [the web terminal card note](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md). ## Model Experience diff --git a/packages/client/ui-primitives/README.zh.md b/packages/client/ui-primitives/README.zh.md index e7a5b5ad57..19e02c3e46 100644 --- a/packages/client/ui-primitives/README.zh.md +++ b/packages/client/ui-primitives/README.zh.md @@ -10,7 +10,7 @@ ## 终端输出 -`TerminalBlock` 将一条 shell 命令渲染为终端表层:命令的每一行各占一个提示行(缩短后的 `cwd` 标签只出现在第一行,因为视图只知道一个工作目录,而一个 `cd` 就会让后面的行去到别处,标签之后是该行)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。一枚运行状态 `StateDot` 为整次调用标记一次,位于第一行,以脱离文档流的方式落在卡片表面左侧的落区中。它用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它携带一处视觉隐藏的文本标签。无论多少行都只有一枚状态点是有意为之:退出状态属于整次调用,因此每行一枚就会声称一个视图并不携带的逐行结果。命令文本使用 `white-space: pre`,因此重复空格、制表符与缩进续行都原样呈现,同时该行仍保持单行并以省略号截断。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;回车重绘与退格覆盖会按终端的行为先行结算,之后才剥除无显示意义的控制符;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 +`TerminalBlock` 将一条 shell 命令渲染为终端表层:命令的每一行各占一个提示行(缩短后的 `cwd` 标签只出现在第一行,因为视图只知道一个工作目录,而一个 `cd` 就会让后面的行去到别处,标签之后是该行)、命令输出、非零退出码或终止信号对应的状态胶囊,以及写入原始 `output` prop 的复制控件。一枚运行状态 `StateDot` 为整次调用标记一次,位于第一行,以脱离文档流的方式落在卡片表面左侧的落区中。它用到 `StateDot` 的三种状态——`running` 期间为追逐动画,与渲染状态胶囊相同的退出状态为红色,其余为绿色——因此卡片直接陈述其命令是否仍在运行,而不是让人从有无输出中推断;由于 `StateDot` 是 `aria-hidden`,它携带一处视觉隐藏的文本标签。无论多少行都只有一枚状态点是有意为之:退出状态属于整次调用,因此每行一枚就会声称一个视图并不携带的逐行结果。命令文本使用 `white-space: pre`,因此重复空格、制表符与缩进续行都原样呈现,同时该行仍保持单行并以省略号截断。ANSI 转义序列通过运行时依赖 `anser` 解析为 React span;回车与退格在剥除无显示意义控制符之前先重放进逐行的列缓冲,因为两者都只移动光标(所以 `100%` 加回车再加 `OK` 显示为 `OK0%`),且 SGR 状态按列打戳,与终端按单元格存储颜色一致;基础 16 色前景色映射到 `--dsw-*` token,而 256 色板与真彩色值按字面 rgb 透传。输出保持 `white-space: pre` 并支持横向滚动,因此按列对齐的输出保留其对齐而不会软换行;超过 `maxLines`(默认 16,与 TUI 转录相同的切分算法)时折叠为头部切片加尾部切片,由展开按钮控制。原理:[Web 终端卡片笔记](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)。 ## 模型体验 diff --git a/packages/client/ui-primitives/src/ansi.ts b/packages/client/ui-primitives/src/ansi.ts index 115d3faffc..1d7dd87796 100644 --- a/packages/client/ui-primitives/src/ansi.ts +++ b/packages/client/ui-primitives/src/ansi.ts @@ -82,95 +82,99 @@ const NON_CSI_ESCAPE = /\u001b(?!\[)[\u0020-\u002f]*[\u0030-\u007e]?/g /** * C0 controls with no display meaning here. Tab, newline, backspace and ESC - * survive: the first two for layout, backspace for its overwrite, ESC for - * anser's CSI split. + * survive: the first two for layout, backspace for the cursor replay, ESC + * for anser's CSI split. */ const INERT_CONTROL = /[\u0000-\u0007\u000b-\u001a\u001c-\u001f\u007f]/g /** - * Apply carriage-return redraws: within a line, only the text after the last - * `\r` survives, which is what a terminal shows for progress output. A `\r` - * that only terminates a CRLF line is dropped first so those lines keep - * their text. SGR codes preceding a dropped redraw are dropped with it. - * @param text - output text, already free of OSC and non-CSI escapes. - * @returns the text with each line reduced to its final redraw. - */ -function applyCarriageReturns(text: string): string { - return text.split('\n').map((raw) => { - const line = raw.replace(/\r+$/, '') - return line.slice(line.lastIndexOf('\r') + 1) - }).join('\n') -} - -/** - * Apply backspaces as the cursor-left-then-overwrite a terminal performs, so - * `abc` followed by two backspaces and `XY` reads `aXY` instead of keeping the - * characters it overwrote. Progress meters and captured PTY output use - * backspace this way. Resolved per line, so a backspace neither eats the - * newline before it nor reaches into the previous line's tail; one at a line - * start has nothing to erase. - * @param text - output text, already reduced to its carriage-return redraws. - * @returns the text with each backspace resolved against the character before it. - */ -function applyBackspaces(text: string): string { - if (!text.includes('\u0008')) return text - return text.split('\n').map(applyBackspacesToLine).join('\n') -} - -/** - * One line's backspaces, resolved over VISIBLE characters only. A CSI sequence - * moves no cursor, so it must survive intact: erasing its bytes would corrupt - * the sequence and repaint the rest of the output with whatever the mangled - * remainder parses as. The sequences are therefore held as indivisible units - * that a backspace steps over on its way to the last printed character, and a - * unit already erased stays erased so a run's own color still applies to what - * remains of it. + * Replay one line's cursor movements the way a terminal paints it, into a + * column buffer. Carriage return and backspace only MOVE the cursor — neither + * erases anything — so what a reader sees is whatever each column last had + * written to it. That distinction is the whole point of doing this as a buffer + * rather than as string surgery: `100%\rOK` shows `OK0%` because the redraw is + * shorter than the frame beneath it, and a trailing `abc\b` still shows `abc` + * because nothing ever overwrote the `c`. + * + * A CSI sequence occupies no column; it changes the state that the NEXT writes + * are stamped with, which is how a terminal stores color per cell. `red bad` + * then three backspaces then `ok` therefore shows `okd` with the `d` still red: + * `ok` overwrote two cells and the third kept the state it was written with. + * The columns are re-emitted as runs, so anser sees that same styling. * @param line - one output line, still carrying its CSI sequences. - * @returns the line with each backspace applied to the character before it. + * @returns the line as the terminal would have it after every movement. */ -function applyBackspacesToLine(line: string): string { - if (!line.includes('\u0008')) return line - const units: { text: string; visible: boolean }[] = [] - // Same shape anser splits on: CSI ... final byte. Matched here so a sequence - // is one unit rather than a run of erasable characters. +function replayLine(line: string): string { + // Same shape anser splits on, so a sequence is one unit here as well. const csi = /\u001b\[[\u0030-\u003f]*[\u0020-\u002f]*[\u0040-\u007e]/g + /** Per column: the SGR state in force when it was written, and its character. */ + const columns: { sgr: string; char: string }[] = [] + let cursor = 0 + // SGR state accumulates as the line is scanned, exactly as a terminal tracks + // it: each cell is stamped with whatever was in force at the moment of the + // write, so a later redraw cannot restyle the cells it does not reach. + let sgr = '' let at = 0 + + const consume = (chunk: string): void => { + for (const char of chunk) { + if (char === '\r') { cursor = 0; continue } + if (char === '\u0008') { cursor = Math.max(0, cursor - 1); continue } + columns[cursor] = { sgr, char } + cursor++ + } + } + for (const match of line.matchAll(csi)) { - for (const char of line.slice(at, match.index)) units.push({ text: char, visible: true }) - units.push({ text: match[0], visible: false }) + consume(line.slice(at, match.index)) + // A reset clears the accumulated state; anything else adds to it. + sgr = /^\u001b\[0?m$/.test(match[0]) ? '' : sgr + match[0] at = match.index + match[0].length } - for (const char of line.slice(at)) units.push({ text: char, visible: true }) + consume(line.slice(at)) - const kept: { text: string; visible: boolean }[] = [] - for (const unit of units) { - if (unit.visible && unit.text === '\u0008') { - // Walk back past any escapes to the last printed character and drop it, - // keeping those escapes so the surviving text stays styled as authored. - for (let index = kept.length - 1; index >= 0; index--) { - if (kept[index]?.visible !== true) continue - kept.splice(index, 1) - break - } - continue + // Re-emit the columns, opening a run only where its SGR state changes and + // closing the previous one, so anser sees the same styling a terminal shows. + // No index can be missing: `\r` and backspace only move the cursor LEFT, so + // every column up to the furthest write has been written at least once. + let out = '' + let active = '' + for (const column of columns) { + if (column.sgr !== active) { + if (active !== '') out += '\u001b[0m' + out += column.sgr + active = column.sgr } - kept.push(unit) + out += column.char } - return kept.map(unit => unit.text).join('') + return active === '' ? out : `${out}\u001b[0m` +} + +/** + * Replay every line's cursor movements. A `\r` that only terminates a CRLF line + * is dropped first, so those lines keep their text instead of being redrawn onto + * themselves. + * @param text - output text, already free of OSC and non-CSI escapes. + * @returns the text with each line painted as the terminal would. + */ +function applyCursorMovements(text: string): string { + return text.split('\n') + .map(raw => raw.replace(/\r+$/, '')) + .map(line => (/[\r\u0008]/.test(line) ? replayLine(line) : line)) + .join('\n') } /** * Remove every escape sequence and control character that carries no color, - * leaving CSI sequences for anser and `\n`/`\t` for layout. Carriage-return - * redraws and backspace overwrites resolve first: both are cursor movements - * whose effect on the visible text must land before the characters that - * expressed them are dropped. + * leaving CSI sequences for anser and `\n`/`\t` for layout. Cursor movements + * (carriage return, backspace) replay first, since their effect on the visible + * text must land before the characters that expressed them are dropped. * @param text - raw command output. * @returns text whose only remaining escapes are CSI sequences. */ function sanitize(text: string): string { const escaped = text.replace(OSC_SEQUENCE, '').replace(NON_CSI_ESCAPE, '') - return applyBackspaces(applyCarriageReturns(escaped)).replace(INERT_CONTROL, '') + return applyCursorMovements(escaped).replace(INERT_CONTROL, '') } /** diff --git a/packages/client/ui-primitives/tests/ansi.spec.ts b/packages/client/ui-primitives/tests/ansi.spec.ts index 76af75a565..801484d6a7 100644 --- a/packages/client/ui-primitives/tests/ansi.spec.ts +++ b/packages/client/ui-primitives/tests/ansi.spec.ts @@ -151,8 +151,26 @@ describe('parseAnsiLines: carriage returns', () => { expect(onlySpan('10%\r55%\r100%')).toEqual({ text: '100%', style: undefined }) }) - it('drops the SGR codes that preceded a discarded redraw', () => { - expect(onlySpan(`${ESC}[31mgone\rkept`)).toEqual({ text: 'kept', style: undefined }) + it('leaves the tail of a longer frame standing under a shorter redraw', () => { + // Verified against a real terminal: `100%\rOK` paints `OK0%`. A carriage + // return only moves the cursor, so the two columns the redraw never reaches + // still hold the frame beneath — truncating to the last `\r` would lose them. + expect(onlySpan('100%\rOK')).toEqual({ text: 'OK0%', style: undefined }) + expect(onlySpan('abcdef\rXY')).toEqual({ text: 'XYcdef', style: undefined }) + }) + + it('clamps a backspace run at the line start rather than going negative', () => { + // More backspaces than characters: the cursor stops at column 0, so the + // following write simply overwrites from there. + expect(onlySpan(`ab${BS}${BS}${BS}${BS}xyz`)).toEqual({ text: 'xyz', style: undefined }) + }) + + it('keeps SGR state in force across a redraw, as a terminal does', () => { + // Verified against a real terminal: `\x1b[31mgone\rkept` paints `kept` RED. + // A carriage return moves the cursor; it does not reset the graphic state, + // so the redraw inherits the color the discarded frame was written with. + expect(onlySpan(`${ESC}[31mgone\rkept`)) + .toEqual({ text: 'kept', style: { color: 'var(--dsw-alias-state-error-primary)' } }) }) it('preserves both lines of a CRLF pair instead of treating it as a redraw', () => { @@ -184,6 +202,17 @@ describe('parseAnsiLines: backspaces', () => { ]) }) + it('treats a trailing backspace as a cursor move, not a delete', () => { + // Verified against a real terminal: `abc\b` still shows `abc`. Only a later + // write overwrites; a backspace with nothing after it erases nothing. + expect(onlySpan(`abc${BS}`)).toEqual({ text: 'abc', style: undefined }) + // Same at a line boundary: the newline ends the line before any overwrite. + expect(parseAnsiLines(`abc${BS}\ndef`)).toEqual([ + [{ text: 'abc', style: undefined }], + [{ text: 'def', style: undefined }], + ]) + }) + it('steps over an SGR sequence instead of erasing its bytes', () => { // `abc` reset then two backspaces then `XY`: erasing the reset's bytes would // corrupt it and repaint the rest of the line with whatever the remainder @@ -202,14 +231,21 @@ describe('parseAnsiLines: backspaces', () => { ]]) }) - it('applies the overwrite after a carriage-return redraw, not before', () => { - // The redraw wins first; the backspace then erases inside what survived. - expect(onlySpan(`old\rnew${BS}`)).toEqual({ text: 'ne', style: undefined }) + it('replays a redraw and a trailing backspace as pure cursor moves', () => { + // Verified against a real terminal: `old\rnew\b` shows `new`. The redraw + // repaints all three columns and the trailing backspace only moves the + // cursor left — nothing overwrites the `w`, so nothing is lost. + expect(onlySpan(`old\rnew${BS}`)).toEqual({ text: 'new', style: undefined }) }) - it('keeps the run\'s style while erasing its own characters', () => { - expect(onlySpan(sgr('31', `bad${BS}${BS}${BS}ok`))) - .toEqual({ text: 'ok', style: { color: 'var(--dsw-alias-state-error-primary)' } }) + it('overwrites only the columns the later write reaches, keeping the rest styled', () => { + // Verified against a real terminal: red `bad`, three backspaces, then `ok` + // shows `okd` — the cursor returned to column 0 and `ok` overwrote two of + // the three columns, so the untouched `d` keeps the run's red. + expect(parseAnsiLines(`${sgr('31', 'bad')}${BS}${BS}${BS}ok`)).toEqual([[ + { text: 'ok', style: undefined }, + { text: 'd', style: { color: 'var(--dsw-alias-state-error-primary)' } }, + ]]) }) }) From 46e1e86c764d0ceaffe75fc60957e3a11fce023d Mon Sep 17 00:00:00 2001 From: j-xiang Date: Wed, 29 Jul 2026 15:29:03 +0800 Subject: [PATCH 14/38] docs(i18n): bind reviewed README terminology --- docs/i18n/terminology.md | 14 +++++++++----- .../request-response.expected.json | 2 +- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/docs/i18n/terminology.md b/docs/i18n/terminology.md index 3a40629372..bf2590931a 100644 --- a/docs/i18n/terminology.md +++ b/docs/i18n/terminology.md @@ -37,6 +37,7 @@ | agent harness | agent harness | agent harness(智能体框架) | | agent 组合词(agent harness/workflow/loop/skill 等)整体保留英文;未括注过 agent 时首现按对应组合词或 agent 行处理 | | agent loop | agent loop | agent loop(智能体循环) | | | | blob hash | blob hash | | | `git hash-object` 的结果 | +| capability seam | 能力 seam | | 功能 seam、能力接缝 | 本仓库接口、实现与消费方分离的命名架构概念;普通 `seam` 仍按其词条处理 | | Cordis | Cordis | | | | | dispose | dispose | dispose(资源释放) | | | | doc-sync | doc-sync | doc-sync(文档同步门禁) | | | @@ -54,7 +55,7 @@ | Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时,领域层级为 Session > Round > Turn(轮次) > Step(步骤);Round 是可选的外层策略迭代,并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次,步骤隶属于该轮次;明确的零步骤轮次仍保持原义。 | | schema | schema | | | | | schema DSL | schema DSL | | | | -| seam | seam | | | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` | +| seam | seam | | 接缝 | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` | | skill | skill | skill(技能) | | | | spawn | spawn | | | | | steering | steering | steering(中途引导) | | | @@ -74,21 +75,23 @@ | adapter | 适配器 | | | | | adapter contract | 适配器契约 | 适配器契约(adapter contract) | | | | append-only | 仅追加 | | | | -| artifact | 产物 | | | | +| artifact | 产物 | | 制品 | | | backend | 后端 | | | | | background task | 后台任务 | | | | | block | 块 | | | | | build target | 构建目标 | | | | | cancel | 取消 | | | | +| canary test | canary 测试 | | 金丝雀测试 | 本仓库保留 `canary` | | feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 | | feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 | | checkpoint | 检查点 | | | | | chunk | 分片 | | | | | compaction | 压缩 | 压缩(compaction) | | | | companion tool | 配套工具 | | | | +| composition bundle | 组合包 | | | 只约束应用或插件的组合语境,不约束所有 `bundle` | | Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 | | config key | 配置键 | | | Cordis 插件配置中的单个字段 | -| consumer | 消费方 | | | | +| consumer | 消费方 | | 消费者 | | | content block | 内容块 | | | | | Cookbook | 实操手册 | | | 文档标题用语 | | context | 上下文 | | | | @@ -145,9 +148,10 @@ | persistence | 持久化 | | | | | pipeline | 流水线 | | | | | plugin | 插件 | | | | +| postmortem | 事故复盘 | 事故复盘(postmortem) | 事后分析、事故记录 | 事故记录与分析文档;目录或路径中的 `postmortem` 保持代码形式 | | prompt | 提示词 | | | | | provider | 提供方 | | | | -| provider-neutral | 提供方无关 | | | | +| provider-neutral | 提供方无关 | | 提供方中立 | | | quality gate | 质量门禁 | | | | | quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 | | reasoning | 推理 | 推理(reasoning) | | 需要和 `inference` 区分时保留英文括注 | @@ -165,7 +169,7 @@ | sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 | | smoke test | 冒烟测试 | | | | | snapshot | 快照 | | | | -| source of truth | 真源 | | | | +| source of truth | 真源 | | 事实来源、唯一来源 | | | spine | 主干 | | | | | staged | 暂存 | | | 沿用 git 官方中文翻译 | | stale | 陈旧 | | 过期 | 与 `fresh`(`新鲜`)成对;门禁输出中保留英文 `stale` 不翻译;`expired` 才译为`过期` | diff --git a/scripts/snapshots/translation-prompt-v4/request-response.expected.json b/scripts/snapshots/translation-prompt-v4/request-response.expected.json index 96d2dc805f..428d3d49a4 100644 --- a/scripts/snapshots/translation-prompt-v4/request-response.expected.json +++ b/scripts/snapshots/translation-prompt-v4/request-response.expected.json @@ -4,7 +4,7 @@ "messages": [ { "role": "system", - "content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from English to Chinese, producing natural, professional technical prose.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.\n- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.\n- Language switcher line: when translating into Chinese, write `[English](source-filename.md) | 中文`. When translating into English, write `English | [中文](source-filename.zh.md)`. Do NOT copy the switcher line from the source file unchanged — you must flip the link direction.\n- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter, digit, or CJK ideograph. Never insert a space before any punctuation (full-width or half-width).\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Use polite imperative forms where the text instructs the reader to do something.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences with commas or semicolons. Avoid run-on sentences.\n- Prefer active voice. Convert passive constructions to active if it reads more naturally.\n- Translate meaning, not words. Restructure sentences where the target language grammar requires it.\n- Do not invent words or expressions that do not exist in natural technical writing of the target language.\n\n### Word Choice\n- Prefer precise, formal vocabulary over casual or colloquial alternatives.\n- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.\n- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.\n- Do not use the same word to translate two different source-language terms that carry distinct meanings.\n- Avoid repeating the same verb in close proximity; vary word choice for readability.\n\n#### When translating into Chinese\n- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: \"three-package seam\" → \"由三个包构成的 seam\", not \"三包 seam\".\n\n### Punctuation\n\n#### When translating into Chinese\n- Use full-width Chinese punctuation in prose: `,。:;?!()「」`.\n- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.\n- Use enumeration commas (、) between parallel items, not regular commas.\n- List item endings: use semicolons or no punctuation. Do not end list items with commas.\n- Put one half-width space between Chinese text and Latin words/numbers.\n- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), translate to the corresponding Chinese term (必须、禁止、应当、可以) and keep the SOURCE emphasis marker: plain source stays plain (必须), italic source stays italic (*必须*), and bold source stays bold (**必须**).\n\n#### When translating into English\n(To be added.)\n\n## Terminology\n\nA terminology table is provided below. Follow it strictly:\n- Render every listed term exactly as specified.\n- When the target language is Chinese, use the \"中文\" column. On first occurrence, write the \"首次出现\" value with its parenthetical gloss; on subsequent occurrences, write only the part before the parentheses.\n- When the target language is English, use the \"English\" column without a Chinese gloss; do not copy the \"中文\" or \"首次出现\" value into English prose.\n- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.\n- NEVER use translations listed in the \"不要译作\" column.\n- For technical terms not in the table, follow the target language: for a Chinese target, use an established Chinese rendering from a major Chinese-language OSS or vendor source, or keep the source term and flag it as pending when no such precedent exists; for an English target, use the established English technical term, or preserve an ambiguous source term with a short English gloss and flag it as pending. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.\n\n# Terminology\n\n本表约定本仓库的中英术语统一译法。\n\n**通用规则:**\n- \"中文\"列为中文译文的正文默认用词。若该列为英文,则中文译文的正文中保留英文不翻译。\n- 首次出现按\"首次出现\"列书写(带括号注释);后续出现只写括号前的部分(可能为中文,也可能为英文),不出现括号内的注释。\n- \"不要译作\"列为严格禁止的译法。\n- 如果某术语已经作为另一个术语的组成部分被括注过(如 `agent loop(智能体循环)` 中已包含 `agent` 的括注),则该术语后续单独出现时无需再次括注。\n\n## 缩写类(中英文文本中均使用缩写)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| ACP | ACP | ACP(Agent Client Protocol) | | |\n| AI | AI | AI(人工智能) | | |\n| API | API | | | |\n| CI | CI | | | |\n| CLI | CLI | CLI(命令行界面) | | |\n| e2e | e2e | | | |\n| HMR | HMR | HMR(热模块替换) | | |\n| JSON Schema | JSON Schema | | | |\n| JSONL | JSONL | | | |\n| LLM | LLM | LLM(大语言模型) | | |\n| MCP | MCP | | | |\n| PR | PR | PR(Pull Request) | | |\n| RAG | RAG | RAG(检索增强生成) | | |\n| SDK | SDK | | | |\n| SSE | SSE | SSE(Server-Sent Events) | | |\n\n## 英文类(中英文文本中均使用英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| agent | agent | agent(智能体) | | |\n| Agent Note | Agent Note | Agent Note(agent 决策记录) | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 |\n| agent harness | agent harness | agent harness(智能体框架) | | agent 组合词(agent harness/workflow/loop/skill 等)整体保留英文;未括注过 agent 时首现按对应组合词或 agent 行处理 |\n| agent loop | agent loop | agent loop(智能体循环) | | |\n| blob hash | blob hash | | | `git hash-object` 的结果 |\n| Cordis | Cordis | | | |\n| dispose | dispose | dispose(资源释放) | | |\n| doc-sync | doc-sync | doc-sync(文档同步门禁) | | |\n| fiber | fiber | | | |\n| fixture | fixture | fixture(测试前置数据) | | |\n| fork | fork | | | |\n| Function Calling | Function Calling | Function Calling(函数调用) | | |\n| harness | harness | | | |\n| harness engineering | harness engineering | | | |\n| lint | lint | | | |\n| mock | mock | | | 保留英文;指测试替身 |\n| loader | loader | | | |\n| manifest | manifest | manifest(元数据清单) | | |\n| monorepo | monorepo | | | |\n| Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时,领域层级为 Session > Round > Turn(轮次) > Step(步骤);Round 是可选的外层策略迭代,并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次,步骤隶属于该轮次;明确的零步骤轮次仍保持原义。 |\n| schema | schema | | | |\n| schema DSL | schema DSL | | | |\n| seam | seam | | | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` |\n| skill | skill | skill(技能) | | |\n| spawn | spawn | | | |\n| steering | steering | steering(中途引导) | | |\n| task id | task id | | 任务 id | 保留英文 |\n| subagent | subagent | | | |\n| thinking | thinking | | | API 字段保留英文;描述模型模式时译为`思考` |\n| transcript | transcript | transcript(文本记录) | | 指会话渲染给用户或编辑器的完整文本,区别于事件日志 |\n| waterfall | waterfall | waterfall(瀑布式事件) | | |\n| wheel | wheel 包 | | | Python 打包格式 |\n| worktree | worktree | | | git 工作区概念 |\n| Zstandard | Zstandard | | | RFC 8878 compression format; `zstd` remains a code value. |\n\n## 双语类(中英文文本各自使用中英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| adapter | 适配器 | | | |\n| adapter contract | 适配器契约 | 适配器契约(adapter contract) | | |\n| append-only | 仅追加 | | | |\n| artifact | 产物 | | | |\n| backend | 后端 | | | |\n| background task | 后台任务 | | | |\n| block | 块 | | | |\n| build target | 构建目标 | | | |\n| cancel | 取消 | | | |\n| feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 |\n| feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 |\n| checkpoint | 检查点 | | | |\n| chunk | 分片 | | | |\n| compaction | 压缩 | 压缩(compaction) | | |\n| companion tool | 配套工具 | | | |\n| Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 |\n| config key | 配置键 | | | Cordis 插件配置中的单个字段 |\n| consumer | 消费方 | | | |\n| content block | 内容块 | | | |\n| Cookbook | 实操手册 | | | 文档标题用语 |\n| context | 上下文 | | | |\n| counterpart | 对侧文件 | | 对应物、配对物 | 双语配对语境;泛指\"另一侧\"时可写「另一侧」 |\n| context compaction | 上下文压缩 | 上下文压缩(context compaction) | | |\n| contract | 契约 | | | 如:`pairing contract` →`配对契约` |\n| Cordis config entry | Cordis 配置项 | | | 指 `cordis.yml` 插件列表中的一项;插件实现本身写`Cordis 插件` |\n| Cordis plugin | Cordis 插件 | | | Cordis 加载的插件实现,不指 `cordis.yml` 中的一项配置 |\n| coverage | 覆盖率 | | | |\n| crash recovery | 崩溃恢复 | | | |\n| deploy root | 部署根目录 | | | |\n| durability | 持久性 | | | |\n| feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 |\n| ergonomics | 易用性 / 开发体验 | | 人体工学 | API 或面向模型的接口用「易用性」;工具链或开发者工作流用「开发体验」 |\n| event | 事件 | | | |\n| event log | 事件日志 | | | |\n| event stream | 事件流 | | | |\n| event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 |\n| Executive summary | 摘要 | | | 事故复盘标题用语 |\n| executor | 执行器 | | | |\n| expected output | 预期输出 | | 金标 | 指 snapshot 比较产物;翻译语料的人工校准样例不在此列 |\n| extension | 扩展 | | | |\n| extension point | 扩展点 | | | 注意与 `seam` 区分 |\n| fail-fast | 快速失败 | | | |\n| fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |\n| fingerprint | 指纹 | | | 通用内容指纹;双语配对机制使用 sidecar record 记录两侧 blob hash |\n| finish reason | 结束原因 | | | |\n| foreground run | 前台运行 | | | |\n| freshness | 新鲜度 | | | 沿用 MDN 中文翻译;在本项目中指译文相对源文的同步状态 |\n| hook | 钩子 | | | |\n| implementation | 实现 | | | |\n| inference | 推理 | 推理(inference) | | 需要和 `reasoning` 区分时保留英文括注 |\n| info string | 信息字符串 | | | 沿用 CommonMark 中文翻译;指代码围栏 ``` 之后的语言标注 |\n| injection | 注入 | | | |\n| integration | 集成 | | | |\n| interface | 接口 | | | |\n| language switcher | 语言切换行 | | | i18n 配对机制用语:双语配对文件顶部的互链行 |\n| memory | 记忆 / 内存 | | | 与 `agent` 搭配时译为`记忆`(如 `agent memory` →`智能体记忆`);指系统资源时译为`内存` |\n| merge | 合并 | | | |\n| message | 消息 | | | |\n| mod | 模组 | | | |\n| model provider | 模型提供方 | | | |\n| module | 模块 | | | |\n| non-escalation | 非升权 | | 非升级、不可升级 | 仅用于安全与权限语境,指主体不得获得超出既有授权的权限;普通升级不适用此行 |\n| npm dependency | NPM 依赖 | | | `package.json` 中的包关系;`dependencies`、`devDependencies` 等字段保持原样 |\n| opt-out ratio | opt-out 比例 | | 退出检查比例 | |\n| orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`(如「遗留译文」);进程语境按 OS 惯用语译「孤儿进程」 |\n| orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |\n| package | 包 | 包(package) | | 指 npm 包(`@deepseek-ai/dsh-*`);`package.json` 等代码标识保持原样 |\n| pairing | 配对 | | | |\n| parent-subset grants | 父级子集授权 | | 父集合授权 | 指授权范围仅限于父级所持授权的子集 |\n| peer dependency | 对等依赖 | 对等依赖(peer dependency) | | |\n| permission | 权限 | | | |\n| persistence | 持久化 | | | |\n| pipeline | 流水线 | | | |\n| plugin | 插件 | | | |\n| prompt | 提示词 | | | |\n| provider | 提供方 | | | |\n| provider-neutral | 提供方无关 | | | |\n| quality gate | 质量门禁 | | | |\n| quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 |\n| reasoning | 推理 | 推理(reasoning) | | 需要和 `inference` 区分时保留英文括注 |\n| reasoning_content | 思考内容 | | | |\n| registry | 注册表 | | | |\n| replay | 回放 | | | |\n| resume | 恢复 | | | |\n| runtime | 运行时 | | | |\n| same-world subprocess | 与宿主共享文件系统和内核的子进程 | | 同世界子进程 | |\n| sandbox | 沙箱 | | | |\n| service | 服务 | | | |\n| serving surface | 对外服务接口 | | | |\n| session | 会话 | | | |\n| session event | 会话事件 | | | |\n| sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 |\n| smoke test | 冒烟测试 | | | |\n| snapshot | 快照 | | | |\n| source of truth | 真源 | | | |\n| spine | 主干 | | | |\n| staged | 暂存 | | | 沿用 git 官方中文翻译 |\n| stale | 陈旧 | | 过期 | 与 `fresh`(`新鲜`)成对;门禁输出中保留英文 `stale` 不翻译;`expired` 才译为`过期` |\n| step | 步骤 | | | |\n| stream | 流 | | | |\n| streaming | 流式输出 | | | |\n| structural signature | 结构签名 | | | i18n 配对机制用语:门禁比对两侧文件时提取的有序结构序列(标题层级、代码块、列表等) |\n| Summary | 概述 | | | 事故复盘标题用语 |\n| system prompt | 系统提示词 | | | |\n| taxonomy | 分类体系 | | | |\n| token usage | token 用量 | | | |\n| tool | 工具 | | | |\n| tool call | 工具调用 | | | |\n| tool result | 工具结果 | | | |\n| tool schema | 工具 schema | | | |\n| toolkit | 工具包 | | | |\n| turn | 轮次 | | | |\n| VFS | VFS | 虚拟文件系统(VFS) | | |\n| typecheck | 类型检查 | | | |\n| vocabulary | 词汇 | | | |\n| wire format | 协议格式 | 协议格式(wire format) | | |\n| workflow | 工作流 | | | |\n| wrapper | 包装层 | | | 软件层或 SDK 包装层 |\n| wrapper script | 包装脚本 | | | 可执行脚本包装层 |\n\n\n## Output Format\n\nProduce your output in three XML sections:\n\nThe outer section tags are framing. If Markdown inside any section body contains a line consisting only of ``, ``, ``, ``, ``, or ``, prefix that line with `\\`. If the original line already has one or more backslashes immediately before the tag, add one more. The parser removes exactly one framing escape; tags mentioned inline need no escaping.\n\n```xml\n\n(Complete translation of the source document)\n\n\n\n(Self-review notes, one correction per line with category tag, e.g.)\n- [Tone] \"旁挂记录\" → \"伴随记录\"(生造词)\n- [Sentence] 第 3 段补充逗号断句\n- [Punctuation] 两处破折号替换为冒号\n- 无修正\n\n\n\n(Final translation after corrections)\n\n```\n\n## Self-Review Instructions\n\nAfter writing ``, re-read it in the target language only, without looking at the source. Check by category:\n\n**Structure**\n- Is the heading hierarchy, list shape, and code block content identical to the source?\n- Are ALL comments inside code blocks left untranslated (byte-identical to source)?\n- Is the language switcher line correctly flipped (not copied from source)?\n- Are link targets preserved, and are spaces after bold markers present only before Latin letters, digits, or CJK ideographs?\n- Are wrapper-tag lines inside section bodies escaped with one additional backslash?\n\n**Tone & Style**\n- Does every sentence read as if originally written by a native speaker?\n- Is there any colloquial, casual, or overly informal phrasing?\n\n**Sentence Structure**\n- Are there run-on sentences that need breaking?\n- Are there stiff passive constructions that should be converted to active voice?\n\n**Word Choice**\n- Are there overly literal translations that sound unnatural?\n- Is the same target-language word used to translate two distinct source concepts?\n- Is any slang or internal jargon present?\n\n**Terminology**\n- For a Chinese target, are first-occurrence glosses correctly applied (not missing, not repeated)? For an English target, are Chinese glosses absent?\n- Are any \"不要译作\" forbidden translations present?\n- For unlisted terms, does a Chinese target use established Chinese precedent or retain the source term as pending, and does an English target use established English terminology or preserve only an ambiguous source term with a short English gloss?\n\n**Punctuation** (when target is Chinese)\n- Are there em-dashes that should be replaced with colons, periods, or commas?\n- Are list items ending with commas instead of semicolons?\n- Do RFC 2119 keywords preserve the source emphasis exactly?\n\nRecord corrections in `` with category tags. Then output the corrected version in ``. If no corrections are needed, write \"无修正\" in `` and copy the translation unchanged into ``.\n\n## Examples\n\nBelow are representative examples of common problems and their corrections. Follow the \"Good\" versions.\n\n### Colloquial verb → Professional verb\n- Source: `The repo pins pnpm@11.7.0 in package.json`\n- Bad: `仓库在 package.json 中钉住 pnpm@11.7.0`\n- Good: `该仓库在 package.json 中固定使用 pnpm@11.7.0`\n\n### Run-on sentence → Natural phrasing with pause\n- Source: `Read docs/architecture.md before changing anything under packages/.`\n- Bad: `改动 packages/ 下的任何东西之前先读 docs/architecture.md。`\n- Good: `在修改 packages/ 目录下的任何内容之前,请先阅读 docs/architecture.md。`\n\n### Stiff passive voice → Active and natural\n- Source: `a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.`\n- Bad: `门禁绿意味着这对文档曾在当前内容上被确认一致,不意味着这次确认本身是对的。`\n- Good: `门禁通过意味着这组文档在当前内容上的一致性得到了确认,不代表确认本身正确可靠。`\n\n### Invented word → Natural expression\n- Source: `A sidecar record of both blob hashes makes consistency checkable`\n- Bad: `旁挂记录两侧 blob hash,使一致性可检查`\n- Good: `伴随记录保存两侧 blob hash,使一致性可检查`\n\n### Em-dash → Colon/period\n- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`\n- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入,发布不应带着未解决的 FIXME 出门。`\n- Good: `FIXME:应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并,否则发布版本不应包含未解决的 FIXME。`\n\n### Overly literal → Meaningful rendering\n- Source: `awkward phrasing is easier to hear without the source anchoring you`\n- Bad: `没有源文锚着,别扭的表述更容易被听出来`\n- Good: `不对照原文时,更容易察觉别扭的表达`\n\n### Terminology — do not translate what should be kept in English\n- Source: `typed service seams, and explicit extension points`\n- Bad: `类型化的服务 seam(扩展点)与显式扩展点`\n- Good: `类型化的服务 seam 与显式扩展点`\n\n### Slang/jargon → Professional phrasing\n- Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`\n- Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`\n- Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`\n\n### \"For humans\" — translate the intent, not the word\n- Source: `For humans, start with the development guide`\n- Bad: `对于人工读者,请先从开发指南开始`(\"人工读者\"生硬)\n- Good: `面向开发者:请先阅读开发指南`(\"开发者\"自然,且中文里冒号在此处更自然)\n\n### Code block comments — NEVER translate\n- Source code block contains: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)`\n- Bad: `# 全屏 TUI coding agent(需要 DEEPSEEK_API_KEY)`\n- Good: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)\n\n### Language switcher — flip direction\n- Source file (English) has: `English | [中文](README.zh.md)`\n- Bad (copying source unchanged): `English | [中文](README.zh.md)`\n- Good (flipped for Chinese file): `[English](README.md) | 中文`\n\n---\n\nNow translate the following document:" + "content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from English to Chinese, producing natural, professional technical prose.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.\n- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.\n- Language switcher line: when translating into Chinese, write `[English](source-filename.md) | 中文`. When translating into English, write `English | [中文](source-filename.zh.md)`. Do NOT copy the switcher line from the source file unchanged — you must flip the link direction.\n- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter, digit, or CJK ideograph. Never insert a space before any punctuation (full-width or half-width).\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Use polite imperative forms where the text instructs the reader to do something.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences with commas or semicolons. Avoid run-on sentences.\n- Prefer active voice. Convert passive constructions to active if it reads more naturally.\n- Translate meaning, not words. Restructure sentences where the target language grammar requires it.\n- Do not invent words or expressions that do not exist in natural technical writing of the target language.\n\n### Word Choice\n- Prefer precise, formal vocabulary over casual or colloquial alternatives.\n- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.\n- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.\n- Do not use the same word to translate two different source-language terms that carry distinct meanings.\n- Avoid repeating the same verb in close proximity; vary word choice for readability.\n\n#### When translating into Chinese\n- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: \"three-package seam\" → \"由三个包构成的 seam\", not \"三包 seam\".\n\n### Punctuation\n\n#### When translating into Chinese\n- Use full-width Chinese punctuation in prose: `,。:;?!()「」`.\n- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.\n- Use enumeration commas (、) between parallel items, not regular commas.\n- List item endings: use semicolons or no punctuation. Do not end list items with commas.\n- Put one half-width space between Chinese text and Latin words/numbers.\n- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), translate to the corresponding Chinese term (必须、禁止、应当、可以) and keep the SOURCE emphasis marker: plain source stays plain (必须), italic source stays italic (*必须*), and bold source stays bold (**必须**).\n\n#### When translating into English\n(To be added.)\n\n## Terminology\n\nA terminology table is provided below. Follow it strictly:\n- Render every listed term exactly as specified.\n- When the target language is Chinese, use the \"中文\" column. On first occurrence, write the \"首次出现\" value with its parenthetical gloss; on subsequent occurrences, write only the part before the parentheses.\n- When the target language is English, use the \"English\" column without a Chinese gloss; do not copy the \"中文\" or \"首次出现\" value into English prose.\n- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.\n- NEVER use translations listed in the \"不要译作\" column.\n- For technical terms not in the table, follow the target language: for a Chinese target, use an established Chinese rendering from a major Chinese-language OSS or vendor source, or keep the source term and flag it as pending when no such precedent exists; for an English target, use the established English technical term, or preserve an ambiguous source term with a short English gloss and flag it as pending. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.\n\n# Terminology\n\n本表约定本仓库的中英术语统一译法。\n\n**通用规则:**\n- \"中文\"列为中文译文的正文默认用词。若该列为英文,则中文译文的正文中保留英文不翻译。\n- 首次出现按\"首次出现\"列书写(带括号注释);后续出现只写括号前的部分(可能为中文,也可能为英文),不出现括号内的注释。\n- \"不要译作\"列为严格禁止的译法。\n- 如果某术语已经作为另一个术语的组成部分被括注过(如 `agent loop(智能体循环)` 中已包含 `agent` 的括注),则该术语后续单独出现时无需再次括注。\n\n## 缩写类(中英文文本中均使用缩写)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| ACP | ACP | ACP(Agent Client Protocol) | | |\n| AI | AI | AI(人工智能) | | |\n| API | API | | | |\n| CI | CI | | | |\n| CLI | CLI | CLI(命令行界面) | | |\n| e2e | e2e | | | |\n| HMR | HMR | HMR(热模块替换) | | |\n| JSON Schema | JSON Schema | | | |\n| JSONL | JSONL | | | |\n| LLM | LLM | LLM(大语言模型) | | |\n| MCP | MCP | | | |\n| PR | PR | PR(Pull Request) | | |\n| RAG | RAG | RAG(检索增强生成) | | |\n| SDK | SDK | | | |\n| SSE | SSE | SSE(Server-Sent Events) | | |\n\n## 英文类(中英文文本中均使用英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| agent | agent | agent(智能体) | | |\n| Agent Note | Agent Note | Agent Note(agent 决策记录) | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 |\n| agent harness | agent harness | agent harness(智能体框架) | | agent 组合词(agent harness/workflow/loop/skill 等)整体保留英文;未括注过 agent 时首现按对应组合词或 agent 行处理 |\n| agent loop | agent loop | agent loop(智能体循环) | | |\n| blob hash | blob hash | | | `git hash-object` 的结果 |\n| capability seam | 能力 seam | | 功能 seam、能力接缝 | 本仓库接口、实现与消费方分离的命名架构概念;普通 `seam` 仍按其词条处理 |\n| Cordis | Cordis | | | |\n| dispose | dispose | dispose(资源释放) | | |\n| doc-sync | doc-sync | doc-sync(文档同步门禁) | | |\n| fiber | fiber | | | |\n| fixture | fixture | fixture(测试前置数据) | | |\n| fork | fork | | | |\n| Function Calling | Function Calling | Function Calling(函数调用) | | |\n| harness | harness | | | |\n| harness engineering | harness engineering | | | |\n| lint | lint | | | |\n| mock | mock | | | 保留英文;指测试替身 |\n| loader | loader | | | |\n| manifest | manifest | manifest(元数据清单) | | |\n| monorepo | monorepo | | | |\n| Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时,领域层级为 Session > Round > Turn(轮次) > Step(步骤);Round 是可选的外层策略迭代,并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次,步骤隶属于该轮次;明确的零步骤轮次仍保持原义。 |\n| schema | schema | | | |\n| schema DSL | schema DSL | | | |\n| seam | seam | | 接缝 | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` |\n| skill | skill | skill(技能) | | |\n| spawn | spawn | | | |\n| steering | steering | steering(中途引导) | | |\n| task id | task id | | 任务 id | 保留英文 |\n| subagent | subagent | | | |\n| thinking | thinking | | | API 字段保留英文;描述模型模式时译为`思考` |\n| transcript | transcript | transcript(文本记录) | | 指会话渲染给用户或编辑器的完整文本,区别于事件日志 |\n| waterfall | waterfall | waterfall(瀑布式事件) | | |\n| wheel | wheel 包 | | | Python 打包格式 |\n| worktree | worktree | | | git 工作区概念 |\n| Zstandard | Zstandard | | | RFC 8878 compression format; `zstd` remains a code value. |\n\n## 双语类(中英文文本各自使用中英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| adapter | 适配器 | | | |\n| adapter contract | 适配器契约 | 适配器契约(adapter contract) | | |\n| append-only | 仅追加 | | | |\n| artifact | 产物 | | 制品 | |\n| backend | 后端 | | | |\n| background task | 后台任务 | | | |\n| block | 块 | | | |\n| build target | 构建目标 | | | |\n| cancel | 取消 | | | |\n| canary test | canary 测试 | | 金丝雀测试 | 本仓库保留 `canary` |\n| feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 |\n| feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 |\n| checkpoint | 检查点 | | | |\n| chunk | 分片 | | | |\n| compaction | 压缩 | 压缩(compaction) | | |\n| companion tool | 配套工具 | | | |\n| composition bundle | 组合包 | | | 只约束应用或插件的组合语境,不约束所有 `bundle` |\n| Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 |\n| config key | 配置键 | | | Cordis 插件配置中的单个字段 |\n| consumer | 消费方 | | 消费者 | |\n| content block | 内容块 | | | |\n| Cookbook | 实操手册 | | | 文档标题用语 |\n| context | 上下文 | | | |\n| counterpart | 对侧文件 | | 对应物、配对物 | 双语配对语境;泛指\"另一侧\"时可写「另一侧」 |\n| context compaction | 上下文压缩 | 上下文压缩(context compaction) | | |\n| contract | 契约 | | | 如:`pairing contract` →`配对契约` |\n| Cordis config entry | Cordis 配置项 | | | 指 `cordis.yml` 插件列表中的一项;插件实现本身写`Cordis 插件` |\n| Cordis plugin | Cordis 插件 | | | Cordis 加载的插件实现,不指 `cordis.yml` 中的一项配置 |\n| coverage | 覆盖率 | | | |\n| crash recovery | 崩溃恢复 | | | |\n| deploy root | 部署根目录 | | | |\n| durability | 持久性 | | | |\n| feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 |\n| ergonomics | 易用性 / 开发体验 | | 人体工学 | API 或面向模型的接口用「易用性」;工具链或开发者工作流用「开发体验」 |\n| event | 事件 | | | |\n| event log | 事件日志 | | | |\n| event stream | 事件流 | | | |\n| event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 |\n| Executive summary | 摘要 | | | 事故复盘标题用语 |\n| executor | 执行器 | | | |\n| expected output | 预期输出 | | 金标 | 指 snapshot 比较产物;翻译语料的人工校准样例不在此列 |\n| extension | 扩展 | | | |\n| extension point | 扩展点 | | | 注意与 `seam` 区分 |\n| fail-fast | 快速失败 | | | |\n| fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |\n| fingerprint | 指纹 | | | 通用内容指纹;双语配对机制使用 sidecar record 记录两侧 blob hash |\n| finish reason | 结束原因 | | | |\n| foreground run | 前台运行 | | | |\n| freshness | 新鲜度 | | | 沿用 MDN 中文翻译;在本项目中指译文相对源文的同步状态 |\n| hook | 钩子 | | | |\n| implementation | 实现 | | | |\n| inference | 推理 | 推理(inference) | | 需要和 `reasoning` 区分时保留英文括注 |\n| info string | 信息字符串 | | | 沿用 CommonMark 中文翻译;指代码围栏 ``` 之后的语言标注 |\n| injection | 注入 | | | |\n| integration | 集成 | | | |\n| interface | 接口 | | | |\n| language switcher | 语言切换行 | | | i18n 配对机制用语:双语配对文件顶部的互链行 |\n| memory | 记忆 / 内存 | | | 与 `agent` 搭配时译为`记忆`(如 `agent memory` →`智能体记忆`);指系统资源时译为`内存` |\n| merge | 合并 | | | |\n| message | 消息 | | | |\n| mod | 模组 | | | |\n| model provider | 模型提供方 | | | |\n| module | 模块 | | | |\n| non-escalation | 非升权 | | 非升级、不可升级 | 仅用于安全与权限语境,指主体不得获得超出既有授权的权限;普通升级不适用此行 |\n| npm dependency | NPM 依赖 | | | `package.json` 中的包关系;`dependencies`、`devDependencies` 等字段保持原样 |\n| opt-out ratio | opt-out 比例 | | 退出检查比例 | |\n| orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`(如「遗留译文」);进程语境按 OS 惯用语译「孤儿进程」 |\n| orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |\n| package | 包 | 包(package) | | 指 npm 包(`@deepseek-ai/dsh-*`);`package.json` 等代码标识保持原样 |\n| pairing | 配对 | | | |\n| parent-subset grants | 父级子集授权 | | 父集合授权 | 指授权范围仅限于父级所持授权的子集 |\n| peer dependency | 对等依赖 | 对等依赖(peer dependency) | | |\n| permission | 权限 | | | |\n| persistence | 持久化 | | | |\n| pipeline | 流水线 | | | |\n| plugin | 插件 | | | |\n| postmortem | 事故复盘 | 事故复盘(postmortem) | 事后分析、事故记录 | 事故记录与分析文档;目录或路径中的 `postmortem` 保持代码形式 |\n| prompt | 提示词 | | | |\n| provider | 提供方 | | | |\n| provider-neutral | 提供方无关 | | 提供方中立 | |\n| quality gate | 质量门禁 | | | |\n| quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 |\n| reasoning | 推理 | 推理(reasoning) | | 需要和 `inference` 区分时保留英文括注 |\n| reasoning_content | 思考内容 | | | |\n| registry | 注册表 | | | |\n| replay | 回放 | | | |\n| resume | 恢复 | | | |\n| runtime | 运行时 | | | |\n| same-world subprocess | 与宿主共享文件系统和内核的子进程 | | 同世界子进程 | |\n| sandbox | 沙箱 | | | |\n| service | 服务 | | | |\n| serving surface | 对外服务接口 | | | |\n| session | 会话 | | | |\n| session event | 会话事件 | | | |\n| sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 |\n| smoke test | 冒烟测试 | | | |\n| snapshot | 快照 | | | |\n| source of truth | 真源 | | 事实来源、唯一来源 | |\n| spine | 主干 | | | |\n| staged | 暂存 | | | 沿用 git 官方中文翻译 |\n| stale | 陈旧 | | 过期 | 与 `fresh`(`新鲜`)成对;门禁输出中保留英文 `stale` 不翻译;`expired` 才译为`过期` |\n| step | 步骤 | | | |\n| stream | 流 | | | |\n| streaming | 流式输出 | | | |\n| structural signature | 结构签名 | | | i18n 配对机制用语:门禁比对两侧文件时提取的有序结构序列(标题层级、代码块、列表等) |\n| Summary | 概述 | | | 事故复盘标题用语 |\n| system prompt | 系统提示词 | | | |\n| taxonomy | 分类体系 | | | |\n| token usage | token 用量 | | | |\n| tool | 工具 | | | |\n| tool call | 工具调用 | | | |\n| tool result | 工具结果 | | | |\n| tool schema | 工具 schema | | | |\n| toolkit | 工具包 | | | |\n| turn | 轮次 | | | |\n| VFS | VFS | 虚拟文件系统(VFS) | | |\n| typecheck | 类型检查 | | | |\n| vocabulary | 词汇 | | | |\n| wire format | 协议格式 | 协议格式(wire format) | | |\n| workflow | 工作流 | | | |\n| wrapper | 包装层 | | | 软件层或 SDK 包装层 |\n| wrapper script | 包装脚本 | | | 可执行脚本包装层 |\n\n\n## Output Format\n\nProduce your output in three XML sections:\n\nThe outer section tags are framing. If Markdown inside any section body contains a line consisting only of ``, ``, ``, ``, ``, or ``, prefix that line with `\\`. If the original line already has one or more backslashes immediately before the tag, add one more. The parser removes exactly one framing escape; tags mentioned inline need no escaping.\n\n```xml\n\n(Complete translation of the source document)\n\n\n\n(Self-review notes, one correction per line with category tag, e.g.)\n- [Tone] \"旁挂记录\" → \"伴随记录\"(生造词)\n- [Sentence] 第 3 段补充逗号断句\n- [Punctuation] 两处破折号替换为冒号\n- 无修正\n\n\n\n(Final translation after corrections)\n\n```\n\n## Self-Review Instructions\n\nAfter writing ``, re-read it in the target language only, without looking at the source. Check by category:\n\n**Structure**\n- Is the heading hierarchy, list shape, and code block content identical to the source?\n- Are ALL comments inside code blocks left untranslated (byte-identical to source)?\n- Is the language switcher line correctly flipped (not copied from source)?\n- Are link targets preserved, and are spaces after bold markers present only before Latin letters, digits, or CJK ideographs?\n- Are wrapper-tag lines inside section bodies escaped with one additional backslash?\n\n**Tone & Style**\n- Does every sentence read as if originally written by a native speaker?\n- Is there any colloquial, casual, or overly informal phrasing?\n\n**Sentence Structure**\n- Are there run-on sentences that need breaking?\n- Are there stiff passive constructions that should be converted to active voice?\n\n**Word Choice**\n- Are there overly literal translations that sound unnatural?\n- Is the same target-language word used to translate two distinct source concepts?\n- Is any slang or internal jargon present?\n\n**Terminology**\n- For a Chinese target, are first-occurrence glosses correctly applied (not missing, not repeated)? For an English target, are Chinese glosses absent?\n- Are any \"不要译作\" forbidden translations present?\n- For unlisted terms, does a Chinese target use established Chinese precedent or retain the source term as pending, and does an English target use established English terminology or preserve only an ambiguous source term with a short English gloss?\n\n**Punctuation** (when target is Chinese)\n- Are there em-dashes that should be replaced with colons, periods, or commas?\n- Are list items ending with commas instead of semicolons?\n- Do RFC 2119 keywords preserve the source emphasis exactly?\n\nRecord corrections in `` with category tags. Then output the corrected version in ``. If no corrections are needed, write \"无修正\" in `` and copy the translation unchanged into ``.\n\n## Examples\n\nBelow are representative examples of common problems and their corrections. Follow the \"Good\" versions.\n\n### Colloquial verb → Professional verb\n- Source: `The repo pins pnpm@11.7.0 in package.json`\n- Bad: `仓库在 package.json 中钉住 pnpm@11.7.0`\n- Good: `该仓库在 package.json 中固定使用 pnpm@11.7.0`\n\n### Run-on sentence → Natural phrasing with pause\n- Source: `Read docs/architecture.md before changing anything under packages/.`\n- Bad: `改动 packages/ 下的任何东西之前先读 docs/architecture.md。`\n- Good: `在修改 packages/ 目录下的任何内容之前,请先阅读 docs/architecture.md。`\n\n### Stiff passive voice → Active and natural\n- Source: `a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.`\n- Bad: `门禁绿意味着这对文档曾在当前内容上被确认一致,不意味着这次确认本身是对的。`\n- Good: `门禁通过意味着这组文档在当前内容上的一致性得到了确认,不代表确认本身正确可靠。`\n\n### Invented word → Natural expression\n- Source: `A sidecar record of both blob hashes makes consistency checkable`\n- Bad: `旁挂记录两侧 blob hash,使一致性可检查`\n- Good: `伴随记录保存两侧 blob hash,使一致性可检查`\n\n### Em-dash → Colon/period\n- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`\n- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入,发布不应带着未解决的 FIXME 出门。`\n- Good: `FIXME:应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并,否则发布版本不应包含未解决的 FIXME。`\n\n### Overly literal → Meaningful rendering\n- Source: `awkward phrasing is easier to hear without the source anchoring you`\n- Bad: `没有源文锚着,别扭的表述更容易被听出来`\n- Good: `不对照原文时,更容易察觉别扭的表达`\n\n### Terminology — do not translate what should be kept in English\n- Source: `typed service seams, and explicit extension points`\n- Bad: `类型化的服务 seam(扩展点)与显式扩展点`\n- Good: `类型化的服务 seam 与显式扩展点`\n\n### Slang/jargon → Professional phrasing\n- Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`\n- Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`\n- Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`\n\n### \"For humans\" — translate the intent, not the word\n- Source: `For humans, start with the development guide`\n- Bad: `对于人工读者,请先从开发指南开始`(\"人工读者\"生硬)\n- Good: `面向开发者:请先阅读开发指南`(\"开发者\"自然,且中文里冒号在此处更自然)\n\n### Code block comments — NEVER translate\n- Source code block contains: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)`\n- Bad: `# 全屏 TUI coding agent(需要 DEEPSEEK_API_KEY)`\n- Good: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)\n\n### Language switcher — flip direction\n- Source file (English) has: `English | [中文](README.zh.md)`\n- Bad (copying source unchanged): `English | [中文](README.zh.md)`\n- Good (flipped for Chinese file): `[English](README.md) | 中文`\n\n---\n\nNow translate the following document:" }, { "role": "user", From 333b4bcd30fd211fdfbc657853fc4cda10f593c8 Mon Sep 17 00:00:00 2001 From: j-xiang Date: Wed, 29 Jul 2026 15:29:24 +0800 Subject: [PATCH 15/38] docs(i18n): proofread README translations 1-20 --- .agents/notes/README.zh.md | 14 ++++---- docs/postmortem/README.zh.md | 6 ++-- examples/README.zh.md | 14 ++++---- examples/acp-agent/README.zh.md | 12 +++---- examples/cordis-agent/README.zh.md | 8 ++--- examples/headless-agent/README.zh.md | 10 +++--- examples/jsonrpc-agent/README.zh.md | 8 ++--- examples/tui-agent/README.zh.md | 30 ++++++++-------- native/README.zh.md | 6 ++-- native/landlock-run/README.zh.md | 8 ++--- .../landlock-run/packages/entry/README.zh.md | 6 ++-- .../packages/linux-arm64/README.zh.md | 4 +-- .../packages/linux-x64/README.zh.md | 4 +-- packages/acp/README.zh.md | 4 +-- packages/acp/acp/README.zh.md | 36 +++++++++---------- packages/bash/README.zh.md | 4 +-- packages/bash/bash-local/README.zh.md | 14 ++++---- packages/bash/bash-sandbox/README.zh.md | 28 +++++++-------- packages/bash/bash/README.zh.md | 14 ++++---- 19 files changed, 115 insertions(+), 115 deletions(-) diff --git a/.agents/notes/README.zh.md b/.agents/notes/README.zh.md index ddecac7951..a3369a94c6 100644 --- a/.agents/notes/README.zh.md +++ b/.agents/notes/README.zh.md @@ -11,7 +11,7 @@ - **生命周期**(顶层文件夹)是 Agent Note 的状态,Agent Note 随状态变化在文件夹之间移动: - **`proposed/`**:实施前评审的提案;尚未构建(或仅部分构建)。 - **`implemented/`**:决策已交付。文件记录做了什么决定、否决了什么,并**与实际交付的内容保持同步**:当代码后续移动文件、重命名包(package)或更改键名/默认值时,Agent Note 在同一个变更中同步更新(仅限事实——路径、名称、结构——而非决策本身)。见 [implemented/AGENTS.md](implemented/AGENTS.md)。 - - **`rejected/`**:提案经过讨论后被否决。仅当其决策依据仍能避免一种诱人且影响重大的错误时保留;否则删除完整的三个配对文件。 + - **`rejected/`**:提案经过讨论后被否决。仅当其决策依据仍能避免一种诱人且影响重大的错误时保留;否则删除完整的英文、中文和伴随记录三文件组。 - **类别**(嵌套文件夹)是决策的*种类*——见下方[分类](#classification)。 文件名中的日期是该主题**首次提出**的时间(以 git 历史为准)。Agent Note 之间的交叉引用使用相对 Markdown 链接(`[topic](../../implemented/architecture/2026-…-….md)`),从不使用纯文字或编号,这样既可机械检查,也能在文件夹间移动时保持有效。 @@ -28,7 +28,7 @@ |---|---| | `feature` | 面向用户或模型的新功能。 | | `bug-fix` | 修正缺陷或弥补事故复盘(postmortem)发现的缺口。 | -| `simplification` | 在不增加功能的前提下移除代码、行为或对外表面积。 | +| `simplification` | 在不增加功能的前提下移除代码、行为或对外范围。 | | `architecture` | 关于**交付源码**的结构性决策:包之间的关系、运行时词汇。 | | `process` | 代码**周边**的工具、策略或工作流——门禁、包管理器、vendor 化——不涉及运行时行为。 | | `testing` | 测试基础设施与策略。 | @@ -39,13 +39,13 @@ 当一份 implemented Agent Note 记录的交付决策已经完整落地,且其决策依据不太可能再指导未来工作时,将其归档。如果其中的备选方案、归属边界、否定性保证、持久化语义或协议语义、安全规则,或者重新引入条件仍有价值,则继续作为活跃记录保留。绝不归档 proposed Agent Note:过时的提案应转为 rejected。仅当 rejected Agent Note 仍能避免一种可能发生的错误时保留;否则一并删除其英文、中文和伴随记录文件。请使用经过校准的 [`dsh-archive-agent-notes`](../skills/dsh-archive-agent-notes/SKILL.md) 工作流,不要根据字数、存续时间或目标配额来判断。 -归档路径编码为 `archived/{class}/yyyy-mm-dd-topic-title.md`;其中有意省略 `implemented`,因为只有 implemented Agent Note 可以进入归档。归档变更会移动完整的英文、中文和伴随记录三个文件,保留 `Status: implemented`,在两种语言的文件中紧接该状态行插入相同的 `Archived: YYYY-MM-DD` 行,重新记录伴随文件,并修复或删除入站链接。归档时只允许对内容做这些更改。 +归档路径编码为 `archived/{class}/yyyy-mm-dd-topic-title.md`;其中有意省略 `implemented`,因为只有 implemented Agent Note 可以进入归档。归档变更会移动完整的英文、中文和伴随记录三个文件,保留 `Status: implemented`,在两种语言的文件中紧接该状态行插入相同的 `Archived: YYYY-MM-DD` 行,重新记录伴随记录,并修复或删除入站链接。归档时只允许对内容做这些更改。 封存后,每组归档文件都永久冻结。禁止编辑、翻译、重新格式化、更新、移动或删除,也不得将其视为当前行为的权威依据。文档门禁会跳过归档源文件,包括其中的出站链接;当活跃文档有意引用历史时,仍可链接到归档 Agent Note。[`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) 强制执行封闭的类别目录树、完整的三文件配对、归档元数据、伴随记录 hash,以及仅追加的冻结内容 manifest。[归档政策 Agent Note](implemented/process/2026-07-26-frozen-agent-note-archive.md) 记录了设计依据。 ## 何时需要写一份 -每个非平凡变更都必须在同一 PR(Pull Request)中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包契约、流程或工具、测试策略、磁盘、协议或配置格式,或者其他维护者可能合理重新审视的决策,就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始;已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹(见[分类](#classification))。 +每个非平凡变更都必须在同一 PR(Pull Request)中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包契约、流程或工具、测试策略、磁盘存储格式、协议格式(wire format)或配置格式,或者其他维护者可能合理重新审视的决策,就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始;已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹(见[分类](#classification))。 更新已经拥有该决策的 Agent Note 即可满足规则;不要创建重复记录。只有不涉及行为、契约、结构、流程或理由变化的纯机械性或局部编辑才可豁免。Agent Note 永远不会被编辑为一个*不同的决策*:用新 Agent Note 取代旧记录,并让两个记录保持互相链接,除非后续依据下方规则完全合并旧记录。编辑 `implemented/` Agent Note 以跟踪其现有决策的所在位置是必需的,而非禁止的;见 [implemented/AGENTS.md](implemented/AGENTS.md)。 @@ -112,7 +112,7 @@ Status: ### 曾考虑的替代方案——必需 -每份 Agent Note 都必须包含 `## Alternatives considered` 章节:每个真实的替代方案及其落选原因,每个替代方案用一个加粗引导的段落,或对争议较大的替代方案用 `### Why not ?` 子节。记录决策时不记录它击败了什么,就是在邀请反复争论——正是这些 Agent Note 存在的意义所要防止的。 +每份 Agent Note 都必须包含 `## Alternatives considered` 章节:每个真实的替代方案及其落选原因,每个替代方案用一个加粗引导的段落,或对争议较大的替代方案用 `### Why not ?` 子节。记录决策时不记录它击败了什么,就是在邀请反复争论——这正是 Agent Note 旨在防止的问题。 替代方案是记录下来的,不是凭空编造的。日期早于 2026-07-05 且替代方案无法从记录中重建的 Agent Note,在该章节位置放置以下精确注释,门禁仅对格式规范之前的文件接受此注释: @@ -122,8 +122,8 @@ Status: ### 在生命周期之间移动 -将文件在生命周期文件夹之间移动意味着在同一个变更中更新 `Status:` 行并满足目标文件夹的骨架要求——否则门禁会失败。具体而言,`proposed/` → `implemented/` 将 `## Proposal` 改写为现在时态的 `## Decision`,将 `## Acceptance criteria` 和 `## Risks` 折入 `## Consequences`(或折入一个现在时态的 `## Testing`/`## Verification` 章节,用于描述现在锁定该行为的内容),并用实际交付的内容替换计划——即 [implemented/AGENTS.md](implemented/AGENTS.md) 所要求的改写,使之机械化。`proposed/` → `rejected/` 仅在 `Status:` 行添加原因并冻结文件。 +将文件在生命周期文件夹之间移动意味着在同一个变更中更新 `Status:` 行并满足目标文件夹的骨架要求——否则门禁会失败。具体而言,`proposed/` → `implemented/` 将 `## Proposal` 改写为现在时态的 `## Decision`,将 `## Acceptance criteria` 和 `## Risks` 折入 `## Consequences`(或折入一个现在时态的 `## Testing`/`## Verification` 章节,用于描述现在锁定该行为的内容),并用实际交付的内容替换计划——也就是将 [implemented/AGENTS.md](implemented/AGENTS.md) 所要求的改写变成可机械检查的规则。`proposed/` → `rejected/` 仅在 `Status:` 行添加原因并冻结文件。 ### 中文对侧文件 -`.zh.md` 对侧文件按 [i18n 契约](../../docs/i18n/README.md)逐章节镜像其英文兄弟文件的结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。 +`.zh.md` 对侧文件按 [i18n 契约](../../docs/i18n/README.md)逐章节镜像其英文对侧文件的结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。 diff --git a/docs/postmortem/README.zh.md b/docs/postmortem/README.zh.md index 2ce6de475c..e364ef30e3 100644 --- a/docs/postmortem/README.zh.md +++ b/docs/postmortem/README.zh.md @@ -2,13 +2,13 @@ [English](README.md) | 中文 -事故复盘:一个 bug 到达了它不该到达的地方(真实用户、已合并的 PR(Pull Request)、已发布的版本),值得关注的是*为什么我们的流程放过了它*,而不仅仅是那一行修复。 +事故复盘记录的是:一个 bug 流入了不该流入的环节(真实用户、已合并的 PR(Pull Request)、已发布的版本),值得关注的是*为什么我们的流程放过了它*,而不仅仅是那一行修复。 -事故复盘不是 [Agent Note(agent 决策记录)](../../.agents/notes/README.md)(Agent Note 记录一个经过深思熟虑的设计决策及其被否决的替代方案,或提出未来工作)。它是一份回顾性的失败记录:什么坏了、机制是什么、为什么每道安全网都没拦住、以及加了哪些具体的防护措施使同类 bug 下次能被显式暴露。 +事故复盘不是 [Agent Note(agent 决策记录)](../../.agents/notes/README.md)(Agent Note 记录一个经过深思熟虑的设计决策及其被否决的替代方案,或提出未来工作)。它是一份回顾性的失败记录:什么坏了、机制是什么、为什么每道安全网都没拦住、以及为此新增了哪些具体防护措施,以确保同类 bug 下次出现时会明确报错。 当一个 bug 满足以下条件时,请撰写事故复盘:**隐蔽**(机制不显而易见,即使是细心的工程师也得费力重新推导)、**系统性**(逃逸的原因是测试/工具/约定的缺口,而非一次性的笔误)、**重新发现的代价高**(它消耗了真实的调试时间,且下次还会如此)。请链接该事故复盘所推动建立的防护措施(测试、AGENTS.md 规则、ADR)。 -每篇事故复盘以一段**摘要**开头:一个简短段落,让忙碌的读者在三十秒内吸收要点——什么坏了、用直白的话说根因是什么、为什么逃逸了、持久的教训是什么——然后才是后续的详细「概述 / 时间线 / 根因 / 防护措施」各节。 +每篇事故复盘以一段**摘要**开头:一个简短段落,让忙碌的读者在三十秒内吸收要点——什么坏了、用直白的话说根因是什么、为什么逃逸了、可长期沿用的教训是什么——然后才是后续的详细「概述 / 时间线 / 根因 / 防护措施」各节。 | # | 标题 | |---|---| diff --git a/examples/README.zh.md b/examples/README.zh.md index 72ab92602d..6f2029fe48 100644 --- a/examples/README.zh.md +++ b/examples/README.zh.md @@ -2,11 +2,11 @@ [English](README.md) | 中文 -展示 harness 如何接线的可运行演示(不是 workspace)。每个示例都是一个 **轻量叶节点**:一份选择可替换后端、加载一个应用包(package)并可添加可选产品工具的 `cordis.yml`。组合和启动粘合代码位于 [`@deepseek-ai/dsh-tui-demo`](../packages/examples/tui-demo)、[`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo)、[`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 及它们共享的 [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) 组合包中。没有 `start.ts`;终端 `demo:*` 脚本通过 [`dsh`](../apps/cli/README.md) CLI(命令行界面)启动(该 CLI 挂载 `tui-demo` 组合包),无头/ACP(Agent Client Protocol)脚本则调用 `cli-demo`/`acp-demo` bin。 +展示 harness 如何组装的可运行演示(不是 workspace)。每个示例都是一个 **轻量叶节点**:一份选择可替换后端、加载一个应用包(package)并可添加可选产品工具的 `cordis.yml`。组合和启动粘合代码位于 [`@deepseek-ai/dsh-tui-demo`](../packages/examples/tui-demo)、[`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo)、[`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 及它们共享的 [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) 组合包中。没有 `start.ts`;终端 `demo:*` 脚本通过 [`dsh`](../apps/cli/README.md) CLI(命令行界面)启动(该 CLI 挂载 `tui-demo` 组合包),无头/ACP(Agent Client Protocol)脚本则调用 `cli-demo`/`acp-demo` bin。 ## headless-agent -非交互式 agent(智能体)演示:接受一个位置任务,在 `@deepseek-ai/dsh-cli-demo` 应用上运行一个完整模型/工具轮次,持久化新会话,打印 `text`、`json` 或 `stream-json`,然后退出。 +非交互式 agent(智能体)演示:接受一个位置参数形式的任务,在 `@deepseek-ai/dsh-cli-demo` 应用上运行一个完整模型/工具轮次,持久化新会话,打印 `text`、`json` 或 `stream-json`,然后退出。 运行:`pnpm run demo:headless "task"`(需要 `DEEPSEEK_API_KEY`)。输出契约、安全边界和快照套件详见 [headless-agent/README.md](headless-agent/README.md)。 @@ -18,18 +18,18 @@ ## jsonrpc-agent -通过 Python SDK 驱动的无人值守编码 agent:JSON-RPC stdio、仅前台 `bash`、`read`/`write`/`edit`、一个前台 `subagent`、`todo_write`、JSONL 持久化和压缩。它不包含终端 UI、stdout 日志、批准、skill 和后台任务控制。详见 [jsonrpc-agent/README.md](jsonrpc-agent/README.md)。 +通过 Python SDK 驱动的无人值守编码 agent:JSON-RPC stdio、仅前台 `bash`、`read`/`write`/`edit`、一个前台 `subagent`、`todo_write`、JSONL 持久化和压缩。它不包含终端 UI、stdout 日志、批准、skill(技能) 和后台任务控制。详见 [jsonrpc-agent/README.md](jsonrpc-agent/README.md)。 ## cordis-agent -**自指** 演示:编码主干加 [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis),其三个工具(`cordis_inspect`/`cordis_mount`/`cordis_unmount`)使 agent 可以检查当前 DSH 进程、挂载模型编写的临时 Plugin(事件监听器、一个全新工具,或一个供另一临时 Plugin 注入的服务),并再次卸载它们。这些 Plugin 只存在于内存中,共享一个内部 `cordis-dynamic` fiber 子树;`ctx.fs`/`ctx.web` 仅作为它们可用的能力提供方。 +**自指** 演示:编码主干加 [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis),其三个工具(`cordis_inspect`/`cordis_mount`/`cordis_unmount`)使 agent 可以检查当前 DSH 进程、挂载模型编写的临时插件(事件监听器、一个全新工具,或一个供另一临时插件 注入的服务),并再次卸载它们。这些插件 只存在于内存中,共享一个内部 `cordis-dynamic` fiber 子树;`ctx.fs`/`ctx.web` 仅作为它们可用的能力提供方。 -使用 `pnpm run demo:cordis` 运行 TUI,使用 `pnpm run demo:cordis web` 在 `http://127.0.0.1:3081` 启动浏览器 UI,或使用 `pnpm run demo:cordis acp` 启动 ACP 服务器(三者均需 `DEEPSEEK_API_KEY`)。分阶段演示脚本详见 [cordis-agent/README.md](cordis-agent/README.md),设计与沙箱注意事项详见[工具集 Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。 +使用 `pnpm run demo:cordis` 运行 TUI,使用 `pnpm run demo:cordis web` 在 `http://127.0.0.1:3081` 启动浏览器 UI,或使用 `pnpm run demo:cordis acp` 启动 ACP 服务器(三者均需 `DEEPSEEK_API_KEY`)。分阶段演示脚本详见 [cordis-agent/README.md](cordis-agent/README.md),设计与沙箱注意事项详见[工具集 Agent Note(agent 决策记录)](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。 ## acp-agent -作为 **Agent Client Protocol (ACP)** 自动化服务器通过 JSON-RPC stdio 公开的 agent,由 [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 提供。程序化客户端可以创建新会话、发送文本提示词、消费已提交的 assistant 文本、回答一次性权限请求并取消工作。它拥有 ACP 无密钥快照套件。 +一个通过 JSON-RPC stdio 公开、作为 **Agent Client Protocol (ACP)** 自动化服务器运行的 agent,由 [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 提供。程序化客户端可以创建新会话、发送文本提示词、消费已提交的 assistant 文本、回答一次性权限请求并取消工作。它拥有 ACP 无密钥快照套件。 运行:`pnpm run demo:acp`(需要 `DEEPSEEK_API_KEY`);`pnpm run demo:code-mode acp` 通过 `code-mode.cordis.yml` 覆盖以 Code Mode 启动同一服务器。协议与快照测试契约详见 [acp-agent/README.md](acp-agent/README.md)。 -默认 `cordis.yml` 组合 [`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local)、[`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) 和 [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval)。`workspace-write` 将 bash 和文件系统变更限制在每个会话 workspace 中;范围更广的重试会通过 ACP 成为一次性机器权限请求。 +默认 `cordis.yml` 组合 [`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local)、[`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) 和 [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval)。`workspace-write` 将 bash 和文件系统变更限制在每个会话 workspace 中;请求更广泛沙箱权限的重试会通过 ACP 触发一次性的机器权限请求。 diff --git a/examples/acp-agent/README.zh.md b/examples/acp-agent/README.zh.md index 0c5f8866ea..33dc6842b6 100644 --- a/examples/acp-agent/README.zh.md +++ b/examples/acp-agent/README.zh.md @@ -2,29 +2,29 @@ [English](README.md) | 中文 -通过 JSON-RPC stdio 提供的自动化导向 [Agent Client Protocol](https://agentclientprotocol.com) 服务器。它面向父 agent(智能体)、subagent 提供方和其他程序化客户端,而非产品 UI。 +通过 JSON-RPC stdio 提供的面向自动化的 [Agent Client Protocol(ACP)](https://agentclientprotocol.com) 服务器。它面向parent agent(父智能体)、subagent 提供方和其他程序化客户端,而非产品 UI。 ```sh pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env) pnpm run demo:code-mode acp # same protocol with the Code Mode tool transport ``` -该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩(compaction)、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent,将会话持久化到 JSONL,并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时/溢出策略;[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储,[`code-mode.cordis.yml`](code-mode.cordis.yml) 添加 `run_code` 及其生成的 TypeScript SDK,[`web.cordis.yml`](web.cordis.yml) 则为 web-fetch 快照添加 web seam、本地抓取提供方、`web_fetch` 与一个回环 HTML fixture 服务器。 +该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩(compaction)、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent,将会话持久化到 JSONL,并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时/溢出策略;[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储,[`code-mode.cordis.yml`](code-mode.cordis.yml) 添加 `run_code` 及其生成的 TypeScript SDK,[`web.cordis.yml`](web.cordis.yml) 则为 web-fetch 快照添加 web seam、本地抓取提供方、`web_fetch` 与一个回环 HTML fixture(测试前置数据)服务器。 ## 协议通道 -Stdout 只携带以换行分隔的 ACP JSON-RPC。`@deepseek-ai/dsh-acp-demo` 不安装 stdout logger;叶节点的附加项必须使用 stderr 输出诊断信息。 +Stdout 只携带以换行分隔的 ACP JSON-RPC。`@deepseek-ai/dsh-acp-demo` 不安装 stdout logger;该叶节点新增的组件必须使用 stderr 输出诊断信息。 自动化契约(支持的方法、基线提示词内容、已提交文本输出,以及有意缺少的 UI 界面)位于 [`@deepseek-ai/dsh-acp`](../../packages/acp/acp/README.md)。 ## 会话 workspace 与权限 -每次 `session/new` 都提供一个绝对 `cwd`。受沙箱限制的 bash 与文件系统变更会根据该会话 cwd 解析 `workspace-write`,因此并发会话可以使用不同的项目根目录;平台临时根目录仍是共享可写暂存空间(参见[沙箱契约](../../packages/sandbox/sandbox/README.md))。`DSH_PERMISSION_MODE` 在部署和测试中选择 `workspace-write` 或 `danger-full-access`。 +每次 `session/new` 都提供一个绝对 `cwd`。受沙箱限制的 bash 和文件系统修改会以该会话 cwd 为基准应用 `workspace-write`,因此并发会话可以使用不同的项目根目录;平台临时根目录仍是共享可写暂存空间(参见[沙箱契约](../../packages/sandbox/sandbox/README.md))。`DSH_PERMISSION_MODE` 在部署和测试中选择 `workspace-write` 或 `danger-full-access`。 -在 `workspace-write` 下,模型请求扩大沙箱权限的重试会触发 `session/request_permission`,选项为 `allow_once` 和 `reject_once`。客户端以程序方式决策;解除对话框或答案不可用时会失败闭合。选定结果仅适用于该次重试,并通过常规工具结果/审计路径记录。服务器绝不公开权限选择器,也不持久化客户端策略。 +在 `workspace-write` 下,如果模型重试请求更广泛的沙箱访问权限,就会触发 `session/request_permission`,选项为 `allow_once` 和 `reject_once`。客户端以程序方式决策;客户端放弃选择或无法给出答复时,系统会按拒绝处理。选定结果仅适用于该次重试,并通过常规工具结果/审计路径记录。服务器绝不公开权限选择器,也不持久化客户端策略。 ## 快照测试 -此示例拥有 ACP 快照套件。它会启动真实自动化服务器,通过 `dsh-llm-replay` 回放已提交的模型流,并比较规范化后的协议输出与重新持久化的会话日志。录制使用真实模型;刷新会复用已提交的回放输入。覆盖场景包括抛出/挂起行为,可选 `workspace/` fixture(测试前置数据)则为外部状态检查预置环境。 +此示例拥有 ACP 快照套件。它会启动真实自动化服务器,通过 `dsh-llm-replay` 回放已提交的模型流,并比较规范化后的协议输出与重新持久化的会话日志。录制使用真实模型;刷新会复用已提交的回放输入。覆盖配置涵盖抛错/挂起行为,可选的 `workspace/` fixture 则为环境状态检查预置状态。 大多数场景锁定后端行为,而非 ACP 专用行为;[仅面向自动化的 ACP 决策](../../.agents/notes/implemented/simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)说明了为何该覆盖仍与传输层耦合。 diff --git a/examples/cordis-agent/README.zh.md b/examples/cordis-agent/README.zh.md index c2873b6de9..f038ce8368 100644 --- a/examples/cordis-agent/README.zh.md +++ b/examples/cordis-agent/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -自指 harness 演示:在全屏 TUI 上运行 DeepSeek V4 编码主干,并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、挂载仅存于内存的临时 Plugin,并再次卸载它们。临时 Plugin 可跨 turn 保持活跃,但会在卸载、工具集卸载或 DSH 重启后消失;它们不创建文件或配置,也可能影响同一进程中的其他 session。`ctx.fs` 和 `ctx.web` 是这些 Plugin 可用的 provider-only 能力。设计详见[工具集 Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。 +自指 harness 演示:在全屏 TUI 上运行 DeepSeek V4 编码主干,并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、挂载仅存于内存的临时插件,并卸载它们。临时插件 可跨轮次 保持活跃,但会在卸载、工具集卸载或 DSH 重启后消失;它们不创建文件或配置,也可能影响同一进程中的其他会话。`ctx.fs` 和 `ctx.web` 仅以能力提供方形式加载,供这些插件使用。设计详见[工具集 Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。 ## 运行 @@ -15,7 +15,7 @@ pnpm run demo:cordis web # browser UI at http://127.0.0.1:3081 pnpm run demo:cordis acp # ACP server ``` -预期演示分阶段进行:先验证监听器链接,再让 agent 扩展自身: +预期演示分阶段进行:先验证监听器链路,再让 agent(智能体)扩展自身: ``` > Mount a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash. @@ -30,8 +30,8 @@ pnpm run demo:cordis acp # ACP server [tool call] cordis_unmount({"id": "dyn-1"}) ``` -请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`,即可查看编写 Plugin 代码所用的生成服务/事件资料。还可挂载两个协作临时 Plugin(一个中调用 `ctx.provide`,另一个中使用 `inject`),观察 Cordis 如何暂停并恢复消费方。 +请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`,即可查看编写插件代码所用的生成服务/事件资料。还可挂载两个协作临时插件(一个中调用 `ctx.provide`,另一个中使用 `inject`),观察 Cordis 如何暂停并恢复消费方。 ## 端到端测试 -`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`,并断言横幅、包名解析和 EOF 后干净退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试:真实模型挂载一个临时状态 listener,测试验证其带标记的 console 行;然后创建并使用 `reverse_text` 工具,再通过 provide/inject 组合两个临时 Plugin。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 在每文件 100% 覆盖率门禁下承载单元覆盖。 +`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`,并断言横幅、包名解析和 收到 EOF 后正常退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试:真实模型挂载一个临时状态监听器,测试验证其带标记的控制台输出行;然后创建并使用 `reverse_text` 工具,再通过 provide/inject 组合两个临时插件。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 包含相关单元测试,并受逐文件 100% 覆盖率门禁约束。 diff --git a/examples/headless-agent/README.zh.md b/examples/headless-agent/README.zh.md index 68ec718afe..956bc82e77 100644 --- a/examples/headless-agent/README.zh.md +++ b/examples/headless-agent/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -无头单次 agent(智能体)接线:DeepSeek V4 + 本地 bash 与文件系统工具 + subagent 委托 + 工作流与新 agent Ralph 迭代 + `todo_write` + JSONL 持久化,并以 [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo) 作为应用入口。 +无头单次 agent(智能体)接线:DeepSeek V4 + 本地 bash 与文件系统工具 + subagent 委托 + 工作流与全新 agent Ralph 迭代 + `todo_write` + JSONL 持久化,并以 [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo) 作为应用入口。 ## 运行 @@ -15,12 +15,12 @@ pnpm run demo:headless --output-format json -- "summarize the implementation" pnpm run demo:headless --output-format stream-json -- "run the focused tests" ``` -必须提供且只能提供一个非空位置任务;含空格的任务需要加引号。没有 `-p` 标志。`text` 打印最后一条包含文本的 assistant 消息,`json` 打印一条 DSH 原生结果记录,`stream-json` 则在该记录之前发出顶层会话的规范任务轮次事件。子会话只通过父工具事件和结果对外显示。 +必须提供一个且仅一个非空的任务位置参数;含空格的任务需要加引号。没有 `-p` 标志。`text` 打印最后一条包含文本的 assistant 消息,`json` 打印一条 DSH 原生结果记录,`stream-json` 则在该记录之前发出顶层会话的规范任务轮次事件。子会话只通过父会话的工具事件和结果对外显示。 -每次调用都会创建并持久化新会话,在一个轮次中运行所有模型和工具步骤,然后刷新、释放并退出。这是非交互式自动化:没有提示符、批准、恢复、第二轮次或 stdin 上下文。已配置工具可以修改启动 workspace、运行命令、spawn 子 agent,并消耗提供方 token。 +每次调用都会创建并持久化新会话,在一个轮次中运行所有模型和工具步骤,然后刷写持久化数据、执行 dispose(资源释放),再退出。这是非交互式自动化:没有提示符、批准、恢复、第二轮次或 stdin 上下文。已配置工具可以修改启动时所在的工作区、运行命令、spawn 子 agent,并消耗提供方 token。 ## 高级与快照接线 -[`advanced.cordis.yml`](advanced.cordis.yml) 在已交付叶节点上添加 Code Mode 和 Cordis 工具。[`advanced.cordis.snapshot.yml`](advanced.cordis.snapshot.yml) 只将实时 LLM(大语言模型)替换为回放。[`tests/`](tests/) 下的测试拥有无密钥真实 Loader 冒烟测试、密钥门控的外部状态验证冒烟测试,以及带父子会话 fixture(测试前置数据)的 `stream-json` 回放快照。 +[`advanced.cordis.yml`](advanced.cordis.yml) 在已交付叶节点上添加 Code Mode 和 Cordis 工具。[`advanced.cordis.snapshot.yml`](advanced.cordis.snapshot.yml) 只将实时 LLM(大语言模型)替换为回放。[`tests/`](tests/) 下涵盖无密钥真实 Loader 冒烟测试、密钥门控的外部状态验证冒烟测试,以及带父子会话 fixture(测试前置数据)的 `stream-json` 回放快照。 -包级 [CLI 契约](../../packages/examples/cli-demo/README.md)记录输出记录、退出状态、取消、持久化以及模型/token 影响。 +这份包(package)级 [CLI(命令行界面)契约](../../packages/examples/cli-demo/README.md) 说明输出记录、退出状态、取消、持久化以及模型/token 影响。 diff --git a/examples/jsonrpc-agent/README.zh.md b/examples/jsonrpc-agent/README.zh.md index dc9b6233e7..43290fc365 100644 --- a/examples/jsonrpc-agent/README.zh.md +++ b/examples/jsonrpc-agent/README.zh.md @@ -2,16 +2,16 @@ [English](README.md) | 中文 -面向 Python SDK 内置 JSON-RPC 运行时的无人值守编码 agent(智能体)组合。它有意不加载终端 UI、console logger、批准界面或用户交互工具,因为 stdout 属于 SDK 协议,轮次由 SDK 驱动。 +面向 Python SDK 内置 JSON-RPC 运行时的无人值守编码 agent(智能体)组合。它有意不加载终端 UI、控制台日志记录器、批准界面或用户交互工具,因为 stdout 属于 SDK 协议,轮次由 SDK 驱动。 面向模型的工具为: - `bash`,仅前台 - `read`、`write` 和 `edit` -- `subagent`,使用一个前台进程内 spawn 提供方 +- `subagent`,使用一个在进程内以前台方式运行的 spawn 提供方 - `todo_write` -周边运行时还加载 JSONL 会话持久化和自动上下文压缩(compaction)。`maxTokensAsSuccess` 将受 token 上限限制的模型轮次保留为已接受的评估结果,同时保留其 `max-tokens` 原因。 +周边运行时还加载 JSONL 会话持久化和自动上下文压缩(context compaction)。`maxTokensAsSuccess` 将受 token 上限限制的模型轮次保留为已接受的评估结果,同时保留其 `max-tokens` 原因。 ## 运行时环境 @@ -24,4 +24,4 @@ | `DSH_SESSION_ROOT` | JSONL 轨迹目录 | | `DSH_SYSTEM_PROMPT` | 由部署提供的编码人格 | -通过 Python SDK 的 `cordis` 选项或 `DSH_CORDIS_CONFIG` 传入配置路径。内置可执行文件已携带此文件命名的每个插件;目标机器无需 Node.js。 +通过 Python SDK 的 `cordis` 选项或 `DSH_CORDIS_CONFIG` 传入配置路径。内置可执行文件已携带此文件中指定的每个插件;目标机器无需 Node.js。 diff --git a/examples/tui-agent/README.zh.md b/examples/tui-agent/README.zh.md index b3f6dc1853..dd9bbaa141 100644 --- a/examples/tui-agent/README.zh.md +++ b/examples/tui-agent/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -全屏交互式编码 agent(智能体):DeepSeek V4、本地 bash 与文件系统工具、压缩(compaction)、subagent、工作流与新 agent Ralph 迭代、plan mode(`/plan` 进入,`exit_plan_mode` 评审退出)、超时/溢出策略,以及通过 [`@deepseek-ai/dsh-tui-demo`](../../packages/examples/tui-demo) 提供的 JSONL 持久化;该应用从 `cordis.yml` 加载。同级 [`headless-agent`](../headless-agent/README.md) 以适合单次管道的任务形式运行同一能力类,[`acp-agent`](../acp-agent/README.md) 则通过 JSON-RPC 提供该能力。 +全屏交互式编码 agent(智能体):DeepSeek V4、本地 bash 与文件系统工具、压缩(compaction)、subagent、工作流与全新 agent Ralph 迭代、plan mode(`/plan` 进入,`exit_plan_mode` 评审退出)、超时/溢出策略,以及通过 [`@deepseek-ai/dsh-tui-demo`](../../packages/examples/tui-demo) 提供的 JSONL 持久化;该应用从 `cordis.yml` 加载。同级 [`headless-agent`](../headless-agent/README.md) 以适合管道调用的单次任务形式运行同一能力类,[`acp-agent`](../acp-agent/README.md) 则通过 JSON-RPC 提供该能力。 ## 运行 @@ -13,13 +13,13 @@ pnpm run demo:tui ``` -演示脚本和可安装的 `dsh` CLI([`apps/cli`](../../apps/cli/README.md))都会作为已交付的默认配置启动此示例的 `cordis.yml`;`dsh` 还会应用 `~/.dsh` 中的个人覆盖,并将调用目录作为 workspace。 +演示脚本和可安装的 `dsh` CLI(命令行界面,见 [`apps/cli`](../../apps/cli/README.md))都会以此示例的 `cordis.yml` 作为已交付的默认配置启动;`dsh` 还会应用 `~/.dsh` 中的个人覆盖,并将调用目录作为工作区。 -输入一项编码任务。agent 使用 `read`/`write`/`edit` 文件系统工具处理常规文件操作,使用 `bash`(加上面向后台任务的通用 `task_output`/`task_list`/`task_kill`)执行 shell 命令、搜索和测试。每次操作都在新的 `bash -c` 中运行(系统提示词要求模型传递 `workdir`,而不是使用 `cd`)。fs 工具和 bash 都会根据会话 workspace 解析相对路径。agent 还可以通过 `subagent`/`subagent_fork` 委托。 +输入一项编码任务。agent 使用 `read`/`write`/`edit` 文件系统工具处理常规文件操作,使用 `bash`(加上面向后台任务的通用 `task_output`/`task_list`/`task_kill`)执行 shell 命令、搜索和测试。每次 bash 调用都在新的 `bash -c` 中运行(系统提示词要求模型传递 `workdir`,而不是使用 `cd`)。文件系统工具和 bash 都会相对于会话工作区解析相对路径。agent 还可以通过 `subagent`/`subagent_fork` 委托。 `todo_write` 任务跟踪器是选用的,不在已交付配置中:请将 `@deepseek-ai/dsh-tool-todo` 添加到 `cordis.yml`(或在 `~/.dsh` 下使用个人配置覆盖)以公开该工具。加载后,模型会把整表计划记录到会话日志,TUI 则渲染它。 -TUI 渲染 Markdown 历史、推理、工具所有的终端/diff/通用卡片、token 总量,以及加载 `todo_write` 时的最新计划。较长的工具正文保留首尾预览;Ctrl+O 展开或折叠所有卡片。Enter 用于提交,或在 agent 运行时进行 steering(中途引导);Ctrl+R 切换推理,Escape 取消,`/help` 列出命令。`/plan` 为下一步骤选择 plan mode;`/plan ` 还会将消息提交到该步骤,`/plan off` 则在没有模型输入的情况下选择默认 mode。`/status` 会展开当前会话的标识、活动计数、精确 token/缓存 bucket、上下文用量和时间戳,而不中断正在运行的轮次。`/model` 打开当前提供方目录的键盘选择器;使用 Up/Down 聚焦模型,使用 Shift+Tab 循环切换为该模型公布的推理强度,再用 Enter 选择;也可以使用 `/model ` 和 `/model /` 直接选择。`ask_user_question` 会打开一个位于左下方的宽键盘面板,包含批次进度和编号选项。 +TUI 渲染 Markdown 历史、推理(reasoning)、工具自有的终端/diff/通用卡片、token 总量,以及加载 `todo_write` 时的最新计划。较长的工具正文保留首尾预览;Ctrl+O 展开或折叠所有卡片。Enter 用于提交,或在 agent 运行时进行 steering(中途引导);Ctrl+R 切换推理,Escape 取消,`/help` 列出命令。`/plan` 为下一步骤选择 plan mode;`/plan ` 还会将消息提交到该步骤,`/plan off` 则在没有模型输入的情况下选择默认 mode。`/status` 会展开当前会话的标识、活动计数、精确 token/缓存 bucket、上下文用量和时间戳,而不中断正在运行的轮次。`/model` 打开当前提供方目录的键盘选择器;使用 Up/Down 聚焦模型,使用 Shift+Tab 循环切换为该模型公布的推理强度,再用 Enter 选择;也可以使用 `/model ` 和 `/model /` 直接选择。`ask_user_question` 会打开一个位于左下方的宽键盘面板,包含批次进度和编号选项。 ### 恢复早先的会话 @@ -29,11 +29,11 @@ TUI 渲染 Markdown 历史、推理、工具所有的终端/diff/通用卡 dsh --resume ``` -`/resume` 打开可搜索键盘选择器,显示标题、活动、上一轮结果、模型路由、持久 goal 阶段和实时/已持久化状态。已安装的 `dsh` 宿主会刷新并释放当前应用,然后以 `dsh --resume ` 替换进程。TUI 仍会在退出时打印该命令,并在自定义宿主无法移交时显示它。`dsh --resume ` 在启动上下文中提供 id,`cordis.yml` 会读取它(`resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`);没有标志时,agent 会开始新会话。缺失或无法读取的 id 不会启动 agent,而会发出 `agent-loop/config-start-failed`:TUI 打印失败并以非零状态退出。选择器没有跨进程会话锁,因此拥有并发宿主的部署必须自行协调会话所有权。 +`/resume` 打开可搜索键盘选择器,显示标题、活动、上一轮结果、模型路由、持久化目标阶段和实时/已持久化状态。已安装的 `dsh` 宿主会等待刷写完成,对当前应用执行 dispose(资源释放),然后以 `dsh --resume ` 替换进程。TUI 仍会在退出时打印该命令,并在自定义宿主无法移交时显示它。`dsh --resume ` 在启动上下文中提供 id,`cordis.yml` 会读取它(`resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`);没有标志时,agent 会开始新会话。缺失或无法读取的 id 不会启动 agent,而会发出 `agent-loop/config-start-failed`:TUI 打印失败并以非零状态退出。选择器没有跨进程会话锁,因此拥有并发宿主的部署必须自行协调会话所有权。 ## Code Mode -[`code-mode.cordis.yml`](code-mode.cordis.yml) 在同一树上覆盖 worker 线程运行时和 `tools: { mode: code }`。模型会收到一个 `run_code` 传输工具,加上一份为可见工具生成的 TypeScript SDK;只有程序输出会返回模型上下文。使用 `mode: both` 可在 `run_code` 旁同时公开原生调用。执行契约详见 [Code Mode Agent Note](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)。 +[`code-mode.cordis.yml`](code-mode.cordis.yml) 在同一树上覆盖 worker 线程运行时和 `tools: { mode: code }`。模型会收到一个 `run_code` 传输工具,加上一份为可见工具生成的 TypeScript SDK;只有程序输出会返回模型上下文。使用 `mode: both` 可在 `run_code` 旁同时公开原生调用。执行契约详见 [Code Mode Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)。 ```sh pnpm run demo:code-mode # this overlay under the TUI (default UI) @@ -54,27 +54,27 @@ pnpm run demo:code-mode acp # the acp-agent example's same-shaped overlay |---|---| | `hmr` (`@cordisjs/plugin-hmr`) | 开发/演示的编辑-重载循环:它是 **叶节点** 配置项(不内置到应用),因为它依赖 Loader 的内部模块访问 | | `llm-deepseek` | 默认原生适配器 | -| `bash` (`dsh-bash-local`) | 执行器实现:bash seam 的可替换一半。面向模型的 `bash` schema(`tool-bash`)和通用 `task_*` 控制(`tool-tasks`)由 `dsh-agent-spine-demo` 提供,因此叶节点只选择执行器 | +| `bash` (`dsh-bash-local`) | 执行器实现:bash 服务边界中可替换的实现侧。面向模型的 `bash` schema(`tool-bash`)和通用 `task_*` 控制(`tool-tasks`)由 `dsh-agent-spine-demo` 提供,因此叶节点只选择执行器 | | `tui-agent` (`@deepseek-ai/dsh-tui-demo`) | 应用组合包:agent-spine 演示 + JSONL 持久化 + pi-tui 通道 + 预创建的 `main` agent | | `subagent`, `subagent-spawn`, `subagent-fork` | subagent 提供方注册表加两个进程内后端:新子 agent,以及用父 agent 已完成轮次前缀播种的子 agent | | `tool-subagent`, `tool-subagent-fork` | 两次面向模型的 `dsh-tool-subagent` 加载,每次绑定不同提供方,并以不同工具名(`subagent`、`subagent_fork`)公开 | | `workflow-workerthread`, `tool-workflow` | worker 线程工作流引擎及其面向模型的 `workflow` 工具,子调用通过 spawn 后端路由 | | `plan-mode` | 插件拥有的 `/plan [message]` 进入命令和 `/plan off` 退出命令、plan-mode 提示词策略、工具限制,以及经评审的 `exit_plan_mode` 转换 | -| `fs-local`, `fs-policy`, `tool-fs` | 文件系统栈:本地 `ctx.fs` 提供方、先读后写/编辑策略门禁(位于 `fs/*` 事件门禁),以及面向模型的 `read`/`write`/`edit` 工具。相对路径根据会话 workspace 解析 | +| `fs-local`, `fs-policy`, `tool-fs` | 文件系统栈:本地 `ctx.fs` 提供方、先读后写/编辑策略门禁(位于 `fs/*` 事件门禁),以及面向模型的 `read`/`write`/`edit` 工具。相对路径相对于会话工作区解析 | ## 端到端测试(`pnpm run test:e2e`) 与 UI 无关的带密钥套件通过 `tests/harness.ts` 以程序方式组装完整栈(无 PTY、无 Loader): - `tests/full-loop.e2e.ts`:canary 测试:真实模型通过真实 bash 工具运行 `echo e2e-ok`;断言 `tool/call`/`tool/result` 会话事件和最终答案。 -- `tests/coding-task.e2e.ts`:类 swebench 冒烟测试:临时目录包含 `add.js`(其中 `a - b` 写在本应是 `a + b` 的位置)和失败的 `add.test.js`;agent 必须修复错误并验证。测试会自行重新运行 `node add.test.js` 并检查文件,不信任 agent 的声称。 -- `tests/resume.e2e.ts`:跨进程持久连续性:第一次运行告诉真实模型一个密码并将轮次持久化到临时 JSONL 根目录,然后释放整个上下文;第二次运行在同一根目录上创建新上下文,恢复会话 id 并要求模型回忆密码。只有重新水化的日志能够提供该回忆。 -- `tests/compaction.e2e.ts`:压缩冒烟测试:一项真实多步 bash 任务在故意设得很小的上下文窗口中运行,使自动压缩监听器在会话中途触发。测试验证外部状态:真实日志中出现 `compact/start…end` 对,表层缩减(替换节点遮蔽旧节点),且 agent 在压缩后仍给出正确最终答案。 -- `tests/todo-write.e2e.ts`:加载选用 `todo_write` 工具,由真实模型驱动,测试验证产生的 `todo/write` 会话事件。 -- `tests/code-mode.e2e.ts`:带密钥 Code Mode 证明:使用真实模型和双工具任务,断言线上工具列表精确为 `[run_code]`,`tool/code-dispatch` 事件位于父调用下,且筛选后的答案已返回。 +- `tests/coding-task.e2e.ts`:类 swebench 冒烟测试:临时目录包含 `add.js`(其中 `a - b` 写在本应是 `a + b` 的位置)和失败的 `add.test.js`;agent 必须修复错误并验证。测试会自行重新运行 `node add.test.js` 并检查文件,不信任 agent 的说法。 +- `tests/resume.e2e.ts`:跨进程持久连续性:第一次运行告诉真实模型一个密码并将轮次持久化到临时 JSONL 根目录,然后 dispose 整个上下文;第二次运行在同一根目录上创建新上下文,恢复会话 id 并要求模型回忆密码。只有重新水化的日志能够提供该回忆。 +- `tests/compaction.e2e.ts`:压缩冒烟测试:一项真实多步 bash 任务在故意设得很小的上下文窗口中运行,使自动压缩监听器在会话中途触发。测试验证外部状态:真实日志中出现 `compact/start…end` 对,模型可见内容缩减(一个替换节点遮蔽了较旧节点),且 agent 在压缩后仍给出正确最终答案。 +- `tests/todo-write.e2e.ts`:加载选用的 `todo_write` 工具,由真实模型驱动,测试验证产生的 `todo/write` 会话事件。 +- `tests/code-mode.e2e.ts`:带密钥 Code Mode 证明:使用真实模型和双工具任务,断言协议层工具列表精确为 `[run_code]`,`tool/code-dispatch` 事件位于父调用下,且筛选后的答案已返回。 -这些测试在没有 `DEEPSEEK_API_KEY` 时自行跳过。无密钥 `tests/tui-keyless-smoke.e2e.ts` 通过 PTY 启动真实 Loader 树(唯一获准的 PTY 界面):基础启动 + `/plan` + `/exit`,一次带问题对话框和工具往返的脚本 LLM 对话,Code Mode 覆盖欢迎行,以及恢复失败退出路径。 +这些测试在没有 `DEEPSEEK_API_KEY` 时自行跳过。无密钥 `tests/tui-keyless-smoke.e2e.ts` 通过 PTY 启动真实 Loader 树(唯一获准的 PTY 界面):基础启动 + `/plan` + `/exit`,一次带问题对话框和工具往返的脚本 LLM(大语言模型)对话,Code Mode 覆盖配置的欢迎行,以及恢复失败退出路径。 ## 快照测试 -`tests/snapshots//session.jsonl` 提供已录制的用户提示词和模型分片;同级子日志驱动 subagent 和工作流。无密钥套件通过真实循环和工具实现执行这些脚本,然后比较可读的预期终端单元格/样式输出。使用 `pnpm run test:snapshot:refresh` 刷新仅展示变更;已录制模型旅程改变时,使用 DeepSeek 密钥运行 `pnpm run test:snapshot:record`。已实现的 [TUI 快照 Agent Note](../../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) 拥有场景矩阵,以及已录制旅程、瞬时包快照与 PTY 覆盖之间的分工。 +`tests/snapshots//session.jsonl` 提供已录制的用户提示词和模型分片;同级子日志驱动 subagent 和工作流。无密钥套件通过真实循环和工具实现执行这些脚本,然后比较可读的预期终端单元格/样式输出。对于仅涉及展示的变更,使用 `pnpm run test:snapshot:refresh`;已录制的模型流程改变时,使用 DeepSeek 密钥运行 `pnpm run test:snapshot:record`。已实现的 [TUI 快照 Agent Note](../../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) 规定了场景矩阵,以及已录制旅程、包级瞬态快照与 PTY 覆盖之间的分工。 diff --git a/native/README.zh.md b/native/README.zh.md index f73d417645..276db0e655 100644 --- a/native/README.zh.md +++ b/native/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -`node-addon-landlock-run` 的记录真源:这是 harness 从 npm 消费的 Landlock「先限制自身、再执行」启动器(`packages/sandbox/sandbox-local`、`packages/bash/bash-sandbox`)。启动器在此处开发,与消费方相邻;独立仓库是打包并发布 npm 包系列的发布镜像。 +`node-addon-landlock-run` 的权威源码位于此处:这是 harness 从 npm 引入并使用的 Landlock「先限制自身、再执行」启动器(`packages/sandbox/sandbox-local`、`packages/bash/bash-sandbox`)。启动器在此处开发,与消费方相邻;独立仓库是打包并发布 npm 包(package)系列的发布镜像。 ## 发布镜像 @@ -17,6 +17,6 @@ 1. 先通过常规 harness PR 将启动器更改落地于此;触发 `Landlock Run` 工作流,并确保其所有任务通过。 2. 在镜像 checkout 中替换 `.github/` 以外的所有内容:`git -C rm -rq -- . ':!.github'`,然后执行 `git -C archive HEAD:native/landlock-run | tar -x -C `,最后执行 `git -C add -A` 并提交。 3. 在镜像中按照其发布清单(`docs/release.md`)操作:`pnpm release:commit ` → 合并 → 标记 `vX.Y.Z` → 两阶段 `Release` 工作流(先以 `publish=false` 预演,再从标签以 `publish=true` 发布)。 -4. 使用已发布的标签/commit 更新上方 manifest(元数据清单)表,并在同一更改中提升 harness 消费方的依赖范围。 +4. 使用已发布的标签/commit 更新上方 manifest(元数据清单)表,并在同一更改中上调 harness 消费方的依赖版本范围。 -镜像不得分叉:如果更改直接提交到镜像中(例如发布期间的热修复),必须在下次导出前将其移植回此处。 +发布镜像不得与此处的权威源码产生分歧:如果更改直接提交到镜像中(例如发布期间的热修复),必须在下次导出前将其移植回此处。 diff --git a/native/landlock-run/README.zh.md b/native/landlock-run/README.zh.md index 7163314aba..f369799cc8 100644 --- a/native/landlock-run/README.zh.md +++ b/native/landlock-run/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -一个 [Landlock](https://landlock.io/)「先限制自身、再执行」启动器,用于在 Linux 上限制子进程。它以每平台预构建 npm 包加一个轻量 JS 入口包的形式发布;入口包负责解析二进制文件并遵循其 CLI(命令行界面)契约。该启动器面向需要在文件系统允许清单下运行不可信命令、但不能限制自身的 agent harness 和其他宿主。 +一个 [Landlock](https://landlock.io/)「先限制自身、再执行」启动器,用于在 Linux 上限制子进程。它以按平台预构建的 npm 包(package)以及一个轻量 JS 入口包的形式发布;入口包负责解析二进制文件并遵循其 CLI(命令行界面)契约。该启动器面向需要让不可信命令在文件系统允许清单约束下运行、同时保持自身不受限制的 agent harness(智能体框架)和其他宿主。 第一个工具是 **`landlock-run`**:一个「先限制自身、再执行」的 [Landlock](https://landlock.io/) 启动器(基于原始内核 UAPI 编写,约 300 行 C11,并与 musl 静态链接)。它在自身上安装 Landlock 规则集,再 `exec` 被包装的命令;该规则集会跨 `execve` 继承,因此命令及其产生的每个进程都在限制下运行,调用进程仍不受限制。它采用失败闭合:如果内核无法强制执行,则不运行命令并直接退出。 @@ -34,12 +34,12 @@ if (probe(launcher) !== 'unusable') { } ``` -公开 API 有意保持简小: +公开 API 有意保持精简: - `launcherPath()`:当前宿主启动器的绝对路径(有意不检查是否存在;探测结果才是可用性信号)。 - `probe(launcher?, { timeoutMs? })`:功能性强制执行探测,返回 `'full' | 'partial' | 'unusable'`。 - `grantArgs({ readOnly?, readWrite? })`:启动器的授权 argv;未授予的一切都被拒绝。 -- `LAUNCHER_BIN`、`LAUNCHER_FAILURE_EXIT` (125):契约常量。 +- `LAUNCHER_BIN`、`LAUNCHER_FAILURE_EXIT`(125):契约常量。 完整的二进制契约(argv 语法、退出码、报告行)锁定在 [docs/cli-contract.md](docs/cli-contract.md) 中。 @@ -57,4 +57,4 @@ pnpm build:native # this Linux architecture's binaries (apt-get install musl- pnpm test ``` -二进制文件被 git 忽略,并且按架构原生构建:本地只构建当前机器的版本,CI 的每架构 runner 则是记录中的构建者。发布流程详见 [docs/release.md](docs/release.md)。 +二进制文件被 git 忽略,并且按架构原生构建:本地只构建当前机器的版本,CI 各架构 runner 产出的构建则作为正式发布依据。发布流程详见 [docs/release.md](docs/release.md)。 diff --git a/native/landlock-run/packages/entry/README.zh.md b/native/landlock-run/packages/entry/README.zh.md index 03dd18969d..6f8136c335 100644 --- a/native/landlock-run/packages/entry/README.zh.md +++ b/native/landlock-run/packages/entry/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -用于在 Linux 上限制子进程的 Landlock「先限制自身、再执行」启动器:此入口包解析每平台预构建二进制文件,运行功能性强制执行探测,并构建其授权 argv。消费方无需自行拼写启动器标志或解析启动器输出。 +用于在 Linux 上限制子进程的 Landlock「先限制自身、再执行」启动器:此入口包(package)定位对应平台的预构建二进制文件,运行功能性强制执行探测,并构建其授权 argv。消费方无需自行拼写启动器标志或解析启动器输出。 ```js import { grantArgs, launcherPath, probe } from 'node-addon-landlock-run'; @@ -13,6 +13,6 @@ if (probe(launcher) !== 'unusable') { } ``` -启动器在自身上安装 Landlock 规则集,再 `exec` 被包装的命令;该规则集会跨 `execve` 继承,因此整个进程树都在限制下运行。未授予的一切都被拒绝;启动器失败时以 `125` 退出且不运行命令:始终失败闭合,绝不失败开放。二进制契约锁定在仓库的 `docs/cli-contract.md` 中;C 源码作为 `src/main.c` 随该 tarball 分发,便于审计。 +启动器在自身上安装 Landlock 规则集,再 `exec` 被包装的命令;该规则集会跨 `execve` 继承,因此整个进程树都在限制下运行。未授予的一切都被拒绝;启动器失败时以 `125` 退出且不运行命令:采用失败闭合策略,绝不在失败时放行。二进制契约锁定在仓库的 `docs/cli-contract.md` 中;C 源码作为 `src/main.c` 随该 tarball 分发,便于审计。 -平台包(由 `os`/`cpu` 选择的可选依赖,内部不含 JavaScript):`node-addon-landlock-run-linux-x64`、`node-addon-landlock-run-linux-arm64`。在缺少对应包的宿主上,`launcherPath()` 返回确定且不存在的路径,`probe()` 报告 `'unusable'`;系统有意不提供安装时编译回退。 +平台包(由 `os`/`cpu` 选择的可选依赖,内部不含 JavaScript):`node-addon-landlock-run-linux-x64`、`node-addon-landlock-run-linux-arm64`。在缺少对应包的宿主上,`launcherPath()` 返回一个固定但不存在的路径,`probe()` 报告 `'unusable'`;系统有意不提供安装时编译回退。 diff --git a/native/landlock-run/packages/linux-arm64/README.zh.md b/native/landlock-run/packages/linux-arm64/README.zh.md index 93fee68207..abbd0d1040 100644 --- a/native/landlock-run/packages/linux-arm64/README.zh.md +++ b/native/landlock-run/packages/linux-arm64/README.zh.md @@ -2,8 +2,8 @@ [English](README.md) | 中文 -面向 linux-arm64 的预构建 `bin/landlock-run` Landlock 启动器:一个从 [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) 中随包发布的 C 源码原生编译而成的静态 musl 二进制文件(不使用交叉工具链)。npm 的 `os`/`cpu` 字段在安装时选择此包;入口包将其解析为文件路径。该包不包含 JavaScript,也绝不会被导入。 +面向 linux-arm64 的预构建 `bin/landlock-run` Landlock 启动器:一个由 [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) 包(package)所附的 C 源码原生编译而成的静态 musl 二进制文件(不使用交叉工具链)。npm 的 `os`/`cpu` 字段在安装时选择此包;入口包将其定位到文件路径。该包不包含 JavaScript,也绝不会被导入。 -该二进制文件被 git 忽略,并通过 `files` 列表进入 npm tarball;如果文件缺失或 ELF 架构错误,`prepack` 门禁会拒绝打包,发布流水线则会按字节将打包二进制文件锁定到其来源 CI 构建。静态 musl 链接使同一个二进制文件同时适用于 glibc 和 musl 发行版,因此名称中没有 libc 后缀。 +该二进制文件被 git 忽略,并通过 `files` 列表进入 npm tarball;如果文件缺失或 ELF 架构错误,`prepack` 门禁会拒绝打包,发布流水线则会按字节核验打包的二进制文件与其来源 CI 构建产物一致。静态 musl 链接使同一个二进制文件同时适用于 glibc 和 musl 发行版,因此名称中没有 libc 后缀。 同级包:`node-addon-landlock-run-linux-x64`。 diff --git a/native/landlock-run/packages/linux-x64/README.zh.md b/native/landlock-run/packages/linux-x64/README.zh.md index b1fa2e3f16..e813bcef71 100644 --- a/native/landlock-run/packages/linux-x64/README.zh.md +++ b/native/landlock-run/packages/linux-x64/README.zh.md @@ -2,8 +2,8 @@ [English](README.md) | 中文 -面向 linux-x64 的预构建 `bin/landlock-run` Landlock 启动器:一个从 [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) 中随包发布的 C 源码原生编译而成的静态 musl 二进制文件(不使用交叉工具链)。npm 的 `os`/`cpu` 字段在安装时选择此包;入口包将其解析为文件路径。该包不包含 JavaScript,也绝不会被导入。 +面向 linux-x64 的预构建 `bin/landlock-run` Landlock 启动器:一个由 [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) 包(package)所附的 C 源码原生编译而成的静态 musl 二进制文件(不使用交叉工具链)。npm 的 `os`/`cpu` 字段在安装时选择此包;入口包将其定位到文件路径。该包不包含 JavaScript,也绝不会被导入。 -该二进制文件被 git 忽略,并通过 `files` 列表进入 npm tarball;如果文件缺失或 ELF 架构错误,`prepack` 门禁会拒绝打包,发布流水线则会按字节将打包二进制文件锁定到其来源 CI 构建。静态 musl 链接使同一个二进制文件同时适用于 glibc 和 musl 发行版,因此名称中没有 libc 后缀。 +该二进制文件被 git 忽略,并通过 `files` 列表进入 npm tarball;如果文件缺失或 ELF 架构错误,`prepack` 门禁会拒绝打包,发布流水线则会按字节核验打包的二进制文件与其来源 CI 构建产物一致。静态 musl 链接使同一个二进制文件同时适用于 glibc 和 musl 发行版,因此名称中没有 libc 后缀。 同级包:`node-addon-landlock-run-linux-arm64`。 diff --git a/packages/acp/README.zh.md b/packages/acp/README.zh.md index 9999ecdd01..8679f2428a 100644 --- a/packages/acp/README.zh.md +++ b/packages/acp/README.zh.md @@ -6,6 +6,6 @@ ACP(Agent Client Protocol)组将 harness 中的 agent(智能体)公开 | 包 | 职责 | |---|---| -| [`acp/`](acp/README.md) | 仅面向自动化的 ACP 服务器:新文本会话、已提交的 assistant 输出、机器权限策略、取消和由连接拥有的清理。 | +| [`acp/`](acp/README.md) | 仅面向自动化的 ACP 服务器:新文本会话、已提交的 assistant 输出、机器权限策略、取消和由连接负责的清理。 | -与之匹配的进程外 subagent 客户端仍位于 [`subagent/subagent-acp`](../subagent/subagent-acp/README.md),因为它实现 subagent 提供方接口;任意 ACP 客户端都可以驱动同一服务器契约。 +与之匹配的进程外 subagent 客户端仍位于 [`subagent/subagent-acp`](../subagent/subagent-acp/README.md),因为它实现 subagent 提供方接口;任意 ACP 客户端都可以按照同一服务器契约驱动该服务器。 diff --git a/packages/acp/acp/README.zh.md b/packages/acp/acp/README.zh.md index f8abe9e45a..a937bff27c 100644 --- a/packages/acp/acp/README.zh.md +++ b/packages/acp/acp/README.zh.md @@ -2,9 +2,9 @@ [English](README.md) | 中文 -通过 JSON-RPC stdio 提供的仅面向自动化的 [Agent Client Protocol](https://agentclientprotocol.com) 服务器。程序化客户端可以创建新 harness agent(智能体)、发送文本提示词、收集已提交的 assistant 文本、通过策略解决一次性权限请求并取消工作。仓库中的主要客户端是 [`dsh-subagent-acp`](../../subagent/subagent-acp/README.md)。 +通过 JSON-RPC stdio 提供的仅面向自动化的 [ACP(Agent Client Protocol)](https://agentclientprotocol.com) 服务器。程序化客户端可以创建新 harness agent(智能体)、发送文本提示词、收集已提交的 assistant 文本、按策略响应一次性权限请求并取消工作。仓库中的主要客户端是 [`dsh-subagent-acp`](../../subagent/subagent-acp/README.md)。 -此包(package)是传输适配器,而非 UI 集成或能力 seam。它不公开编辑器导航、transcript(文本记录)回放、命令、mode、配置选择器、信息征集、推理、计划、标题或工具展示。交互渲染与人类问题属于 Web 和 TUI 模块。 +此包(package)是传输适配器,而非 UI 集成或能力 seam。它不公开编辑器导航、transcript(文本记录)回放、命令、模式、配置选择器、信息征集、推理、计划、标题或工具展示。交互式渲染与向用户提问属于 Web 和 TUI 模块。 ## 插件 @@ -15,7 +15,7 @@ | `provider` | 无 | 每个已创建 agent 的初始提供方路由。 | | `model` | 无 | 每个已创建 agent 的初始模型。 | -两个字段都是可选的,以便由另一个 agent/request 监听器提供目标。可运行 ACP 组合同时要求两者。 +两个字段都是可选的,以便由另一个 agent/request 监听器提供目标。可运行的 ACP 组合同时要求两者。 ## 协议契约 @@ -23,19 +23,19 @@ |---|---| | `initialize` | 协商受支持的版本,并仅公布基线提示词(无图像、音频或嵌入上下文能力)。不公布会话、编辑器、终端、文件系统或 MCP 能力。 | | `authenticate` | 空操作,因为服务器不公布身份验证方法。 | -| `session/new` | 使用绝对主 `cwd` 创建新 agent;接受空的 `additionalDirectories` 和 `mcpServers`,拒绝非空值。 | -| `session/prompt` | 连接文本块,将基线资源链接渲染为带方括号的文本引用,拒绝空输入或超出基线的输入,每个会话只允许一个正在处理的请求,并从该请求拥有的持久 `turn/end` 结算。 | -| `session/cancel` | 仅取消被定址的 agent,并将其待处理提示词结算为 `cancelled`;未知 id 为空操作。 | +| `session/new` | 以绝对路径作为主 `cwd` 创建新 agent;接受空的 `additionalDirectories` 和 `mcpServers`,拒绝非空值。 | +| `session/prompt` | 拼接文本块,将基线资源链接渲染为带方括号的文本引用,拒绝空输入或超出基线的输入,每个会话只允许一个正在处理的请求,并根据该请求所属的持久 `turn/end` 结算。 | +| `session/cancel` | 仅取消指定的 agent,并将其待处理提示词结算为 `cancelled`;未知 id 为空操作。 | | `session/update` | 为每个非空文本块发出一个 `agent_message_chunk`;这些文本块来自已提交的 `assistant/message`。省略原始增量和非消息事件。 | -| `session/request_permission` | 为携带工具调用 id 的桥接层所有批准请求提供一次性允许/拒绝选项。客户端可以自动回答。 | +| `session/request_permission` | 为携带工具调用 id、由桥接层拥有的批准请求提供一次性允许/拒绝选项。客户端可以自动回答。 | -一个连接可以拥有多个会话。桥接层使用带品牌的 session id 为记录建键,并在路由事件或权限请求前检查精确的 agent 标识。每个会话都有独立的提示词槽位、workspace、取消路径和 disposer。 +一个连接可以拥有多个会话。桥接层以带品牌的会话 id 作为记录键,并在路由事件或权限请求前检查 agent 是否为同一对象。每个会话都有独立的提示词槽位、工作区、取消路径和资源释放器。 -已提交消息输出有意以逐 token 延迟换取干净的自动化结果。未提交的提供方分片和重试尝试无法泄漏部分文本;推理与工具活动仍保留在会话日志中,以便其他界面观测。 +已提交消息输出有意牺牲逐 token 输出的低延迟,以换取干净的自动化结果。未提交的提供方分片和重试尝试无法泄漏部分文本;推理与工具活动仍保留在会话日志中,以便其他界面观测。 ## 生命周期 -客户端断开与 Cordis 释放共用同一个记忆化清理流程。桥接层先拒绝新会话和提示词,结算待处理提示词,然后并行释放所有已拥有的 agent handle,并等待它们的循环/会话清理完成。因此,仅 ACP 的插件重载不会遗留 agent。 +客户端断开连接与 Cordis 的 dispose(资源释放)共用同一个记忆化清理流程。桥接层先拒绝新会话和提示词,结算待处理提示词,然后并行对其拥有的全部 agent 句柄执行 dispose,并等待它们的循环/会话清理完成。因此,单独重载 ACP 插件不会遗留孤儿 agent。 ## 运行 @@ -47,11 +47,11 @@ #### 模型所见内容 -`session/prompt` 文本块会原样连接为一条用户消息;基线资源链接会在该消息中表示为带方括号的 `[resource_link name=… uri=…]` 引用,模型可以使用自身工具打开它。协议元数据、客户端能力、权限选择和 session id 绝不进入模型请求。 +`session/prompt` 文本块会原样拼接为一条用户消息;基线资源链接会在该消息中表示为带方括号的 `[resource_link name=… uri=…]` 引用,模型可以使用自身工具打开它。协议元数据、客户端能力、权限选择和 session id 绝不进入模型请求。 #### Token 影响 -提示词 token 取决于数据,并保留在该会话的历史中直到压缩。并发 ACP 会话保留独立上下文。 +提示词 token 取决于数据,并保留在该会话的历史中直到上下文压缩(context compaction)。并发 ACP 会话保留独立上下文。 #### KV Cache 影响 @@ -61,19 +61,19 @@ #### 模型所见内容 -没有直接内容。拥有该决策的工具通过常规工具结果路径记录允许、拒绝、取消或不可用结果。 +不会直接看到任何内容。所属工具通过常规工具结果路径记录其结果:允许、拒绝、取消或不可用。 #### Token 影响 -只有拥有该决策的工具结果会贡献 token。 +只有该工具的结果会贡献 token。 #### KV Cache 影响 -通过所属工具结果仅追加。 +随该工具的结果仅追加。 ## 已知限制与延后工作 - **仅新会话**:不支持加载、列出、恢复、删除和 fork。 -- **仅基线提示词和一个 workspace**:图像、音频、嵌入资源、非空附加目录和 MCP 服务器都会被拒绝;资源链接会被展平为文本引用,而不是已获取内容。 -- **仅已提交答案**:实时进度、推理、工具活动、计划、标题和用量不上线。 -- **连接拥有的生命期**:一个连接会释放其所有会话;尚未实现每会话关闭。 +- **仅基线提示词和一个 workspace**:图像、音频、嵌入资源、非空附加目录和 MCP 服务器都会被拒绝;资源链接只会展平为文本引用,不会获取其内容。 +- **仅已提交答案**:实时进度、推理、工具活动、计划、标题和用量不会通过协议传输。 +- **由连接管理的生命周期**:一个连接会释放其所有会话;尚未实现单个会话关闭功能。 diff --git a/packages/bash/README.zh.md b/packages/bash/README.zh.md index 57c28b45cf..deb23ea820 100644 --- a/packages/bash/README.zh.md +++ b/packages/bash/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -规范的三包能力 seam(见[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)):抽象执行器接口、具体实现,以及消费该接口的面向模型工具。这些全是**产品** 包。 +规范的三包能力 seam(见[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)):抽象执行器接口、具体实现,以及消费该接口的面向模型工具。这些全是**产品**包。 | 包 | 职责 | ctx key | |---|---|---| @@ -11,4 +11,4 @@ | `bash-sandbox/` | 消费沙箱的 `BashExecutor`(通过 `ctx.sandbox` 包装每个命令 argv,标记拒绝/强制执行事实;扩展 `bash-local` 的机制) | (注册 `ctx.bash`) | | `tool-bash/` | 面向模型的 `bash` schema;后台进程注册到通用 [`tasks/`](../tasks/README.md) 运行时 | (注册到 `ctx.tools`) | -接口位于 `bash/bash/`。以 `bash-sandbox` 替换 `bash-local`,同时不改动接口或工具,正是这种拆分存在的意义:叶级 `cordis.yml` 选择一个执行器配置项;受限实现还需选择一个 `ctx.sandbox` 提供方配置项(见 [acp-agent 示例的默认组合](../../examples/acp-agent/))。 +接口位于 `bash/bash/`。以 `bash-sandbox` 替换 `bash-local`,同时不改动接口或工具,正是这种拆分存在的意义:叶级 `cordis.yml` 选择一个执行器插件条目;受限实现还需再选择一个 `ctx.sandbox` 提供方插件条目(见 [acp-agent 示例的默认组合](../../examples/acp-agent/))。 diff --git a/packages/bash/bash-local/README.zh.md b/packages/bash/bash-local/README.zh.md index aa6de87df4..16c8ca50a0 100644 --- a/packages/bash/bash-local/README.zh.md +++ b/packages/bash/bash-local/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -`@deepseek-ai/dsh-bash` 执行器 seam 的本地实现,构建在 [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.md) 服务之上:`LocalBashExecutor` 每次调用都通过 `ctx.subprocess` 把 `bash -c ` 作为受管进程组 spawn,并拥有所有 bash 形态的职责(命令默认值补全与上限、超时与取消分类、适合模型的终端环境,以及后台读取时面向模型的 stdout/stderr 合并)。进程组机制(以 spill 文件兜底的有界输出、凭据清除、kill 升级、dispose(资源释放))归进程管理器服务所有。 +`@deepseek-ai/dsh-bash` 执行器 seam 的本地实现,构建在 [`@deepseek-ai/dsh-subprocess`](../../subprocess/subprocess/README.md) 服务之上:`LocalBashExecutor` 每次调用都通过 `ctx.subprocess` 把 `bash -c ` 作为受管进程组 spawn,并负责所有 Bash 层职责(命令默认值补全与上限、超时与取消分类、适合模型的终端环境,以及后台读取时面向模型的 stdout/stderr 合并)。进程组机制(以 spill 文件兜底的有界输出、凭据清除、kill 升级、dispose(资源释放))则由 subprocess 服务负责。 包根目录导出默认与具名的 `LocalBashExecutor` 插件及其 `Config`。 @@ -24,11 +24,11 @@ 设计时调研了 Claude Code、OpenCode、Codex 和 pi 的 bash 工具,主要取舍如下: -- **每次调用都 spawn,不保留 shell 状态**:每次调用都启动新的非登录 `bash -c`(行为确定,不读取 rc 文件)。调研的四种工具均会每次调用单独 spawn。`XXX(stateful-shell)` 位于 `src/index.ts`,记录了两种已验证的有状态设计(Claude Code 仅持久化 cwd;Codex 使用 PTY exec 会话),供真实工作流程需要时采用。 +- **每次调用都 spawn,不保留 shell 状态**:每次调用都启动新的非登录 `bash -c`(行为确定,不读取 rc 文件)。调研的四种工具均会每次调用单独 spawn。`XXX(stateful-shell)` 位于 `src/index.ts`,记录了两种已验证的有状态设计(Claude Code 仅持久化 cwd;Codex 使用 PTY exec 会话),供真实工作流需要时采用。 - **在受管进程组之上应用配置预算**:`resolve()` 从配置补全 `workdir`/`timeoutMs`/`stdoutMaxBytes`,每次 spawn 都向服务传入显式的字节上限、spill 上限与 `graceMs`(默认 3 秒,沿用 OpenCode 的升级策略)。进程组终止、退出后的管道排空宽限期、尾部保留截断与有界 spill 文件是 [`dsh-subprocess-local`](../../subprocess/subprocess-local/README.md) 的机制。前台 `BashExecRequest.stdoutMaxBytes` 可为某个受信任调用方提高单次 stdout 捕获预算;stderr 和后台运行仍使用 `maxOutputBytes`。 -- **超时与取消分类**:`run()` 通过同一个 deadline 把经配置钳位的超时与调用方的信号融合;只有执行器自身的超时报告 `timedOut`,上游取消报告 `aborted`,自行发出信号终止的命令两者皆不报告(见[超时库 Agent Note(agent 决策记录)](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md))。 +- **超时与取消分类**:`run()` 通过同一个 deadline 把经配置钳位的超时与调用方的信号融合;只有执行器自身的超时报告 `timedOut`,上游取消报告 `aborted`,自身因信号终止的命令两者皆不报告(见[超时库 Agent Note(agent 决策记录)](../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md))。 - **适合模型的终端环境**:设置 `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat`(Codex 硬编码的集合),防止分页器与 ANSI 颜色破坏结果;这些条目作为普通 env 合并,遵循服务的凭据清除与 `DSH_*` 通道规则;调用方的显式条目依旧优先。详见 [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) 与 [受管环境 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md)。 -- **后台进程**:`start()` 会立即返回实时 `BashProcess` 句柄,不应用超时(Claude Code 在转为后台时会解除超时);句柄的 `readOutput()` 把服务基于偏移量的 stdout/stderr 读取合并为一条带标记分节的增量,由一个消费游标驱动。仍在运行的进程归进程管理器服务所有,因此它能在执行器重载后存活,并随服务的 dispose 被终止且等待退出。所有具有任务形态的事项(id、所有权、轮询、通知)都属于通用 [`ctx.tasks` 运行时](../../tasks/tasks/README.md),工具层会在其中注册该句柄;本执行器不会接触会话或注册表。 +- **后台进程**:`start()` 会立即返回活动的 `BashProcess` 句柄,不应用超时(Claude Code 在转为后台时会解除超时);句柄的 `readOutput()` 把服务基于偏移量的 stdout/stderr 读取合并为一条带分节标记的增量,并以消费游标记录读取进度。仍在运行的进程则由 subprocess 服务负责,因此它能在执行器重载后存活,并随服务的 dispose 被终止且等待退出。所有具有任务形态的事项(id、所有权、轮询、通知)都属于通用 [`ctx.tasks` 运行时](../../tasks/tasks/README.md),工具层会在其中注册该句柄;本执行器不会接触会话或注册表。 ## 模型体验 @@ -36,12 +36,12 @@ #### KV Cache 影响 -不会直接失效;请求前缀变更由具名消费方负责。 +不会直接导致 KV Cache 失效;请求前缀变更由具名消费方负责。 ## 已知限制与暂缓事项 -- **自身不受约束**:此执行器始终以 harness 进程的权限运行命令;需要限制的部署可以组合 [`dsh-bash-sandbox`](../bash-sandbox/README.md),每次调用的 allow/deny/ask 策略则属于 `tools/pre-execute`。 -- **没有持久 shell 或 PTY**:每次调用都启动新的非登录 `bash -c`;仅持久化 cwd 与交互式终端会话均继续暂缓,直到真实工作流程需要它们。 +- **自身不提供隔离**:此执行器始终以 harness 进程的权限运行命令;需要限制的部署可以组合 [`dsh-bash-sandbox`](../bash-sandbox/README.md),每次调用的 allow/deny/ask 策略则属于 `tools/pre-execute`。 +- **没有持久 shell 或 PTY**:每次调用都启动新的非登录 `bash -c`;仅持久化 cwd 与交互式终端会话均继续暂缓,直到真实工作流需要它们。 - **仅支持 POSIX**:`bash` 二进制已硬编码,底层服务的进程组语义也是 POSIX 的;不支持 Windows。 - **后台 spawn 失败提示只交付一次**:进程管理器不会为从未真正运行的进程缓冲任何输出,因此执行器把 `spawn failed: …` 注入恰好一个 `readOutput()` 增量;丢弃了该增量的读取方无法再恢复它。 diff --git a/packages/bash/bash-sandbox/README.zh.md b/packages/bash/bash-sandbox/README.zh.md index c1a65ead53..4ecc8d533f 100644 --- a/packages/bash/bash-sandbox/README.zh.md +++ b/packages/bash/bash-sandbox/README.zh.md @@ -2,11 +2,11 @@ [English](README.md) | 中文 -消费 [`@deepseek-ai/dsh-bash`](../bash/) 执行器 seam 的沙箱实现。加载它时,应**用它替代** `@deepseek-ai/dsh-bash-local`,并同时加载 [`ctx.sandbox`](../../sandbox/sandbox/) 提供方(例如 [`@deepseek-ai/dsh-sandbox-local`](../../sandbox/sandbox-local/))及 [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/);后者拥有默认模式 + 工作区根目录,并与受沙箱约束的文件系统共享这些设置。无需使用替代工具插件;`dsh-tool-bash` 会检测执行器的 `sandboxMode` 能力并添加升权字段。 +这是使用沙箱能力的 [`@deepseek-ai/dsh-bash`](../bash/) 执行器 seam 实现。加载它时,应**用它替代** `@deepseek-ai/dsh-bash-local`,并同时加载 [`ctx.sandbox`](../../sandbox/sandbox/) 提供方(例如 [`@deepseek-ai/dsh-sandbox-local`](../../sandbox/sandbox-local/))及 [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/);默认模式和工作区根目录由后者负责,并与受沙箱约束的文件系统共享这些设置。无需使用替代工具插件;`dsh-tool-bash` 会检测执行器的 `sandboxMode` 能力并添加升权字段。 包根目录导出默认与具名的 `SandboxBashExecutor` 插件及其 `Config`;引号处理与结果分类 helper 保留在内部。 -每条命令的限制方式都是:把本执行器即将 spawn 的精确 `['bash', '-c', command]` argv 交给提供方,再 spawn 其返回的(已包装)argv。由哪种平台 runner 执行限制,以及是否有 runner 可用(必须快速失败并返回结构化 `SANDBOX_UNAVAILABLE` 错误,绝不能静默无约束运行),属于提供方职责;本包只拥有 bash 侧。 +每条命令的限制方式都是:把本执行器即将 spawn 的精确 `['bash', '-c', command]` argv 交给提供方,再 spawn 其返回的(已包装)argv。由哪种平台 runner 执行限制,以及是否有 runner 可用,属于提供方职责;若无可用 runner,则按失败关闭原则拒绝执行并返回结构化 `SANDBOX_UNAVAILABLE` 错误,绝不能静默地无约束运行。本包只负责 bash 侧。 | 模式 | 文件影响 | |---|---| @@ -17,12 +17,12 @@ 语义: - **拒绝是结果事实。** 如果一次失败运行的 stderr 包含所选后端自身的拒绝方言,即提供方在每次包装时加上的特征(bwrap 下的 EROFS 文本、Landlock 下的 EACCES、Seatbelt 下的 EPERM),则结果报告 `BashRunResult.sandbox.denied: true`(从已收集的 stderr 尾部进行保守分类)。每次受限制运行还会携带执行时模式(`result.sandbox.mode`)与提供方强制执行完整性(`result.sandbox.enforcement`:`full`,或在较旧 Landlock ABI 上为 `partial`)。 -- **Runner 失败是沙箱失败,绝不是命令失败。** 前台执行会抛出 `SANDBOX_UNAVAILABLE`;已结算的后台进程会标记 `process.sandbox.runnerFailed`,bash 产生方通过通用 `task_output` 渲染它。spawn 失败也会经过结算,因此受限制的后台句柄会保留自身的模式/强制执行事实,并释放每进程计数。 -- **部署回退,每次调用策略。** [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) 为每次工具调用解析完整的 `SandboxExecutionPolicy`:调用会话提供自身的模式覆盖与不可变 cwd 根目录,部署配置则为无 agent 调用提供回退。已批准的升权只更改该策略的模式,会话根目录仍然附着其上。`resolve()` 把策略带入 spec,因此来自不同项目的重叠命令会在各自的根目录与模式下运行、分类和报告。能力事实 `ctx.bash.sandboxMode` 报告已配置的默认值,因此工具层只在装载该执行器时才公布升权。模型只能通过结果事实了解沙箱:静态 bash 工具描述会解释拒绝标记,系统提示词中不会声明当前模式。 +- **Runner 失败是沙箱失败,绝不是命令失败。** 前台执行会抛出 `SANDBOX_UNAVAILABLE`;已结算的后台进程会标记 `process.sandbox.runnerFailed`,Bash 结果生成方通过通用 `task_output` 渲染它。spawn 失败也会经过结算,因此受限制的后台句柄会保留自身的模式/强制执行事实,并释放每进程计数。 +- **部署回退,每次调用策略。** [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) 为每次工具调用解析完整的 `SandboxExecutionPolicy`:调用会话提供自身的模式覆盖与不可变 cwd 根目录,部署配置则为无 agent(智能体)调用提供回退。已批准的升权只更改该策略的模式,会话根目录仍然附着其上。`resolve()` 把策略带入 spec,因此来自不同项目的重叠命令会在各自的根目录与模式下运行、分类和报告。能力事实 `ctx.bash.sandboxMode` 报告已配置的默认值,因此工具层只在装载该执行器时才公布升权。模型只能通过结果事实了解沙箱:静态 bash 工具描述会解释拒绝标记,系统提示词中不会声明当前模式。 - **只限制文件影响。** 设计上不限制网络与进程可见性:模式词汇不会声称覆盖后端未强制执行的范围。 - 进程机制(spawn、进程组终止、输出收集/spill、后台句柄、凭证清理)继承自 [`dsh-bash-local`](../bash-local/);runner 选择位于 [`dsh-sandbox-local`](../../sandbox/sandbox-local/)。 -seam 上仅拒绝:拒绝是一项已报告事实,本执行器绝不自行协商权限。批准问题位于工具层(`dsh-tool-bash`),由它驱动本包遵守的覆盖。 +该 seam 只报告拒绝:拒绝是一项结果事实,本执行器绝不自行协商权限。批准问题位于工具层(`dsh-tool-bash`),由它设置本包所遵守的模式覆盖值。 ```yaml - id: sandbox @@ -36,7 +36,7 @@ seam 上仅拒绝:拒绝是一项已报告事实,本执行器绝不自行协 name: '@deepseek-ai/dsh-bash-sandbox' ``` -无密钥消费方集成证明是 `tests/bwrap.e2e.ts`、`tests/landlock.e2e.ts` 和 `tests/seatbelt.e2e.ts`(通过 `ctx.bash` 驱动真实提供方 + 真实 runner,在真实世界验证,并在相应 runner 缺失时各自自行跳过)。agent-spine e2e 还会在一个 Cordis 上下文中驱动两个并发会话,并证明每个真实 bash 工具调用只能写入自身项目。可运行 demo 见 [acp-agent 示例的默认组合](../../../examples/acp-agent/)。 +无密钥消费方集成证明是 `tests/bwrap.e2e.ts`、`tests/landlock.e2e.ts` 和 `tests/seatbelt.e2e.ts`(通过 `ctx.bash` 驱动真实提供方 + 真实 runner,从外部验证实际文件效果,并在相应 runner 缺失时各自自行跳过)。agent-spine e2e 还会在一个 Cordis 上下文中驱动两个并发会话,并证明每个真实 bash 工具调用只能写入自身项目。可运行 demo 见 [acp-agent 示例的默认组合](../../../examples/acp-agent/)。 ## 模型体验 @@ -44,11 +44,11 @@ seam 上仅拒绝:拒绝是一项已报告事实,本执行器绝不自行协 #### 模型看到的内容 -基线是生成的 [`dsh-tool-bash` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-bash)。通过公布一个执行限制的 `sandboxMode`,此后端会为 `bash` 增加 `sandbox_permissions`,其 enum 为 `workspace-write` | `danger-full-access`,并增加 `justification`。后端不添加提示词文本,会话的有效模式仍不会声明。 +基线是生成的 [`dsh-tool-bash` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-bash)。通过公布表明启用隔离的 `sandboxMode` 能力,此后端会为 `bash` 增加 `sandbox_permissions`,其 enum 为 `workspace-write` | `danger-full-access`,并增加 `justification`。后端不添加提示词文本,会话的有效模式仍不会声明。 #### Token 影响 -在 `bash` 可见的请求上增加少量固定 schema;模式切换不增加上下文 token。 +在 `bash` 可见的请求上,schema 固定增加少量内容;模式切换不增加上下文 token。 #### KV Cache 影响 @@ -62,29 +62,29 @@ seam 上仅拒绝:拒绝是一项已报告事实,本执行器绝不自行协 #### Token 影响 -除普通输出外,正常允许的运行不会增加 token。拒绝或失败会增加上述有条件标记,并保留到压缩。 +除普通输出外,正常允许的运行不会增加 token。拒绝或失败会增加上述有条件标记,并保留到上下文压缩(context compaction)。 #### KV Cache 影响 -仅追加;新可见内容位于可复用请求前缀之后,不会使现有 KV-cache 配置项失效。 +仅追加;新可见内容位于可复用请求前缀之后,不会使现有 KV-cache 条目失效。 ### 间接的 Bash 工具错误 #### 模型看到的内容 -如果没有 runner 能强制执行受限模式,前台调用会传播 [`SANDBOX_UNAVAILABLE` 错误;它由 `dsh-sandbox` 持有](../../sandbox/sandbox/README.md#confinement-error-indirectly)。如果 runner 在执行时失败,此后端会提供第一行 stderr 作为详细信息。 +如果没有 runner 能强制执行受限模式,前台调用会传播 [`SANDBOX_UNAVAILABLE` 错误](../../sandbox/sandbox/README.md#confinement-error-indirectly);该错误由 `dsh-sandbox` 定义。如果 runner 在执行时失败,此后端会提供第一行 stderr 作为详细信息。 #### Token 影响 -该次调用可见的是有条件错误文本,并保留在历史记录中直到压缩。 +该次调用会在相应条件下显示错误文本,该文本会保留在历史记录中直到上下文压缩。 #### KV Cache 影响 -仅追加;新可见内容位于可复用请求前缀之后,不会使现有 KV-cache 配置项失效。 +仅追加;新可见内容位于可复用请求前缀之后,不会使现有 KV-cache 条目失效。 ## 已知限制与暂缓事项 - **限制只覆盖文件影响**:网络访问与进程可见性不变,因此这些模式不是通用安全沙箱。 -- **拒绝从失败命令的 stderr 推断**:后端特征使该推断可跨平台使用,但匹配的应用错误可能被分类为拒绝,也可能遗漏未出现在保留尾部中的拒绝。 +- **拒绝从失败命令的 stderr 推断**:后端特征使该推断可跨平台使用,但包含相同后端特征的应用错误可能被分类为拒绝,也可能遗漏未出现在保留尾部中的拒绝。 - **后台 runner 失败没有即时错误通道**:它记录在已结算进程上,并在调用方使用 `task_output` 读取通用任务时呈现。 - **`danger-full-access` 有意绕过 `ctx.sandbox`**:它是显式无约束模式,不是更宽的沙箱 profile。 diff --git a/packages/bash/bash/README.zh.md b/packages/bash/bash/README.zh.md index 14476b7703..a7c0cac0bc 100644 --- a/packages/bash/bash/README.zh.md +++ b/packages/bash/bash/README.zh.md @@ -4,7 +4,7 @@ **bash 执行器 seam**:抽象 `BashExecutor` 服务(`ctx.bash`)定义 bash 后端做什么,即运行前台命令与启动后台进程,但不规定如何实现。task id、所有权、收集、取消与通知属于通用 `ctx.tasks` 运行时。 -本包是 bash 能力中负责接口的四分之一,各项职责因此可以独立演进(和替换): +本包(package)是 bash 能力中负责接口的四分之一,各项职责因此可以独立演进(和替换): | 包 | 职责 | |---|---| @@ -13,19 +13,19 @@ | `@deepseek-ai/dsh-bash-sandbox` | 实现:沿用 `dsh-bash-local` 的机制,但通过 [`ctx.sandbox`](../../sandbox/sandbox/) 限制每次 spawn,并将拒绝报告为结果事实 | | `@deepseek-ai/dsh-tool-bash` | 基于 `ctx.bash`、面向模型的工具 schema | -该拆分与 LLM seam(`LlmService`/`LlmAdapter`)及 agent 工具调研结果一致:pi 将执行隐藏在 `BashOperations` 接口之后(本地 shell/SSH/VM 后端),Codex 则隐藏在 exec-server 协议之后。`dsh-bash-sandbox` 正是这种替换的实际应用:沙箱执行器位于同一接口之后;消费方检测其 `sandboxMode` 能力并添加升权字段,无需导入实现。容器化或远程执行器也可以同样接入。 +该拆分与 LLM(大语言模型) seam(`LlmService`/`LlmAdapter`)及 agent(智能体)工具调研结果一致:pi 将执行隐藏在 `BashOperations` 接口之后(本地 shell/SSH/VM 后端),Codex 则隐藏在 exec-server 协议之后。`dsh-bash-sandbox` 正是这种替换的实际应用:沙箱执行器位于同一接口之后;消费方检测其 `sandboxMode` 能力并添加升权字段,无需导入实现。容器化或远程执行器也可以同样接入。 ## 服务 API(`ctx.bash`) | 成员 | 语义 | |---|---| -| `run(spec)` | 前台执行。命令完成时 resolve。**只会因基础设施失败而 reject**(工作目录不可用、shell 缺失、信号已在调用前中止);非零退出、超时终止和中止终止都会 resolve 为描述性 `BashRunResult`。 | +| `run(spec)` | 前台执行。命令完成时 resolve。**只会因基础设施失败而 reject**(工作目录不可用、shell 缺失、信号已在调用前中止);非零退出、超时终止和中止导致的终止都会 resolve 为描述性 `BashRunResult`。 | | `start(spec)` | 后台执行。立即返回不含任务语义的 `BashProcess` 句柄;**不应用超时**。调用方可以将其适配到 `ctx.tasks`。 | | `sandboxMode` | 工具层的能力事实:沙箱执行器用于限制执行的默认模式(基类中为 `undefined`,即「此执行器不使用沙箱」)。`dsh-tool-bash` 会在注册时读取它,仅当组合确实支持升权字段时才公布这些字段。 | | `BashProcess.readOutput()` | **增量** 读取输出:连续读取绝不会重复交付。因缓冲区边界丢失数据的读取会标记 `lossy`,并指向完整流 spill 文件。 | | `BashProcess.kill()` | 终止进程组。如果进程已结束,返回 `false`。 | -实现会继承 `BashExecutor` 并实现抽象方法。dispose 必须终止每个运行中的进程并等待其退出,详见 HMR 安全测试。 +实现会继承 `BashExecutor` 并实现抽象方法。dispose(资源释放)必须终止每个运行中的进程并等待其退出,详见 HMR(热模块替换)安全测试。 ## 词汇 @@ -33,7 +33,7 @@ 每会话沙箱模式覆盖词汇(`'sandbox/mode'` 事件、`effectiveSandboxMode(events)` fold 以及 `setSandboxMode(session, mode)` 写入路径)不位于此处。它是所有强制执行家族共享的策略状态,属于 [`@deepseek-ai/dsh-sandbox-policy`](../../sandbox/sandbox-policy/)。`run()` 返回 `BashRunResult`;`start()` 返回 `BashProcess`,其增量读取与终止方法由 `dsh-tool-bash` 适配为通用任务注册。沙箱执行器会在前台结果与已结算进程句柄上标记 `BashSandboxInfo`。详见 `src/types.ts` 与 [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md)。 -`stdin` 与普通 `env` 由同进程插件(hooks 桥接、原生插件)设置,用于向 hook 命令提供其 JSON payload 和 `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` 值。`dshEnv` 是受类型限制、仅允许受管 key 的独立受信任 overlay;导出的 `DSH_ENV_PREFIX` 是该 namespace、其 `DshEnvironmentKey` 模板类型、执行器清理、注册表验证、派生内置名称与模型指引的单一真源。模型 bash 使用 `ctx.bashEnv` 收集的当前快照。实现会移除继承的受管 key,再在普通 `env` 之后合并 `dshEnv`,因此省略的当前事实不会回退到陈旧环境状态,`env` 条目也无法顶掉受管值。面向模型的工具不公开任何一个字段。这三者在已解析 spec 上仍然可选;缺失表示没有输入/overlay。详见 [bash-stdin-env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) 与 [会话环境 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md)。 +`stdin` 与普通 `env` 由同进程插件(hooks 桥接、原生插件)设置,用于向 hook 命令提供其 JSON payload 和 `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` 值。`dshEnv` 是受类型限制、仅允许受管 key 的独立受信任 overlay;导出的 `DSH_ENV_PREFIX` 是该 namespace、其 `DshEnvironmentKey` 模板类型、执行器清理、注册表验证、派生内置名称与模型指引的统一来源。模型 bash 使用 `ctx.bashEnv` 收集的当前快照。实现会移除继承的受管 key,再在普通 `env` 之后合并 `dshEnv`,因此省略的当前事实不会回退到陈旧环境状态,`env` 条目也无法顶掉受管值。面向模型的工具不将这三者中的任何一个公开为参数。这三者在已解析 spec 上仍然可选;缺失表示没有输入/overlay。详见 [bash-stdin-env Agent Note(agent 决策记录)](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) 与 [会话环境 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md)。 ## 模型体验 @@ -41,9 +41,9 @@ #### KV Cache 影响 -不会直接失效;请求前缀变更由具名消费方负责。 +不会直接导致 KV Cache 失效;请求前缀变更由具名消费方负责。 ## 已知限制与暂缓事项 - **没有交互式输入词汇**:`stdin` 只会在 spawn 时写入一次并关闭;seam 不提供向运行中任务继续输入的通道,也没有 PTY 会话概念。 -- **前台超时始终由执行器拥有**:seam 上的调用方拥有 deadline 模式已由 [工具调用超时策略 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md) 明确暂缓。 +- **前台超时始终由执行器负责**:seam 上由调用方负责 deadline 的模式已由 [工具调用超时策略 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md) 明确暂缓。 From 90c75be466cd77d271977b6b7300ae3327afb77d Mon Sep 17 00:00:00 2001 From: j-xiang Date: Wed, 29 Jul 2026 15:29:38 +0800 Subject: [PATCH 16/38] docs(i18n): proofread README translations 21-40 --- packages/client/hmr/README.zh.md | 12 +++++----- packages/client/locale/README.zh.md | 4 ++-- packages/client/modules/README.zh.md | 10 ++++---- packages/client/runtime/README.zh.md | 22 ++++++++--------- packages/client/ui-model/README.zh.md | 18 +++++++------- packages/client/ui-models/README.zh.md | 2 +- packages/client/ui-primitives/README.zh.md | 6 ++--- packages/client/ui-settings/README.zh.md | 2 +- packages/client/ui-sidebar/README.zh.md | 12 +++++----- packages/client/ui-skill/README.zh.md | 12 +++++----- packages/client/ui-slash/README.zh.md | 12 +++++----- packages/client/ui-slots/README.zh.md | 10 ++++---- packages/client/ui-subagent/README.zh.md | 10 ++++---- packages/client/ui-theme/README.zh.md | 8 +++---- packages/client/ui-trajectory/README.zh.md | 6 ++--- packages/client/web-react/README.zh.md | 6 ++--- packages/client/web/README.zh.md | 10 ++++---- packages/code-runtime/README.zh.md | 6 ++--- .../code-runtime-worker/README.zh.md | 24 +++++++++---------- .../code-runtime/code-runtime/README.zh.md | 16 ++++++------- 20 files changed, 104 insertions(+), 104 deletions(-) diff --git a/packages/client/hmr/README.zh.md b/packages/client/hmr/README.zh.md index 6d94ca4a5e..58fbad900d 100644 --- a/packages/client/hmr/README.zh.md +++ b/packages/client/hmr/README.zh.md @@ -2,9 +2,9 @@ [English](README.md) | 中文 -为通过 fetch 到达的客户端插件提供热重载。该静态到达配置项只组合进 `--dev` 图(`dsh web --dev`);生产图省略此行,因此外壳打包的代码保持不活动。 +为通过 fetch 加载的客户端插件提供热重载。该静态加载配置项只组合进 `--dev` 图(`dsh web --dev`);生产图省略该项,因此打包进 shell 的代码保持不活动。 -浏览器侧订阅系统 SSE 通道(`GET /plugins/events`),每个 `rebuilt` 帧重载一个插件,并通过队列串行执行(组合包交接 slot 只能容纳一个)。每帧的顺序是:`prefetch`(在触碰任何内容前抓取新组合包)、`invalidate`、`registry.delete`(在 fiber 之前执行:只释放 fiber 会触发 vendored Loader 的 self-dispose 分支,把配置项标为禁用)、排空旧 fiber、删除 `entry.fiber`、移除自身拥有的 `