diff --git a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml index b1a81228cf..45e1c99967 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.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 -2026-07-24-single-harness-home-resolver.md: 10ed0e9f1fd6ac4630d92a66953fdf1d52b3b5f1 -2026-07-24-single-harness-home-resolver.zh.md: 1ce56281357595de134ddea285c8c2e0c1801ce9 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md +2026-07-24-single-harness-home-resolver.md: 159ba88b7b4a8d50f1be2cbe5d9162a654014e16 +2026-07-24-single-harness-home-resolver.zh.md: 62046abca48a3c2b07fde4180031dc2186dc101f diff --git a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md index 10ed0e9f1f..159ba88b7b 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md +++ b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md @@ -22,7 +22,7 @@ One resolver owns the harness home, in `@deepseek-ai/dsh-paths`, single-root: explicit configured path > $DSH_HOME > ~/.dsh ``` -An empty or whitespace-only `$DSH_HOME` is treated as unset, matching the guard telemetry's old resolver carried: without it `resolve('')` would silently place the home at the current working directory. The harness keeps all user data under one root; there is no XDG config/data/cache split. `dshHomeDisplay()` names a resolved root symbolically for user-facing paths — `~/.dsh` for the default home, `$DSH_HOME` for any configured home — so the user-global `AGENTS.md` label never leaks an absolute machine path. It replaces workspace-context's bespoke default-vs-`$DSH_HOME` check. +An empty or whitespace-only `$DSH_HOME` is treated as unset, matching the guard telemetry's old resolver carried: without it `resolve('')` would silently place the home at the current working directory. The harness keeps all user data under one root; there is no XDG config/data/cache split. `dshHomePath(...segments)` joins deployment-owned children onto that root, and `dsh-app-boot` exposes it to Loader `!!js` config expressions before mounting entries, so shipped compositions derive `sessions` and `storages` without copying the resolver. `dshHomeDisplay()` names a resolved root symbolically for user-facing paths — `~/.dsh` for the default home, `$DSH_HOME` for any configured home — so the user-global `AGENTS.md` label never leaks an absolute machine path. It replaces workspace-context's bespoke default-vs-`$DSH_HOME` check. `@deepseek-ai/dsh-home` is deleted. Its three importers (`dsh-tool-bash`, `dsh-skill-local`, `dsh-agent-spine-demo`) now import `resolveDshHome` from `dsh-paths`. `dsh-telemetry`'s `globalConfigDir` delegates to `resolveDshHome`, dropping its second resolver, the `DSH_CONFIG_HOME` override, the XDG/`%APPDATA%` branches, and the `deepseek-harness` namespace; the anonymous id now lives directly under the harness home. diff --git a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md index 1ce5628135..62046abca4 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md @@ -22,7 +22,7 @@ Status: implemented explicit configured path > $DSH_HOME > ~/.dsh ``` -空或仅含空白的 `$DSH_HOME` 被当作未设置处理,这与 telemetry 旧解析器所带的保护一致:若无此保护,`resolve('')` 会悄悄把 home 落在当前工作目录。harness 把所有用户数据都放在同一个根目录下;不存在 XDG 的 config/data/cache 拆分。`dshHomeDisplay()` 为面向用户的路径以符号形式命名已解析的根目录——默认 home 显示为 `~/.dsh`,任何已配置的 home 显示为 `$DSH_HOME`——这样面向用户全局的 `AGENTS.md` 标签就绝不会泄露机器上的绝对路径。它取代了 workspace-context 中自定义的"默认值 vs `$DSH_HOME`"判断。 +空或仅含空白的 `$DSH_HOME` 被当作未设置处理,这与 telemetry 旧解析器所带的保护一致:若无此保护,`resolve('')` 会悄悄把 home 落在当前工作目录。harness 把所有用户数据都放在同一个根目录下;不存在 XDG 的 config/data/cache 拆分。`dshHomePath(...segments)` 将部署负责的子路径拼接到该根目录下,`dsh-app-boot` 在挂载条目前向 Loader `!!js` 配置表达式暴露它,因此出厂组合无需复制解析器即可派生 `sessions` 和 `storages`。`dshHomeDisplay()` 为面向用户的路径以符号形式命名已解析的根目录——默认 home 显示为 `~/.dsh`,任何已配置的 home 显示为 `$DSH_HOME`——这样面向用户全局的 `AGENTS.md` 标签就绝不会泄露机器上的绝对路径。它取代了 workspace-context 中自定义的"默认值 vs `$DSH_HOME`"判断。 `@deepseek-ai/dsh-home` 被删除。它的三个引用方(`dsh-tool-bash`、`dsh-skill-local`、`dsh-agent-spine-demo`)现在从 `dsh-paths` 导入 `resolveDshHome`。`dsh-telemetry` 的 `globalConfigDir` 转而委托给 `resolveDshHome`,去掉了它的第二个解析器、`DSH_CONFIG_HOME` 覆盖项、XDG/`%APPDATA%` 分支以及 `deepseek-harness` 命名空间;匿名 id 现在直接存放在 harness home 之下。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.i18n.yaml index bca3fb39ad..2efe235e28 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.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/architecture/2026-07-30-client-locale-full-rollout.md -2026-07-30-client-locale-full-rollout.md: a357f20734d1aa8df60efbf28fd5b8a1a814d63e -2026-07-30-client-locale-full-rollout.zh.md: d22b743f0597405e7f42374ec2caed5523e85595 +2026-07-30-client-locale-full-rollout.md: 09baf5876029295f7a80b6a0fe6a6395d98f406c +2026-07-30-client-locale-full-rollout.zh.md: 806916aea15a21fd24fdfc4654976b3c4577a675 diff --git a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md index a357f20734..09baf58760 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md @@ -14,7 +14,7 @@ After the typed locale standard seat landed (`locale:` on register → framework **Component copy rides the standard `t` seat; deep children take `t` as a plain prop** typed `XxxProps['t']`. The dictionary canon is unchanged: `zh satisfies Record` is the key source and `en satisfies Record` locks bilingual balance. -**Zero-cordis atoms (ui-primitives) take copy as props**: `labels` on `TerminalBlock`/`JsonTree`, `copyLabel`/`copiedLabel` on `CodeBlock`, `codeLabels` on `MarkdownText`, `truncatedLabel` on `JsonBlock`, `label` on `ConnectionBanner`, `closeLabel` on `Modal` — defaults are the previous hardcoded strings, so a consumer passing nothing renders byte-identical output. Localized plugins pass dictionary-driven labels from their own `t` seat; call sites passing object props memoize them on the `t` identity (`MarkdownText` caches its component table on the `codeLabels` identity). +**Zero-cordis atoms (ui-primitives) take copy as props**: `copyLabel`/`copiedLabel` on `HoverCard`, `labels` on `TerminalBlock`/`JsonTree`, `copyLabel`/`copiedLabel` on `CodeBlock`, `codeLabels` on `MarkdownText`, `truncatedLabel` on `JsonBlock`, `label` on `ConnectionBanner`, `closeLabel` on `Modal` — defaults are the previous hardcoded strings, so a consumer passing nothing renders byte-identical output. Localized plugins pass dictionary-driven labels from their own `t` seat; call sites passing object props memoize them on the `t` identity (`MarkdownText` caches its component table on the `codeLabels` identity). **The non-translation boundary (deliberate decisions, not debt):** diff --git a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md index d22b743f05..806916aea1 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md @@ -14,7 +14,7 @@ typed locale 标准席位(`locale:` 注册声明 → 框架注入强类型 `t` **组件文案走标准 `t` 席位;深层子组件用 prop 下传**,类型写 `XxxProps['t']`。字典规范形态不变:`zh satisfies Record` 为 key 源、`en satisfies Record` 锁双语平衡。 -**zero-cordis 原子组件(ui-primitives)文案 props 化**:`TerminalBlock`/`JsonTree` 的 `labels`、`CodeBlock` 的 `copyLabel`/`copiedLabel`、`MarkdownText` 的 `codeLabels`、`JsonBlock` 的 `truncatedLabel`、`ConnectionBanner` 的 `label`、`Modal` 的 `closeLabel`——默认值即原硬编码字符串,不传 props 的消费者渲染逐字节不变。已本地化的插件从自己的 `t` 席位传字典驱动的 label;传对象 props 的调用点按 `t` 身份 memo(`MarkdownText` 的组件表按 `codeLabels` 身份缓存)。 +**zero-cordis 原子组件(ui-primitives)文案 props 化**:`HoverCard` 的 `copyLabel`/`copiedLabel`、`TerminalBlock`/`JsonTree` 的 `labels`、`CodeBlock` 的 `copyLabel`/`copiedLabel`、`MarkdownText` 的 `codeLabels`、`JsonBlock` 的 `truncatedLabel`、`ConnectionBanner` 的 `label`、`Modal` 的 `closeLabel`——默认值即原硬编码字符串,不传 props 的消费者渲染逐字节不变。已本地化的插件从自己的 `t` 席位传字典驱动的 label;传对象 props 的调用点按 `t` 身份 memo(`MarkdownText` 的组件表按 `codeLabels` 身份缓存)。 **不翻译边界(刻意决定,不是欠账):** diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml index cc25329fed..01334b2d8b 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.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/architecture/2026-07-30-session-end-seed-log-boundary.md -2026-07-30-session-end-seed-log-boundary.md: 268646e192d0b8e0a5dde03957a18ef155b7038e -2026-07-30-session-end-seed-log-boundary.zh.md: dca87e16de5e567ff85d2b32b8243f76ebed1c4a +2026-07-30-session-end-seed-log-boundary.md: ca6145f3ce404b88d2a144483c6f1145fe0a9a7e +2026-07-30-session-end-seed-log-boundary.zh.md: d492c4ac5f39328e75d991b285004e2d19c56283 diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md index 268646e192..ca6145f3ce 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md @@ -52,4 +52,4 @@ Cost: a seeded session's log is one event longer, including an empty resumed log `session/end-seed` joins the on-disk vocabulary. Under the pre-release stance (`SESSION_FORMAT_VERSION` pinned at `0`, no compatibility promise) older logs simply lack it, and a log without a boundary correctly classifies nothing as constructor-seed history. -Not built here: no plugin reads the boundary yet. Wiring the compaction seam's staleness check to it is the follow-up that motivated this boundary; the predicate helper belongs with that seam, where a real consumer decides its shape, rather than shipping into core untested against one. +The [queued manual compaction decision](../feature/2026-07-30-queued-manual-compaction.md) now supplies the first consumer. Its tail scan independently finds the unmatched `compact/start` and newest end-seed, treats only a start after that boundary as live, and clears the invariant trace on the same replay transition. The predicate remains in the compaction package rather than becoming a generic core helper. diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md index dca87e16de..d492c4ac5f 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md @@ -52,4 +52,4 @@ Status: implemented `session/end-seed` 加入了落盘词汇表。在预发布立场下(`SESSION_FORMAT_VERSION` 固定为 `0`,不作兼容承诺),更旧的日志只是没有它,而没有边界的日志会正确地判定没有任何内容属于构造种子历史。 -此处未做:还没有任何插件读取该边界。把压缩 seam 的陈旧性检查接到它上面,是催生这条边界的后续工作;谓词辅助函数应当归属那个 seam——在那里由真实消费方决定它的形状——而不是未经真实消费方检验就先落进核心。 +[排队手动压缩决策](../feature/2026-07-30-queued-manual-compaction.md)如今提供了第一个消费方。其尾部扫描会分别查找未匹配的 `compact/start` 与最新 end-seed,只把位于该边界之后的 start 视为活动锁,并在同一个回放转换上清除不变量追踪状态。该谓词仍位于压缩包中,不会成为通用核心辅助函数。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.i18n.yaml new file mode 100644 index 0000000000..ed2f7646bc --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.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/bug-fix/2026-07-30-hover-popup-pointer-grace.md +2026-07-30-hover-popup-pointer-grace.md: 3f60c98ec6453b633feebe408cbc0c0c49eedea1 +2026-07-30-hover-popup-pointer-grace.zh.md: db10e156103284383f911684b2c92977a0315275 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md new file mode 100644 index 0000000000..3f60c98ec6 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md @@ -0,0 +1,35 @@ +# Agent Note: Hover popup pointer grace + +Status: implemented + +English | [中文](2026-07-30-hover-popup-pointer-grace.zh.md) + +## Problem + +Both popups the workspace browser rows raise floated out of reach of the pointer. `HoverCard` closed on the first `pointerleave` from its anchor and rendered its card `pointer-events: none`, but the card sits 8px off the anchor's right edge, so every path to it crossed ground belonging to neither and killed the card before it arrived — the full workspace path and session title it exists to show could be read only in passing. The row action menus passed `closeOnPointerLeave`, whose handler sat on the portaled list: aiming back at the `...` trigger that opened the list closed it, and so did any overshoot past a list edge, with no window to come back. + +## Decision + +`usePointerGrace` ([packages/client/ui-primitives/src/pointer-grace.ts](../../../../packages/client/ui-primitives/src/pointer-grace.ts)) owns one cancelable delayed close, shared by both atoms, with `POINTER_GRACE_MS` at 200. Leaving arms the close; coming back cancels it. Transit through an anchor-to-popup gap is therefore survivable, while a pointer that has genuinely moved on still dismisses the popup. + +`HoverCard` arms the grace on leave instead of closing, and its card no longer sets `pointer-events: none`, so resting on the card holds it open. Re-entering while already open cancels the pending close without restarting the dwell, which keeps the card from blinking when the pointer crosses the gap. A press on the card starts a selection instead of dismissing it; only anchor-region presses and an owner flipping `disabled` dismiss immediately, ahead of the grace. + +`Menu` moves pointer-leave dismissal from the portaled list to the wrapper span. React's enter/leave traversal runs over the React tree, so the trigger and the portaled list are one region there: crossing the 4px gap between them, or aiming back at the trigger, no longer counts as leaving. Leaving is only armed while the list is open, and an owner-driven close (selection, Escape, outside click) disarms a pending grace close in an effect keyed on `open` alone — folding that into the outside-click effect would cancel the grace on every re-render, since owners pass a fresh `onClose` closure each time. + +## Alternatives considered + +**Close the popups only on outside click and Escape.** Rejected because both popups are hover-raised and unlabeled as dismissible; leaving them up after the pointer has moved to another row would strand a card over unrelated content. + +**Widen the anchor's hit area to abut the popup.** Rejected because the 8px and 4px offsets are the design's, and an invisible bridge element would have to track every reposition the fixed-positioned popups already do on scroll and resize. + +**Keep the hover card `pointer-events: none` and only add the grace.** Rejected because the pointer resting on the card would then hit whatever is behind it, so the grace would expire and close the card the user had just reached. + +**Give each atom its own timer.** Rejected because the two closes are the same behavior with the same tuning; a shared hook keeps them from drifting apart. + +## Consequences + +The hover card is now hit-testable and covers 244px of whatever it overlays while shown, which is the price of being reachable; it still lives only as long as the pointer is on the row or the card. Row menus survive the round trip between trigger and list, and a menu that closes for its own reason cannot be reopened into a stale pending close. Menus without `closeOnPointerLeave` are untouched — the wrapper handlers are only attached when it is set. + +## Testing + +`packages/client/ui-primitives/tests/hover-card.spec.tsx` and `tests/atoms.spec.tsx` pin the grace boundary, cancel-on-return, no-second-dwell, disarm-on-owner-close, and the no-arming-while-closed case. The reachability gestures themselves — hovering onto the card, and moving between an open list and its trigger — are pinned in the real browser by `apps/web/tests/workspace-management.e2e.ts`, since they depend on hit testing and layout that jsdom does not model. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md new file mode 100644 index 0000000000..db10e15610 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 悬浮弹层的指针宽限期 + +Status: implemented + +[English](2026-07-30-hover-popup-pointer-grace.md) | 中文 + +## 问题 + +工作区浏览器行弹出的两种弹层都处于指针无法抵达的位置。`HoverCard` 在指针离开锚点的第一个 `pointerleave` 上就关闭,其卡片还设置了 `pointer-events: none`;但卡片位于锚点右边缘外 8px 处,因此通往卡片的每条路径都要穿过既不属于锚点也不属于卡片的区域,卡片在指针抵达之前就已被销毁——它本应展示的完整工作区路径和会话标题只能匆匆一瞥。行操作菜单传入了 `closeOnPointerLeave`,而其处理器挂在传送后的列表上:把指针移回打开该列表的 `...` 触发按钮会关闭列表,越过列表边缘的任何一次抖动同样如此,且没有任何折返窗口。 + +## 决策 + +`usePointerGrace`([packages/client/ui-primitives/src/pointer-grace.ts](../../../../packages/client/ui-primitives/src/pointer-grace.ts))持有唯一一个可取消的延迟关闭,由两个原子组件共享,`POINTER_GRACE_MS` 为 200。离开会启动关闭,折返则取消它。因此指针可以安全穿越锚点与弹层之间的间隙,而真正移开的指针仍会关闭弹层。 + +`HoverCard` 在离开时启动宽限期而不再立即关闭,其卡片也不再设置 `pointer-events: none`,因此指针停在卡片上即可让它保持打开。在已打开状态下重新进入只取消待执行的关闭,而不重启停留计时,从而避免指针穿越间隙时卡片闪烁。在卡片上按下指针用于开始文本选择,不会关闭卡片;只有锚点区域内的按下和所有者将 `disabled` 置真,才会抢在宽限期之前立即关闭卡片。 + +`Menu` 把指针离开关闭的处理从传送后的列表移到包裹 span 上。React 的 enter/leave 遍历基于 React 树进行,因此触发按钮与传送后的列表在这里属于同一区域:穿越两者之间 4px 的间隙、或把指针移回触发按钮,都不再算作离开。只有在列表打开时才会启动离开关闭;由所有者驱动的关闭(选择、Escape、外部点击)会在一个仅以 `open` 为依赖的 effect 中解除待执行的宽限关闭——若把它折叠进外部点击的 effect,则每次重新渲染都会取消宽限期,因为所有者每次都传入新的 `onClose` 闭包。 + +## 考虑过的替代方案 + +**仅通过外部点击和 Escape 关闭这两种弹层。** 之所以否决:两者都由悬停唤起,且没有可见的关闭标识;在指针已移到其他行之后仍让它们停留,会把卡片遗留在无关内容之上。 + +**扩大锚点的命中区域,使其与弹层相接。** 之所以否决:8px 与 4px 的偏移来自设计稿,而一个不可见的桥接元素还必须跟随这两个固定定位弹层已经在滚动和缩放时执行的每一次重新定位。 + +**保留悬浮卡片的 `pointer-events: none`,只加入宽限期。** 之所以否决:那样指针停在卡片上时命中的是卡片背后的元素,宽限期仍会到期,并关闭用户刚刚够到的卡片。 + +**让两个原子组件各自持有计时器。** 之所以否决:这两处关闭是同一种行为、同一套调参;共享 hook 可以防止它们各自漂移。 + +## 后果 + +悬浮卡片现在可被命中,显示期间会遮挡其覆盖区域的 244px——这是可抵达性的代价;它依然只在指针位于行或卡片上时存在。行菜单现在能承受触发按钮与列表之间的往返,而因自身原因关闭的菜单也不会被残留的待执行关闭重新关掉。未设置 `closeOnPointerLeave` 的菜单不受影响——只有设置该属性时才会挂上包裹层处理器。 + +## 测试 + +`packages/client/ui-primitives/tests/hover-card.spec.tsx` 与 `tests/atoms.spec.tsx` 固定验证宽限期边界、折返取消、不重启停留计时、所有者关闭时解除待执行关闭,以及列表关闭时不启动关闭。可抵达性手势本身——把指针移到卡片上,以及在打开的列表与其触发按钮之间移动——由 `apps/web/tests/workspace-management.e2e.ts` 在真实浏览器中固定验证,因为它们依赖 jsdom 无法建模的命中测试与布局。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml new file mode 100644 index 0000000000..12b3982d54 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.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/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md +2026-07-31-hero-visible-while-blank-session-opens.md: b39963beffa403ef6fa44735aa88395a99139751 +2026-07-31-hero-visible-while-blank-session-opens.zh.md: b451d7c00ec7eb8d736134e738d72e5e07fd1b04 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md new file mode 100644 index 0000000000..b39963beff --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md @@ -0,0 +1,35 @@ +# Agent Note: Hero stays visible while a blank session opens + +Status: implemented + +English | [中文](2026-07-31-hero-visible-while-blank-session-opens.zh.md) + +## Problem + +The conversation root has a `settling` phase for a session that is still opening while its composer reads `blank`: the hero-versus-docked outcome is unknowable until history arrives, so the composer seat is hidden (`visibility:hidden`) rather than flashing the centered hero and snapping to the docked bar. Startup auto-selection turned that guard into the defect it was meant to prevent. From the no-workspace hero, `WorkspacesService.startInitialSelection` connects the most recent workspace and opens its blank session; `openState` flips to `loading` the moment `open()` lands, so the center column went blank for the whole history round-trip and then repainted, which reads as a full-page refresh on every launch. + +## Decision + +`ConversationRoot` reads the session list summary's `blank` flag alongside the conversation snapshot and exempts summary-proven blank sessions from settling: `settling` additionally requires `summaryBlank !== true`, and `hero` accepts a blank composer whenever the summary proves the session blank, in every open state rather than only `loading`. A session the list already reports as blank can only land on the hero, so hiding buys nothing and costs the visible flash; the same proof holds before the open starts (`cold`) and after one fails (`error`), where the previous conditions fell through to the active phase and rendered a docked bare composer under chrome `ConversationSession` hides for blank sessions. Whenever the summary does not prove the session blank — a row reporting `blank: false`, or no row at all because the list has not caught up — `summaryBlank` is not `true` and the conservative settling hide is unchanged. + +The summary flag and the snapshot's own `blank` are distinct sources: the snapshot describes the session being opened, the summary is the list row that already exists before the open resolves. Only the latter is available early enough to decide the phase. + +## Alternatives considered + +**Drop the settling phase entirely.** Rejected because it still earns its keep for a session with no summary row: without a prior claim about emptiness, hero-versus-docked is genuinely unknowable and the flash it prevents is the worse one. + +**Delay the `loading` flip until history returns.** Rejected because `openState` is authoritative about the open operation; deferring it to suppress a presentation artifact would misreport the data state to every other consumer. + +**Cross-fade or otherwise animate the settling hide.** Rejected because the column has nothing to show during the round-trip either way — the fix is to not hide content whose outcome is already known, not to decorate the hiding. + +## Deferred + +The no-session→session tree relocation in `ConversationRoot` (the hero/composer subtree moves into the `conversation.session` outlet) still rebuilds the composer DOM on the same transition; removing it means moving `conversation.session` to `session-maybe` scope, a slot-contract change that needs its own proposal. + +Object-layer reference churn found while diagnosing this — no-op projections minting fresh snapshots, the create path projecting twice, `select()` using `notifyNow` from async continuations — is real but independent of the visible flash. + +## Consequences + +Startup auto-selection renders the hero immediately and keeps the composer seat and header visible through the history round-trip, so launching into a recent workspace no longer looks like a page reload. Sessions whose summary does not prove them blank keep the previous settling behavior, so the guard still covers the case it was written for. Skeleton tests pin all three summary shapes: a row reporting `blank: false` settles, an absent row settles, and a summary-proven blank session opening under `loading` renders hero chrome with a live textarea. + +The assembled coverage is `apps/web/tests/startup-auto-selection.e2e.ts` (keyless web browser lane): it registers a workspace, holds the `session.history` response open at the browser's network boundary, and asserts the visible frame while the auto-selected open is in flight — hero phase, hero title, painted composer — plus a recorded phase timeline of exactly `['hero']` for the whole load. Holding the round-trip is what makes it a regression test rather than a race: against a loopback host the open settles too fast to sample, and with the exemption reverted the held window is precisely when the root reports `settling`. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md new file mode 100644 index 0000000000..b451d7c00e --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 空白会话打开期间保持 hero 可见 + +Status: implemented + +[English](2026-07-31-hero-visible-while-blank-session-opens.md) | 中文 + +## 问题 + +会话根节点为"正在打开且 composer 处于 `blank`"的会话保留了一个 `settling` 阶段:在历史记录返回之前,hero 与 docked 的归属不可知,因此宁可隐藏 composer 座位(`visibility:hidden`),也不要先闪出居中的 hero 再跳到底部输入条。启动时的自动选择把这道防护变成了它本要防止的缺陷。从无工作区的 hero 进入时,`WorkspacesService.startInitialSelection` 会连接最近的工作区并打开其空白会话;`open()` 一落地 `openState` 立即翻为 `loading`,中间栏因此在整个历史往返期间保持空白,随后重绘一次——每次启动看起来都像整页刷新。 + +## 决策 + +`ConversationRoot` 在读取会话快照的同时读取会话列表摘要的 `blank` 标志,并让"摘要已证明为空白"的会话豁免 settling:`settling` 额外要求 `summaryBlank !== true`,而 `hero` 在摘要证明会话为空白时接受处于 blank 的 composer——覆盖全部 open state,而非仅 `loading`。列表已报告为空白的会话只可能落到 hero,因此隐藏毫无收益,只换来一次可见闪烁;同一份证明在打开开始之前(`cold`)与打开失败之后(`error`)同样成立,而此前的条件会在这两种状态下落到 active 阶段,在 `ConversationSession` 为空白会话隐藏的外壳之下渲染出一条停靠的裸 composer。只要摘要没有证明会话为空白——无论是报告 `blank: false` 的行,还是列表尚未跟上因而根本没有该行——`summaryBlank` 都不为 `true`,保守的 settling 隐藏行为保持不变。 + +摘要标志与快照自身的 `blank` 是两个不同来源:快照描述正在打开的这个会话,摘要则是在打开操作完成之前就已存在的列表行。只有后者足够早,可用于决定阶段。 + +## 备选方案 + +**彻底移除 settling 阶段。** 否决,因为对没有摘要行的会话它仍有价值:在缺少任何关于"是否为空"的先验断言时,hero 与 docked 的归属确实不可知,而它所防止的那种闪烁更糟糕。 + +**推迟 `loading` 的翻转,直到历史返回。** 否决,因为 `openState` 是打开操作的权威状态;为了压制一个呈现层瑕疵而推迟它,会向其他所有消费者误报数据状态。 + +**为 settling 的隐藏加交叉淡入或其他动画。** 否决,因为无论如何该栏在往返期间都没有内容可展示——正确的修复是不隐藏结局已知的内容,而不是把隐藏装饰得好看些。 + +## 推迟事项 + +`ConversationRoot` 中"无会话→有会话"的树位置迁移(hero/composer 子树移入 `conversation.session` 出口)仍会在同一次转换中重建 composer 的 DOM;消除它意味着把 `conversation.session` 移到 `session-maybe` 作用域,这是一次插槽契约变更,需要单独立项。 + +诊断期间发现的对象层引用抖动——空操作投影铸造出新的快照、创建路径重复投影一次、`select()` 在异步续体中使用 `notifyNow`——确实存在,但与这次可见闪烁相互独立。 + +## 影响 + +启动自动选择会立即渲染 hero,并在整个历史往返期间保持 composer 座位与 header 可见,因此启动进入最近工作区不再像页面重载。摘要未证明为空白的会话保持原有的 settling 行为,这道防护仍覆盖它当初针对的场景。骨架测试固定了摘要的三种形态:报告 `blank: false` 的行进入 settling;根本没有该行同样进入 settling;摘要已证明为空白的会话在 `loading` 期间渲染 hero 外壳与可用的文本框。 + +组装级覆盖是 `apps/web/tests/startup-auto-selection.e2e.ts`(无密钥的 Web 浏览器泳道):它注册一个工作区,在浏览器网络边界上扣住 `session.history` 的响应,并在自动选择的打开仍在飞行途中断言可见画面——hero 阶段、hero 标题、已绘制的 composer——外加整次加载记录到的阶段时间线恰好为 `['hero']`。扣住这次往返正是它成为回归测试而非竞态的原因:对着回环主机,打开会快到无从采样;而一旦回退这条豁免,被扣住的这段窗口恰恰就是根节点报告 `settling` 的时刻。 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml index 414c63211a..714b75d942 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.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/2026-06-18-compaction-capability-seam.md -2026-06-18-compaction-capability-seam.md: 3c219b734e148b963fb5857de89c16f28c2bd402 -2026-06-18-compaction-capability-seam.zh.md: b2c7e9720b596705b60a284e6ccf1448a782b7fc +2026-06-18-compaction-capability-seam.md: ef37313bc6fb984689793fa5a3e7ac4d9238ea88 +2026-06-18-compaction-capability-seam.zh.md: 9f123a8c40f303a2635af78cafd34de448e27e03 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md index 3c219b734e..ef37313bc6 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -18,10 +18,10 @@ Two forces shape the design. First, compaction policy and reusable token measure Per the [capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: -1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, the `compact/*` session events, and the canonical checkpoint message source. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. +1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, the `compact/*` session events, the manual failure taxonomy, and the canonical checkpoint message source. It declares `compactIfNeeded()`, `compactNow()`, and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. 2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. 3. **Model-free companion** — `@deepseek-ai/dsh-compact-tool-result-prune`: a concrete optional service that rewrites oversized current `tool/result` nodes before the backend selects a summary range. It is not a second compaction implementation and does not implement `CompactService`. -4. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. +4. **Human consumer** — `@deepseek-ai/dsh-command-compact` registers argument-free `/compact` through `ctx.commands` and calls the backend-independent `compactNow()` operation. It is direct human control, not a model-facing tool. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -29,11 +29,11 @@ The capability-seams Agent Note states the interface package "depends only on co This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. -### Abstract `compactIfNeeded` / `compactRegion`, algorithm in the backend +### Three abstract operations, algorithm in the backend -An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. +An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. -`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for manual callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`. +`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` reserves idle turn admission and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`. ### Automatic pressure runs after successful durable step work @@ -91,42 +91,44 @@ The basic backend wraps the summary as established checkpoint context and tags i ### Blocking via a log-recorded lock, plus a crash/recoverable failure taxonomy -The `compact/start … compact/end` bracket is justified, in order of what now does the work: +The `compact/start … compact/end` bracket is justified by two roles: 1. **Crash-detectable orphan + provenance** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan. -2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across either awaited automatic seam, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) +2. **Prevents concurrent compaction.** Every automatic, manual, and explicit-range entry point refuses a live unmatched `compact/start`. The bracket is the single lock; no process-local mutex duplicates it. -The lock excludes another compaction, not unrelated log-only facts. The basic backend snapshots the token meter's surface nodes after `compact/start` and compares them again after asynchronous summarization; any surface mutation rejects before replacement, while a title or other log-only append leaves the selected span valid. +The lock excludes another compaction, not unrelated facts. Its markers are time points rather than an exclusive container, so idle injected context may appear between a standalone manual start and end. Automatic work requires whole-surface stability inside its turn. Manual work revalidates only the selected positional span, letting append-only context outside it remain visible after replacement. -Two failure paths, both documented: +The lifecycle boundary makes crash state unambiguous: -- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — no summary replacement lands. The derived surface remains the durable surface present at `compact/start`: full history when pruning made no replacement, or the already-pruned history when it did. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. -- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and lands no summary replacement. Post-step pressure warns and continues from the latest durable surface — full history if no replacement preceded the attempt, or the pruned surface if pruning already landed. Overflow recovery delegates only before any replacement; generation progress from earlier pruning authorizes a retry from that durable surface unless cancellation or disposal wins. +- **Current lifecycle:** a dangling `compact/start` after the newest `session/end-seed` is the live durable lock and reports busy. +- **Later lifecycle:** a newer constructor-written `session/end-seed` proves that the older unmatched start is stale, so resume, fork, and adoption do not remain wedged by a dead writer. +- **Recoverable failure:** once start lands, the backend makes exactly one `compact/end { error }` attempt. Summary or stability failure leaves the conversation surface unchanged while preserving the failed attempt in the log. If the close append fails, the unmatched start remains intentionally blocking. `compact/end` keeps its `error?` field (mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling). There is no separate `compact/error` event. -**Core session repair stays compaction-agnostic — deliberately.** `interruptedTurnClosers` is never taught about `compact/*`. Teaching it would force every future `xxx/start … xxx/end` plugin pair to patch a core module — exactly the coupling the capability-seam architecture exists to avoid. Because the log-only orphan is inert, no special repair is needed: generic turn-repair plus the inertness of an un-landed surface mutation is sufficient. +**Core session repair stays compaction-agnostic — deliberately.** `interruptedTurnClosers` is never taught about `compact/*`. The general `session/end-seed` lifecycle boundary supplies the evidence the compaction owner needs; the compaction invariant and backend interpret it without adding plugin-specific repair to core. ## Alternatives considered -- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. +- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. All three operations are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. - **Compaction on `agent/request` or provisional `agent/pre-step` inputs** — rejected because neither proves the final durable request and both couple generic lifecycle to compaction-specific envelope data. Post-step replay plus canonical overflow recovery covers both successful and rejected calls. - **A `compact` boolean or untyped request metadata map** — rejected because multiple auxiliary call kinds would become mutually exclusive flags, while an open bag would discard compiler-checked vocabulary. One typed `purpose` discriminant extends with additional call kinds without adding another `GenerateOptions` field. - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling. -- **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid. +- **Teaching core turn-repair about `compact/*`** — rejected: the general end-seed boundary already distinguishes prior-lifecycle history, and patching core for every future `xxx/start … xxx/end` pair is exactly the coupling the capability-seam architecture exists to avoid. ## Consequences -- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, and `compact-tool-result-prune` supplies optional deterministic rewriting. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. +- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, `compact-tool-result-prune` supplies optional deterministic rewriting, and `command-compact` supplies human `/compact`. `packages/llm/token-meter` owns replay-aware measurement independently. - **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `COMPACT_CHECKPOINT_SOURCE`, `isCompactCheckpointSource(source)`, `toolPairingBalancedBefore(session, seq)`, and `toolPairingBalancedAfter(session, seq)`. The marker identifies replacement summaries across backend implementations. The cached surface-edge checks prevent `compactRegion` and `compactIfNeeded` from splitting a tool-call/result pair, validate current membership by seq, answer both edges from one per-cut balance sequence, and reject stale or missing seqs and orphan results. -- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call; validated replacements remain turn-enclosed rewrites. -- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, then `dsh-compact-basic`; service-wide defaults make the composition usable without repeated numeric policy. +- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call, while the compaction companion owns numeric-turn versus standalone-null bracket relations. +- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, `dsh-compact-basic`, then `dsh-command-compact`; service-wide defaults make the composition usable without repeated numeric policy. ## Testing - **Unit:** Real Loader and invariant plugins cover whole-unit retention, pruning configuration and replay, rich-block ordering, metadata preservation, convergence, both `compact/end` outcomes, open-tail refusal, pruning-only and summarized overflow recovery, generation proof, caps, and original-error preservation. - **Loop:** Tests pin post-step after durable tool results and before `step/end`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. +- **Manual:** Admission, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. - **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md index b2c7e9720b..9f123a8c40 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md @@ -18,10 +18,10 @@ Status: implemented 遵循[能力 seam Agent Note(agent 决策记录)](../architecture/2026-06-13-capability-seams.md),压缩以独立包(package)发布,使契约、算法和(后续的)消费方 surface 各自独立演进: -1. **接口** — `@deepseek-ai/dsh-compact`:抽象 `CompactService`,拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件以及规范的检查点消息来源。它将 `compactIfNeeded()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*,而非*怎么做*。 +1. **接口** — `@deepseek-ai/dsh-compact`:抽象 `CompactService`,拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件、手动失败分类体系以及规范的检查点消息来源。它将 `compactIfNeeded()`、`compactNow()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*,而非*怎么做*。 2. **实现** — `@deepseek-ai/dsh-compact-basic`:具体的 `BasicCompactService`,消费 `ctx.tokenMeter`,并拥有尾→头保留遍历、通过 `ctx.llm.stream()` 生成摘要、surface 替换、锁、步骤后压力处理和规范的上下文溢出恢复。`summarize()` 是其唯一的子类钩子;计价与回放仍归 meter 所有。 3. **无模型配套服务** — `@deepseek-ai/dsh-compact-tool-result-prune`:一个具体的可选服务,在后端选择摘要范围之前,重写当前过大的 `tool/result` 节点。它不是第二种压缩实现,也不实现 `CompactService`。 -4. **消费方** — 推迟。一个 `/compact` 工具和斜杠命令将 `inject: ['compact']` 并调用契约;它们被有意排除在本 Agent Note 范围之外,以便 seam 先稳定下来。 +4. **面向用户的消费方** — `@deepseek-ai/dsh-command-compact` 通过 `ctx.commands` 注册无参数 `/compact`,并调用后端无关的 `compactNow()` 操作。它是供用户直接控制的命令,不是面向模型的工具。 ### 契约依赖 `dsh-session` 和 `dsh-llm`——有意为之的偏离 @@ -29,11 +29,11 @@ Status: implemented 这不是耦合异味,而是契约的领域所在。「仅 cordis」的指导原则一直是「接口仅依赖契约真正需要命名的东西,绝不依赖实现」的简写。`dsh-session` 和 `dsh-llm` 本身是接口/词汇包,不是实现;`dsh-compact` 仍然不导入任何后端。seam 的真正不变式——*消费方和实现在抽象服务背后独立演进*——完好无损。 -### 抽象 `compactIfNeeded` / `compactRegion`,算法在后端 +### 三个抽象操作,算法在后端 -早期草案将完整算法(保留遍历、token 求和、文本提取)作为接口上的具体方法。这会将契约重新耦合到一种策略:想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将两个核心方法都设为抽象,把所有*怎么做*的决策放在后端,并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子;单例服务使多个消费方能够共享逐会话的回放折叠。 +早期草案将完整算法(保留遍历、token 求和、文本提取)作为接口上的具体方法。这会将契约重新耦合到一种策略:想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象,把所有*怎么做*的决策放在后端,并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子;单例服务使多个消费方能够共享逐会话的回放折叠。 -`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求;没有 header 就不执行工作,任何已路由的提供方/模型目标都使用单例估算器。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份,并为手动调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标,并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀,并将压缩指令追加为尾部 user 消息,从而复用提供方的热 KV cache;见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`;适配器可以将此用途映射为对模型隐藏的传输元数据,DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 +`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求;没有 header 就不执行工作,任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 会预留空闲轮次接纳,即使未达到压力也进行一次有效的平衡缩减;不存在这种范围时返回 `null`,且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份,并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标,并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀,并将压缩指令追加为尾部 user 消息,从而复用提供方的热 KV cache;见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`;适配器可以将此用途映射为对模型隐藏的传输元数据,DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 ### 成功的持久步骤工作完成后运行自动压力检查 @@ -91,42 +91,44 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab ### 通过日志记录的锁实现阻塞,加上崩溃/可恢复失败的分类 -`compact/start … compact/end` 括号的存在理由,按当前实际承担的职责排序: +`compact/start … compact/end` 标记对承担两项职责: 1. **可检测的崩溃孤儿 + 来源追溯**(首要)。摘要生成是一次慢速模型调用,持久化在 `compact/start` *之后*。摘要生成中途崩溃会留下一个没有匹配 `compact/end` 的 `compact/start`——一个可检测的孤儿。最后释放锁(而非最先)将崩溃窗口从*静默损坏*转变为可检测的孤儿。 -2. **防止并发压缩。** 如果当前轮次持有未匹配的 `compact/start`,`compactRegion` 拒绝启动。(循环在任一 awaited 自动 seam 上都是单线程的,因此这也是重入绊线——抛出「already in progress」表示真正的 bug。) +2. **防止并发压缩。** 每个自动、手动和显式范围入口点都会拒绝活动的未匹配 `compact/start`。该标记对就是唯一的锁;没有进程本地 mutex 重复承担同一职责。 -该锁只排除另一项压缩,不排除无关的仅日志事实。基础后端会在 `compact/start` 之后对 token meter 的 surface 节点取快照,并在异步摘要后再次比较;任何 surface 变更都会使替换前的检查失败,而标题或其他仅日志追加不会使已选范围失效。 +该锁只排除另一项压缩,不排除无关事实。其标记是时间点,而不是排他的容器,因此空闲注入的上下文可以出现在独立手动 start 与 end 之间。自动工作要求其轮次内的整个 surface 保持稳定。手动工作只重新验证所选位置 span,使其外部的仅追加上下文在替换后保持可见。 -两种失败路径,均有文档记录: +生命周期边界使崩溃状态含义明确: -- **崩溃**(循环在摘要生成中途死亡):悬空的 `compact/start`,无关闭事件。由于 `compact/*` 是**仅日志**事件,孤儿是**惰性的**,不会落地摘要替换。派生 surface 保持为 `compact/start` 时已经持久化的 surface:如果修剪未产生替换,就是完整历史;如果已经修剪,就是已修剪历史。通用轮次修复(`interruptedTurnClosers`)用合成的 `turn/end` 关闭轮次;孤儿位于该 `turn/end` *之前*,因此轮次范围内的进行中检查永远看不到它,崩溃不会卡住未来的压缩。 -- **可恢复**(摘要生成抛出异常但循环存活):后端追加设置了 **`error`** 字段的 `compact/end`,但不落地摘要替换。步骤后压力处理发出警告,并从最新的持久 surface 继续:如果尝试前没有替换,就是完整历史;如果修剪已经落地,就是已修剪 surface。溢出恢复只会在没有任何替换前委托;先前修剪带来的 generation 进展允许从该持久 surface 重试,除非取消或资源释放胜出。 +- **当前生命周期:** 最新 `session/end-seed` 之后悬空的 `compact/start` 是活动的持久锁,并报告 busy。 +- **后续生命周期:** 构造函数写入的较新 `session/end-seed` 证明更早的未匹配 start 已陈旧,因此恢复、fork 和接手不会被已死的写入方持续卡住。 +- **可恢复失败:** start 落地后,后端会恰好尝试一次 `compact/end { error }`。摘要或稳定性失败会保持会话 surface 不变,同时在日志中保留失败尝试。如果追加闭合事件失败,未匹配 start 会继续有意阻塞。 `compact/end` 保留其 `error?` 字段(与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败,无需关联兄弟事件)。没有单独的 `compact/error` 事件。 -**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。如果教导它,每个未来的 `xxx/start … xxx/end` 插件对都必须修补核心模块——这恰好是能力 seam 架构存在的意义所要避免的耦合。由于仅日志的孤儿是惰性的,不需要特殊修复:通用轮次修复加上未落地 surface 变更的惰性就足够了。 +**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。通用 `session/end-seed` 生命周期边界提供压缩所有方所需的证据;压缩不变量与后端负责解释它,无需向核心添加插件专属修复。 ## 曾考虑的替代方案 -- **完整算法作为接口的具体方法**——否决,因为它将契约重新耦合到一种保留策略。两个核心方法都是抽象的;可复用测量属于单独的 LLM 系列服务,`summarize()` 是 basic 唯一的钩子。 +- **完整算法作为接口的具体方法**——否决,因为它将契约重新耦合到一种保留策略。三个操作都是抽象的;可复用测量属于单独的 LLM 系列服务,`summarize()` 是 basic 唯一的钩子。 - **在 `agent/request` 或临时 `agent/pre-step` 输入上执行压缩**——否决,因为两者都无法证明最终的持久请求,而且都会将通用生命周期耦合到压缩专属的信封数据。步骤后回放与规范溢出恢复同时覆盖成功和被拒绝的调用。 - **`compact` 布尔值或无类型的请求元数据 map**——否决,因为多个辅助调用种类会变成互斥标志,而开放 map 会丢弃由编译器检查的词汇。一个类型化的 `purpose` 判别字段可以扩展其他调用种类,而无需再为 `GenerateOptions` 添加字段。 - **单独的 `compact/error` 事件**——否决:`compact/end` 保留 `error?` 字段,与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败,无需关联兄弟事件。 -- **教导核心轮次修复识别 `compact/*`**——否决:仅日志的孤儿是惰性的,为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块恰好是能力 seam 架构存在的意义所要避免的耦合。 +- **教导核心轮次修复识别 `compact/*`**——否决:通用 end-seed 边界已经能够区分先前生命周期的历史;为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块,恰好是能力 seam 架构存在的意义所要避免的耦合。 ## 后果 -- **包**:`packages/compact/compact` 提供接口,`compact-basic` 提供后端,`compact-tool-result-prune` 提供可选的确定性重写。`packages/llm/token-meter` 独立拥有回放感知的测量。消费方层推迟。 +- **包**:`packages/compact/compact` 提供接口,`compact-basic` 提供后端,`compact-tool-result-prune` 提供可选的确定性重写,`command-compact` 提供面向用户的 `/compact`。`packages/llm/token-meter` 独立拥有回放感知的测量。 - **自动 seam**:`agent/post-step`(`@mode serial`)处理成功调用的压力,`agent/request-error`(`@mode waterfall`)处理失败步骤关闭后的最终请求失败。通用 `agent/pre-step` 保持为四参数检查点,不携带压缩专属的提示词/前缀 payload。 - **`SessionEventMap`** 通过可合并扩展的声明合并获得 `compact/start` / `compact/summary` / `compact/end`;`SurfaceEventType` **未被**触及。这些是会话事件,不是 cordis `Events`,因此事件分类门禁无需新增条目。 - **`dsh-compact`** 拥有 `COMPACT_CHECKPOINT_SOURCE`、`isCompactCheckpointSource(source)`、`toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`。该标记用于跨后端实现识别替换摘要。带缓存的 surface 边缘检查会防止 `compactRegion` 和 `compactIfNeeded` 拆分工具调用/结果对,按 seq 校验当前成员关系,从每个切割点的一条平衡序列回答两侧边缘,并拒绝陈旧或缺失的 seq 与孤立结果。 -- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行,要求存在已打开的步骤与待处理调用;已校验的替换仍是位于轮次内的重写。 -- **接线**:`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune` 和 `dsh-compact-basic`;服务级默认值使组合无需重复数值策略即可使用。 +- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行,要求存在已打开的步骤与待处理调用,而压缩配套组件拥有数字轮次归属与独立 `null` 归属标记对之间的关系。 +- **接线**:`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune`、`dsh-compact-basic`,然后加载 `dsh-command-compact`;服务级默认值使组合无需重复数值策略即可使用。 ## 测试 - **单元测试:** 使用真实 Loader 和 invariant 插件覆盖完整单元保留、修剪配置与回放、富块顺序、元数据保留、收敛、`compact/end` 的两种结果、开放尾部拒绝、仅修剪与带摘要的溢出恢复、generation 证明、上限和原始错误保留。 - **循环测试:** 测试固定步骤后处理发生在持久工具结果之后、`step/end` 之前,使用实际 `agent/request` 路由,关闭失败步骤,分配新的重试编号,并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。 +- **手动测试:** 无需模型密钥即可固定接纳、标记顺序、注入保留、活动/陈旧未匹配标记分类、取消、闭合/flush 失败、命令映射以及排队 TUI 流程。 - **带密钥 e2e:** 真实模型和 bash 会话在降低的限制下触发压缩,记录完整的 `compact/start…end` 对,缩小 surface,并完成任务。 - **快照缺口:** 失控轮次压缩尚无法回放,因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`;交错摘要调用的回放仍是后续工作。 diff --git a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml index ebc2df795a..9259180188 100644 --- a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.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/2026-07-25-session-list-browsing-and-manual-order.md -2026-07-25-session-list-browsing-and-manual-order.md: 831aa53e532a75392690c330837482bb0f9c32b1 -2026-07-25-session-list-browsing-and-manual-order.zh.md: 9ad074d59c13585aa4fca46ae4d40e2deb15cde6 +2026-07-25-session-list-browsing-and-manual-order.md: 5af9cf026c5a0e32837822b3d8cff827c052b07f +2026-07-25-session-list-browsing-and-manual-order.zh.md: 2cfa4efe2f0e53b419b264c9af0aff878d321cac diff --git a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md index 831aa53e53..5af9cf026c 100644 --- a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md +++ b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md @@ -34,7 +34,7 @@ The UI is HTML5 drag on session rows inside a group (workspace grouping only, ou ### Shell/region split -ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine, New Session, Settings, and one `sidebar.workspaces` hole; the shell↔region contract is two facts, `{ wide, expandSidebar }`. ui-workspace fully owns the browsing region (section header, search, grouped tree and flat list, every workspace dialog, drag) plus its groupBy store; the rail-state search/new-workspace icons belong to the region too and request shell expansion via `expandSidebar()`. The picker splits into the core `WorkspaceCreateFlow` (composed directly inside the region) and the thin `WorkspacePicker` wrapper (still filling ui-conversation's hero slot); the old `sidebar.workspace` picker slot and its declaration-aware deferral are deleted with it. +ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine, New Session, Settings, and one `sidebar.workspaces` hole; the shell↔region contract is two facts, `{ wide, expandSidebar }`. ui-workspace fully owns the browsing region (section header, search, grouped tree and flat list, every workspace dialog, drag) plus its groupBy store; the rail-state search/add-workspace icons belong to the region too and request shell expansion via `expandSidebar()`. The picker splits into the core `WorkspacePickFlow` (composed directly inside the region; named `WorkspaceCreateFlow` until the [one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)) and the thin `WorkspacePicker` wrapper (still filling ui-conversation's hero slot); the old `sidebar.workspace` picker slot and its declaration-aware deferral are deleted with it. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md index 9ad074d59c..2cfa4efe2f 100644 --- a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md +++ b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md @@ -34,7 +34,7 @@ UI 为组内 session 行的 HTML5 拖拽(仅 workspace 分组、非搜索态;f ### 壳/区域切分 -ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settings,以及一个 `sidebar.workspaces` 洞;壳与区域的契约只有两个事实 `{ wide, expandSidebar }`。ui-workspace 全权拥有浏览区域(section header、搜索、分组树与平铺、全部 workspace 对话框、拖拽)及其 groupBy store;rail 态的搜索/新建图标也归区域,经 `expandSidebar()` 请求壳展开。picker 拆为核心件 `WorkspaceCreateFlow`(区域内直接组件组合)与薄包装 `WorkspacePicker`(继续填 ui-conversation 的 hero 坑);原 `sidebar.workspace` picker 坑与声明感知延迟注册随之删除。 +ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settings,以及一个 `sidebar.workspaces` 洞;壳与区域的契约只有两个事实 `{ wide, expandSidebar }`。ui-workspace 全权拥有浏览区域(section header、搜索、分组树与平铺、全部 workspace 对话框、拖拽)及其 groupBy store;rail 态的搜索/添加工作区图标也归区域,经 `expandSidebar()` 请求壳展开。picker 拆为核心件 `WorkspacePickFlow`(区域内直接组件组合;在[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)之前名为 `WorkspaceCreateFlow`)与薄包装 `WorkspacePicker`(继续填 ui-conversation 的 hero 坑);原 `sidebar.workspace` picker 坑与声明感知延迟注册随之删除。 ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml index b8266cdd49..b876fa890c 100644 --- a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.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/2026-07-25-workspace-ui-product-flow.md -2026-07-25-workspace-ui-product-flow.md: b8e1ec1efe19127cad8a12405dddeec38a4ff91e -2026-07-25-workspace-ui-product-flow.zh.md: b80b75a80671e9aa2ab59ff72c44c18a8ec5c16e +2026-07-25-workspace-ui-product-flow.md: 7e3338cfcb04c1588bbc97f6e8aa1cd2dac59141 +2026-07-25-workspace-ui-product-flow.zh.md: 8c092151f737b6bc10aa8424281eeda359f07c1d diff --git a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md index b8e1ec1efe..7e3338cfcb 100644 --- a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md +++ b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md @@ -50,9 +50,9 @@ On initial entry, the application waits until both the Workspace and Session bas When no Workspace exists, the page creates a frontend Workspace object named `workspace` and a frontend Session that targets it. Neither writes to the Host, and the composer always accepts input; the first send materializes the Workspace, attaches the Session, and sends the message in that order. -Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the most recent Workspace, or the Workspace Intent if no real Workspace exists. The Workspace picker's Use an existing folder and Create a new workspace actions immediately create a real Workspace when the user confirms, then retarget the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message. +Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the most recent Workspace, or the Workspace Intent if no real Workspace exists. The Workspace picker's one Add workspace action ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md); it was a pair of Use-an-existing-folder and create-by-name actions when this was decided) immediately creates a real Workspace when the user confirms a directory, then retargets the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message. -Create a new workspace temporarily uses the same input as both the directory name and display name. The UI prevents duplicate confirmation based on current Workspace titles, while the Host continues to reject same-name requests that bypass the UI or race concurrently. Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow. +A new Workspace takes its display name from the directory it was created in, and the Host rejects a title already registered (the UI's own duplicate-name pre-check went with the create-by-name dialog). Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow. ### First send and recovery diff --git a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md index b80b75a806..8c092151f7 100644 --- a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md +++ b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md @@ -50,9 +50,9 @@ Session 自己持有首条输入并驱动一条内部流水线:必要时以预 完全没有 Workspace 时,页面创建默认名为 `workspace` 的前端 Workspace 对象和指向它的前端 Session。两者不写 Host,composer 始终可输入;首次发送才依次 materialize Workspace、attach Session、发送消息。 -顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作:显式 Workspace id 直接成为目标,未指定时使用最近 Workspace,没有真实 Workspace 时使用 Workspace Intent。Workspace picker 的 Use an existing folder 与 Create a new workspace 会在用户确认时立即创建真实 Workspace,再把前端 Session 定位到该 Workspace;即使用户不发送消息,显式创建的空 Workspace 也保留。 +顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作:显式 Workspace id 直接成为目标,未指定时使用最近 Workspace,没有真实 Workspace 时使用 Workspace Intent。Workspace picker 的单一 Add workspace 动作(见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md);本决策做出时是 Use an existing folder 与按名称创建两个动作)会在用户确认目录时立即创建真实 Workspace,再把前端 Session 定位到该 Workspace;即使用户不发送消息,显式创建的空 Workspace 也保留。 -Create a new workspace 暂时用同一个输入作为目录名和显示名。UI 根据当前 Workspace title 禁止重复确认,Host 继续拒绝绕过 UI 或并发产生的同名请求。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。 +新建 Workspace 的显示名取自其所在目录,Host 拒绝已注册的同名 title(UI 侧的重名预检随按名称创建的对话框一并删除)。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。 ### 首次发送与恢复 diff --git a/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.i18n.yaml index 47416d5a30..a2b2e940fd 100644 --- a/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.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/2026-07-27-native-workspace-directory-picker.md -2026-07-27-native-workspace-directory-picker.md: 847b7a7c7844a47e534183008acfdc32e2e08125 -2026-07-27-native-workspace-directory-picker.zh.md: e484a2ba5860d43925aba82be31c803716a33bc5 +2026-07-27-native-workspace-directory-picker.md: 8dd7084eb8ffa417d9366cbc54bcbc59170c64fe +2026-07-27-native-workspace-directory-picker.zh.md: 9efc6571207b1f6a6996b9990c2a55afb70872bd diff --git a/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.md b/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.md index 847b7a7c78..8dd7084eb8 100644 --- a/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.md +++ b/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.md @@ -10,7 +10,7 @@ The desktop GUI asks users to type an absolute path when they add an existing wo ## Decision -Add a single-folder `host.pickDirectory` RPC and expose it through `WorkspacesService`. The workspace menu presents two flat actions: **Open local folder...** and **Create a new workspace**. Selecting a folder reuses the existing `workspace.create({ path })` flow, selects the returned workspace, and starts a blank session. +Add a single-folder `host.pickDirectory` RPC and expose it through `WorkspacesService`. The workspace menu presents the flat **Add workspace...** action (two actions when this was decided — **Open local folder...** beside a create-by-name entry the [one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md) later removed). Selecting a folder reuses the existing `workspace.create({ path })` flow, selects the returned workspace, and starts a blank session. The workspace manager must upsert the returned workspace before the selection callback runs. A newly adopted directory therefore renders its basename immediately. Reopening an already registered path preserves its existing workspace title. @@ -21,7 +21,7 @@ The workspace manager must upsert the returned workspace before the selection ca - A duplicate path selects the existing workspace. - A different path whose derived title conflicts with another workspace shows a focused error with **Choose again** and **Cancel** actions. - Other picker failures show a compact retryable error. -- The existing create-by-name flow remains unchanged. +- The create-by-name flow this decision left untouched is gone; picking a directory is now the whole of adding a workspace ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)). ## Host boundary @@ -41,7 +41,7 @@ Platform adapters invoke native tools without a shell: ## Consequences -The current GUI opens one local folder through a native picker on macOS, Windows, and Linux. Cancelling changes no state, failures remain retryable, and duplicate paths are idempotent while title conflicts require an explicit new choice. The selected workspace and its displayed name refresh before a new blank session starts. Existing workspace creation by name remains available. +The current GUI opens one local folder through a native picker on macOS, Windows, and Linux. Cancelling changes no state, failures remain retryable, and duplicate paths are idempotent while title conflicts require an explicit new choice. The selected workspace and its displayed name refresh before a new blank session starts. This picker is now the only route to a workspace ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)): the operator picks an existing directory, or creates one inside the chooser. The added host, runtime, component, and GUI tests cover the native boundary, request trust checks, cancellation and failure handling, existing-path reuse, title conflicts, and the immediate visible-name update. The privileged RPC remains specific to the local desktop carrier; a remote Web directory browser is outside this decision. diff --git a/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.zh.md b/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.zh.md index e484a2ba58..9efc657120 100644 --- a/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-native-workspace-directory-picker.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -新增一个用于选择单个文件夹的 `host.pickDirectory` RPC,并通过 `WorkspacesService` 暴露该 RPC。工作区菜单提供两个平铺操作:**打开本地文件夹…** 和 **创建新工作区**。选定文件夹后,系统复用现有的 `workspace.create({ path })` 流程,选中返回的工作区,并启动一个空白会话。 +新增一个用于选择单个文件夹的 `host.pickDirectory` RPC,并通过 `WorkspacesService` 暴露该 RPC。工作区菜单提供平铺操作 **添加工作区…**(本决策做出时是两个操作:**打开本地文件夹…** 与一个按名称创建的入口,后者已被[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)删除)。选定文件夹后,系统复用现有的 `workspace.create({ path })` 流程,选中返回的工作区,并启动一个空白会话。 工作区管理器必须在选择回调运行前插入或更新返回的工作区。因此,新纳入的目录会立即显示其 basename。再次打开已注册的路径时,则保留该工作区现有的标题。 @@ -21,7 +21,7 @@ Status: implemented - 路径重复时,选中现有工作区。 - 如果路径不同,但其派生标题与另一个工作区冲突,则显示明确指出该冲突的错误提示,其中包含 **重新选择** 和 **取消** 操作。 - 选择器的其他故障会显示简洁且可重试的错误提示。 -- 现有的按名称创建流程保持不变。 +- 本决策当时未触碰的按名称创建流程现已删除;选择目录就是添加工作区的全部(见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md))。 ## 宿主边界 @@ -41,7 +41,7 @@ Status: implemented ## 后果 -当前 GUI 可以在 macOS、Windows 和 Linux 上通过原生选择器打开一个本地文件夹。取消操作不会改变任何状态,故障仍可重试;重复路径的处理具有幂等性,标题冲突则要求用户明确重新选择。选中的工作区及其显示名称会在启动新的空白会话前完成刷新。现有的按名称创建工作区功能仍可使用。 +当前 GUI 可以在 macOS、Windows 和 Linux 上通过原生选择器打开一个本地文件夹。取消操作不会改变任何状态,故障仍可重试;重复路径的处理具有幂等性,标题冲突则要求用户明确重新选择。选中的工作区及其显示名称会在启动新的空白会话前完成刷新。该选择器现已是获得工作区的唯一路径(见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)):操作者要么选一个已有目录,要么在选择器内新建一个。 新增的宿主、运行时、组件和 GUI 测试覆盖原生边界、请求信任校验、取消与故障处理、已有路径复用、标题冲突和可见名称即时更新。该特权 RPC 仍仅面向本地桌面载体;远程 Web 目录浏览器不属于本次决策范围。 diff --git a/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.i18n.yaml index 7123353c03..df8239ba4b 100644 --- a/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.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-cross-workspace-resume.md -2026-07-28-cross-workspace-resume.md: 1ef6195b6f269a6dc8cf869902b7772ad48f00c2 -2026-07-28-cross-workspace-resume.zh.md: d31dc5f0470e20f86062edb4ad75c37a6160fe23 +2026-07-28-cross-workspace-resume.md: e8a8636911015a5b300b45a30e268ee1be5d47d1 +2026-07-28-cross-workspace-resume.zh.md: 9e5e126f4b204927d7fb134a196dd0d0a98468d4 diff --git a/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.md b/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.md index 1ef6195b6f..e8a8636911 100644 --- a/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.md +++ b/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.md @@ -18,7 +18,7 @@ Finally, resume never changed directory. The host re-execs `dsh --resume=` t The shared CLI configuration supplies one session root under the Harness home, the picker gains a workspace scope, and the handoff carries the target directory. -**Storage.** The shared base owns the default in `apps/cli/config/base.cordis.yml`: its `session-persistence-jsonl` row resolves `sessions` beneath `DSH_HOME`, with the standard `~/.dsh` fallback when the environment has not been initialized. TUI, Web, and headless therefore consume one default without launcher patches or a boot slot. An overlay or personal patch that states an explicit root replaces that row's whole `config` and remains the deployment's authoritative choice. +**Storage.** The shared base owns the default in `apps/cli/config/base.cordis.yml`: its `session-persistence-jsonl` row calls the app-boot-provided `dshHomePath('sessions')`, which uses the canonical `DSH_HOME` resolver and its standard `~/.dsh` fallback. TUI, Web, and headless therefore consume one default without a session-specific launcher patch or slot. An overlay or personal patch that states an explicit root replaces that row's whole `config` and remains the deployment's authoritative choice. **Scope, not exclusion.** A workspace other than the current one is a display scope rather than a disabled reason. `showResume()` summarizes every record and the `ResumePicker` owns a `scope` of `'workspace' | 'all'`, defaulting to the current workspace so the common case is unchanged. Tab toggles; the scope line names the active scope and the count the other holds; each row in the all-workspaces scope reports its own workspace, and that label joins the searchable text only in the scope that shows it. A toggle clears the query and selection so the highlighted row always belongs to the visible list, and the per-row workspace line makes a row one terminal row taller in that scope, which the visible-count budget accounts for. diff --git a/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.zh.md b/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.zh.md index d31dc5f047..9e5e126f4b 100644 --- a/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-cross-workspace-resume.zh.md @@ -18,7 +18,7 @@ Status: implemented 共享 CLI 配置提供 Harness home 下的同一个会话根目录,选择器获得 workspace 范围,交接过程携带目标目录。 -**存储。** 共享 base 在 `apps/cli/config/base.cordis.yml` 中拥有默认值:其 `session-persistence-jsonl` 配置项把 `sessions` 解析到 `DSH_HOME` 下;环境尚未初始化时则使用标准的 `~/.dsh` 回退值。因此 TUI、Web 与 headless 使用同一个默认值,无需启动器补丁或启动槽位。若 overlay 或个人 patch 显式声明根目录,它会整体替换该配置项的 `config`,并继续作为部署的权威选择。 +**存储。** 共享 base 在 `apps/cli/config/base.cordis.yml` 中拥有默认值:其 `session-persistence-jsonl` 配置项调用由 app-boot 提供的 `dshHomePath('sessions')`,该函数使用规范的 `DSH_HOME` 解析器及其标准的 `~/.dsh` 回退值。因此 TUI、Web 与 headless 使用同一个默认值,无需针对会话的启动器补丁或槽位。若 overlay 或个人 patch 显式声明根目录,它会整体替换该配置项的 `config`,并继续作为部署的权威选择。 **是范围,不是排除。** 当前 workspace 之外的 workspace 是一种展示范围,而不是禁用理由。`showResume()` 汇总每一条记录,`ResumePicker` 持有一个 `'workspace' | 'all'` 的 `scope`,默认为当前 workspace,因此常见场景毫无变化。Tab 切换范围;范围行会说明当前生效的范围,以及另一个范围下的数量;在全 workspace 范围中每一行都报告自己的 workspace,而该标签只在展示它的范围里才加入可搜索文本。切换范围会清空查询和选中项,使高亮行始终属于可见列表;而逐行的 workspace 行会让该范围下的每一行在终端里多占一行,可见条数预算已经把这一点计入。 diff --git a/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.i18n.yaml b/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.i18n.yaml index a16f07a63c..5fc6eacf97 100644 --- a/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.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/2026-07-29-persistent-bash-str-replace-editor.md -2026-07-29-persistent-bash-str-replace-editor.md: a97af750bdd80ddf38dc2d126e70c245ed035f35 -2026-07-29-persistent-bash-str-replace-editor.zh.md: 0c2ab26693d90c91d5c41a128ebb77a3c6cc2e7f +2026-07-29-persistent-bash-str-replace-editor.md: 22851078c1cc8fa9d5716afa41c8a2e2b7e7725c +2026-07-29-persistent-bash-str-replace-editor.zh.md: cf4d18f26d11380a637d573e8ea98cb3ccfcdb59 diff --git a/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.md b/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.md index a97af750bd..22851078c1 100644 --- a/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.md +++ b/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.md @@ -18,6 +18,8 @@ Some deployments need a one-call Bash schema whose shell state survives across m Both plugins are included in the Python runtime closure. The persistent Bash closure also includes the PTY service/local backend and the sandbox services required by that backend. Because `node-pty` executes a native `spawn-helper` on macOS, each packaged macOS runtime executable ships with a `-spawn-helper` sibling; Linux uses `forkpty` directly. A pinned `node-pty` patch checks `DSH_NODE_PTY_SPAWN_HELPER` first, so it remains a true override for a current external consumer that supplies a non-sibling helper. When the override is unset, the patch resolves the packaged executable sibling if present and otherwise preserves upstream lookup in ordinary Node runs. The macOS builders fail before publication when the helper is absent or not executable. +The shipped [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) overlay composes both plugins over the ordinary Web surface, disables its other model-facing consumers, and leaves the Web host, browser, Workspace, persistence, sandbox, and permission stack in place. The local PTY backend resolves the effective session sandbox mode when it creates the shell. While that owner has an open shell or a spawn in progress, a different permission mode is rejected before its session event commits; the editor continues through the Web filesystem sandbox. + ## Alternatives considered **One combined compatibility plugin.** Rejected because neither tool requires the other and the combined name would tie reusable capabilities to one benchmark. @@ -30,4 +32,4 @@ Both plugins are included in the Python runtime closure. The persistent Bash clo ## Consequences -Profiles can reproduce an external agent by configuring persona and descriptions while the underlying packages remain general. Persistent Bash requires an owning Agent and real PTY backend. Shell exit, timeout, or cancellation loses state. The editor delegates security and mutation policy to the mounted filesystem stack. Runtime-wheel consumers still need no Node installation; Linux wheels contain one executable, while macOS wheels also contain its private native helper. +Profiles can reproduce an external agent by configuring persona and descriptions while the underlying packages remain general. Persistent Bash requires an owning Agent and real PTY backend. Shell exit, timeout, or cancellation loses state. The editor delegates security and mutation policy to the mounted filesystem stack. The Core Web profile retains Web permissions but must close its persistent shell before changing modes. Runtime-wheel consumers still need no Node installation; Linux wheels contain one executable, while macOS wheels also contain its private native helper. diff --git a/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.zh.md b/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.zh.md index 0c2ab26693..cf4d18f26d 100644 --- a/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.zh.md +++ b/.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.zh.md @@ -18,6 +18,8 @@ 两个插件都进入 Python runtime 闭包。持久 Bash 的闭包还包含 PTY 服务/本地后端,以及该后端要求的沙箱服务。由于 `node-pty` 在 macOS 上会执行原生 `spawn-helper`,每个打包后的 macOS 运行时可执行文件都会携带一个 `-spawn-helper` 伴随文件;Linux 直接使用 `forkpty`。固定版本的 `node-pty` 补丁会先检查 `DSH_NODE_PTY_SPAWN_HELPER`,因此对当前提供非伴随 helper 的外部消费方而言,该变量仍是真正的覆盖项。未设置该覆盖时,补丁会在打包可执行文件的伴随文件存在时解析它,否则在普通 Node 运行中保留上游查找方式。若 helper 缺失或不可执行,macOS 构建器会在发布前失败。 +已交付的 [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) 覆盖层在常规 Web 界面之上组合这两个插件,禁用该界面的其他面向模型的消费方,并保留 Web 宿主、浏览器、Workspace、持久化、沙箱与权限栈。本地 PTY 后端会在创建 shell 时解析会话的有效沙箱模式。只要该所有者仍有打开的 shell 或仍在进行中的 spawn,另一种权限模式就会在对应的会话事件提交前遭到拒绝;编辑器则继续经由 Web 文件系统沙箱运行。 + ## 考虑过的替代方案 **单一组合兼容插件。** 被拒绝,因为两个工具互不依赖,组合命名还会把可复用能力绑定到某个基准。 @@ -30,4 +32,4 @@ ## 后果 -Profile 可以通过配置 persona 和描述复现外部 Agent,而底层包保持通用。持久 Bash 需要拥有它的 Agent 与真实 PTY 后端;shell 退出、超时或取消会丢失状态。编辑器把安全与变更策略委托给挂载的文件系统栈。运行时 wheel 包的消费方仍无需安装 Node;Linux wheel 包包含一个可执行文件,macOS wheel 包还包含其私有原生 helper。 +Profile 可以通过配置 persona 和描述复现外部 Agent,而底层包保持通用。持久 Bash 需要拥有它的 Agent 与真实 PTY 后端;shell 退出、超时或取消会丢失状态。编辑器把安全与变更策略委托给挂载的文件系统栈。Core Web profile 保留 Web 权限,但必须先关闭持久 shell 才能更改权限模式。运行时 wheel 包的消费方仍无需安装 Node;Linux wheel 包包含一个可执行文件,macOS wheel 包还包含其私有原生 helper。 diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml new file mode 100644 index 0000000000..33740e2b31 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.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/2026-07-30-queued-manual-compaction.md +2026-07-30-queued-manual-compaction.md: 05676ef824bc62ddbdbd8895a325570e91e4bafd +2026-07-30-queued-manual-compaction.zh.md: b2e40a42451570887a194c215df07e98aa1bd864 diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md new file mode 100644 index 0000000000..05676ef824 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md @@ -0,0 +1,110 @@ +# Agent Note: Queued manual compaction with one durable lock + +Status: implemented + +English | [中文](2026-07-30-queued-manual-compaction.zh.md) + +## Problem + +Automatic compaction protects the context window, but an interactive user also needs a deterministic way to condense accumulated history before pressure policy fires. Sending `/compact` as prompt text would spend a model turn and let the conversation model reinterpret a direct control action. Implementing it inside one UI would duplicate command discovery, lifecycle logging, cancellation, and backend policy. + +The human command arrives between turns and must summarize asynchronously. A prompt accepted during that wait must keep its ordinary identity, FIFO position, and wakeup behavior, but it must not derive a request from history that compaction is about to replace. A status check is insufficient: a waking send schedules the driver's claim as a microtask, leaving a same-tick interval where status still reads idle even though the prompt already has right of way. + +Compaction also needs one mutual-exclusion fact shared by manual, pressure, overflow, and explicit-range entry points. A process-local flag alone cannot explain a crash-recovered log, while a summarize-first transaction leaves no durable evidence during the expensive interval. Conversely, treating marker pairs as exclusive containers would forbid valid idle injection even though injection is explicitly non-waking and immediate between turns. + +This note extends the [compaction capability seam](2026-06-18-compaction-capability-seam.md), the [session end-seed boundary](../architecture/2026-07-30-session-end-seed-log-boundary.md), and the [removal of synthetic log-only turns](../simplification/2026-07-28-remove-synthetic-log-only-turns.md). The supersession audit found partial overlap only: each remains active and owns its broader decision. + +## Decision + +### `/compact` is a command over a backend-independent seam + +`@deepseek-ai/dsh-command-compact` registers one argument-free human command through `ctx.commands`. It calls the third abstract `CompactService` operation, `compactNow(agent, signal)`, and maps the closed `ManualCompactionError` taxonomy (`busy | changed | summary | commit | persistence`) to direct UI results. `command/run` and `command/done` preserve the command lifecycle without entering model history or consuming a model-loop turn. + +The command plugin tracks each real handler promise independently of the command executor's abort-aware wait. Its composite lifecycle effect unregisters `/compact` before asynchronously draining handlers that already started, so root teardown reaches quiescence only after backend close and flush work settles. + +The seam's `ManualCompactAgentContext` adds only `reserveTurnAdmission()` to the session and routing facts compaction already needs. Retention, balancing, summarization, marker ordering, replacement, and durability remain backend responsibilities. + +### Idle turn admission is synchronously reservable + +`Agent.reserveTurnAdmission(): (() => void) | undefined` claims the boundary before the next ordinary turn. It succeeds only when the driver is idle, no reservation exists, and no accepted waking item already owns the next turn, including a wake whose claim is still a pending microtask. + +The reservation does not create a second queue. Later sends keep their `InboxItemId`, placement, FIFO order, and wakeup facts. `acceptsNextStep` remains false, so waking next-step input becomes an ordinary queued follow-up rather than steering. Release is idempotent and re-arms the existing driver path. `inject()` is not withheld. + +`whenIdle()` treats a reservation as unfinished activity, including when it holds a waking item. Lifecycle teardown still drains the driver's own activity promise rather than awaiting an external operation, so disposal can cancel and unwind without depending on the reservation holder. + +### One parameterized transaction owns every bracket + +`dsh-compact-basic` has one region transaction parameterized by bracket owner (`number | null`), stability rule (whole surface or selected span), and an optional flush. It performs one ordering: + +1. validate the selected positional range and inspect the durable tail; +2. reject a live unmatched compaction marker; +3. append `compact/start` synchronously; +4. prepare and await summarization; +5. revalidate the required stability; +6. append `compact/summary` and the replacement `user/message`; +7. make exactly one `compact/end` attempt; +8. flush when the manual caller requested durability. + +Automatic and explicit-region work use the numeric owner recovered from the open turn and require whole-surface stability. Manual work reserves admission first, selects a useful range before the transaction, and writes nothing when selection returns `null`. Its bracket uses `turn: null`, requires only selected-span stability, and flushes every successfully closed attempt before releasing admission in `finally`. + +`compact/start` is therefore the only compaction lock. There is no `WeakSet`, wrapper mutex, locked/unlocked method split, or redundant activity check around the transaction. + +### Bracket-first deliberately differs from the surveyed implementations + +Codex models manual compaction as a `CompactTask` occupying its active-turn slot while automatic compaction runs inline. Pi uses the existence of a compaction abort controller as its mutex and appends compaction only after success. Claude Code shares one compaction routine between automatic and manual paths but constructs its boundary after summary streaming. + +DSH deliberately records `compact/start` before calling the summarizer. A slow or crashed attempt is observable, automatic and manual paths share the same durable lock, and a later writer cannot mistake an in-flight summary for an unlocked session. This is a conscious divergence from summarize-first behavior, not an accidental event-order difference. + +### Markers are time points, not an event container + +`compact/start` and `compact/end` mean lock acquisition and release. They do not claim exclusive ownership of every event between their seqs. An idle `inject()` may append a `user/message` while a manual summary is pending, so that unrelated event can sit inside the marker interval. + +Manual stability checks only the selected span: it must remain present, contiguous, ordered, equally priced, and balanced. Append-only context outside it does not stale the summary. Positional replacement places the checkpoint at the old span's surface position and leaves injected context after it in derived model history, even though the injection's log seq precedes the later summary and replacement events. + +Failed `changed` or `summary` attempts leave the conversation surface unchanged, but the log is not unchanged: it contains `compact/start` and `compact/end { error }`. User-facing text states that distinction. + +### End-seed distinguishes live and stale orphans + +Tail scanning finds the current turn, unmatched compaction start, and newest `session/end-seed` independently. An unmatched start after the newest end-seed is live and blocks every compaction entry point. An unmatched start before a later end-seed belongs to an earlier session lifecycle and is stale, so it does not wedge the resumed or forked session. + +The compaction invariant uses the same transition logic during seed replay: `session/end-seed` clears an open historical trace. The boundary need not publish live from the constructor for this case; replay is the load-bearing path. + +The client request projection closes an unmatched compaction request as interrupted at the `session/end-seed` time and clears its active index. A later `compact/start` therefore creates an independent request instead of leaving or overwriting a permanently running orphan. + +Once a transaction has appended its start, every later failure makes one closing attempt. A failed close leaves the unmatched start deliberately visible and blocking, and no flush is attempted. A closed manual attempt is flushed even when it reports an expected failure. Cancellation retains exact-reason precedence after required close and flush cleanup. + +### Reference implementation boundaries + +[PR #835](https://github.com/deepseek-harness/deepseek-harness/pull/835) was used as a reference implementation for the command, reservation, tests, and snapshot shape, but was not merged. Its process-local `WeakSet` lock and locked/unlocked method splits were considered and not adopted because the durable bracket is the single reachable lock. + +That reference also carried client-side replacement-anchor machinery to preserve transcript placement. The log-ordered transcript projection already consumes compaction from event order and does not consult mutable surface positions, so those anchors were considered and not adopted. + +## Alternatives considered + +**Check `agent.status` without reserving admission.** Rejected because an accepted waking send can still be waiting on its claim microtask while status reads idle. + +**Queue the command itself.** Rejected because `/compact` is direct control, not model input, and a prompt already accepted first must retain right of way rather than being reordered around a second command queue. + +**Summarize before appending `compact/start`.** Rejected because the expensive in-flight operation would be invisible and would not participate in the lock shared by automatic compaction. + +**Use both a durable marker and a process-local mutex.** Rejected because two authorities can disagree after replay and require wrapper branches for states the bracket already expresses. + +**Hold injection with waking prompts.** Rejected because idle injection is non-waking durable context by contract; delaying it would make plugin ordering depend on a UI command. + +**Require the marker interval to contain only compaction events.** Rejected because markers represent lock time points. Provenance names the selected and shadowed seqs exactly; exclusivity would add no correctness and would reject valid injection. + +**Treat every unmatched marker as permanently busy.** Rejected because a crash-recovered or forked session would remain wedged. `session/end-seed` is the explicit lifecycle evidence that distinguishes stale history from a live process-local attempt. + +## Verification + +Agent-loop tests cover same-tick right of way, preserved IDs and FIFO lifecycle, waking and quiet queued work, idempotent release, `whenIdle()`, cancellation, and teardown. Compact tests cover standalone and numbered invariant ownership, end-seed replay, live versus stale orphans, re-entrant listeners, selected-span drift, commit and close failures, flush ordering, exact cancellation causes, raw output and usage preservation, and automatic/manual mutual exclusion. + +The command package pins registration, Loader composition, argument rejection, exact success/failure text, cancellation, absence from model history, and disposal waiting across separate close and flush boundaries after an abort stops the executor from awaiting the handler. The client runtime projection test pins end-seed interruption followed by an independent completed attempt. The `queued-manual-compact` terminal snapshot drives real keystrokes through the assembled TUI: `/help` discovers the command, a held summary admits a queued prompt and immediate injection, `turn: null` markers and the flush precede the queued prompt turn, command lifecycle stays log-only, and the derived order is checkpoint → injection → queued prompt. + +## Consequences + +Interactive users can compact useful history without spending a conversation-model turn. A prompt accepted before the command wins; one submitted during the command waits with its original queue identity. Manual compaction consumes session seqs but no turn number. + +The log exposes slow, failed, crashed, and successful attempts through the same bracket. A stale pre-boundary orphan no longer wedges a new lifecycle, while a current unmatched start remains a hard busy signal. Marker intervals may contain unrelated events, so consumers use provenance and relative ordering rather than assuming a contiguous compaction-only slice. + +The shared transaction keeps one ordering and one lock across every entry point. Failure reporting is precise about whether only the log changed, the surface may have partially changed, or the in-memory commit could not be persisted. diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md new file mode 100644 index 0000000000..b2e40a4245 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md @@ -0,0 +1,110 @@ +# Agent Note: 使用单一持久锁实现排队手动压缩 + +Status: implemented + +[English](2026-07-30-queued-manual-compaction.md) | 中文 + +## 问题 + +自动压缩(compaction)可以保护上下文窗口,但交互用户还需要一种确定性方法,在压力策略触发前压缩累积的历史。把 `/compact` 作为提示词文本发送会消耗一个模型轮次,还会让会话模型重新解释一项直接控制操作。在某个 UI 内实现该功能,则会重复命令发现、生命周期日志记录、取消与后端策略。 + +面向用户的命令在轮次之间到达,并且必须异步生成摘要。在等待期间获接纳的提示词必须保留普通身份、FIFO 位置与唤醒行为,但不得从即将被压缩替换的历史派生请求。仅检查状态并不足够:唤醒发送会把驱动器的认领安排为 microtask,因此在同一 tick 内存在一段间隔,此时状态仍显示 idle,但提示词已经拥有优先权。 + +手动、压力、溢出和显式范围入口点还需要共享同一项互斥事实。仅使用进程本地标志无法解释一份崩溃恢复后的日志,而先摘要再记录的事务在开销较大的等待期间不会留下持久证据。反过来,把标记对视为排他容器又会禁止有效的空闲注入,尽管注入按定义不会唤醒,并且会在轮次之间立即执行。 + +本 Agent Note 扩展[压缩能力 seam](2026-06-18-compaction-capability-seam.md)、[会话 end-seed 边界](../architecture/2026-07-30-session-end-seed-log-boundary.md)和[移除纯日志事件的合成轮次](../simplification/2026-07-28-remove-synthetic-log-only-turns.md)。取代关系审计只发现部分重叠:三者均保持活动状态,并拥有各自更广泛的决策。 + +## 决策 + +### `/compact` 是基于后端无关 seam 的命令 + +`@deepseek-ai/dsh-command-compact` 通过 `ctx.commands` 注册一个无参数、面向用户的命令。它调用第三个抽象 `CompactService` 操作 `compactNow(agent, signal)`,并把封闭的 `ManualCompactionError` 分类体系(`busy | changed | summary | commit | persistence`)映射为直接 UI 结果。`command/run` 和 `command/done` 保留命令生命周期,同时不进入模型历史,也不消耗模型循环轮次。 + +命令插件会独立跟踪每个实际处理器 promise,不依赖命令执行器的中止感知等待。其复合生命周期 effect 先注销 `/compact`,再异步等待所有已开始的处理器结算,因此根级 teardown 只有在后端的闭合与 flush 工作结算后才会完全停稳。 + +该 seam 的 `ManualCompactAgentContext` 只在压缩已需使用的会话与路由事实之上增加 `reserveTurnAdmission()`。保留、平衡、摘要、标记排序、替换与持久性仍由后端负责。 + +### 可以同步预留空闲轮次接纳 + +`Agent.reserveTurnAdmission(): (() => void) | undefined` 会在下一个普通轮次之前认领边界。仅当驱动器空闲、没有既存预留,而且尚无已获接纳的唤醒项拥有下一轮次时,它才会成功;仍在等待 microtask 认领的唤醒项也包括在内。 + +该预留不会创建第二个队列。之后发送的项保留其 `InboxItemId`、位置、FIFO 顺序与唤醒信息。`acceptsNextStep` 保持 false,因此唤醒的 next-step 输入会成为普通的排队 follow-up,而不是 steering(中途引导)。释放操作可幂等调用,并重新启用既有驱动器路径。`inject()` 不受阻塞。 + +`whenIdle()` 会把预留视为尚未完成的活动,包括预留持有唤醒项的情况。生命周期 teardown 仍会排空驱动器自身的 activity promise,而不会等待外部操作,因此 dispose(资源释放)可以执行取消并完成退出清理,无需依赖预留持有方。 + +### 一个参数化事务拥有每一对标记 + +`dsh-compact-basic` 只有一个区域事务,由标记归属值(`number | null`)、稳定性规则(整个 surface 或所选 span)与可选 flush 参数化。它按同一顺序执行: + +1. 验证所选位置范围,并检查持久日志尾部; +2. 拒绝活动的未匹配压缩标记; +3. 同步追加 `compact/start`; +4. 准备并等待摘要; +5. 重新验证所需稳定性; +6. 追加 `compact/summary` 与替换用的 `user/message`; +7. 恰好尝试一次 `compact/end`; +8. 当手动调用方要求持久性时执行 flush。 + +自动和显式区域工作使用从开放轮次恢复的数字归属值,并要求整个 surface 保持稳定。手动工作会先预留接纳,在进入事务前选择有效范围;选择结果为 `null` 时不写入任何内容。其标记对使用 `turn: null`,只要求所选 span 保持稳定,并在 `finally` 中释放接纳预留前 flush 每次成功闭合的尝试。 + +因此,`compact/start` 是唯一的压缩锁。不存在 `WeakSet`、包装层 mutex、locked/unlocked 方法拆分,也不存在事务外部重复的活动状态检查。 + +### 先记录标记有意不同于调研过的实现 + +Codex 将手动压缩建模为占用其活动轮次槽位的 `CompactTask`,自动压缩则以内联方式运行。Pi 使用压缩 abort controller 是否存在作为 mutex,并仅在成功后追加压缩。Claude Code 的自动和手动路径共享同一个压缩例程,但会在摘要流结束后才构造边界。 + +DSH 有意在调用摘要器前记录 `compact/start`。缓慢或崩溃的尝试因此可观察,自动与手动路径共享同一个持久锁,之后的写入方也不会把正在生成的摘要误判为未锁定会话。这是对先摘要行为的主动偏离,而不是偶然的事件顺序差异。 + +### 标记是时间点,而不是事件容器 + +`compact/start` 和 `compact/end` 表示获取与释放锁。它们不声称排他拥有二者 seq 之间的每个事件。手动摘要等待期间,空闲的 `inject()` 可以追加 `user/message`,因此该不相关事件可能位于标记区间内。 + +手动稳定性只检查所选 span:它必须仍然存在、连续、有序、计价相同且保持平衡。其外部的仅追加上下文不会使摘要陈旧。位置替换会把检查点放在旧 span 的 surface 位置,并使注入上下文在派生模型历史中位于其后,即使注入的日志 seq 早于后续摘要和替换事件。 + +失败的 `changed` 或 `summary` 尝试会保持会话 surface 不变,但日志并非没有变化:其中会包含 `compact/start` 和 `compact/end { error }`。面向用户的文本会明确说明这一区别。 + +### End-seed 区分活动与陈旧的未匹配标记 + +尾部扫描会分别查找当前轮次、未匹配的 compaction start 与最新 `session/end-seed`。位于最新 end-seed 之后的未匹配 start 是活动锁,会阻塞每个压缩入口点。位于较新 end-seed 之前的未匹配 start 属于更早的会话生命周期,已经陈旧,因此不会卡住恢复或 fork 后的会话。 + +压缩不变量在 seed 回放期间使用同一项转换逻辑:`session/end-seed` 会清除开放的历史追踪状态。此场景不要求构造函数实时发布该边界;回放才是承重路径。 + +客户端请求投影会在 `session/end-seed` 时刻将未匹配的压缩请求以中断状态结束,并清除其活动索引。因此,后续 `compact/start` 会创建一个独立请求,而不是让该遗留的未匹配请求永久保持运行状态或将其覆盖。 + +事务追加 start 后,每次后续失败都会进行一次闭合尝试。闭合失败会有意留下可见且具有阻塞作用的未匹配 start,并且不尝试 flush。已闭合的手动尝试即使报告预期失败也会 flush。完成必需的闭合与 flush 清理后,取消仍保留原始原因优先级。 + +### 参考实现边界 + +[PR #835](https://github.com/deepseek-harness/deepseek-harness/pull/835) 用作命令、预留、测试与快照结构的参考实现,但未被合并。它的进程本地 `WeakSet` 锁与 locked/unlocked 方法拆分经过评估后未被采用,因为持久标记对是唯一可达的锁。 + +该参考实现还包含客户端侧替换锚点机制,用于保留 transcript(文本记录)位置。按日志顺序排列的 transcript 投影已经从事件顺序消费压缩,并且不会查询可变 surface 位置,因此这些锚点经过评估后未被采用。 + +## 曾考虑的替代方案 + +**仅检查 `agent.status`,不预留接纳。** 不予采用,因为已获接纳的唤醒发送可能仍在等待其认领 microtask,而状态仍显示 idle。 + +**把命令本身加入队列。** 不予采用,因为 `/compact` 是直接控制而非模型输入;先获接纳的提示词必须保留优先权,不能围绕第二个命令队列重新排序。 + +**在追加 `compact/start` 前生成摘要。** 不予采用,因为开销较大的进行中操作将不可见,也不会参与自动压缩共享的锁。 + +**同时使用持久标记与进程本地 mutex。** 不予采用,因为两项权威在回放后可能产生分歧,还会要求用包装层分支处理标记对已经表达的状态。 + +**与唤醒提示词一起阻塞注入。** 不予采用,因为按契约,空闲注入是不会唤醒的持久上下文;延迟注入会使插件排序依赖某个 UI 命令。 + +**要求标记区间只包含压缩事件。** 不予采用,因为标记表示锁的时间点。溯源信息会精确指明所选 seq 与被遮蔽 seq;排他性不会增加正确性,只会拒绝有效注入。 + +**把每个未匹配标记都永久视为 busy。** 不予采用,因为崩溃恢复或 fork 后的会话会永久卡住。`session/end-seed` 是区分陈旧历史与当前进程活动尝试的显式生命周期证据。 + +## 验证 + +Agent loop 测试覆盖同一 tick 内的优先权、保留 ID 与 FIFO 生命周期、会唤醒和静默的排队工作、幂等释放、`whenIdle()`、取消与 teardown。压缩测试覆盖独立与数字形式的不变量 owner、end-seed 回放、活动与陈旧未匹配标记、listener 重入、所选 span 漂移、commit 与闭合失败、flush 顺序、原始取消原因、raw output 与 usage 保留,以及自动/手动互斥。 + +命令包固定注册行为、Loader 组合、参数拒绝、精确的成功/失败文本、取消、不进入模型历史的保证,以及处置操作在中止使执行器停止等待处理器后,仍会跨越相互独立的闭合与 flush 边界等待该处理器结算。客户端运行时投影测试固定 end-seed 中断,以及随后一次独立尝试的完成。`queued-manual-compact` 终端快照通过已组装 TUI 驱动真实按键:`/help` 可发现该命令;被暂停的摘要会接纳一个排队提示词和即时注入;`turn: null` 标记与 flush 先于排队提示词轮次;命令生命周期保持纯日志;派生顺序固定为检查点 → 注入 → 排队提示词。 + +## 后果 + +交互用户无需消耗会话模型轮次即可压缩有效历史。在命令前获接纳的提示词胜出;命令期间提交的提示词会以原有队列身份等待。手动压缩会消耗会话 seq,但不消耗轮次编号。 + +日志通过同一对标记暴露缓慢、失败、崩溃与成功的尝试。边界前的陈旧未匹配标记不会再卡住新的生命周期,而当前未匹配 start 仍是严格的 busy 信号。标记区间可以包含不相关事件,因此消费方使用溯源信息与相对顺序,而不假定存在连续且仅含压缩事件的切片。 + +共享事务让每个入口点保持同一种顺序并使用同一把锁。失败报告会精确区分只有日志发生变化、surface 可能部分改变,以及内存 commit 无法持久化这三种情况。 diff --git a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.i18n.yaml new file mode 100644 index 0000000000..d4f7f72fe2 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.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/2026-07-31-hover-card-click-copy.md +2026-07-31-hover-card-click-copy.md: c87734fe328fa2adb396d6685495faa82bc1fff2 +2026-07-31-hover-card-click-copy.zh.md: a57b5238b095de293605d4e309dcc2da3516e904 diff --git a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md b/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md new file mode 100644 index 0000000000..c87734fe32 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md @@ -0,0 +1,29 @@ +# Agent Note: Hover cards copy their primary value on activation + +Status: implemented + +English | [中文](2026-07-31-hover-card-click-copy.zh.md) + +## Problem + +Workspace and Session rows clip the two values their hover cards expose in full: the Workspace directory path and Session title. The [reachable card](../bug-fix/2026-07-30-hover-popup-pointer-grace.md) permits text selection, but selecting and copying a single known value is a needlessly precise gesture, and the card gives no confirmation that the clipboard accepted it. + +## Decision + +`HoverCard` accepts an optional `copyText` plus `copyLabel` and `copiedLabel`. With `copyText`, the whole card has button semantics for pointer and keyboard activation; its accessible name combines the localized action prefix with the exact value, it writes that value through the shared clipboard helper, and it replaces its content with the success label for up to one second only after the host accepts the write. The feedback retains the pre-copy card height and clears with the card. Without `copyText`, the atom retains its read/select-only behavior. + +The Workspace browser chooses the payload rather than making the primitive infer it from rendered text: a Workspace card passes the full directory path, and a non-blank Session card passes the full display title. A provisional blank New Session card remains read-only because its localized label is a placeholder, not session content. The browser's locale seat supplies `Copy`/`复制` and the success state `Copied`/`已复制`. + +Press and activation remain separate contracts. A pointer press inside the card keeps it mounted so text selection can begin; a completed non-collapsed selection intersecting the card suppresses pointer-click activation, while a plain click or button key activates copy. Anchor-region presses still dismiss immediately, and clipboard rejection leaves the original content visible without claiming success. + +## Alternatives considered + +**Copy the card's rendered `textContent`.** That would concatenate the primary value with creation time or running status, making the clipboard payload depend on presentation and localization. + +**Implement clipboard state in both Workspace card bodies.** The two consumers would duplicate host fallback, keyboard behavior, timer ownership, and success rendering even though the card owns the activation surface. + +**Change the common Chinese `copied` label from `复制成功` to `已复制`.** That would alter every existing copy control to satisfy one card interaction. The Workspace dictionary owns the card-specific wording instead. + +## Consequences + +Both non-placeholder hover-card variants gain the same click and keyboard affordance while retaining consumer-owned payload semantics and localized feedback. The generic atom adds one optional behavior path and a one-second timer; it clears copied state on close, ignores completion after close or unmount, and never reports a rejected write as success. Focused component coverage pins pointer selection precedence, activation, failure, feedback geometry and expiry, and cleanup, while the real-browser Workspace scenario verifies the English label, stable feedback height, and browser clipboard. diff --git a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.zh.md b/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.zh.md new file mode 100644 index 0000000000..a57b5238b0 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.zh.md @@ -0,0 +1,29 @@ +# Agent Note(agent 决策记录):悬浮卡片激活时复制主要值 + +Status: implemented + +[English](2026-07-31-hover-card-click-copy.md) | 中文 + +## 问题 + +Workspace 与 Session 行会截断对应悬浮卡片完整展示的两个值:Workspace 目录路径和 Session 标题。这张[可抵达的卡片](../bug-fix/2026-07-30-hover-popup-pointer-grace.md)支持文本选择,但复制单个已知值仍需精确选择,操作没有必要地繁琐;卡片也不会确认剪贴板是否接受了写入。 + +## 决策 + +`HoverCard` 接收可选的 `copyText`,以及 `copyLabel` 和 `copiedLabel`。传入 `copyText` 后,整个卡片都会为指针与键盘激活提供按钮语义;其无障碍名称由本地化操作前缀和原值组成,卡片通过共享剪贴板辅助函数写入该值,并且只有宿主接受写入后,才会用成功标签替换内容最长一秒。反馈保持复制前的卡片高度,并会随卡片关闭一同清除。未传入 `copyText` 时,该原子组件维持只读且可选择文本的行为。 + +Workspace 浏览器选择复制载荷,不让基础组件从渲染文本中推断:Workspace 卡片传入完整目录路径,非空白 Session 卡片传入完整显示标题。临时的空白「新会话」卡片保持只读,因为其本地化标签是占位文案,并非会话内容。浏览器的 locale 席位提供 `Copy`/`复制`,成功状态则使用 `Copied`/`已复制`。 + +按下与激活仍是两份独立契约。卡片内发生指针按下时,卡片保持挂载,以便用户开始选择文本;文本选择完成后,若非折叠选区与卡片相交,就会阻止指针点击激活,而普通点击或按钮激活键会激活复制。锚点区域内发生指针按下时,卡片仍会立即消失;剪贴板拒绝写入时,卡片继续显示原内容,不会声称复制成功。 + +## 备选方案 + +**复制卡片渲染后的 `textContent`。** 这会把主要值与创建时间或运行状态拼接起来,使剪贴板载荷依赖表现形式和本地化结果。 + +**在两个 Workspace 卡片主体中分别实现剪贴板状态。** 两个消费方会重复实现宿主回退、键盘行为、计时器所有权和成功状态渲染,尽管激活表层由卡片持有。 + +**将通用中文 `copied` 标签从 `复制成功` 改为 `已复制`。** 这样会为了满足一种卡片交互而改变所有现有复制控件。卡片专用文案应由 Workspace 字典持有。 + +## 后果 + +两种非占位悬浮卡片都获得相同的点击与键盘操作能力,同时保留由消费方决定载荷的语义和本地化反馈。通用原子组件增加一条可选行为路径和一个一秒计时器;卡片关闭时会清除已复制状态,关闭或卸载后到达的完成结果会被忽略,写入被拒绝时绝不会报告成功。聚焦组件测试会固定指针选择文本的优先级、激活、失败、反馈尺寸与到期清除以及清理行为,真实浏览器中的 Workspace 场景则验证英文标签、反馈期间高度稳定和浏览器剪贴板。 diff --git a/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.i18n.yaml new file mode 100644 index 0000000000..0eddfa1740 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.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/2026-07-31-third-party-memory-mcp-examples.md +2026-07-31-third-party-memory-mcp-examples.md: e82d65a3a5a60cafcc47df5a6873cf5768cd8b8f +2026-07-31-third-party-memory-mcp-examples.zh.md: ee0e9f2e1378f9787e09e32cc05dd13a3648254c diff --git a/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.md b/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.md new file mode 100644 index 0000000000..e82d65a3a5 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.md @@ -0,0 +1,78 @@ +# Agent Note: Third-party memory MCP examples + +Status: implemented + +English | [中文](2026-07-31-third-party-memory-mcp-examples.zh.md) + +## Problem + +A direct vendor integration made one provider's API, configuration, health behavior, and tool semantics part of DSH. That was too much product surface for a capability already expressible through MCP, and it would require repeating the same adaptation for every memory system. Users instead need a small, inspectable way to opt into one external memory server while preserving the generic MCP boundary. + +The acceptance bar is stronger than "the socket connects": each reference must support a real DSH write in session A, recall from the provider in a fresh DSH session B, and use of the recalled value. At the same time, provider downloads, accounts, models, embeddings, storage initialization, and separate HTTP processes must remain upstream responsibilities. + +## Decision + +Ship three default-off Cordis overlay examples under `examples/mcp-memory`: Memorix, MCP Reference Memory, and Engram. Every file inserts exactly one `@deepseek-ai/dsh-mcp-client` row. None is referenced by the shipped composition, and the CLI declares the generic bridge only so an explicitly selected overlay can resolve it. + +These third-party configurations are provided as interoperability examples only. Their inclusion does not imply endorsement, recommendation, partnership, or ongoing support by DeepSeek. There is no memory preset registry, vendor-specific DSH plugin, universal memory service, installation UI, migration layer, health checker, or reconnect controller. Another memory MCP server uses the same documented stdio or Streamable HTTP row. + +## Responsibility boundary + +| Concern | DSH | Upstream provider or user | +|---|---|---| +| Parse selected overlay | Yes | Select one file | +| Start stdio command and stop it on plugin disposal | Yes | Install the pinned executable | +| Connect to Streamable HTTP and discover tools | Yes | Run and supervise the HTTP service | +| Register tools as `mcp____` | Yes | Define tool schemas and behavior | +| Account, auth, model, embedding, storage initialization | No | Yes | +| Vendor data migration, retry, crash recovery | No | Yes | + +The generic stdio transport scrubs ambient credential-shaped and `DSH_*` variables while inheriting other ambient variables. Baseline examples add only required overrides; optional provider secrets must be added to `config.env` or configured in the provider's own files. + +## Pins, storage, and identity + +| Provider | Tested contract | +|---|---| +| Memorix | npm `1.3.0`, tag commit `500792cad3144142293bfbb20acb4841c9f7fcfa` | +| MCP Reference Memory | npm `2026.7.4`, package commit `6dd0a683e198783e30feabf7abaf42f925bd18b1` | +| Engram | tag `v1.20.0`, commit `ba9e46ced152c37a7cb9e576153c41995873e2fc` | + +Storage remains provider-owned. Memorix uses `~/.memorix/data` and Engram uses `~/.engram` by default. The Reference Memory example sets a stable `$HOME/.dsh-mcp-reference-memory.jsonl` path instead of writing into the installed npm package directory. Each provider's own environment variable can override these locations before DSH starts. + +Project identity remains provider-owned: Memorix and Engram use the DSH working directory's Git project, with Engram optionally accepting `ENGRAM_PROJECT`. + +## Model guidance + +The examples do not patch `@deepseek-ai/dsh-system-prompt`: a config patch replaces a row's complete config and could erase an existing persona. The README instead offers one optional additive instruction: + +> When the user asks you to remember something, call a memory write tool. When historical information may be relevant, search memory and use relevant results. + +Provider tool descriptions remain authoritative. + +## Validation contract + +Remote CI never contacts third-party services or consumes secrets. The keyless suite parses all three overlay files, checks their generic bridge and secret boundary, replaces the upstream endpoint with the package-owned MCP fixture server, boots the real Cordis Loader, and proves tool discovery. + +Before merge, manual evidence for every pinned provider must separately show: + +1. DSH session A calls a write tool and receives success for a unique value. +2. Fresh DSH session B, under the same provider storage scope, calls search or recall and returns that value without session A's transcript. +3. Session B uses the recalled value in a subsequent answer. + +"Fresh session" means a new DSH session in the same Host. No Host restart is required. The generic MCP client discovers asynchronously and has no automatic reconnect after a child or HTTP transport closes; validation waits for tools before the first turn and uses HMR or a Host restart only after a crash. + +## Alternatives considered + +**One DSH plugin per provider.** Rejected because it repeats auth, configuration, lifecycle, and tool wrappers that MCP already standardizes and expands ownership for every added provider. + +**A memory-provider preset registry.** Rejected because a registry would make third-party versions and recommendations look like a supported DSH product surface. Copyable overlays keep ownership and drift visible. + +**Run `npx` or `go run` inside the MCP row.** Rejected after probes showed first-run npm downloads can exceed the MCP initialization timeout and an interrupted `npx` cache can become unusable. DSH starts a server process; it is not the provider package manager. Pinned installation commands are explicit prerequisites. + +**Inject the common instruction from the generic MCP client.** Rejected because the bridge serves non-memory MCP servers too, and generic prompt mutation would reintroduce provider semantics into shared runtime code. + +## Consequences + +Selecting a file gives the model the provider's complete discovered MCP tool surface, with schema/token cost determined by that provider. Removing `--config` removes the memory server. Users accept each upstream license, data policy, cloud cost, and operational model directly. + +The earlier vendor-specific change is superseded by this generic path. Future provider drift is handled by updating and revalidating a small example pin rather than adding runtime branches to DSH. diff --git a/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.zh.md b/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.zh.md new file mode 100644 index 0000000000..ee0e9f2e13 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-third-party-memory-mcp-examples.zh.md @@ -0,0 +1,78 @@ +# Agent Note: 第三方记忆 MCP 示例 + +Status: implemented + +[English](2026-07-31-third-party-memory-mcp-examples.md) | 中文 + +## 问题 + +直接集成某个提供方会使该提供方的 API、配置、健康状态行为和工具语义成为 DSH 的一部分。对于已经可以通过 MCP 表达的功能,这会让产品接口过于庞大,而且每接入一个记忆系统都需要重复同样的适配工作。用户需要的是一种精简、可检查的方式,在保留通用 MCP 边界的同时,选择启用一个外部记忆服务器。 + +验收标准不止于「套接字可以连接」:每份参考配置都必须支持 DSH 在会话 A 中实际写入,在新的 DSH 会话 B 中从提供方召回,并使用召回的值。与此同时,提供方下载、账户、模型、embedding、存储初始化和独立 HTTP 进程仍由上游负责。 + +## 决策 + +在 `examples/mcp-memory` 下交付三份默认关闭的 Cordis overlay 示例:Memorix、MCP Reference Memory 和 Engram。每个文件只插入一个 `@deepseek-ai/dsh-mcp-client` 配置项。交付组合不会引用这些文件;CLI(命令行界面)仅声明通用桥接器,使用户显式选择 overlay 时可以解析它。 + +这些第三方配置仅作为互操作参考;收录不代表 DeepSeek 的认可、推荐、合作关系或持续支持承诺。系统没有记忆预设注册表、提供方专属 DSH 插件、通用记忆服务、安装 UI、迁移层、健康检查器或重连控制器。其他记忆 MCP 服务器可以使用同一份文档中的 stdio 或 Streamable HTTP 配置项。 + +## 职责边界 + +| 事项 | DSH | 上游提供方或用户 | +|---|---|---| +| 解析选中的 overlay | 是 | 选择一个文件 | +| 启动 stdio 命令,并在插件 dispose(资源释放)时将其停止 | 是 | 安装固定版本的可执行文件 | +| 连接 Streamable HTTP 并发现工具 | 是 | 运行并监管 HTTP 服务 | +| 以 `mcp____` 注册工具 | 是 | 定义工具 schema 和行为 | +| 账户、认证、模型、embedding、存储初始化 | 否 | 是 | +| 提供方数据迁移、重试、崩溃恢复 | 否 | 是 | + +通用 stdio 传输会清除环境中名称类似凭据的变量和 `DSH_*` 变量,同时继承其他环境变量。基线示例仅添加必需的覆盖项;可选的提供方密钥必须添加到 `config.env`,或配置在提供方自己的文件中。 + +## 版本固定、存储与身份 + +| 提供方 | 已测试契约 | +|---|---| +| Memorix | npm `1.3.0`,tag commit `500792cad3144142293bfbb20acb4841c9f7fcfa` | +| MCP Reference Memory | npm `2026.7.4`,package commit `6dd0a683e198783e30feabf7abaf42f925bd18b1` | +| Engram | tag `v1.20.0`,commit `ba9e46ced152c37a7cb9e576153c41995873e2fc` | + +存储仍由提供方负责。Memorix 默认使用 `~/.memorix/data`,Engram 默认使用 `~/.engram`。Reference Memory 示例设置稳定的 `$HOME/.dsh-mcp-reference-memory.jsonl` 路径,而不是写入已安装的 npm 包(package)目录。每个提供方自己的环境变量都可以在 DSH 启动前覆盖这些位置。 + +项目身份仍由提供方负责:Memorix 和 Engram 使用 DSH 工作目录中的 Git 项目,其中 Engram 还可以选择接受 `ENGRAM_PROJECT`。 + +## 模型指导 + +示例不会修改 `@deepseek-ai/dsh-system-prompt`:配置 patch 会替换某个配置项的完整配置,可能抹除已有 persona。README 改为提供一条可选的附加指令: + +> 用户要求记住时调用写入工具;涉及历史信息时,主动检索并使用相关记忆。 + +提供方的工具描述仍然是权威定义。 + +## 验证契约 + +远程 CI 不会访问第三方服务或消耗密钥。无密钥套件解析全部三份 overlay 文件,检查其通用桥接器和密钥边界,将上游端点替换为包自带的 MCP fixture(测试前置数据)服务器,通过真实 Cordis Loader 启动,并验证工具发现。 + +合并前,每个固定版本的提供方都必须分别提供以下人工证据: + +1. DSH 会话 A 调用写入工具,为一个唯一值写入记忆,并收到成功结果。 +2. 新的 DSH 会话 B 在相同的提供方存储范围下调用搜索或召回,不借助会话 A 的 transcript(文本记录)便可返回该值。 +3. 会话 B 在后续回答中使用该召回值。 + +「新会话」是指同一个 Host 中新建的 DSH 会话,不需要重启 Host。通用 MCP 客户端以异步方式发现工具,子进程或 HTTP 传输关闭后不会自动重连;验证会在第一轮之前等待工具出现,并且只在崩溃后使用 HMR 或重启 Host。 + +## 考虑过的替代方案 + +**每个提供方使用一个 DSH 插件。** 不予采纳,因为这会重复 MCP 已经标准化的认证、配置、生命周期和工具包装层,并随着每增加一个提供方而扩大维护范围。 + +**记忆提供方预设注册表。** 不予采纳,因为注册表会让第三方版本和推荐看起来像受支持的 DSH 产品接口。可复制的 overlay 让所有权和版本偏移保持可见。 + +**在 MCP 配置项内运行 `npx` 或 `go run`。** 不予采纳,因为探测表明首次 npm 下载可能超过 MCP 初始化超时,而中断的 `npx` 缓存可能变得不可用。DSH 负责启动服务器进程,不是提供方的包管理器。固定版本的安装命令属于显式前置条件。 + +**由通用 MCP 客户端注入共用指令。** 不予采纳,因为该桥接器也服务于非记忆类 MCP 服务器,而且通用提示词变更会把提供方语义重新带入共享运行时代码。 + +## 后果 + +选择一个文件后,模型可以使用提供方发现到的完整 MCP 工具接口;工具 schema 和 token 成本由提供方决定。移除 `--config` 就会移除记忆服务器。用户直接接受各上游的许可证、数据政策、云服务费用和运维模式。 + +通用方案取代了早期针对特定提供方的改动。未来出现提供方版本偏移时,只需更新并重新验证一份小型示例的固定版本,不必向 DSH 添加运行时分支。 diff --git a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.i18n.yaml new file mode 100644 index 0000000000..483e4cc132 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.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/2026-07-31-web-cards-toolrow.md +2026-07-31-web-cards-toolrow.md: caa18563a9e66f882873e8d7e84cc3ac20702033 +2026-07-31-web-cards-toolrow.zh.md: 4e9c429497e1265b4b39ed2479f382a2f36e7741 diff --git a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.md b/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.md new file mode 100644 index 0000000000..caa18563a9 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.md @@ -0,0 +1,32 @@ +# Agent Note: Card tool rows collapse through one ToolRow + +Status: implemented + +English | [中文](2026-07-31-web-cards-toolrow.zh.md) + +## Problem + +The Web client grew five card render intents over successive PRs — terminal, diff, read, search, web — each landing as a keyed toolview registrant under `packages/client/ui-conversation/src/client/toolviews/`. They diverged in two ways the earlier PRs each acknowledged but deferred: + +- **Chrome duplication.** `read-row`, `search-row`, `web-row`, and `file-mutation-row` each hand-drew the summary row (leading state slot, visually-hidden status, title, separator dot, path-link/summary) as their own `
` with a private `.module.css`, instead of composing the shared `ToolRow`. `read-row` carried a `jscpd:ignore` marker naming the duplication and pointing at "a separate change tracked for all rows at once" — this change. +- **Resident vs. collapsed.** Those four rows kept their card (`ReadBlock`/`SearchBlock`/`WebBlock`/`DiffBlock`) resident below the summary — always expanded — while the terminal card (via `GenericToolCard`/`BashRow`) and every text row started collapsed behind ToolRow's whole-row expand. A conversation with several read/search/web/edit calls became a wall of always-open cards, defeating the summary-surface purpose of the message flow. + +## Decision + +`ToolRow` owns every card kind, and every keyed card row composes it. ToolRow already took `terminal` and `diff` card material; it now also takes `read`, `search`, and `web`, rendering whichever is present in its collapsed-by-default expanded body through the matching primitive (capped at the chat `CHAT_*` bounds). A call carries at most one card kind, so the props are mutually exclusive and the body picks the first present. + +The four keyed rows — `ReadRow`, `SearchRow`, `WebRow`, `FileMutationRow` — drop their hand-drawn chrome and private CSS and become thin `ToolRow` compositions, exactly like `AskQuestionRow`: derive the card model, pass it as the matching ToolRow prop, forward `filePath`/`onOpenFile` for the file tools and `output`/`errorSummary` for the cardless failure paths. Each row is now `ToolRowProps & PropsLocale<'conversation'>` and registers with `locale: NS`, because ToolRow needs the conversation `t` for its terminal/code body copy. `GenericToolCard` (the render-site fallback) does the same for read/search/web, so a card-declaring tool without its own keyed row collapses identically. + +The `DetailsPanel` Output section is unchanged: the panel is the single-call reading surface, so it renders each card resident at the primitive's full height, and a capped search keeps its recovery footer there. + +## Consequences + +- One expand interaction across all tool rows: collapsed one-line summary, whole row toggles the card. The card is not in the DOM until expanded (`DisclosureRow` renders `children` only when open), so tests assert absent-then-present around a `[data-expandable]` click. +- Deleted: `read-row.module.css`, `search-row.module.css`, `web-row.module.css`, `file-mutation-row.module.css`, `GenericToolCard.module.css`. The rows carry no CSS of their own; ToolRow's module owns the chrome and the card-body indentation. +- The cardless failure paths (an errored mutation, an errored/nested/legacy search) no longer draw their own `.failure`/recovery `
`; they ride ToolRow's `output` (Output section) and `errorSummary` (collapsed summary first line), which already flatten the result text with the `error.name: error.code` fallback. +- `bash-sample` keeps its own local expand chrome deliberately (the third-party-posture exemplar that never imports the chat domain); it was already collapsed, so its behavior is unchanged. + +## Alternatives considered + +- **Keep the rows resident, only unify chrome.** Rejected: the user's requirement is default-collapsed, and resident cards are what made the flow unscannable. +- **A shared `CardRow` wrapper between the rows and ToolRow.** Rejected: ToolRow already is that wrapper once it takes every card kind; a second layer would be the premature extraction the package rules warn against. diff --git a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.zh.md b/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.zh.md new file mode 100644 index 0000000000..4e9c429497 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.zh.md @@ -0,0 +1,32 @@ +# Agent Note:卡片工具行通过同一个 ToolRow 折叠 + +Status: implemented + +[English](2026-07-31-web-cards-toolrow.md) | 中文 + +## 问题 + +Web 客户端在连续几个 PR 里长出五种卡片渲染意图——terminal、diff、read、search、web,每一种都作为一个键控 toolview 注册项落在 `packages/client/ui-conversation/src/client/toolviews/` 下。它们在两处出现分歧,之前每个 PR 都承认却推迟处理: + +- **Chrome 重复。** `read-row`、`search-row`、`web-row`、`file-mutation-row` 各自把摘要行(行首状态槽、视觉隐藏状态、标题、分隔点、路径链接/摘要)手绘成自己的 `
`,配一份私有 `.module.css`,而不是组合共享的 `ToolRow`。`read-row` 带着一个 `jscpd:ignore` 标记,点名这处重复并指向"一处针对所有行一次性处理的独立改动"——就是本次改动。 +- **常驻 vs 折叠。** 那四个行把卡片(`ReadBlock`/`SearchBlock`/`WebBlock`/`DiffBlock`)常驻在摘要下方——始终展开——而终端卡片(经 `GenericToolCard`/`BashRow`)与每个文本行都从折叠状态起步,藏在 ToolRow 的整行展开之后。一个有多个 read/search/web/edit 调用的对话就成了一堵始终打开的卡片墙,违背了消息流作为摘要面的目的。 + +## 决策 + +`ToolRow` 拥有每一种卡片,而每个键控卡片行都组合它。ToolRow 原本就接收 `terminal` 与 `diff` 卡片材料;现在还接收 `read`、`search`、`web`,在其默认折叠的展开 body 里用对应原语渲染当前存在的那一种(按 chat 的 `CHAT_*` 上限截断)。一次调用最多携带一种卡片,因此这些 prop 互斥,body 取第一个存在的。 + +四个键控行——`ReadRow`、`SearchRow`、`WebRow`、`FileMutationRow`——丢掉手绘 chrome 与私有 CSS,成为薄薄的 `ToolRow` 组合,与 `AskQuestionRow` 完全一样:推导卡片模型,作为对应的 ToolRow prop 传入,为文件工具转发 `filePath`/`onOpenFile`,为无卡片的失败路径转发 `output`/`errorSummary`。每个行现在是 `ToolRowProps & PropsLocale<'conversation'>` 并以 `locale: NS` 注册,因为 ToolRow 需要对话的 `t` 来渲染其终端/代码 body 文案。`GenericToolCard`(渲染点兜底)对 read/search/web 做同样的事,所以一个没有自己键控行的卡片声明工具也以同样方式折叠。 + +`DetailsPanel` 的 Output 区不变:面板是单次调用的阅读面,因此它以原语的完整高度常驻渲染每张卡片,被截断的搜索也把恢复脚注留在那里。 + +## 后果 + +- 所有工具行共享一套展开交互:折叠时是单行摘要,整行切换卡片。卡片在展开前不在 DOM 里(`DisclosureRow` 只在打开时渲染 `children`),因此测试围绕一次 `[data-expandable]` 点击断言"先无后有"。 +- 已删除:`read-row.module.css`、`search-row.module.css`、`web-row.module.css`、`file-mutation-row.module.css`、`GenericToolCard.module.css`。这些行不再带自己的 CSS;ToolRow 的 module 拥有 chrome 与卡片 body 的缩进。 +- 无卡片的失败路径(出错的改动,出错/嵌套/旧日志的搜索)不再画自己的 `.failure`/恢复 `
`;它们改走 ToolRow 的 `output`(Output 区)与 `errorSummary`(折叠摘要首行),后者已经用 `error.name: error.code` 兜底压平结果文本。 +- `bash-sample` 有意保留自己本地的展开 chrome(第三方姿态的范例,从不引入 chat 域);它本来就是折叠的,因此行为不变。 + +## 考虑过的替代方案 + +- **保持行常驻,只统一 chrome。** 否决:用户的要求是默认折叠,而常驻卡片正是让流不可扫读的原因。 +- **在行与 ToolRow 之间加一层共享的 `CardRow` 包装。** 否决:ToolRow 一旦接收每一种卡片,它本身就是那层包装;再加一层就是 package 规则警告的过早抽取。 diff --git a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml new file mode 100644 index 0000000000..d65dae2802 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.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/process/2026-07-30-generated-third-party-notices.md +2026-07-30-generated-third-party-notices.md: e480954d29d5dc09ef8ecd4069059a1f0c8b1043 +2026-07-30-generated-third-party-notices.zh.md: 78ba7250e797c57048078d1b4f62b7a9a5d9d561 diff --git a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md new file mode 100644 index 0000000000..e480954d29 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md @@ -0,0 +1,53 @@ +# Agent Note: Generated third-party notices + +Status: implemented + +English | [中文](2026-07-30-generated-third-party-notices.zh.md) + +## Problem + +Open-sourcing this repository requires disclosing the third-party software it depends on, with each project's license. The disclosure has to be complete, has to stay true as dependencies change, and has to say something a reader can act on — which of these packages end up on a user's machine, and which only build and test the repository. + +A hand-written inventory answers none of those durably. Roughly a hundred rows of names and license strings derived from manifests drift silently the moment a package is added, removed, or relicensed, and nothing would notice. + +## Decision + +[`THIRD_PARTY_NOTICES.md`](../../../../THIRD_PARTY_NOTICES.md) is generated by [`scripts/gen-third-party-notices.ts`](../../../../scripts/gen-third-party-notices.ts) from the workspace manifests, `vendor/README.md`, the `pyproject.toml` files, and `pnpm-workspace.yaml`. The root README pair links the file from its License section. + +**Freshness is maintained, not merely enforced.** A pre-commit job regenerates the file and stages it whenever a generator input is staged — any manifest, a workspace declaration, the root lock file, `vendor/README.md`, a `pyproject.toml`, the generator itself, or the script holding the build-time pin — so an unrelated dependency edit never has to come back and rerun a generator. The committed bytes are then asserted inside [`scripts/gen-third-party-notices.spec.ts`](../../../../scripts/gen-third-party-notices.spec.ts), which the test lane already runs — the check adds no gate process, no scheduler slot, and no separate CI step. `pnpm run verify-third-party-notices` remains available for a standalone check. + +One trigger gap is accepted rather than worked around: lefthook inspects only files present on disk, so **deleting** a manifest runs no job, and removing a package reaches the assertion in the test lane instead. Reconstructing the staged file list to include deletions was tried and does not work — lefthook filters the list against the working tree either way. The assertion is the backstop for exactly this case. + +The file discloses **direct** dependencies only. The complete npm closure with pinned versions already lives in `pnpm-lock.yaml` (`pnpm licenses list` renders it) and the Python closure in `python/sdk/uv.lock`; re-materializing either as prose would be a second, worse copy. + +**Tiering is by declaring area, not by manifest section.** A package is a runtime dependency when any manifest outside `DEV_ONLY_AREAS` — the root manifest, `packages/support/`, `packages/client/test-runtime/`, `website/`, `examples/`, `native/` — names it under `dependencies` or `optionalDependencies`. Section names alone are wrong in both directions: a test-support package declares `vitest` under `dependencies` without shipping it, and the `bin/dsh` launcher execs through `tsx`, which no manifest declares as a runtime dependency at all (the generator marks it runtime explicitly). + +The runtime tier deliberately covers **every mountable plugin**, not just what the CLI, Web UI, and Python runtime load by default. `scripts/install.sh` installs the repository itself, so a user's `cordis.yml` can mount any plugin package; `@modelcontextprotocol/sdk` and the OpenTelemetry packages reach real users even though no default assembly imports them. Under-disclosure is the costly direction for a legal notice. + +The manifest set is derived from the `packages:` members each `pnpm-workspace.yaml` declares — the root one and the nested Landlock workspace's — so a new member area is read the day it is declared rather than the day someone remembers to extend a list. License and repository metadata come from the installed pnpm stores, both the root one and the Landlock workspace's, so the generator requires an installed tree and fails loud when a package resolves to neither, rather than emitting an empty cell. `OVERRIDES` carries the packages whose published manifest cannot answer — Rust-built npm bins that omit `license`, and the `modelcontextprotocol/servers` packages whose repository is mid MIT→Apache-2.0 relicensing, so their effective terms are per-contribution. A runtime dependency whose license is not on the permissive list is a hard error: shipping copyleft is a distribution decision, not something a regenerated table may absorb silently. Vendored packages are cross-checked against `vendor/README.md` and rejected if any is not MIT, and `pnpm-workspace.yaml`'s `patchedDependencies` are listed under the runtime table because pnpm applies those patches at install time — shipped artifacts carry modified copies of `@earendil-works/pi-tui` and `node-pty`, and the patch files are the record of what changed. + +## Testing + +The same spec that asserts freshness pins the tiering rule against fixture manifests — including the two cases that motivate it, a `dependencies` entry of a test-support package and a plugin package no app mounts. It also pins the parsers against the shapes that would otherwise drop a package without a word: a `vendor/README.md` table that stops covering a vendored directory, a requirement array holding extras (`"httpx[http2]"`), a requirement with no version at all, an author-named `[dependency-groups]` table, and a workspace member area absent from any hardcoded list. Each of those is a silent-omission path, which is the failure mode a disclosure file cannot afford. + +## Alternatives considered + +**Keep the hand-written file and review it at release time.** Reviewing a hundred derived rows by eye is exactly the work a generator does correctly, and the file's own claim — that it lists every direct dependency — would be unverified between releases. + +**Verify through a dedicated `doc-sync` gate.** That is how every other generated artifact here is checked, and it was the first shape of this change. It costs a gate process and a scheduler slot in a matrix that is already long, and — worse — its only failure mode is telling a contributor, minutes after they pushed an unrelated dependency bump, to go rerun a generator. Regenerating at commit time removes the interruption, and the assertion inside a spec the test lane already runs keeps the guarantee at no additional CI cost. + +**Enumerate the full transitive closure.** The closure is thousands of packages, already recorded in the lock files with exact versions, and would bury the direct dependencies that a reader actually evaluates. The file points at the lock files and the `pnpm licenses list` renderer instead. + +**Tier by manifest section (`dependencies` vs `devDependencies`).** Mechanically simple and wrong on real data in both directions, as the tiering paragraph above records. + +**Tier by reachability from the shipped assemblies only** (`apps/*` plus `python/sdk-runtime`). This produces a tighter runtime tier, but classifies the MCP client and the OpenTelemetry exporter as development-only even though a user running the installed repository can mount them. It understates the disclosure, which is the wrong direction to err for a legal notice. + +**Emit the notices as a bilingual pair.** Every other root document is paired, but the file is a table of upstream package names, SPDX identifiers, and URLs; the translatable surface is a handful of section blurbs. `scripts/translation-pairing.ts` scopes discovery to `README*`, `.agents/notes/**`, `docs/**`, and `python/**`, so a root non-README file is outside the bilingual corpus by construction, and the README pair carries the bilingual entry points into it. + +## Consequences + +A dependency edit now carries a regenerated notices file into the same commit. Contributors pay one generator run — about a second — on commits that touch a manifest, and nothing on any other commit. Committing with hooks disabled defers the cost to a test-lane failure that names the command. + +The generator needs an installed tree, which makes it heavier than a pure-source generator, and a new package with unusable published metadata needs an `OVERRIDES` entry rather than silently rendering a blank license. Both failures are loud and name the remedy. + +The tiering rule is a policy encoded in one constant. Adding a workspace area that never ships — a second test-infrastructure tier, another site — requires extending `DEV_ONLY_AREAS`, or its dependencies will be disclosed as runtime. diff --git a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md new file mode 100644 index 0000000000..78ba7250e7 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md @@ -0,0 +1,53 @@ +# Agent Note: Generated third-party notices + +Status: implemented + +[English](2026-07-30-generated-third-party-notices.md) | 中文 + +## Problem + +本仓库开源需要披露所依赖的第三方软件及各自的许可证。这份披露必须完整,必须随依赖变化保持为真,还必须给出读者用得上的信息:哪些包最终会进到用户机器上,哪些只用于构建和测试。 + +手写清单无法长期满足其中任何一条。约一百行从各清单文件推导出来的包名与许可证标识,只要有依赖新增、移除或换用许可证就会悄悄失真,而没有任何检查会察觉。 + +## Decision + +[`THIRD_PARTY_NOTICES.md`](../../../../THIRD_PARTY_NOTICES.md) 由 [`scripts/gen-third-party-notices.ts`](../../../../scripts/gen-third-party-notices.ts) 依据各工作区清单、`vendor/README.md`、`pyproject.toml` 与 `pnpm-workspace.yaml` 生成。根 README 双语两侧都从「许可证」一节链到该文件。 + +**新鲜度靠维护而非拦截。** 只要暂存了生成器的任一输入——任何清单文件、工作区声明、根锁文件、`vendor/README.md`、某个 `pyproject.toml`、生成器自身,或持有构建期 pin 的脚本——pre-commit 任务就会重新生成并一并入库,改依赖的人不必事后再折返跑一次生成器。已提交的字节随后由 [`scripts/gen-third-party-notices.spec.ts`](../../../../scripts/gen-third-party-notices.spec.ts) 断言,而测试 lane 本就会跑这个文件——这项校验不增加门禁进程、不占调度位、也不新增 CI 步骤。需要单独校验时,`pnpm run verify-third-party-notices` 仍然可用。 + +有一处触发缺口是接受而非绕过的:lefthook 只检视磁盘上存在的文件,因此**删除**清单文件不会触发任何任务,移除一个包会落到测试 lane 的断言上。重构暂存文件列表以纳入删除的做法试过,不成立——无论怎么给列表,lefthook 都会拿工作树过滤一遍。这个场景正由断言兜底。 + +文件只披露**直接**依赖。完整的 npm 闭包连同锁定版本已记录在 `pnpm-lock.yaml`(`pnpm licenses list` 可渲染),Python 闭包记录在 `python/sdk/uv.lock`;再用散文誊一遍只会得到一份更差的副本。 + +**分层依据是声明方所在区域,而非清单字段名。** 只要 `DEV_ONLY_AREAS` 之外的任一清单——即根清单、`packages/support/`、`packages/client/test-runtime/`、`website/`、`examples/`、`native/` 之外——在 `dependencies` 或 `optionalDependencies` 里点名某个包,它就是运行时依赖。单看字段名在两个方向上都会出错:测试支撑包把 `vitest` 写在 `dependencies` 里却并不交付它;而 `bin/dsh` 启动器 exec 经过的 `tsx`,根本没有任何清单把它声明为运行时依赖,只能由生成器显式标记。 + +运行时层刻意覆盖**所有可挂载的插件**,而不止 CLI、Web UI 与 Python 运行时默认加载的那些。`scripts/install.sh` 安装的就是仓库本身,用户的 `cordis.yml` 可以挂载任何插件包;`@modelcontextprotocol/sdk` 与 OpenTelemetry 系列即使没有任何默认装配引入,也会触达真实用户。对法务披露而言,披露不足才是代价更高的那个方向。 + +清单集合由两个 `pnpm-workspace.yaml`——根工作区与嵌套的 Landlock 工作区——各自声明的 `packages:` 成员派生,因此新增成员区域在声明当天就会被读取,而不必等谁想起来去补一份列表。许可证与仓库地址取自已安装的 pnpm store,根 store 与 Landlock 工作区的 store 都会查;某个包两处都解析不到时直接失败,而不是留下空单元格。`OVERRIDES` 收录已发布清单答不上来的包:用 Rust 构建、发布时省略 `license` 字段的 npm 可执行包,以及 `modelcontextprotocol/servers` 系列——该仓库正处在 MIT 向 Apache-2.0 的重新许可过程中,实际条款按贡献逐条而定。运行时依赖的许可证若不在宽松清单内即为硬失败:交付 copyleft 是一项分发决策,不该被一次重新生成悄悄吸收。被源码收编的包会与 `vendor/README.md` 交叉核对,出现非 MIT 即报错;`pnpm-workspace.yaml` 的 `patchedDependencies` 列在运行时表格之后,因为 pnpm 在安装期就会打上这些补丁——交付产物携带的是改动过的 `@earendil-works/pi-tui` 与 `node-pty`,补丁文件本身就是改动的完整记录。 + +## Testing + +断言新鲜度的同一个 spec 也用夹具清单钉住分层规则,覆盖促成该规则的两个场景:测试支撑包的 `dependencies` 条目,以及没有任何应用挂载的插件包。它还把各解析器钉在那些原本会让某个包无声消失的形态上:不再覆盖全部收编目录的 `vendor/README.md` 表、含 extras 的依赖数组(`"httpx[http2]"`)、完全不带版本的依赖、作者自取名字的 `[dependency-groups]` 表,以及任何硬编码列表都不含的工作区成员区域。这些都是静默漏报路径——正是披露文件最担不起的失败方式。 + +## Alternatives considered + +**保留手写文件,发版时人工过一遍。** 用肉眼审阅上百行推导数据,恰恰是生成器能做对的活;而且在两次发版之间,文件自称「列出全部直接依赖」这句话无人验证。 + +**用专门的 `doc-sync` 门禁校验。** 仓库里其他生成产物都是这么把关的,本次改动最初也是这个形态。但它要在本已冗长的矩阵里再占一个门禁进程和一个调度位;更糟的是,它唯一的失败方式,就是在别人推完一个无关的依赖升级几分钟后,通知对方回去重跑一次生成器。改为提交时重新生成消除了这次打断,而把断言放进测试 lane 本就会跑的 spec 里,则以零额外 CI 成本保住了这项保证。 + +**列出完整传递闭包。** 闭包有数千个包,锁文件里已带精确版本,铺开只会淹没读者真正要评估的直接依赖。文件转而指向锁文件与 `pnpm licenses list`。 + +**按清单字段分层(`dependencies` 与 `devDependencies`)。** 机械上最省事,但在真实数据上两个方向都会出错,理由见上文分层段落。 + +**只按已交付装配的可达性分层**(`apps/*` 加 `python/sdk-runtime`)。这样得到的运行时层更紧凑,但会把 MCP 客户端与 OpenTelemetry 导出器判为仅开发用途——而运行已安装仓库的用户完全可以挂载它们。这会低估披露,对法务通告来说错在了更危险的一侧。 + +**把披露文件做成双语对。** 其他根文档都是成对的,但这份文件是上游包名、SPDX 标识与网址构成的表格,可翻译的只有寥寥几段章节导语。`scripts/translation-pairing.ts` 的发现范围限定在 `README*`、`.agents/notes/**`、`docs/**` 与 `python/**`,根目录下的非 README 文件在构造上就不属于双语语料;双语入口由 README 对承担。 + +## Consequences + +此后改动依赖时,重新生成的披露文件会随同一个提交入库。触及清单文件的提交多付一次生成器运行——约一秒;其余提交不受影响。若禁用钩子提交,代价推迟为一次测试 lane 失败,其报错会指明补救命令。 + +生成器需要已安装的工作树,因此比纯源码生成器更重;发布元数据不可用的新包需要补一条 `OVERRIDES`,而不是默默渲染出空白许可证。这两类失败都会明确报错并指出补救方式。 + +分层规则是编码在一个常量里的政策。若新增了不参与交付的工作区区域——第二层测试基础设施、另一个站点——就要同步扩展 `DEV_ONLY_AREAS`,否则其依赖会被当作运行时依赖披露出去。 diff --git a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml index 9031dc8eb0..75e8ca8d37 100644 --- a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.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/simplification/2026-07-28-remove-synthetic-log-only-turns.md -2026-07-28-remove-synthetic-log-only-turns.md: af4da00f4fe1d7aebff845cd55053bb5b807c979 -2026-07-28-remove-synthetic-log-only-turns.zh.md: 9d72781d6b7cf396a830790d108f4ff25adc816a +2026-07-28-remove-synthetic-log-only-turns.md: fc76667924ec839301aad993efd996112c9a6b09 +2026-07-28-remove-synthetic-log-only-turns.zh.md: 7520c33e2219c5fe7ab7d8da6312247e42cc69b0 diff --git a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md index af4da00f4f..fc76667924 100644 --- a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md +++ b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md @@ -18,11 +18,11 @@ The generic seam also duplicated domain policy. Its marker map said which plugin Core session invariants continue to enforce core-owned execution relations: turn and step numbering, enclosure of steering, assistant, tool, todo, and request-header events, and same-step tool call/result pairing. Core permits merge-extensible events between turns because only their declaring plugin knows whether they are execution-scoped or standalone. Plugin invariant companions remain responsible for their own event relations. -The title service appends `session/title` directly after its existing service, revision, cancellation, and live-session checks. The bundled model helper appends its literal `session/title-llm-request` record before dispatch. Persistence observes both through the eager `session/event` path and drains them at ordinary checkpoints and lifecycle teardown; neither append forces a flush merely because it is between turns. A fallback, auxiliary request record, or accepted provider title may therefore appear after `turn/end` and before the next `turn/start`. +The title service appends `session/title` directly after its existing service, revision, cancellation, and live-session checks. The bundled model helper appends its literal `session/title-llm-request` record before dispatch. Persistence observes both through the eager `session/event` path and drains them at ordinary checkpoints and lifecycle teardown; neither append forces a flush merely because it is between turns. A fallback, auxiliary request record, or accepted provider title may therefore appear after `turn/end` and before the next `turn/start`. Manual compaction uses the same between-turn capability for a `compact/* { turn: null }` bracket, but explicitly flushes the closed attempt because `/compact` promises durability before releasing queued prompt admission. A session fork may end at any stable event position outside an open turn, not only at `turn/end`. This preserves standalone title and context records in a default fork while still rejecting a prefix cut through active execution. -The historical [universal turn-enclosure decision](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md) remains useful only as the reason the synthetic mechanism was introduced. The [context-injection decision](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md) established the current meaning: one turn represents one model-loop execution. +The historical [universal turn-enclosure decision](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md) remains useful only as the reason the synthetic mechanism was introduced. The [context-injection decision](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md) established the current meaning: one turn represents one model-loop execution. The [queued manual compaction decision](../feature/2026-07-30-queued-manual-compaction.md) applies that rule to a durable multi-event bracket and owns its marker and admission semantics. ## Alternatives considered @@ -36,8 +36,8 @@ The historical [universal turn-enclosure decision](../../archived/architecture/2 ## Verification -Core invariant tests accept an unknown plugin event between turns while continuing to reject built-in execution events there. Hook, compaction, plan-mode, Code Mode dispatch, and approval invariant companions replay existing logs and reject the same execution-scoped events before commit when no turn is open. Session-title service tests pin one direct fallback event under concurrent refresh, detached-session rejection, and newest-revision acceptance. JSONL and SQLite round trips preserve a title appended after `turn/end` through the persistence lifecycle drain, and fork tests retain a standalone log-only tail while rejecting boundaries inside an open turn. A keyless assembled ACP snapshot delays the model-backed title until after `turn/end` and pins one standalone provider title with no synthetic turn. Generated API and type-equivalence catalogs contain no removed symbol. +Core invariant tests accept an unknown plugin event between turns while continuing to reject built-in execution events there. Hook, plan-mode, Code Mode dispatch, and approval invariant companions reject their execution-scoped events when no turn is open; the compaction companion separately accepts a balanced `turn: null` manual bracket between turns and requires numeric owners to match an open turn. Session-title service tests pin one direct fallback event under concurrent refresh, detached-session rejection, and newest-revision acceptance. JSONL and SQLite round trips preserve a title appended after `turn/end` through the persistence lifecycle drain, and fork tests retain a standalone log-only tail while rejecting boundaries inside an open turn. A keyless assembled ACP snapshot delays the model-backed title until after `turn/end` and pins one standalone provider title with no synthetic turn. Generated API and type-equivalence catalogs contain no removed symbol. ## Consequences -Turn counts and outcomes again describe model-loop executions only. Standalone events consume session seqs, start eager persistence like every other append, and require owners to request an explicit durability barrier only when their operation promises one. Generic plugin mistakes no longer fail under a core default enclosure rule, so each plugin that needs an execution relation must state and test that relation itself. The title capability keeps revision ordering and lifecycle persistence with less core state, no duplicate type seam, and no turn-number collision. +Turn counts and outcomes again describe model-loop executions only. Standalone events and manual compaction brackets consume session seqs without consuming a turn number, start eager persistence like every other append, and require owners to request an explicit durability barrier only when their operation promises one. Generic plugin mistakes no longer fail under a core default enclosure rule, so each plugin that needs an execution relation must state and test that relation itself. The title capability keeps revision ordering and lifecycle persistence with less core state, and manual compaction gains durable control with no synthetic-turn or turn-number collision. diff --git a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md index 9d72781d6b..7520c33e22 100644 --- a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md @@ -18,11 +18,11 @@ Status: implemented 核心会话不变量继续强制核心所属的执行关系:轮次与步骤编号、steering、助手、工具、待办和请求头事件的封闭,以及同一步骤内的工具调用/结果配对。核心允许可合并扩展事件位于轮次之间,因为只有声明它们的插件知道这些事件受执行作用域约束,还是可以独立存在。插件的不变量配套组件仍负责其自身的事件关系。 -标题服务会在完成既有的服务状态、修订、取消和实时会话检查后,直接追加 `session/title`。随附模型辅助函数会在发起调用前追加其字面量 `session/title-llm-request` 记录。持久化通过尽快处理的 `session/event` 路径观察两者,并在常规检查点与生命周期 teardown 时排空;二者都不会仅因为位于轮次之间就强制 flush。因此,回退标题、辅助请求记录或已接受的提供方标题可以出现在 `turn/end` 之后、下一个 `turn/start` 之前。 +标题服务会在完成既有的服务状态、修订、取消和实时会话检查后,直接追加 `session/title`。随附模型辅助函数会在发起调用前追加其字面量 `session/title-llm-request` 记录。持久化通过尽快处理的 `session/event` 路径观察两者,并在常规检查点与生命周期 teardown 时排空;二者都不会仅因为位于轮次之间就强制 flush。因此,回退标题、辅助请求记录或已接受的提供方标题可以出现在 `turn/end` 之后、下一个 `turn/start` 之前。手动压缩(compaction)利用同一项轮次间能力记录 `compact/* { turn: null }` 标记对,但会显式 flush 已闭合的尝试,因为 `/compact` 承诺在释放排队提示词接纳预留前完成持久化。 会话 fork 可以结束于开放轮次之外的任意稳定事件位置,而不限于 `turn/end`。这样,默认 fork 会保留独立标题和上下文记录,同时仍拒绝在活跃执行过程中截断前缀。 -历史上的[通用轮次封闭决策](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md)如今只适合用于解释为何曾引入合成机制。[上下文注入决策](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md)确立了当前语义:一个轮次表示一次模型循环执行。 +历史上的[通用轮次封闭决策](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md)如今只适合用于解释为何曾引入合成机制。[上下文注入决策](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md)确立了当前语义:一个轮次表示一次模型循环执行。[排队手动压缩决策](../feature/2026-07-30-queued-manual-compaction.md)将该规则应用于持久多事件标记对,并拥有其标记与接纳语义。 ## 曾考虑的替代方案 @@ -36,8 +36,8 @@ Status: implemented ## 验证 -核心不变量测试会接受轮次之间的未知插件事件,同时继续拒绝位于该处的内置执行事件。钩子、压缩(compaction)、plan-mode、Code Mode 分发和审批的不变量配套组件会回放既有日志,并在没有开放轮次时,于提交前拒绝相同的执行作用域事件。会话标题服务测试会在并发刷新、会话脱离拒绝和最新修订接受场景下,固定一个直接追加的回退事件。JSONL 和 SQLite 往返测试会通过持久化生命周期排空保留追加在 `turn/end` 之后的标题;fork 测试会保留独立纯日志尾部,同时拒绝位于开放轮次内的边界。一个无密钥、经完整组装的 ACP(Agent Client Protocol)快照会将模型生成的标题延迟到 `turn/end` 之后,并固定一个不含合成轮次的独立提供方标题。生成的 API 和类型等价性目录不含任何已移除符号。 +核心不变量测试会接受轮次之间的未知插件事件,同时继续拒绝位于该处的内置执行事件。钩子、plan-mode、Code Mode 分发和审批的不变量配套组件会在没有开放轮次时拒绝其执行作用域事件;压缩配套组件则另外接受轮次之间平衡的 `turn: null` 手动标记对,并要求数字 owner 匹配一个开放轮次。会话标题服务测试会在并发刷新、会话脱离拒绝和最新修订接受场景下,固定一个直接追加的回退事件。JSONL 和 SQLite 往返测试会通过持久化生命周期排空保留追加在 `turn/end` 之后的标题;fork 测试会保留独立纯日志尾部,同时拒绝位于开放轮次内的边界。一个无密钥、经完整组装的 ACP(Agent Client Protocol)快照会将模型生成的标题延迟到 `turn/end` 之后,并固定一个不含合成轮次的独立提供方标题。生成的 API 和类型等价性目录不含任何已移除符号。 ## 后果 -轮次计数和结果重新只描述模型循环执行。独立事件会占用会话 seq,像其他追加一样启动尽快持久化,并且仅当操作承诺持久性时,才要求事件所有方请求显式持久性屏障。通用插件错误不再因核心默认的封闭规则而失败,因此每个需要执行关系的插件都必须自行声明并测试该关系。标题功能保留修订排序和生命周期持久化,同时减少了核心状态,不再重复类型 seam,并消除了轮次编号冲突。 +轮次计数和结果重新只描述模型循环执行。独立事件和手动压缩标记对会占用会话 seq,但不占用轮次编号;它们像其他追加一样启动尽快持久化,并且仅当操作承诺持久性时,才要求事件所有方请求显式持久性屏障。通用插件错误不再因核心默认的封闭规则而失败,因此每个需要执行关系的插件都必须自行声明并测试该关系。标题功能保留修订排序和生命周期持久化,同时减少了核心状态;手动压缩则获得持久控制,不产生合成轮次或轮次编号冲突。 diff --git a/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.i18n.yaml new file mode 100644 index 0000000000..e4491b6c7b --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.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/simplification/2026-07-31-one-route-to-add-a-workspace.md +2026-07-31-one-route-to-add-a-workspace.md: 0d3f4096b11ec2d0bd1339268bfb8567380d3e1a +2026-07-31-one-route-to-add-a-workspace.zh.md: b9b25b15680cb54ae980e217e6218a91cd1e366a diff --git a/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.md b/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.md new file mode 100644 index 0000000000..0d3f4096b1 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.md @@ -0,0 +1,57 @@ +# Agent Note: One route to add a Workspace + +Status: implemented + +English | [中文](2026-07-31-one-route-to-add-a-workspace.zh.md) + +## Problem + +Both Workspace surfaces — the sidebar region header's `+` and the conversation hero's chip — offered two ways to get a Workspace: **Open local folder…**, which raised the composed directory flow, and **Create a new workspace**, which took a name and created `/`. The two overlapped: the browse occupant carries its own **New folder** affordance, so picking a directory already covered creating one. Two entries meant two vocabularies for one outcome, a name dialog with its own duplicate-name rule, and a create target the operator could neither see nor choose. + +Removing the weaker entry leaves the sidebar header with exactly one action, which raised the presentation question this Note also settles: what a popover with a single row should look like. + +## Decision + +Adding a Workspace has one route: pick a host directory through the composed directory flow, new or existing. `menu.addWorkspace` ("添加工作区…" / "Add workspace…") is the entry; the create-by-name dialog and its `create.*` / `menu.createWorkspace` / `workspace.new` strings are gone. The label names the outcome, not the mechanism, because it is now the only door to that outcome — a user looking for "新建" must find it. + +**A menu exists to disambiguate between targets.** When the only entry left is the add action — the add-only sidebar surface, or the hero with an empty list — the anchor gesture *is* that action: the flow opens directly and no popover renders. A one-row popover costs a click and offers nothing to choose between. The rule is one predicate (`addIsTheOnlyEntry`) covering both surfaces rather than a per-surface special case. + +Two boundaries fall out of that rule and are part of it: + +- **An empty list is only final once the baseline lands.** While `phase` is `pending` the hero keeps its menu and loading status instead of jumping into a flow that the arriving workspaces would have made unnecessary. The add-only surface lists nothing and never waits. +- **An unoccupied directory-flow hole leaves nothing to add with.** The sidebar header then renders no button at all rather than a dead one; the hero's menu keeps working as a picker over whatever is listed, and shows nothing when nothing is listed either — an empty popover would claim a choice that does not exist. This is the seam's documented no-flow default reaching its conclusion: with the occupant gone, so is the only creation affordance. The hero's anchor chip belongs to ui-conversation, so this package can suppress the popover but cannot hide the chip. + +The direct-open path carries the busy rule the menu entry states: while a pick is still being adopted (`flowBusy`), the anchor gesture is held exactly as the entry is disabled, so a late outcome cannot race a second flow. + +`WorkspaceCreateFlow` is now `WorkspacePickFlow` and its `createOnly` prop is `addOnly`; the injected `createWorkspace` narrows from `{ name } | { path }` to `{ path }`. + +## Wire and CLI residue + +The host's `workspace.create` still accepts `{ name }`, and `dsh web --workspace-root` still feeds its target directory, but no product surface reaches either any more. The same is true of the client seam that carried the name to the wire: `WorkspaceCreateInput`, `WorkspacesService.create`'s `{ name }` arm, `intentName`'s name branch, and the manager's "name under workspaceRoot" contract. `apps/cli/README.md` and its Chinese counterpart still document `--workspace-root` as creating named Workspaces. The whole set is marked for deletion at the call site in `packages/host/apiproxy/src/api-proxy.ts` and left to a follow-up change: it is backend, client-seam, and CLI surface with its own reviewer and its own test fallout (the api-proxy workspace suite, the runtime workspace suite, the config catalog), and the release-blocking part of this decision is the UI. + +## Testing + +`connectFreshWorkspace` — the helper every web e2e scenario boots through — stages `/workspace` and adopts it through the dialog's path editor, so the produced session cwd stays identical to what create-by-name produced and scenario goldens stay valid. Staging rather than creating in-dialog keeps the helper idempotent across the repeated connects a scenario may make (a second create of the same folder fails, and the create dialog holds the flow open on that failure). Creating a folder from inside the chooser — the other half of the same route — is covered by `workspace-management.e2e.ts`, which owns the focused coverage: two workspaces added on folders the dialog creates, a deleted title reused on a different directory, and the browser-dialog aria golden. + +`smoke-real.e2e.ts` is the one scenario booting the unpatched shipped tree, where the `-auto` row resolves per host; it now pins `-browse` through a `--config` overlay so the developer's display environment cannot decide whether the picker is drivable at all. + +## Alternatives considered + +**Keep `Open local folder…` as the label.** Rejected: after the merge the entry both opens and creates, and naming it after the mechanism hides the creation half from exactly the users whose entry we removed. The counter-argument — "本地" usefully disambiguates the browser's machine from the harness's — is answered one step later by the dialog's own title and breadcrumbs. + +**Keep the two-entry menu and make `Create a new workspace` open the same flow.** Rejected: two labels for one action is the confusion we were asked to remove, not a smaller version of it. + +**Keep a one-row popover for consistency with the hero's menu.** Rejected: a popover that offers no choice is a wasted click and reads as unfinished. Consistency here is the *rule* (menu ⇔ a choice exists), not the widget. + +**Keep the menu shell for entries we might add later (clone a repo, remote directory).** Rejected under "require a current owner and need": no such entry exists, and restoring a menu when one arrives is a smaller change than shipping an empty frame now. + +**Delete the wire's create-by-name branch in the same change.** Rejected for this PR: it is backend/CLI surface with a different reviewer and a wider test fallout, and the urgent decision is the UI. See the residue section — it is marked, not forgotten. + +**Register the workspace through the host in the e2e scaffold instead of driving the dialog.** Rejected: it would have decoupled all 15 scenarios from the picker, so nothing in the lane would prove the surviving route reaches a live composer. Every scenario now walks the real dialog to adopt its directory; only the create-a-folder half is concentrated in one scenario, because repeating it everywhere makes the shared helper non-idempotent for no extra signal. + +## Consequences + +- Creating a Workspace outside the operator's chosen directory is no longer possible from the UI; the server-controlled `--workspace-root` target was the one way to constrain where new workspace folders land, and nothing replaces it. A deployment that needs that constraint has to re-introduce it deliberately. +- The one remaining route browses the host filesystem, so the picker's reach is now the whole host rather than one configured parent. That is already the browse occupant's contract; this change makes it the only contract. +- A composition that mounts `ui-workspace` without any directory-picker package can no longer add a Workspace at all, and now says so by omitting the button instead of offering a create-by-name fallback. +- The hero chip still announces `aria-haspopup="menu"` while the direct-open path raises a dialog instead. Making that truthful means routing the flow's presentation choice up through the `conversation.hero.workspace` owner contract — the flow owns the decision, the chip owns the announcement, and they sit in different packages — so it is a named follow-up rather than a silent inconsistency. The sidebar button this change added makes no popup claim at all. diff --git a/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.zh.md b/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.zh.md new file mode 100644 index 0000000000..b9b25b1568 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.zh.md @@ -0,0 +1,57 @@ +# Agent Note: One route to add a Workspace + +Status: implemented + +[English](2026-07-31-one-route-to-add-a-workspace.md) | 中文 + +## Problem + +两处 Workspace 表层——侧边栏区头的 `+` 与会话主视觉区的 chip——都提供了两条获得 Workspace 的路径:**打开本地文件夹…** 拉起组合的目录流程,**新建工作区** 接收一个名称并创建 `/`。两者重叠:浏览占用者自带 **新建文件夹** 能力,因此"选一个目录"本就覆盖了"建一个目录"。两个入口意味着同一结果有两套词汇、一个自带重名规则的名称对话框,以及一个操作者既看不到也选不了的创建位置。 + +删掉较弱的那个入口后,侧边栏区头只剩一个动作,于是引出了本 Note 一并裁定的展示问题:只有一行的浮层应该长什么样。 + +## Decision + +添加 Workspace 只有一条路径:通过组合的目录流程选一个宿主机目录,新建的或已存在的都可以。入口是 `menu.addWorkspace`("添加工作区…" / "Add workspace…");按名称创建的对话框及其 `create.*`/`menu.createWorkspace`/`workspace.new` 文案全部删除。标签命名的是结果而非机制,因为它现在是通往该结果的唯一一扇门——找"新建"的用户必须能找到它。 + +**菜单的存在是为了在多个目标之间消歧。** 当只剩添加这一个入口时——仅添加的侧边栏表层,或列表为空的主视觉区——锚点手势*就是*该动作:直接拉起流程,不渲染浮层。只有一行的浮层多花一次点击,却没有任何可选项。这条规则是一个谓词(`addIsTheOnlyEntry`)覆盖两处表层,而不是逐表层特判。 + +由该规则派生出两条边界,它们同属这个决定: + +- **列表为空只有在基线落地后才算最终结果。** `phase` 仍为 `pending` 时,主视觉区保留菜单与加载状态,而不是跳进一个即将到达的 workspace 会使其变得多余的流程。仅添加表层不列任何东西,因此从不等待。 +- **目录流程的洞没有占用者时,就没有任何可添加的手段。** 此时侧边栏区头干脆不渲染按钮,而不是留下一个点了没反应的按钮;主视觉区的菜单则继续作为选择器工作,列出已有内容——而当同样没有内容可列时,它什么也不弹:空浮层会宣称一个并不存在的选择。这是 seam 文档化的无流程默认行为走到它的结论:占用者不在,唯一的创建能力也就不在。主视觉区的锚点 chip 归 ui-conversation 所有,因此本包能压掉浮层,却无法隐藏该 chip。 + +直接拉起的这条路径同样遵守菜单项声明的 busy 规则:某次选取仍在接纳中(`flowBusy`)时,锚点手势会被按住,正如该菜单项会被禁用,从而使迟到的结果无法抢开第二个流程。 + +`WorkspaceCreateFlow` 现更名为 `WorkspacePickFlow`,其 `createOnly` prop 更名为 `addOnly`;注入的 `createWorkspace` 从 `{ name } | { path }` 收窄为 `{ path }`。 + +## Wire and CLI residue + +Host 侧的 `workspace.create` 仍接受 `{ name }`,`dsh web --workspace-root` 也仍在为它提供目标目录,但已没有任何产品表层会走到它们。把名称送到 wire 的客户端一段同样如此:`WorkspaceCreateInput`、`WorkspacesService.create` 的 `{ name }` 分支、`intentName` 的名称分支,以及 manager 中"workspaceRoot 下的 name"这一契约。`apps/cli/README.md` 及其中文对照本也仍把 `--workspace-root` 记为"创建具名 Workspace"。这一整套都在 `packages/host/apiproxy/src/api-proxy.ts` 的调用点标记为待删除,并留给后续改动:它横跨 backend、客户端 seam 与 CLI 面,有各自的 reviewer 和各自的测试波及面(api-proxy workspace 套件、runtime workspace 套件、配置目录),而本决定中阻塞发布的部分是 UI。 + +## Testing + +`connectFreshWorkspace`——所有 web e2e 场景启动时都会走的辅助函数——会预先备好 `/workspace`,再经对话框的路径编辑器接纳它,因此产出的会话 cwd 与按名称创建时完全一致,场景 golden 保持有效。选择预先备好而不是在对话框内新建,是为了让该辅助函数在一个场景可能发生的多次连接之间保持幂等(第二次创建同名文件夹会失败,而创建对话框会在失败时把流程停在原地)。在选择器内新建文件夹——同一条路径的另一半——由 `workspace-management.e2e.ts` 覆盖,它承担针对性覆盖:在对话框自己创建的文件夹上添加两个 workspace、在另一个目录上复用已删除的标题、以及浏览对话框的 aria golden。 + +`smoke-real.e2e.ts` 是唯一启动未打补丁的出厂配置树的场景,其中 `-auto` 行会按宿主机解析;它现在通过 `--config` overlay 钉死 `-browse`,使开发机的显示环境无法决定选择器是否可被驱动。 + +## Alternatives considered + +**保留 `打开本地文件夹…` 作为标签。** 否决:合并后该入口既能打开也能创建,用机制命名会恰好对那些入口被我们删掉的用户隐藏创建这一半。反方理由——"本地"二字有效区分了浏览器所在机器与 harness 所在机器——在下一步就由对话框自身的标题和面包屑回答了。 + +**保留双入口菜单,让 `新建工作区` 也打开同一个流程。** 否决:同一动作两个标签正是我们被要求消除的混淆,而不是它的缩小版。 + +**为了与主视觉区菜单保持一致而保留只有一行的浮层。** 否决:不提供选择的浮层是一次浪费的点击,读起来像半成品。这里要一致的是*规则*(有菜单 ⇔ 存在选择),不是控件。 + +**为将来可能新增的入口(克隆仓库、远程目录)保留菜单壳。** 否决,依据"require a current owner and need":这样的入口目前并不存在,而等它到来时再恢复菜单,比现在就发一个空壳的改动更小。 + +**在同一改动中删除 wire 的按名称创建分支。** 本 PR 否决:那是 backend/CLI 面,reviewer 不同、测试波及面更广,而紧急的决定是 UI。见 residue 一节——它是被标记了,不是被遗忘了。 + +**在 e2e scaffold 中经 host 注册 workspace,而不驱动对话框。** 否决:那会让全部 15 个场景与选择器解耦,整条 lane 将无法证明幸存的这条路径能走到可用的 composer。现在每个场景都会走真实对话框来接纳自己的目录;只有"新建文件夹"那一半集中在一个场景里,因为处处重复只会让共享辅助函数失去幂等性,却换不来额外信号。 + +## Consequences + +- 从 UI 已无法在操作者选定目录之外创建 Workspace;服务端控制的 `--workspace-root` 目标曾是约束新 workspace 文件夹落点的唯一手段,现在没有替代品。需要该约束的部署必须有意识地重新引入它。 +- 仅存的这条路径会浏览宿主机文件系统,因此选择器的可达范围现在是整台宿主机,而非一个配置好的父目录。这本就是浏览占用者的契约,本改动使它成为唯一的契约。 +- 挂载了 `ui-workspace` 但未挂任何 directory-picker 包的组合,已完全无法添加 Workspace;现在它通过不渲染按钮来说明这一点,而不是提供一个按名称创建的兜底。 +- 主视觉区的 chip 仍声明 `aria-haspopup="menu"`,而直接拉起的路径实际弹出的是对话框。要让它如实,需要把流程的展示方式经 `conversation.hero.workspace` 的 owner 契约上报——决定权在流程,播报权在 chip,两者分属不同的包——因此这被列为一项具名的后续工作,而不是一处无声的不一致。本次新增的侧边栏按钮完全不作任何 popup 声明。 diff --git a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml index 4603c65221..0c5c704684 100644 --- a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.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/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md -2026-07-28-storage-root-and-derived-medium-recovery.md: 7759d0b6a8d522d6f853be0cd31a0b3909292446 -2026-07-28-storage-root-and-derived-medium-recovery.zh.md: 893b91c2ad3943cce9f64702e52afbb8075b907c +2026-07-28-storage-root-and-derived-medium-recovery.md: 2edb60d204da736bf14ace6278fa4ee7b9e4b8f7 +2026-07-28-storage-root-and-derived-medium-recovery.zh.md: daef4f7661df069df3438f909f2744880a93a873 diff --git a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md index 7759d0b6a8..2edb60d204 100644 --- a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md +++ b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.md @@ -18,7 +18,7 @@ Two independent changes, one per gap. ### One global storage root (shipped, amended form); resolved once at construction (still open) -- **Shipped**: the Web overlay anchors `storage-json.root` to `$DSH_HOME/storages` directly in the row, with the same `!!js` IIFE the session root uses (`~/.dsh/storages` by default, beside `~/.dsh/sessions`; no leading dot — the home is already a hidden tree). The user ruled this form in over this section's original launcher-patch + `storageRoot` profile key (see Alternatives); per-row overrides ride the personal `~/.dsh/config.yaml` patch layer. The verbatim duplication of the expression against the session root (`base.cordis.yml`) is a known cost — acceptable at two consumers; a third `$DSH_HOME`-derived root triggers extracting a single source (a launcher variable or a shared expression). The web e2e scaffold already patches the row to an absolute temp root, so tests never touch the user's home. +- **Shipped**: the Web overlay anchors `storage-json.root` to `$DSH_HOME/storages` directly in the row through the app-boot-provided `dshHomePath('storages')` (`~/.dsh/storages` by default, beside `~/.dsh/sessions`; no leading dot — the home is already a hidden tree). The helper delegates to the canonical `dsh-paths` resolver, and the session root uses the same function without duplicating its fallback and tilde rules. The user ruled the per-row form in over this section's original launcher-patch + `storageRoot` profile key (see Alternatives); per-row overrides ride the personal `~/.dsh/config.yaml` patch layer. The web e2e scaffold already patches the row to an absolute temp root, so tests never touch the user's home. - **Still open**: `JsonStorageBackend` resolves its configured root once at construction (`resolve(config.root)`), adopting the JSONL backend's recorded rationale verbatim: a later `process.cwd()` change must not split one backend across roots. The SQLite storage backend already resolves its path. - Pre-release stance applies (and was executed): no migration shim. A deployment that cached under `/.storages` re-derives everything (workspace re-bootstraps from the header index; the projection cache refolds lazily) or moves the two json files by hand once. diff --git a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md index 893b91c2ad..daef4f7661 100644 --- a/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-28-storage-root-and-derived-medium-recovery.zh.md @@ -18,7 +18,7 @@ Status: proposed ### 全局唯一存储根(已落地,形态修正);构造时 resolve 一次(仍开放) -- **已落地**:出厂 Web overlay 直接在 `storage-json` 行内用与会话根同一段 `!!js` IIFE 把 `root` 锚定到 `$DSH_HOME/storages`(默认 `~/.dsh/storages`,与 `~/.dsh/sessions` 并肩;目录名不带点——home 本身已是隐藏树)。用户拍板采用此形态取代本节初版的「launcher patch + `storageRoot` profile 键」(见 Alternatives);按行覆盖仍走个人 `~/.dsh/config.yaml` patch 层。该表达式与 sessions 根(`base.cordis.yml`)逐字重复是已知代价——两个消费者尚可接受;出现第三个 `$DSH_HOME` 派生根时提取单一来源(launcher 变量或共享表达式)。web e2e scaffold 本就把该行 patch 到临时绝对根,测试不触用户 home。 +- **已落地**:出厂 Web overlay 通过 app-boot 提供的 `dshHomePath('storages')`,直接在 `storage-json` 行内把 `root` 锚定到 `$DSH_HOME/storages`(默认 `~/.dsh/storages`,与 `~/.dsh/sessions` 并肩;目录名不带点——home 本身已是隐藏树)。该辅助函数委托给规范的 `dsh-paths` 解析器,会话根也使用同一个函数,无需重复其回退和波浪号规则。用户拍板采用这种按行形态取代本节初版的「launcher patch + `storageRoot` profile 键」(见 Alternatives);按行覆盖仍走个人 `~/.dsh/config.yaml` patch 层。web e2e scaffold 本就把该行 patch 到临时绝对根,测试不触用户 home。 - **仍开放**:`JsonStorageBackend` 在构造时对配置根 `resolve` 一次,原样采纳 JSONL 后端已记录的理由:后续 `process.cwd()` 变化不得把一个后端劈到多个根下。SQLite 存储后端已经 resolve 其路径。 - 适用 pre-release 立场(已按此执行):不做迁移垫片。曾在 `/.storages` 下缓存过的部署要么全部重新派生(工作区从 header 索引重新 bootstrap;投影缓存惰性重折),要么手动把两个 json 文件挪一次。 diff --git a/README.i18n.yaml b/README.i18n.yaml index 6fbb7f5299..b492ed9c37 100644 --- a/README.i18n.yaml +++ b/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 README.md -README.md: 08ae0b3d5d2d7ad8e7cb62bd5e8b3242426735dc -README.zh.md: 9587215b6b17250504877b8930fdf431fd24b2ac +README.md: b447c9634189353854e8be9d0bf597a8b0c7e371 +README.zh.md: f8bbbc36bc670403c0b9a40977f32f598e77ee46 diff --git a/README.md b/README.md index 08ae0b3d5d..b447c96341 100644 --- a/README.md +++ b/README.md @@ -94,3 +94,5 @@ DeepSeek Harness is currently in internal testing. ## License [BSD 3-Clause](LICENSE) + +Third-party dependencies and their licenses are disclosed in [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md). diff --git a/README.zh.md b/README.zh.md index 9587215b6b..f8bbbc36bc 100644 --- a/README.zh.md +++ b/README.zh.md @@ -98,3 +98,5 @@ DeepSeek Harness 目前处于内测阶段。 ## 许可证 [BSD 3-Clause](LICENSE) + +第三方依赖及其许可证在 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) 中披露。 diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md new file mode 100644 index 0000000000..075e1b34c4 --- /dev/null +++ b/THIRD_PARTY_NOTICES.md @@ -0,0 +1,165 @@ + + +# Third-Party Notices + +DeepSeek Harness is licensed under [BSD 3-Clause](LICENSE). It depends on the third-party open-source software listed below. Each project remains under its own license; nothing in this file changes those terms. + +This file lists **direct** dependencies declared by the workspace. It is generated from the workspace manifests by `scripts/gen-third-party-notices.ts`: a pre-commit hook regenerates it whenever a staged file changes one of its inputs, and `scripts/gen-third-party-notices.spec.ts` asserts in the test lane that the committed bytes match. Deleting a manifest runs no hook, so that case is caught by the assertion instead. Run `pnpm run verify-third-party-notices` for the standalone check. + +The complete npm transitive closure, with exact pinned versions, is recorded in [`pnpm-lock.yaml`](pnpm-lock.yaml) — inspect it with `pnpm licenses list`. The Python closure is recorded in [`python/sdk/uv.lock`](python/sdk/uv.lock), and the Landlock launcher workspace keeps its own in [`native/landlock-run/pnpm-lock.yaml`](native/landlock-run/pnpm-lock.yaml). + +## Vendored source (`vendor/`) + +The Cordis framework and its foundation libraries are source-vendored into this repository rather than consumed from npm. All are MIT-licensed; each directory preserves its upstream `LICENSE` file. Exact upstream commits and local modifications are recorded in [`vendor/README.md`](vendor/README.md). + +| Package | Upstream | License | +| --- | --- | --- | +| `cosmokit` | [github.com/deepseek-harness/cosmokit](https://github.com/deepseek-harness/cosmokit) | MIT | +| `schemastery` | [github.com/deepseek-harness/schemastery](https://github.com/deepseek-harness/schemastery) | MIT | +| `cordis` | [github.com/cordiverse/cordis](https://github.com/cordiverse/cordis) | MIT | +| `@cordisjs/plugin-loader` | [github.com/cordiverse/cordis](https://github.com/cordiverse/cordis) | MIT | +| `@cordisjs/plugin-include` | [github.com/deepseek-harness/cordis](https://github.com/deepseek-harness/cordis) | MIT | +| `@cordisjs/plugin-group` | [github.com/deepseek-harness/cordis](https://github.com/deepseek-harness/cordis) | MIT | +| `@cordisjs/plugin-timer` | [github.com/deepseek-harness/cordis](https://github.com/deepseek-harness/cordis) | MIT | +| `@cordisjs/plugin-hmr` | [github.com/deepseek-harness/cordis](https://github.com/deepseek-harness/cordis) | MIT | +| `@cordisjs/plugin-logger-console` | [github.com/deepseek-harness/cordis](https://github.com/deepseek-harness/cordis) | MIT | + +## Runtime npm dependencies + +External packages that a workspace package resolves at runtime. `scripts/install.sh` installs this repository itself, so the tier covers every plugin a user can mount from `cordis.yml` — not only what the `dsh` CLI/TUI, the Web UI, and the Python SDK runtime load by default. + +| Package | License | +| --- | --- | +| [`@agentclientprotocol/sdk`](https://github.com/agentclientprotocol/typescript-sdk) | Apache-2.0 | +| [`@babel/code-frame`](https://github.com/babel/babel) | MIT | +| [`@clack/core`](https://github.com/bombshell-dev/clack) | MIT | +| [`@clack/prompts`](https://github.com/bombshell-dev/clack) | MIT | +| [`@earendil-works/pi-ai`](https://github.com/earendil-works/pi) | MIT | +| [`@earendil-works/pi-tui`](https://github.com/earendil-works/pi) | MIT | +| [`@joplin/turndown-plugin-gfm`](https://github.com/laurent22/joplin-turndown-plugin-gfm) | MIT | +| [`@modelcontextprotocol/sdk`](https://github.com/modelcontextprotocol/typescript-sdk) | MIT | +| [`@opentelemetry/api`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | +| [`@opentelemetry/api-logs`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | +| [`@opentelemetry/exporter-logs-otlp-http`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | +| [`@opentelemetry/otlp-exporter-base`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | +| [`@opentelemetry/resources`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | +| [`@opentelemetry/sdk-logs`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | +| [`@shikijs/langs`](https://github.com/shikijs/shiki) | MIT | +| [`@standard-schema/spec`](https://github.com/standard-schema/standard-schema) | MIT | +| [`anser`](https://github.com/IonicaBizau/anser) | MIT | +| [`chokidar`](https://github.com/paulmillr/chokidar) | MIT | +| [`clsx`](https://github.com/lukeed/clsx) | MIT | +| [`commander`](https://github.com/tj/commander.js) | MIT | +| [`diff`](https://github.com/kpdecker/jsdiff) | BSD-3-Clause | +| [`dotenv`](https://github.com/motdotla/dotenv) | BSD-2-Clause | +| [`eventsource-parser`](https://github.com/rexxars/eventsource-parser) | MIT | +| [`handlebars`](https://github.com/handlebars-lang/handlebars.js) | MIT | +| [`immer`](https://github.com/immerjs/immer) | MIT | +| [`js-yaml`](https://github.com/nodeca/js-yaml) | MIT | +| [`jsonc-parser`](https://github.com/microsoft/node-jsonc-parser) | MIT | +| [`koffi`](https://github.com/Koromix/koffi) | MIT | +| [`mdast-util-from-markdown`](https://github.com/syntax-tree/mdast-util-from-markdown) | MIT | +| [`mdast-util-gfm`](https://github.com/syntax-tree/mdast-util-gfm) | MIT | +| [`micromark-extension-gfm`](https://github.com/micromark/micromark-extension-gfm) | MIT | +| [`node-addon-require-builtin`](https://www.npmjs.com/package/node-addon-require-builtin) | MIT | +| [`node-pty`](https://github.com/microsoft/node-pty) | MIT | +| [`picomatch`](https://github.com/micromatch/picomatch) | MIT | +| [`react`](https://github.com/facebook/react) | MIT | +| [`react-dom`](https://github.com/facebook/react) | MIT | +| [`react-markdown`](https://github.com/remarkjs/react-markdown) | MIT | +| [`remark-gfm`](https://github.com/remarkjs/remark-gfm) | MIT | +| [`saxes`](https://github.com/lddubeau/saxes) | ISC | +| [`shiki`](https://github.com/shikijs/shiki) | MIT | +| [`supports-color`](https://github.com/chalk/supports-color) | MIT | +| [`tsx`](https://github.com/privatenumber/tsx) | MIT | +| [`turndown`](https://github.com/mixmark-io/turndown) | MIT | +| [`typescript`](https://github.com/microsoft/TypeScript) | Apache-2.0 | +| [`use-sync-external-store`](https://github.com/facebook/react) | MIT | +| [`yaml`](https://github.com/eemeli/yaml) | ISC | +| [`zod`](https://github.com/colinhacks/zod) | MIT | +| [`zustand`](https://github.com/pmndrs/zustand) | MIT | + +pnpm applies local patches to the following packages at install time, so shipped artifacts carry modified copies; each patch file is the complete record of the modification: + +- `@earendil-works/pi-tui@0.80.7` — [`patches/@earendil-works__pi-tui@0.80.7.patch`](patches/@earendil-works__pi-tui@0.80.7.patch) +- `node-pty@1.1.0` — [`patches/node-pty@1.1.0.patch`](patches/node-pty@1.1.0.patch) + +## Development-only npm dependencies + +External packages **directly declared** only by repository tooling, test infrastructure, the documentation site, the demo leaves, or the native launcher's build workspace. No shipped surface names them itself. A package here may still be pulled in transitively by a runtime dependency — `pnpm-lock.yaml` is the authority on the full closure — so this tier records who declares a package, not what a build ultimately bundles. + +| Package | License | +| --- | --- | +| [`@braintree/sanitize-url`](https://github.com/braintree/sanitize-url) | MIT | +| [`@modelcontextprotocol/server-everything`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 | +| [`@modelcontextprotocol/server-filesystem`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 | +| [`@stylistic/eslint-plugin`](https://github.com/eslint-stylistic/eslint-stylistic) | MIT | +| [`@testing-library/dom`](https://github.com/testing-library/dom-testing-library) | MIT | +| [`@testing-library/react`](https://github.com/testing-library/react-testing-library) | MIT | +| [`@types/babel__code-frame`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/js-yaml`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/jsdom`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/mdast`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/node`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/picomatch`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/react`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/react-dom`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/spdx-expression-parse`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@types/turndown`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | +| [`@typescript-eslint/parser`](https://github.com/typescript-eslint/typescript-eslint) | MIT | +| [`@vitejs/plugin-react`](https://github.com/vitejs/vite-plugin-react) | MIT | +| [`@vitest/coverage-v8`](https://github.com/vitest-dev/vitest) | MIT | +| [`@xterm/headless`](https://github.com/xtermjs/xterm.js) | MIT | +| [`@yarnpkg/cli-dist`](https://github.com/yarnpkg/berry) | BSD-2-Clause | +| [`cytoscape`](https://github.com/cytoscape/cytoscape.js) | MIT | +| [`cytoscape-cose-bilkent`](https://github.com/cytoscape/cytoscape.js-cose-bilkent) | MIT | +| [`dayjs`](https://github.com/iamkun/dayjs) | MIT | +| [`debug`](https://github.com/debug-js/debug) | MIT | +| [`esbuild`](https://github.com/evanw/esbuild) | MIT | +| [`eslint`](https://github.com/eslint/eslint) | MIT | +| [`eslint-plugin-sonarjs`](https://github.com/SonarSource/SonarJS) | LGPL-3.0-only | +| [`execa`](https://github.com/sindresorhus/execa) | MIT | +| [`fast-check`](https://github.com/dubzzz/fast-check) | MIT | +| [`jscpd`](https://github.com/kucherenko/jscpd) | MIT | +| [`jsdom`](https://github.com/jsdom/jsdom) | MIT | +| [`knip`](https://github.com/webpro-nl/knip) | ISC | +| [`lefthook`](https://github.com/evilmartians/lefthook) | MIT | +| [`lightningcss`](https://github.com/parcel-bundler/lightningcss) | MPL-2.0 | +| [`mermaid`](https://github.com/mermaid-js/mermaid) | MIT | +| [`oxlint`](https://github.com/oxc-project/oxc) | MIT | +| [`oxlint-tsgolint`](https://github.com/oxc-project/tsgolint) | MIT | +| [`playwright`](https://github.com/microsoft/playwright) | Apache-2.0 | +| [`publint`](https://github.com/publint/publint) | MIT | +| [`smol-toml`](https://github.com/squirrelchat/smol-toml) | BSD-3-Clause | +| [`spdx-expression-parse`](https://github.com/jslicense/spdx-expression-parse.js) | MIT | +| [`tsdown`](https://github.com/rolldown/tsdown) | MIT | +| [`typescript-language-server`](https://github.com/typescript-language-server/typescript-language-server) | Apache-2.0 | +| [`vite`](https://github.com/vitejs/vite) | MIT | +| [`vite-tsconfig-paths`](https://github.com/aleclarson/vite-tsconfig-paths) | MIT | +| [`vitepress`](https://github.com/vuejs/vitepress) | MIT | +| [`vitepress-plugin-mermaid`](https://github.com/emersonbottero/vitepress-plugin-mermaid) | MIT | +| [`vitest`](https://github.com/vitest-dev/vitest) | MIT | + +`eslint-plugin-sonarjs` (LGPL-3.0-only) and `lightningcss` (MPL-2.0) run only as development tooling; their code is not linked into or distributed with any DeepSeek Harness artifact. + +## Python SDK dependencies (`python/`) + +Direct dependencies of the `pyproject.toml` manifests, plus `uv` as the development workflow tool. + +| Package | License | Role | +| --- | --- | --- | +| [`hatchling`](https://github.com/pypa/hatch) | MIT | build backend | +| [`pydantic`](https://github.com/pydantic/pydantic) | MIT | runtime dependency of `deepseek-harness` | +| [`pytest`](https://github.com/pytest-dev/pytest) | MIT | test-only | +| [`uv`](https://github.com/astral-sh/uv) | MIT / Apache-2.0 | development workflow tool | + +## Fetched at build time + +| Package | License | Role | +| --- | --- | --- | +| [`@yao-pkg/pkg`](https://github.com/yao-pkg/pkg) | MIT | invoked by `scripts/build-exe-for-python-sdk.ts` to assemble the single-file SDK runtime executable | + +## First-party sibling releases + +`node-addon-landlock-run` (and its platform packages) is released from a DeepSeek Harness sibling repository under BSD 3-Clause. It is listed here for completeness; it is first-party, not third-party. diff --git a/apps/cli/README.i18n.yaml b/apps/cli/README.i18n.yaml index 40b2be951e..367fec957c 100644 --- a/apps/cli/README.i18n.yaml +++ b/apps/cli/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 apps/cli/README.md -README.md: 3f260b5f5f16638d1dc2c28385eb3eccdf59c8e8 -README.zh.md: e57b3c4e94da6e4fe86e2781075118139368f6e2 +README.md: c3d6a359c81cb2dce13d43715b1d816cc010efff +README.zh.md: 9843738e015af1259a228e6023c6096ef624f4dd diff --git a/apps/cli/README.md b/apps/cli/README.md index 3f260b5f5f..c3d6a359c8 100644 --- a/apps/cli/README.md +++ b/apps/cli/README.md @@ -13,6 +13,7 @@ The TUI surface: - tells the agent where its own source lives: after boot it adds a prompt section naming this harness checkout, resolved from the launcher's real path so it holds under a PATH symlink and an arbitrary cwd, so the self-referential `cordis` toolset can read and modify it; - applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../packages/ui/app-boot/README.md#personal-config)): `config.yaml` patches the booted tree, while `.env` there is the credential provider's own store (never hoisted into the environment, so keys stay rotatable). Environment precedence is ambient > project `.env`. - presents the [versioned first-run welcome](../../.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md) through the mounted TUI overlay service when its immutable marker is absent under `DSH_HOME`; only Enter creates that version's marker, while Escape, disposal, or process exit leaves it eligible. The official DeepSeek icon, responsive terminal rasters, all-locale Chinese copy, and notice version are static local owners; the overlay never writes a session event or model context. +- registers bare `/compact`: while the agent is idle, it summarizes useful older history even below automatic pressure, rejects arguments, and reports success only after the standalone replacement bracket is durable. A prompt submitted during compaction keeps its queue identity and starts after that checkpoint; injected context remains visible. `dsh meta` is that same TUI with this harness checkout as the workspace, so working on dsh itself needs no `cd`. It chdirs to the checkout root — resolved from the launcher's real path, the same root the source-path prompt section names — after the environment is settled, so precedence is unchanged while the session cwd and HMR watch root move together. Meta always starts a fresh session and accepts no default-surface options; use ordinary `dsh --resume ` to resume a persisted session. @@ -28,6 +29,14 @@ The Web/headless composition also registers only `web_search`. Search uses DeepS `DSH_TOOLS_MODE` selects the tool presentation mode for the whole Web/headless process: `native` (the schema default when unset), `code` (the `run_code`-only Code Mode wire), or `both`; any other value fails loud at boot through the `dsh-tools` config schema. It is a TEMPORARY seam — process-wide because Loader composition is static — and is removed once the web UI owns per-session tool-mode selection; the TUI surface ignores it (its config tree pins its own mode). +[`core-web.cordis.yml`](config/core-web.cordis.yml) is an opt-in `dsh web --config` overlay that keeps the shipped Web host, browser, Workspace, persistence, and permission composition while reducing the default native model surface to owner-scoped persistent `bash` and `str_replace_editor`. The PTY backend and editor consume the existing Web sandbox and filesystem providers. An open persistent shell prevents changing that session's permission mode until the shell closes, so a shell created under wider access cannot survive a downgrade. `DSH_TOOLS_MODE` still controls native/Code Mode presentation for the resulting two-tool registry. + +From a source checkout, start this minimal Web profile with: + +```sh +pnpm run dsh web --config apps/cli/config/core-web.cordis.yml +``` + Every `dsh` surface — TUI, Web, and headless — reports session telemetry by default (the row lives in the shared `base.cordis.yml`): every session-log event streams as OTLP/HTTP log records to `https://harness-telemetry.deepseeksvc.com/v1/logs` on a 10-second batch cadence. `DSH_TELEMETRY_OTLP_URL` points the exporter at a different collector; setting `DSH_TELEMETRY_DISABLED` to ANY non-empty value — including `0` or `false` — disables the row before it loads (a privacy switch prefers off-by-mistake over on-by-mistake). No redaction rule is mounted in this composition yet: exported records are the raw captured copy, including message text, tool arguments and results, and the session's working-directory path. The deployment rulings live in the [web-telemetry-default-mount Agent Note](../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md). ## Install (developer machine) diff --git a/apps/cli/README.zh.md b/apps/cli/README.zh.md index e57b3c4e94..9843738e01 100644 --- a/apps/cli/README.zh.md +++ b/apps/cli/README.zh.md @@ -13,6 +13,7 @@ TUI 界面: - 告知 agent 自身源码所在位置:启动后添加一个命名此 harness checkout 的提示词段。该路径从启动器的真实路径解析,因此在 PATH 符号链接和任意 cwd 下仍然有效,使自指的 `cordis` 工具集可以读取并修改它; - 应用 `~/.dsh` 中的个人覆盖(参见 [app-boot 的个人配置](../../packages/ui/app-boot/README.md#personal-config)):`config.yaml` 修补已启动的树,而那里的 `.env` 是凭据 provider 自己的存储(绝不会被提升进环境,因此密钥始终可轮换)。环境优先级为环境中已有的值 > 项目 `.env`。 - 当 `DSH_HOME` 下不存在不可变确认标记时,通过已挂载的 TUI overlay 服务呈现[版本化首次运行欢迎页](../../.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md);只有 Enter 会创建该版本的标记,Escape、资源释放或进程退出仍保留展示资格。官方 DeepSeek 图标、响应式终端栅格图、所有 locale 共用的中文文案和通知版本均由静态本地文件持有;overlay 不会写入会话事件或模型上下文。 +- 注册裸 `/compact`:agent 空闲时,即使未达到自动压力,也会摘要有效的较早历史;该命令拒绝参数,并只在独立替换标记对持久化后报告成功。压缩(compaction)期间提交的提示词保留其队列身份,并在该检查点之后启动;注入的上下文仍保持可见。 `dsh meta` 是以本 harness checkout 为 workspace 的同一个 TUI,因此开发 dsh 自身无需 `cd`。它在环境确定之后才 chdir 到 checkout 根目录(从启动器的真实路径解析,与源码路径提示词段所指的根目录相同),因此环境优先级不变,而会话 cwd 与 HMR 监视根目录会一并移动。Meta 始终创建新会话,不接受默认界面的任何选项;恢复已持久化会话应使用普通的 `dsh --resume `。 @@ -28,6 +29,14 @@ Web/无头组合还只会注册 `web_search`。搜索使用 DeepSeek 的 Anthr `DSH_TOOLS_MODE` 为整个 Web/无头进程选择工具呈现模式:可选值为 `native`(未设置时的 schema 默认值)、`code`(仅含 `run_code` 的 Code Mode 协议接口)或 `both`;任何其他值都会经由 `dsh-tools` 配置 schema 在启动时明确报错。它是一个临时 seam:Loader 组合是静态的,因此该设置作用于整个进程;待 Web UI 负责逐会话工具模式选择后便会移除。TUI 界面会忽略该变量(其配置树固定了自身模式)。 +[`core-web.cordis.yml`](config/core-web.cordis.yml) 是一个可选启用的 `dsh web --config` 覆盖层:它保留已交付的 Web 宿主、浏览器、Workspace、持久化与权限组合,同时将默认的原生模型界面精简为以所有者为作用域的持久 `bash` 以及 `str_replace_editor`。PTY 后端和编辑器分别消费现有的 Web 沙箱与文件系统提供方。持久 shell 处于打开状态时,会阻止所属会话更改权限模式;因此,在较宽权限下创建的 shell 无法在降权后继续存活。`DSH_TOOLS_MODE` 仍控制由此得到的双工具注册表采用原生/Code Mode 呈现。 + +在源码 checkout 中,用以下命令启动这个精简 Web profile: + +```sh +pnpm run dsh web --config apps/cli/config/core-web.cordis.yml +``` + 每个 `dsh` 界面——TUI、Web 与无头——都默认上报会话遥测(该行位于共享的 `base.cordis.yml`):每条会话日志事件以 OTLP/HTTP 日志记录的形式、按 10 秒批处理节奏流向 `https://harness-telemetry.deepseeksvc.com/v1/logs`。`DSH_TELEMETRY_OTLP_URL` 可将 exporter 指向其他 collector;将 `DSH_TELEMETRY_DISABLED` 设为**任意非空值**——包括 `0` 或 `false`——都会在该行加载前将其关停(隐私开关取「宁可误关、不可误开」)。该组合当前未挂载任何脱敏规则:导出记录即原始捕获副本,包含消息正文、工具参数与结果、以及会话工作目录路径。部署口径见 [web-telemetry-default-mount Agent Note](../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md)。 ## 安装(开发机) diff --git a/apps/cli/composition.md b/apps/cli/composition.md index 870b926054..1339cf1153 100644 --- a/apps/cli/composition.md +++ b/apps/cli/composition.md @@ -76,6 +76,8 @@ flowchart LR cfg --> plugin_tui_token_meter plugin_tui_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] cfg --> plugin_tui_compact_basic + plugin_tui_command_compact["command-compact
@deepseek-ai/dsh-command-compact"] + cfg --> plugin_tui_command_compact plugin_tui_subagent["subagent
@deepseek-ai/dsh-subagent"] cfg --> plugin_tui_subagent plugin_tui_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] @@ -144,6 +146,7 @@ flowchart LR | `plan-mode` | `@deepseek-ai/dsh-plan-mode` | | `token-meter` | `@deepseek-ai/dsh-token-meter` | | `compact-basic` | `@deepseek-ai/dsh-compact-basic` | +| `command-compact` | `@deepseek-ai/dsh-command-compact` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | | `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | diff --git a/apps/cli/config/base.cordis.yml b/apps/cli/config/base.cordis.yml index 041e7939bc..fe94be48cf 100644 --- a/apps/cli/config/base.cordis.yml +++ b/apps/cli/config/base.cordis.yml @@ -84,8 +84,7 @@ - id: session-persistence-jsonl name: '@deepseek-ai/dsh-session-persistence-jsonl' config: - root: !!js >- - (() => { const path = process.getBuiltinModule('node:path'); const home = process.getBuiltinModule('node:os').homedir(); const configured = process.env.DSH_HOME; const selected = configured !== undefined && configured.trim().length > 0 ? configured : path.join(home, '.dsh'); const expanded = selected === '~' ? home : selected.startsWith('~/') || selected.startsWith('~\\') ? path.join(home, selected.slice(2)) : selected; return path.join(path.resolve(expanded), 'sessions') })() + root: !!js dshHomePath('sessions') # TUI consumes this shared session capability. Its launcher supplies a unique # process-local path; other surfaces repoint or disable the row in their @@ -202,6 +201,11 @@ - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' +# Human `/compact`: one useful reduction below the automatic threshold. Backend +# independent, so it follows whichever compaction service this leaf mounts. +- id: command-compact + name: '@deepseek-ai/dsh-command-compact' + - id: subagent name: '@deepseek-ai/dsh-subagent' diff --git a/apps/cli/config/core-web.cordis.yml b/apps/cli/config/core-web.cordis.yml new file mode 100644 index 0000000000..347a5bfbe6 --- /dev/null +++ b/apps/cli/config/core-web.cordis.yml @@ -0,0 +1,72 @@ +# Opt-in two-tool profile over the shipped Web composition. The default native +# model surface is exactly persistent `bash` plus `str_replace_editor`; the +# Web host, browser shell, workspace, persistence, and permission stack remain. + +# Disable every model-facing consumer in the base/Web tree. plan-mode owns the +# always-registered exit_plan_mode tool even while the session is not planning. +- id: tool-bash + disabled: true + +- id: tool-tasks + disabled: true + +- id: tool-fs + disabled: true + +- id: tool-fs-search + disabled: true + +- id: tool-web + disabled: true + +- id: tool-skill + disabled: true + +- id: plan-mode + disabled: true + +- id: tool-subagent + disabled: true + +- id: tool-subagent-fork + disabled: true + +- id: tool-workflow + disabled: true + +- id: tool-todo + disabled: true + +# The matching browser controls must not offer host tools that this profile +# omits. ui-question's host half owns the ask_user_question registration. +- id: ui-plan + disabled: true + +- id: ui-question + disabled: true + +- insert: + - id: pty + name: '@deepseek-ai/dsh-pty' + + # This backend consumes the existing Web sandbox and permission policy. + # It loads only on Linux/macOS; Windows and other platforms fail at boot. + # Its 300s send wait matches the persistent Bash command timeout instead of + # pty-local's 30s default. An open persistent shell fences permission-mode + # changes until it closes. + - id: pty-local + name: '@deepseek-ai/dsh-pty-local' + config: + timeoutMs: 300000 + + - id: persistent-bash + name: '@deepseek-ai/dsh-tool-bash-persistent' + config: + timeoutMs: 300000 + + # The editor consumes the Web fs-sandbox provider and therefore retains + # the selected session permission mode. + - id: str-replace-editor + name: '@deepseek-ai/dsh-tool-str-replace-editor' + config: + maxOutputChars: 16000 diff --git a/apps/cli/config/web.cordis.yml b/apps/cli/config/web.cordis.yml index 238b3788fe..159b2e270c 100644 --- a/apps/cli/config/web.cordis.yml +++ b/apps/cli/config/web.cordis.yml @@ -119,8 +119,7 @@ - id: storage-json name: '@deepseek-ai/dsh-storage-json' config: - root: !!js >- - (() => { const path = process.getBuiltinModule('node:path'); const home = process.getBuiltinModule('node:os').homedir(); const configured = process.env.DSH_HOME; const selected = configured !== undefined && configured.trim().length > 0 ? configured : path.join(home, '.dsh'); const expanded = selected === '~' ? home : selected.startsWith('~/') || selected.startsWith('~\\') ? path.join(home, selected.slice(2)) : selected; return path.join(path.resolve(expanded), 'storages') })() + root: !!js dshHomePath('storages') - id: storage-domain name: '@deepseek-ai/dsh-storage-domain' diff --git a/apps/cli/package.json b/apps/cli/package.json index 803b298ba4..40f970ee91 100644 --- a/apps/cli/package.json +++ b/apps/cli/package.json @@ -48,6 +48,7 @@ "@deepseek-ai/dsh-client-ui-trajectory": "workspace:^", "@deepseek-ai/dsh-client-ui-workspace": "workspace:^", "@deepseek-ai/dsh-code-runtime-worker": "workspace:^", + "@deepseek-ai/dsh-command-compact": "workspace:^", "@deepseek-ai/dsh-command-goal": "workspace:^", "@deepseek-ai/dsh-commands": "workspace:^", "@deepseek-ai/dsh-compact-basic": "workspace:^", @@ -69,9 +70,12 @@ "@deepseek-ai/dsh-llm-deepseek": "workspace:^", "@deepseek-ai/dsh-llm-pi-ai": "workspace:^", "@deepseek-ai/dsh-llm-retry": "workspace:^", + "@deepseek-ai/dsh-mcp-client": "workspace:^", "@deepseek-ai/dsh-paths": "workspace:^", "@deepseek-ai/dsh-permission": "workspace:^", "@deepseek-ai/dsh-plan-mode": "workspace:^", + "@deepseek-ai/dsh-pty": "workspace:^", + "@deepseek-ai/dsh-pty-local": "workspace:^", "@deepseek-ai/dsh-sandbox-local": "workspace:^", "@deepseek-ai/dsh-sandbox-policy": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", @@ -104,12 +108,14 @@ "@deepseek-ai/dsh-token-meter": "workspace:^", "@deepseek-ai/dsh-tool-ask-user": "workspace:^", "@deepseek-ai/dsh-tool-bash": "workspace:^", + "@deepseek-ai/dsh-tool-bash-persistent": "workspace:^", "@deepseek-ai/dsh-tool-cordis": "workspace:^", "@deepseek-ai/dsh-tool-fs": "workspace:^", "@deepseek-ai/dsh-tool-fs-search": "workspace:^", "@deepseek-ai/dsh-tool-goal": "workspace:^", "@deepseek-ai/dsh-tool-ralph": "workspace:^", "@deepseek-ai/dsh-tool-skill": "workspace:^", + "@deepseek-ai/dsh-tool-str-replace-editor": "workspace:^", "@deepseek-ai/dsh-tool-subagent": "workspace:^", "@deepseek-ai/dsh-tool-tasks": "workspace:^", "@deepseek-ai/dsh-tool-todo": "workspace:^", diff --git a/apps/cli/tests/fixtures/memory-mcp-base.cordis.yml b/apps/cli/tests/fixtures/memory-mcp-base.cordis.yml new file mode 100644 index 0000000000..00878d6c98 --- /dev/null +++ b/apps/cli/tests/fixtures/memory-mcp-base.cordis.yml @@ -0,0 +1,8 @@ +# Minimal keyless composition for loading example MCP overlays against the +# package-owned fixture server in memory-mcp-configs.spec.ts. Source builtins +# keep this unit test independent of prebuilt workspace artifacts. +- id: system-prompt + name: cordis:memory-test-system-prompt + +- id: tools + name: cordis:memory-test-tools diff --git a/apps/cli/tests/memory-mcp-configs.spec.ts b/apps/cli/tests/memory-mcp-configs.spec.ts new file mode 100644 index 0000000000..7069b22738 --- /dev/null +++ b/apps/cli/tests/memory-mcp-configs.spec.ts @@ -0,0 +1,132 @@ +/** + * The third-party memory examples stay config-only. This suite parses every + * checked-in overlay, verifies its pin/transport/secret boundary, then replaces + * only the upstream endpoint with the package-owned keyless MCP fixture and + * proves the real Cordis Loader discovers a tool through the generic bridge. + */ + +import { readFileSync } from 'node:fs' +import { resolve } from 'node:path' +import { afterEach, describe, expect, it } from 'vitest' +import type { Context } from 'cordis' +import type { PatchOptions } from '@cordisjs/plugin-include' +import { boot, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import * as McpClient from '@deepseek-ai/dsh-mcp-client/src/index.ts' + +interface ExampleContract { + file: string + id: string + serverName: string + transport: 'stdio' | 'streamable-http' + pin: string +} + +interface InsertedRow { + id?: string + name?: string + config?: Record +} + +const root = resolve(import.meta.dirname, '../../..') +const exampleDir = resolve(root, 'examples/mcp-memory') +const baseConfig = resolve(import.meta.dirname, 'fixtures/memory-mcp-base.cordis.yml') +const fixtureServer = resolve(root, 'packages/mcp/mcp-client/tests/fixture-server.ts') + +const examples: ExampleContract[] = [ + { + file: 'memorix.cordis.yml', + id: 'memory-memorix', + serverName: 'memorix', + transport: 'stdio', + pin: '1.3.0', + }, + { + file: 'mcp-reference-memory.cordis.yml', + id: 'memory-mcp-reference', + serverName: 'reference_memory', + transport: 'stdio', + pin: '2026.7.4', + }, + { + file: 'engram.cordis.yml', + id: 'memory-engram', + serverName: 'engram', + transport: 'stdio', + pin: '1.20.0', + }, +] + +const liveContexts = new Set() + +afterEach(async () => { + await Promise.all([...liveContexts].map(async ctx => ctx.fiber.dispose())) + liveContexts.clear() +}) + +function insertedRow(patches: PatchOptions[]): InsertedRow { + expect(patches).toHaveLength(1) + const insert = patches[0]?.insert + expect(insert).toHaveLength(1) + return insert?.[0] as InsertedRow +} + +async function waitForTool(ctx: Context, name: string): Promise { + const deadline = Date.now() + 10_000 + while (!ctx.tools.schemas().some(schema => schema.name === name)) { + if (Date.now() >= deadline) throw new Error(`timed out waiting for ${name}`) + await new Promise(resolveWait => setTimeout(resolveWait, 25)) + } +} + +describe('third-party memory MCP example overlays', () => { + it.each(examples)('parses $file with the documented generic boundary', (contract) => { + const file = resolve(exampleDir, contract.file) + const source = readFileSync(file, 'utf8') + const row = insertedRow(loadOverlayPatches('memory-mcp-config-test', file)) + + expect(row.id).toBe(contract.id) + expect(row.name).toBe('@deepseek-ai/dsh-mcp-client') + expect(row.config?.serverName).toBe(contract.serverName) + expect(row.config?.transport).toBe(contract.transport) + expect(source.split('\n', 1)[0]).toContain(contract.pin) + expect(source).not.toMatch(/\bsk-[A-Za-z0-9_-]{8,}\b/) + expect(source).not.toContain('DEEPSEEK_API_KEY') + }) + + it.each(examples)('loads $file and discovers a keyless fixture tool', async (contract) => { + const patches = loadOverlayPatches( + 'memory-mcp-config-test', + resolve(exampleDir, contract.file), + ) + // The static config gate verifies the checked-in bare package specifier. + // The unit test maps it to the source module so a clean checkout needs no + // prebuilt `lib/` artifacts before proving the Loader/MCP behavior. + insertedRow(patches).name = 'cordis:memory-test-mcp-client' + const fixturePatch: PatchOptions = { + id: contract.id, + config: { + serverName: contract.serverName, + transport: 'stdio', + command: process.execPath, + args: [fixtureServer], + env: {}, + cwd: root, + toolCallTimeoutMs: 5_000, + }, + } + const ctx = await boot( + 'memory-mcp-config-test', + baseConfig, + [...patches, fixturePatch], + (ctx) => { + liveContexts.add(ctx) + ctx.loader.builtins['memory-test-system-prompt'] = SystemPrompt + ctx.loader.builtins['memory-test-tools'] = ToolRegistry + ctx.loader.builtins['memory-test-mcp-client'] = McpClient + }, + ) + await waitForTool(ctx, `mcp__${contract.serverName}__greet`) + }, 15_000) +}) diff --git a/apps/cli/tests/snapshots/queued-manual-compact/terminal.expected.txt b/apps/cli/tests/snapshots/queued-manual-compact/terminal.expected.txt new file mode 100644 index 0000000000..0df46a7018 --- /dev/null +++ b/apps/cli/tests/snapshots/queued-manual-compact/terminal.expected.txt @@ -0,0 +1,128 @@ +terminal 100x36 buffer=normal length=66 base=30 viewport=30 +lifecycle started=1 stopped=0 progress=inactive +title "Reply with exactly the word: — DSH TUI snapshot" +cursor hidden column=7 viewportRow=35 bufferRow=65 +buffer +0| " DEEPSEEK HARNESS" + style 1-8 fg=bright-magenta bold + style 10-16 bold +1| " Reply with exactly the word:" + style 1-28 dim +2| " main-session" + style 1-12 dim +3| +4| "Context · snapshot-seed" + style 0-22 dim +5| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +6| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +7| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +8| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +9| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +10| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +11| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +12| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +13| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +14| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +15| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +16| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +17| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +18| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +19| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-94 dim +20| +21| "You " + style 0-2 fg=bright-magenta bold underline +22| "Reply with exactly the word: ONE. No tools. " +23| +24| "Assistant " + style 0-8 fg=bright-magenta bold underline +25| "Reasoning " + style 0-8 dim italic +26| "The user wants me to reply with exactly the word \"ONE\" and use no tools. " + style 0-71 dim italic +27| "ONE " +28| "Model wait 0.0s · Completed 2026-07-21 12:00:00 " + style 0-46 dim +29| +30| "Keyboard shortcuts " + style 0-17 fg=bright-magenta bold +31| "Enter send • Shift/Alt+Enter newline • Up/Down prompt history " + style 0-60 dim +32| "Esc cancel turn • Ctrl+O cycle cards (collapse/expand/hide) • Ctrl+R toggle reasoning • Ctrl+L " + style 0-99 dim +33| "redraw " + style 0-5 dim +34| "Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit " + style 0-72 dim +35| " " +36| "/clear — Clear the transcript view (session history is unchanged) " + style 0-64 dim +37| "/compact — Compact older conversation history " + style 0-44 dim +38| "/exit — Exit after the active turn reaches idle " + style 0-46 dim +39| "/help — Show keyboard shortcuts and commands " + style 0-43 dim +40| "/model [[provider/]model] — Show or switch this session's model " + style 0-62 dim +41| "/palette — Show every color and attribute role this terminal renders " + style 0-67 dim +42| "/quit — Exit after the active turn reaches idle " + style 0-46 dim +43| "/reload — EXPERIMENTAL (dev): re-read loader config files and apply the diff (idle only) " + style 0-87 dim +44| "/resume — List this workspace's resumable sessions " + style 0-49 dim +45| "/status — Show session diagnostics, system prompt, and registered tools " + style 0-70 dim +46| "/skill: [instructions] — load a skill into the conversation " + style 0-64 dim +47| +48| "Context · snapshot-injector" + style 0-26 dim +49| "Injected while compaction was running. " + style 0-37 dim +50| +51| "… earlier context was compacted … " + style 0-32 dim +52| +53| "You " + style 0-2 fg=bright-magenta bold underline +54| "Reply with exactly the word: TWO. No tools. " +55| +56| "Compacted 2 history items (~387 tokens). " + style 0-39 dim +57| +58| "Assistant " + style 0-8 fg=bright-magenta bold underline +59| "Reasoning " + style 0-8 dim italic +60| "The user wants me to reply with exactly the word \"TWO\" and no tools. " + style 0-67 dim italic +61| "TWO " +62| "Model wait 0.0s · Completed 2026-07-21 12:00:00 " + style 0-46 dim +63| +64| "/workspace/project deepseek-v4-flash ↑2.9k ↓41 cache 49% 3% cont" + style 0-49 fg=bright-magenta bold + style 52-68 dim + style 71-90 dim + style 93-99 dim +65| " dsh ◍ " + style 1-3 fg=bright-magenta bold + style 5-6 dim + style 7-7 inverse diff --git a/apps/cli/tests/tui.snapshot.ts b/apps/cli/tests/tui.snapshot.ts index 078e4c191e..01adeb91b8 100644 --- a/apps/cli/tests/tui.snapshot.ts +++ b/apps/cli/tests/tui.snapshot.ts @@ -11,8 +11,12 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local' import WorkerCodeRuntime from '@deepseek-ai/dsh-code-runtime-worker' import CommandService from '@deepseek-ai/dsh-commands' +import * as CommandCompact from '@deepseek-ai/dsh-command-compact' +import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' +import type { SummarizationInput } from '@deepseek-ai/dsh-compact-basic/src/summarizer.ts' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' +import { createUserMessage } from '@deepseek-ai/dsh-llm' import * as ToolFs from '@deepseek-ai/dsh-tool-fs' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { installLlmReplay, parseSessionLog } from '@deepseek-ai/dsh-llm-replay' @@ -45,6 +49,8 @@ type ScenarioInteraction = 'skill-invocation-policy' interface Scenario { name: string + /** Replay fixture owned by an earlier scenario, for a derived presentation case. */ + fixture?: string composition: Composition expectedTools: string[] expectedEventCounts?: Record @@ -68,6 +74,13 @@ interface Scenario { spillMaxInlineBytes?: number /** Run scenario-specific terminal input instead of replaying recorded user prompts. */ interaction?: ScenarioInteraction + /** + * Mount a deterministic compaction backend plus `/compact`, then run the + * human command with a held summary while a prompt and injected context + * arrive. Proves queued input waits for the standalone bracket's durability + * checkpoint instead of racing the replacement. + */ + manualCompact?: boolean } const SCENARIOS: Scenario[] = [ @@ -80,6 +93,14 @@ const SCENARIOS: Scenario[] = [ leavePlanModeAfterFirstTurn: true, recorded: true, }, + { + name: 'queued-manual-compact', + fixture: 'multi-turn-conversation', + composition: 'native', + expectedTools: [], + recorded: false, + manualCompact: true, + }, { name: 'todo-plan', composition: 'native', @@ -149,6 +170,44 @@ function snapshotModeFromEnv(value: string | undefined): SnapshotMode { const MODE = snapshotModeFromEnv(process.env.DSH_SNAPSHOT) const observedScenarios = new Set() +const workerState = Reflect.get(globalThis, '__vitest_worker__') as + | { readonly config?: { readonly testNamePattern?: RegExp } } + | undefined +// Worker argv omits the parent CLI's `-t`; the serialized runner config is the +// authoritative distinction between a focused replay and the full suite. +const TEST_NAME_FILTERED = workerState?.config?.testNamePattern !== undefined + +/** + * Deterministic keyless summary that pauses so the scenario can submit a real + * prompt and inject context while manual compaction holds turn admission. + */ +class DeferredSnapshotCompactService extends BasicCompactService { + readonly summaryStarted = Promise.withResolvers() + readonly releaseSummary = Promise.withResolvers() + + override async summarize( + _input: SummarizationInput, + _agent: Agent, + signal?: AbortSignal, + ): Promise<{ summary: [{ type: 'text'; text: string }]; provider: string; model: string }> { + this.summaryStarted.resolve(undefined) + await this.releaseSummary.promise + signal?.throwIfAborted() + return { + summary: [{ type: 'text', text: 'Keyless manual compaction checkpoint.' }], + provider: 'snapshot', + model: 'snapshot-compactor', + } + } +} + +/** Seed between-turn model-visible history without inventing a loop execution. */ +function seedCompactableHistory(agent: Agent): void { + agent.inject(createUserMessage({ + content: [{ type: 'text', text: 'Older snapshot context. '.repeat(60) }], + source: { kind: 'plugin', plugin: 'snapshot-seed' }, + })) +} function snapshotDisplayPath(displayPath: string, cwd: string, displayCwd: string): string { const rel = relative(cwd, displayPath) @@ -161,10 +220,15 @@ function scenarioDir(scenario: Scenario): string { return join(SNAPSHOTS_DIR, scenario.name) } +/** Directory owning the replay fixture: the scenario's own, or the one it derives from. */ +function fixtureDir(scenario: Scenario): string { + return join(SNAPSHOTS_DIR, scenario.fixture ?? scenario.name) +} + function childFixturePaths(scenario: Scenario): string[] { return Array.from( { length: scenario.childSessions ?? 0 }, - (_, index) => join(scenarioDir(scenario), `session.${index + 1}.jsonl`), + (_, index) => join(fixtureDir(scenario), `session.${index + 1}.jsonl`), ) } @@ -206,6 +270,24 @@ async function settleTerminal(terminal: HeadlessTerminal): Promise { if (stable < 3) throw new Error('TUI frames did not quiesce within 200ms') } +/** Bound deterministic in-process coordination waits with actionable state. */ +async function snapshotDeadline( + operation: Promise, + detail: () => string, +): Promise { + let timer: ReturnType | undefined + try { + return await Promise.race([ + operation, + new Promise((_resolve, reject) => { + timer = setTimeout(() => { reject(new Error(detail())) }, 5_000) + }), + ]) + } finally { + if (timer !== undefined) clearTimeout(timer) + } +} + async function mountScenarioContext( scenario: Scenario, cwd: string, @@ -232,6 +314,9 @@ async function mountScenarioContext( skills: { local: { agentsHome: join(cwd, '.agents') } }, }) await ctx.plugin(TokenMeterService) + if (scenario.manualCompact === true) { + await ctx.plugin(DeferredSnapshotCompactService, { auto: false }) + } await ctx.plugin(LocalSubprocessService) await ctx.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) await ctx.plugin(SnapshotLocalFileSystem, { cwd: '/' }) @@ -249,6 +334,7 @@ async function mountScenarioContext( await ctx.plugin(ToolWorkflow) await ctx.plugin(ToolRalph) await ctx.plugin(CommandService) + if (scenario.manualCompact === true) await ctx.plugin(CommandCompact) if (scenario.enterPlanMode === true) { await ctx.plugin(PlanModeService, { section: 'Snapshot plan mode instructions.' }) } @@ -277,8 +363,7 @@ interface ScenarioResult { async function runScenario(scenario: Scenario): Promise { const clock = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 12, 0, 0).getTime()) - const dir = scenarioDir(scenario) - const fixtureFile = join(dir, 'session.jsonl') + const fixtureFile = join(fixtureDir(scenario), 'session.jsonl') const childFiles = childFixturePaths(scenario) const prompts = userPrompts(await readFile(fixtureFile, 'utf8')) if (scenario.interaction === undefined) { @@ -292,7 +377,7 @@ async function runScenario(scenario: Scenario): Promise { const terminal = new HeadlessTerminal(100, 36) try { if (scenario.seedWorkspace === true) { - const source = join(scenarioDir(scenario), 'workspace') + const source = join(fixtureDir(scenario), 'workspace') await cp(source, cwd, { recursive: true }) } ctx = await mountScenarioContext(scenario, cwd, displayCwd, fixtureFile, childFiles) @@ -308,6 +393,7 @@ async function runScenario(scenario: Scenario): Promise { agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, }) const agent: Agent = handle.agent + if (scenario.manualCompact === true) seedCompactableHistory(agent) controller = createTuiChat(ctx, { sessionId: 'main-session', theme: { color: true }, @@ -380,6 +466,14 @@ async function runScenario(scenario: Scenario): Promise { } let remainingPrompts = prompts + let queuedPrompt: string | undefined + let manualOrder: string[] | undefined + let manualCommandId: string | undefined + if (scenario.manualCompact === true) { + expect(prompts.length, 'queued manual compaction needs a second replayed prompt').toBeGreaterThanOrEqual(2) + queuedPrompt = prompts.at(-1) + remainingPrompts = prompts.slice(0, -1) + } if (scenario.enterPlanMode === true) { const firstPrompt = prompts[0]! terminal.send(`/plan ${firstPrompt}`) @@ -396,12 +490,86 @@ async function runScenario(scenario: Scenario): Promise { } for (const prompt of remainingPrompts) { + const admitted = agent.session.events.filter(event => + event.type === 'user/message' && event.data.source.kind === 'user').length terminal.send(prompt) terminal.send('\r') + await terminal.flush() + await expect.poll(() => agent.session.events.filter(event => + event.type === 'user/message' && event.data.source.kind === 'user').length).toBe(admitted + 1) await agent.whenIdle() await settleTerminal(terminal) } + if (scenario.manualCompact === true && queuedPrompt !== undefined) { + terminal.send('/help') + terminal.send('\r') + await settleTerminal(terminal) + expect(await terminal.snapshot({ includeScrollback: true })) + .toContain('/compact — Compact older conversation history') + + const compact = ctx.compact as DeferredSnapshotCompactService + const inbox: string[] = [] + manualOrder = [] + ctx.on('agent/inbox/enqueue', (subject, item) => { + if (subject === agent) inbox.push(`enqueue:${item.placement}:${item.id}`) + }) + ctx.on('agent/inbox/dequeue', (subject, message) => { + if (subject === agent) inbox.push(`dequeue:${message.id}`) + }) + ctx.on('session/event', (session, event) => { + if (session !== agent.session) return + if (event.type === 'command/run' && event.data.name === 'compact') { + manualCommandId = event.data.commandId + manualOrder?.push('command/run') + } + if (event.type === 'command/done' && event.data.commandId === manualCommandId) { + manualOrder?.push('command/done') + } + if (event.type.startsWith('compact/')) manualOrder?.push(event.type) + if (event.type === 'user/message' + && event.data.source.kind === 'plugin' + && event.data.source.plugin === 'compact') manualOrder?.push('checkpoint') + if (event.type === 'turn/start') manualOrder?.push(`turn/start:${event.data.trigger.kind}`) + }) + ctx.on('session/flush', (session) => { + if (session === agent.session) manualOrder?.push('flush') + }) + + terminal.send('/compact') + terminal.send('\r') + await terminal.flush() + await snapshotDeadline(compact.summaryStarted.promise, () => + `manual summary did not start; status=${agent.status}; tail=${ + agent.session.events.slice(-8).map(event => event.type).join(',') + }`) + + // Real keystrokes: the prompt keeps its ordinary queue identity while + // admission is reserved, and an injection appends immediately. + terminal.send(queuedPrompt) + terminal.send('\r') + await terminal.flush() + await expect.poll(() => inbox.length).toBe(1) + agent.inject(createUserMessage({ + content: [{ type: 'text', text: 'Injected while compaction was running.' }], + source: { kind: 'plugin', plugin: 'snapshot-injector' }, + })) + expect(inbox[0]).toMatch(/^enqueue:queued:/u) + expect(agent.status).toBe('idle') + expect(agent.session.events.some(event => event.type === 'user/message' + && event.data.source.kind === 'user' + && event.data.content.some(block => block.type === 'text' && block.text === queuedPrompt))).toBe(false) + + const idle = agent.whenIdle() + compact.releaseSummary.resolve(undefined) + await snapshotDeadline(idle, () => + `manual compaction did not reach idle; status=${agent.status}; order=${manualOrder?.join(',') ?? ''}; tail=${ + agent.session.events.slice(-12).map(event => event.type).join(',') + }`) + await settleTerminal(terminal) + expect(inbox).toEqual([inbox[0], `dequeue:${inbox[0]?.slice('enqueue:queued:'.length) ?? ''}`]) + } + const events: SessionEvent[] = [...agent.session.events] const firstHeader = events.find(event => event.type === 'request/header') expect(firstHeader?.type === 'request/header' && firstHeader.data.header.system) @@ -437,6 +605,87 @@ async function runScenario(scenario: Scenario): Promise { expect(events.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin').map(event => (event.data as { content: unknown }).content)) .toContainEqual([{ type: 'text', text: 'The user switched this session back to the default mode.' }]) } + if (scenario.manualCompact === true) { + const compactStart = events.find(event => event.type === 'compact/start') + const compactSummary = events.find(event => event.type === 'compact/summary') + const compactCheckpoint = events.find(event => event.type === 'user/message' + && event.data.source.kind === 'plugin' && event.data.source.plugin === 'compact') + const injectedEvent = events.find(event => event.type === 'user/message' + && event.data.source.kind === 'plugin' && event.data.source.plugin === 'snapshot-injector') + const compactEnd = events.find(event => event.type === 'compact/end') + expect(compactStart?.data.turn).toBeNull() + expect(compactEnd?.data.turn).toBeNull() + expect(events.filter(event => event.type === 'compact/summary')).toHaveLength(1) + if (compactStart === undefined || compactSummary === undefined + || compactCheckpoint === undefined || injectedEvent === undefined + || compactEnd === undefined) { + throw new Error('manual compaction snapshot is missing its durable marker, summary, checkpoint, or injection') + } + // The markers are time points, not an exclusive container: unrelated + // idle injection is allowed between them while the selected span stays stable. + expect(compactStart.seq).toBeLessThan(injectedEvent.seq) + expect(injectedEvent.seq).toBeLessThan(compactSummary.seq) + expect(compactSummary.seq).toBeLessThan(compactCheckpoint.seq) + expect(compactCheckpoint.seq).toBeLessThan(compactEnd.seq) + + const manualTimeline = manualOrder ?? [] + const commandRunIndex = manualTimeline.indexOf('command/run') + const compactStartIndex = manualTimeline.indexOf('compact/start') + const compactEndIndex = manualTimeline.indexOf('compact/end') + const firstFlushIndex = manualTimeline.indexOf('flush') + const queuedTurnIndex = manualTimeline.indexOf('turn/start:message') + const commandDoneIndex = manualTimeline.indexOf('command/done') + expect(manualTimeline.filter(item => item === 'command/run')).toHaveLength(1) + expect(manualTimeline.filter(item => item === 'command/done')).toHaveLength(1) + expect(compactStartIndex).toBeGreaterThan(commandRunIndex) + expect(compactEndIndex).toBeGreaterThan(compactStartIndex) + expect(firstFlushIndex).toBeGreaterThan(compactEndIndex) + expect(queuedTurnIndex).toBeGreaterThan(firstFlushIndex) + expect(commandDoneIndex).toBeGreaterThan(firstFlushIndex) + + const commandRun = events.find(event => event.type === 'command/run' + && event.data.name === 'compact') + const commandRunId = commandRun?.type === 'command/run' + ? commandRun.data.commandId + : undefined + const commandDone = events.find(event => event.type === 'command/done' + && event.data.commandId === commandRunId) + expect(commandRun?.type === 'command/run' && commandRun.data).toEqual({ + commandId: commandRunId, + name: 'compact', + args: '', + source: { kind: 'user' }, + }) + expect(commandDone?.type === 'command/done' && commandDone.data).toEqual({ + commandId: commandRunId, + kind: 'success', + text: 'Compacted 2 history items (~387 tokens).', + }) + expect(commandRun !== undefined && commandRun.seq < compactStart.seq).toBe(true) + expect(commandDone !== undefined && commandDone.seq > compactEnd.seq).toBe(true) + expect(agent.session.surface.nodes).not.toContain(commandRun?.seq) + expect(agent.session.surface.nodes).not.toContain(commandDone?.seq) + + // The command line itself never becomes a prompt. + expect(events.some(event => event.type === 'user/message' + && event.data.source.kind === 'user' + && event.data.content.some(block => block.type === 'text' && block.text.trim() === '/compact'))).toBe(false) + const derived = agent.session.deriveMessages().map(message => message.content + .map(block => block.type === 'text' ? block.text : '') + .join('')) + const checkpoint = derived.findIndex(text => text.includes('Keyless manual compaction checkpoint.')) + const injected = derived.findIndex(text => text.includes('Injected while compaction was running.')) + const queued = derived.findIndex(text => text === queuedPrompt) + expect(checkpoint).toBe(0) + expect(injected).toBeGreaterThan(checkpoint) + expect(queued).toBeGreaterThan(injected) + expect(derived).not.toContain('/compact') + expect(derived).not.toContain('Compacted 2 history items (~387 tokens).') + expect(derived.filter(text => text.includes('Injected while compaction was running.'))).toHaveLength(1) + expect(compactSummary.data.shadowedSeqs).not.toContain(injectedEvent.seq) + const queuedTurn = events.findLast(event => event.type === 'turn/start') + expect(queuedTurn !== undefined && compactEnd.seq < queuedTurn.seq).toBe(true) + } if (scenario.spillMaxInlineBytes !== undefined) { // The REAL pipeline ran (tools execute on replay too): the durable // dispatch copy is bounded to a preview + locator under the run cwd, @@ -514,7 +763,23 @@ describe('TUI recorded-session terminal snapshots', () => { }) afterAll(async () => { - expect([...observedScenarios].sort()).toEqual(SCENARIOS.map(scenario => scenario.name).sort()) + const scenarioNames = SCENARIOS.map(scenario => scenario.name).sort() + const observedNames = [...observedScenarios].sort() + if (TEST_NAME_FILTERED) { + expect(observedNames).not.toHaveLength(0) + expect(scenarioNames).toEqual(expect.arrayContaining(observedNames)) + } else { + expect(observedNames).toEqual(scenarioNames) + } + for (const [index, scenario] of SCENARIOS.entries()) { + if (scenario.fixture === undefined) continue + const sourceIndex = SCENARIOS.findIndex(candidate => candidate.name === scenario.fixture) + expect(sourceIndex, `${scenario.name} fixture source ${scenario.fixture} must exist`).toBeGreaterThanOrEqual(0) + expect(sourceIndex, `${scenario.name} fixture source must precede it`).toBeLessThan(index) + const source = SCENARIOS[sourceIndex] + expect(source?.fixture, `${scenario.name} fixture source must own its replay files`).toBeUndefined() + expect(source?.recorded, `${scenario.name} fixture source must be recordable`).toBe(true) + } const directories = (await readdir(SNAPSHOTS_DIR, { withFileTypes: true })) .filter(entry => entry.isDirectory()) .map(entry => entry.name) @@ -522,14 +787,14 @@ afterAll(async () => { expect(directories).toEqual(SCENARIOS.map(scenario => scenario.name).sort()) for (const scenario of SCENARIOS) { const expected = [ - 'session.jsonl', + ...scenario.fixture === undefined ? ['session.jsonl'] : [], 'terminal.expected.txt', - ...scenario.seedWorkspace === true ? ['workspace'] : [], + ...scenario.seedWorkspace === true && scenario.fixture === undefined ? ['workspace'] : [], ...Array.from({ length: scenario.childSessions ?? 0 }, (_, index) => `session.${index + 1}.jsonl`), ].sort() expect((await readdir(scenarioDir(scenario))).sort()).toEqual(expected) for (const fixture of ['session.jsonl', ...childFixturePaths(scenario).map(path => basename(path))]) { - const content = await readFile(join(scenarioDir(scenario), fixture), 'utf8') + const content = await readFile(join(fixtureDir(scenario), fixture), 'utf8') expect(scrubRequestHeaders(content), `${scenario.name}/${fixture} carries request-header bulk`).toBe(content) } } diff --git a/apps/web/tests/access-confirmation.e2e.ts b/apps/web/tests/access-confirmation.e2e.ts index d4669bc142..fae329362b 100644 --- a/apps/web/tests/access-confirmation.e2e.ts +++ b/apps/web/tests/access-confirmation.e2e.ts @@ -2,6 +2,7 @@ // the same locale-aware, in-page risk confirmation. Zero model calls: the // scenario boots the shipped Web composition and exercises the real // permission projection, client command path, HTTP RPC, and pushed update. +import { mkdirSync } from 'node:fs' import { fileURLToPath } from 'node:url' import { join } from 'node:path' import type { Browser, Page } from 'playwright' @@ -19,13 +20,16 @@ import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts' * boots; this scenario deliberately keeps zh, so the localized picker * copy is the anchor set). */ -async function connectFreshWorkspaceZh(page: Page, name = 'workspace'): Promise { +async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise { + mkdirSync(join(root, name), { recursive: true }) await page.getByRole('button', { name: '选择工作区' }).click() - await page.getByRole('menuitem', { name: '新建工作区' }).click() - const dialog = page.getByRole('dialog', { name: '新建工作区' }) + const dialog = page.getByRole('dialog', { name: '选择工作区目录' }) await dialog.waitFor({ timeout: 10_000 }) - await dialog.getByLabel('新工作区名称').fill(name) - await dialog.getByRole('button', { name: '创建工作区' }).click() + await dialog.getByRole('button', { name: '编辑路径' }).click() + const pathInput = dialog.getByRole('textbox', { name: '编辑路径' }) + await pathInput.fill(join(root, name)) + await pathInput.press('Enter') + await dialog.getByRole('button', { name: '打开', exact: true }).click() await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]') .waitFor({ timeout: 15_000 }) } @@ -53,7 +57,7 @@ describe('web e2e: Full access confirmation', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspaceZh(page) + await connectFreshWorkspaceZh(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/approval-composer.e2e.ts b/apps/web/tests/approval-composer.e2e.ts index b66277e0b2..7a2a684765 100644 --- a/apps/web/tests/approval-composer.e2e.ts +++ b/apps/web/tests/approval-composer.e2e.ts @@ -61,7 +61,7 @@ describe('web e2e: approval takeover keeps its actions reachable', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/built-boot.snapshot.ts b/apps/web/tests/built-boot.snapshot.ts index 6fa5aec1ab..d2f6d913dd 100644 --- a/apps/web/tests/built-boot.snapshot.ts +++ b/apps/web/tests/built-boot.snapshot.ts @@ -112,11 +112,19 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn }, { timeout: 10_000 }) // The write/edit turns render a real diff card through the assembled graph - // (the keyed FileMutationRow + DiffBlock), not just the fixture's raw text. - // The write turn's `hello fixture\n` proves the terminator rule end to end: a - // trailing newline terminates its line, so the footer reads `+1` (not a - // phantom `+2`) and one distinct file. The `+ ` prefix is a CSS ::before, so - // it is absent from textContent — assert on the line body and the footer. + // (the keyed FileMutationRow composing ToolRow + DiffBlock), not just the + // fixture's raw text. The card is collapsed by default, so expand each edit/ + // write row first. The write turn's `hello fixture\n` proves the terminator + // rule end to end: a trailing newline terminates its line, so the footer reads + // `+1` (not a phantom `+2`) and one distinct file. The `+ ` prefix is a CSS + // ::before, so it is absent from textContent — assert on the line body and the + // footer. + const mutationRows = [...document.querySelectorAll('[data-variant="write"],[data-variant="edit"]')] + expect(mutationRows.length).toBeGreaterThan(0) + for (const row of mutationRows) { + const toggle = row.querySelector('[data-expandable]') + if (toggle !== null) act(() => { fireEvent.click(toggle) }) + } const diffCards = [...document.querySelectorAll('[data-diff]')] expect(diffCards.length).toBeGreaterThan(0) const footers = diffCards.map(card => card.textContent ?? '') @@ -125,13 +133,20 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn // The web render intent reaches the assembled boot graph: the fixture's // web_search / web_fetch turns render their keyed WebRow cards, proving the // registration, wire projection, and card rendering survive the real bundle - // path (not just the per-package src benches). The selector pins the KEYED - // WebRow (its own `data-variant="web"` wrapper), not the `[data-web]` attribute - // WebBlock draws — the generic fallback renders the same WebBlock, so a silent - // keyed-registration failure would still satisfy a bare `[data-web]` check. + // path (not just the per-package src benches). WebRow composes ToolRow, so the + // card is collapsed behind the row; the keyed row is pinned by its `data-tool` + // (ToolRow sets it from the wire tool name). + const webSearchRow = await waitFor(() => { + const row = document.querySelector('[data-tool="web_search"]') + expect(row).not.toBeNull() + expect(document.querySelector('[data-tool="web_fetch"]')).not.toBeNull() + return row! + }, { timeout: 10_000 }) + // Expand the web_search row to prove its WebBlock card renders end to end. + const webToggle = webSearchRow.querySelector('[data-expandable]') + if (webToggle !== null) act(() => { fireEvent.click(webToggle) }) await waitFor(() => { - expect(document.querySelector('[data-variant="web"][data-tool="web_search"]')).not.toBeNull() - expect(document.querySelector('[data-variant="web"][data-tool="web_fetch"]')).not.toBeNull() + expect(webSearchRow.querySelector('[data-web]')).not.toBeNull() }, { timeout: 10_000 }) // Every bundle injected its plugin-owned style tag (the loader's CSS path). diff --git a/apps/web/tests/code-mode-round.e2e.ts b/apps/web/tests/code-mode-round.e2e.ts index 78f27acaca..6a0379de94 100644 --- a/apps/web/tests/code-mode-round.e2e.ts +++ b/apps/web/tests/code-mode-round.e2e.ts @@ -49,7 +49,7 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => { await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) // Fresh world: connect a Workspace so the composer scenarios start live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/composer-draft-scroll.e2e.ts b/apps/web/tests/composer-draft-scroll.e2e.ts index 34c552401e..e7dc1da238 100644 --- a/apps/web/tests/composer-draft-scroll.e2e.ts +++ b/apps/web/tests/composer-draft-scroll.e2e.ts @@ -232,7 +232,7 @@ describe('web e2e: composer draft scrolling', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page, 'composer-draft-scroll') + await connectFreshWorkspace(page, scaffold.workspaceCwd, 'composer-draft-scroll') await page.locator('textarea:enabled').first().fill(DRAFT) }, 180_000) diff --git a/apps/web/tests/cordis-tool-round.e2e.ts b/apps/web/tests/cordis-tool-round.e2e.ts index 66bc9c6900..a806fcaa67 100644 --- a/apps/web/tests/cordis-tool-round.e2e.ts +++ b/apps/web/tests/cordis-tool-round.e2e.ts @@ -66,7 +66,7 @@ describe('web e2e: Cordis tools use the generic row variants', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/core-web-profile.snapshot.ts b/apps/web/tests/core-web-profile.snapshot.ts new file mode 100644 index 0000000000..58f2a34858 --- /dev/null +++ b/apps/web/tests/core-web-profile.snapshot.ts @@ -0,0 +1,84 @@ +import { writeFile } from 'node:fs/promises' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { afterAll, beforeAll, describe, expect, it } from 'vitest' +import type { AgentHandle } from '@deepseek-ai/dsh-agent' +import { CallId } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' +import { launchWebScaffold, type WebScaffold } from './scaffold.ts' + +const CORE_WEB_OVERLAY = fileURLToPath(new URL('../../cli/config/core-web.cordis.yml', import.meta.url)) + +describe('core Web profile', () => { + let scaffold: WebScaffold + let agentHandle: AgentHandle + + beforeAll(async () => { + scaffold = await launchWebScaffold({ + extraOverlayPath: CORE_WEB_OVERLAY, + toolsMode: 'native', + }) + agentHandle = await scaffold.ctx.agents.create({ + sessionId: SessionId('core-web-profile-smoke'), + meta: { cwd: scaffold.workspaceCwd }, + agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, + }) + }) + + afterAll(async () => { + const failures: unknown[] = [] + await agentHandle?.dispose().catch((error: unknown) => failures.push(error)) + await scaffold?.close().catch((error: unknown) => failures.push(error)) + if (failures.length === 1) throw failures[0] + if (failures.length > 1) throw new AggregateError(failures, 'core Web profile smoke teardown failed') + }) + + it('boots and executes both tools through the shipped Web composition', async () => { + const seedPath = join(scaffold.workspaceCwd, 'profile-smoke.txt') + await writeFile(seedPath, 'CORE_WEB_EDITOR_OK\n') + const signal = new AbortController().signal + const bash = await scaffold.ctx.tools.execute({ + signal, + callId: CallId('core-web-bash-smoke'), + name: 'bash', + arguments: { command: "printf 'CORE_WEB_BASH_OK\\n'" }, + agent: agentHandle.agent, + }) + const editor = await scaffold.ctx.tools.execute({ + signal, + callId: CallId('core-web-editor-smoke'), + name: 'str_replace_editor', + arguments: { command: 'view', path: seedPath }, + agent: agentHandle.agent, + }) + + const text = (result: typeof bash): string => result.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') + .replaceAll(scaffold.workspaceCwd, '{{cwd}}') + .trimEnd() + + expect({ + tools: scaffold.ctx.tools.schemas().map(tool => tool.name), + bash: text(bash), + editor: text(editor), + }).toMatchInlineSnapshot(` + { + "bash": "CORE_WEB_BASH_OK", + "editor": "Here's the content of {{cwd}}/profile-smoke.txt with line numbers (which has a total of 2 lines): + 1 CORE_WEB_EDITOR_OK + 2", + "tools": [ + "bash", + "str_replace_editor", + ], + } + `) + + const entries = [...scaffold.ctx.loader.entries()] + expect(entries.find(entry => entry.options.id === 'persistent-bash')?.fiber).toBeDefined() + expect(entries.find(entry => entry.options.id === 'pty-local')?.fiber).toBeDefined() + expect(entries.find(entry => entry.options.id === 'str-replace-editor')?.fiber).toBeDefined() + }) +}) diff --git a/apps/web/tests/details-session-lifecycle.e2e.ts b/apps/web/tests/details-session-lifecycle.e2e.ts index ce97cfb2a1..cb6c9ba914 100644 --- a/apps/web/tests/details-session-lifecycle.e2e.ts +++ b/apps/web/tests/details-session-lifecycle.e2e.ts @@ -80,7 +80,7 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await appFrame(page).waitFor({ timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/lifecycle-chrome.e2e.ts b/apps/web/tests/lifecycle-chrome.e2e.ts index 97ffefccf7..e285b0f0ac 100644 --- a/apps/web/tests/lifecycle-chrome.e2e.ts +++ b/apps/web/tests/lifecycle-chrome.e2e.ts @@ -50,7 +50,7 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', () await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) // Fresh world: connect a Workspace so the composer scenarios start live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { @@ -93,7 +93,7 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', () try { await activePage.goto(activeScaffold.baseUrl, { waitUntil: 'load' }) await activePage.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(activePage) + await connectFreshWorkspace(activePage, activeScaffold.workspaceCwd) const input = activePage.locator('textarea').first() await activePage.getByRole('button', { name: 'Commands' }).click() const menu = activePage.getByRole('listbox', { name: 'Trigger suggestions' }) @@ -172,10 +172,10 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', () await expect.poll(() => page.getByText('1 session', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1) await expect.poll(() => page.locator('[role="treeitem"][aria-selected="true"]').count(), { timeout: 10_000 }).toBe(1) await expect.poll(() => page.getByText('LIGHTHOUSE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1) - // Host: the session's durable header cwd is the workspace flow's - // create-by-name target (/workspace, the composer's - // default draft name) — the proof the send went through workspace - // materialization rather than a bare default-cwd session. + // Host: the session's durable header cwd is the folder the workspace + // flow created and adopted (/workspace) — the proof the + // send went through workspace materialization rather than a bare + // default-cwd session. const cwds = scaffold.ctx.sessions.list().map(session => session.header.cwd) expect(cwds).toEqual([join(scaffold.workspaceCwd, 'workspace')]) const turnEnds = sessionEvents.filter(e => e.type === 'turn/end') diff --git a/apps/web/tests/live-interactions.e2e.ts b/apps/web/tests/live-interactions.e2e.ts index 1707a6478f..186c71be11 100644 --- a/apps/web/tests/live-interactions.e2e.ts +++ b/apps/web/tests/live-interactions.e2e.ts @@ -96,7 +96,7 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => { await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) // Fresh world: connect a Workspace so the composer scenarios start live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) } /** diff --git a/apps/web/tests/navigation-panes.e2e.ts b/apps/web/tests/navigation-panes.e2e.ts index 8ffeb25ad1..87e19a6915 100644 --- a/apps/web/tests/navigation-panes.e2e.ts +++ b/apps/web/tests/navigation-panes.e2e.ts @@ -43,7 +43,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { beforeAll(async () => { scaffold = await launchWebScaffold({}) - // The workspace-aware flow runs sessions in /workspace; + // The workspace-aware flow runs sessions in /workspace; // the read targets must live in that session cwd (pre-creation is safe: // create-by-name adopts an existing directory). const sessionCwd = join(scaffold.workspaceCwd, 'workspace') diff --git a/apps/web/tests/permission-policy-context.e2e.ts b/apps/web/tests/permission-policy-context.e2e.ts index 3dec5d1784..867685678f 100644 --- a/apps/web/tests/permission-policy-context.e2e.ts +++ b/apps/web/tests/permission-policy-context.e2e.ts @@ -79,7 +79,7 @@ describe('web e2e: current sandbox policy reaches the model before tools', () => tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/pin-browse-picker.overlay.yml b/apps/web/tests/pin-browse-picker.overlay.yml new file mode 100644 index 0000000000..266c35e94b --- /dev/null +++ b/apps/web/tests/pin-browse-picker.overlay.yml @@ -0,0 +1,11 @@ +# Loader overlay for the W5 real-host smoke (`dsh web --config`): pin the +# in-browser directory picker. The shipped row is `-auto`, which resolves to +# the native OS chooser on a loopback bind with a local display — an +# interaction a Playwright page cannot drive, so the resolved backend would +# otherwise decide whether the smoke passes. The disable+insert pair mirrors +# apps/web/tests/scaffold.ts. +- id: directory-picker + disabled: true +- insert: + - id: directory-picker-browse + name: '@deepseek-ai/dsh-host-directory-picker-browse' diff --git a/apps/web/tests/plan-review.e2e.ts b/apps/web/tests/plan-review.e2e.ts index 28272777fb..e37e3954ab 100644 --- a/apps/web/tests/plan-review.e2e.ts +++ b/apps/web/tests/plan-review.e2e.ts @@ -54,7 +54,7 @@ describe('web e2e: plan review takeover round trip', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/question-composer.e2e.ts b/apps/web/tests/question-composer.e2e.ts index ac4be25299..37f6964c73 100644 --- a/apps/web/tests/question-composer.e2e.ts +++ b/apps/web/tests/question-composer.e2e.ts @@ -49,7 +49,7 @@ describe('web e2e: resident question composer round trip', () => { await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) // Fresh world: connect a Workspace so the composer scenarios start live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/queue-actions.e2e.ts b/apps/web/tests/queue-actions.e2e.ts index 069ef398d9..57b8afb4ff 100644 --- a/apps/web/tests/queue-actions.e2e.ts +++ b/apps/web/tests/queue-actions.e2e.ts @@ -68,7 +68,7 @@ describe('web e2e: queue row actions', () => { const tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) onTestFailed(() => saveFailureShot(page, 'web-e2e-queue-actions')) const input = page.locator('textarea').first() diff --git a/apps/web/tests/replay-round-trip.e2e.ts b/apps/web/tests/replay-round-trip.e2e.ts index 01544ad71f..cf1121599b 100644 --- a/apps/web/tests/replay-round-trip.e2e.ts +++ b/apps/web/tests/replay-round-trip.e2e.ts @@ -48,7 +48,7 @@ describe('web e2e: fresh round trip through the real assembly', () => { await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) // Fresh world: connect a Workspace so the composer scenarios start live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/scaffold.ts b/apps/web/tests/scaffold.ts index 49a6b0709e..ea39e2d29b 100644 --- a/apps/web/tests/scaffold.ts +++ b/apps/web/tests/scaffold.ts @@ -33,6 +33,7 @@ import Loader from '@cordisjs/plugin-loader' import Include, { type PatchOptions } from '@cordisjs/plugin-include' import { scrubRequestHeaders } from '@deepseek-ai/dsh-acp-snapshot' import { assertEntriesLoaded, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot' +import { dshHomePath } from '@deepseek-ai/dsh-paths' import { WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_SETTINGS_NAMESPACE, WELCOME_NOTICE_VERSION, } from '@deepseek-ai/dsh-client-ui-settings-general' @@ -105,6 +106,12 @@ export interface WebScaffold { /** Options for {@link launchWebScaffold}. */ export interface LaunchOptions { + /** + * Optional product overlay applied after the shipped Web surface and before + * the scaffold's hermetic test patches, matching AppCLIEntry's `--config` + * ordering. + */ + extraOverlayPath?: string /** * Replay fixture (session.jsonl) served by the inserted dsh-llm-replay row * in replay/refresh modes; ignored in record mode (the real adapter @@ -214,8 +221,12 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise { await waitFor(() => { expect(document.querySelector('[data-sample="bash-global"]')).not.toBeNull() }, { timeout: 10_000 }) - // The grep turn's keyed SearchRow renders the card resident: wait for it. + // The grep turn's keyed SearchRow composes ToolRow: the card is collapsed + // by default, so wait for the summary row, then expand it to reach the card. await waitFor(() => { const tools = [...document.querySelectorAll('[data-tool]')].map(el => el.getAttribute('data-tool')) expect(tools, `tools present: ${tools.join(', ')}`).toContain('grep') }, { timeout: 10_000 }) - // `data-tool` sits on the summary row; the card and recovery footer are its - // siblings inside the SearchRow wrapper, so shape the wrapper (its parent). - const grepRow = document.querySelector('[data-tool="grep"]')!.parentElement! + // `data-tool` sits on the ToolRow root; the collapsed row is the expand + // toggle. Click it so the card and its recovery footer mount, then shape the + // whole row (the card lives inside ToolRow's body wrapper). + const grepRow = document.querySelector('[data-tool="grep"]')! + act(() => { fireEvent.click(grepRow.querySelector('[data-expandable]') ?? grepRow) }) + await waitFor(() => { + expect(grepRow.querySelector('[data-search]')).not.toBeNull() + }, { timeout: 10_000 }) const shape = cardShape(grepRow) if (refreshing) { mkdirSync(dirname(EXPECTED), { recursive: true }) diff --git a/apps/web/tests/seeded-history.e2e.ts b/apps/web/tests/seeded-history.e2e.ts index 56d911419a..9acb0fa136 100644 --- a/apps/web/tests/seeded-history.e2e.ts +++ b/apps/web/tests/seeded-history.e2e.ts @@ -127,7 +127,7 @@ describe('web e2e: seeded history renders through cold resume', () => { beforeAll(async () => { scaffold = await launchWebScaffold({}) - // The workspace-aware flow runs sessions in /workspace + // The workspace-aware flow runs sessions in /workspace // (the composer's default draft name); the read-tool targets must live in // that session cwd. Pre-creating the directory is safe: create-by-name // adopts an existing directory. diff --git a/apps/web/tests/skill-invocation-policy.e2e.ts b/apps/web/tests/skill-invocation-policy.e2e.ts index cb252c724b..143bc0d4db 100644 --- a/apps/web/tests/skill-invocation-policy.e2e.ts +++ b/apps/web/tests/skill-invocation-policy.e2e.ts @@ -84,7 +84,7 @@ describe('web e2e: skill invocation policy through the real host', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/smoke-real.e2e.ts b/apps/web/tests/smoke-real.e2e.ts index e19d7cfab1..4a104724fb 100644 --- a/apps/web/tests/smoke-real.e2e.ts +++ b/apps/web/tests/smoke-real.e2e.ts @@ -20,7 +20,7 @@ import { createServer } from 'node:http' import { createRequire } from 'node:module' import { tmpdir } from 'node:os' import { join } from 'node:path' -import { pathToFileURL } from 'node:url' +import { fileURLToPath, pathToFileURL } from 'node:url' import type { Browser, Page } from 'playwright' import { chromium } from 'playwright' import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' @@ -472,7 +472,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href child = spawn( process.execPath, - ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', String(port)], + [ + '--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', String(port), + // Pin the in-browser picker: the shipped `-auto` row would resolve to + // the native OS chooser on this bind, and no page can drive that. + '--config', fileURLToPath(new URL('./pin-browse-picker.overlay.yml', import.meta.url)), + ], { cwd: sessionsDir, env: { @@ -513,8 +518,18 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke it('2+3 empty-state first send completes a real model round', async () => { onTestFailed(() => saveFailureShot(page, 'w5-first-round')) + // This scenario spawns its own server against a fresh $DSH_HOME, so the + // first-run welcome notice is unacknowledged and its overlay owns pointer + // events (the shared scaffold acknowledges it before boot instead). The + // notice is anchored structurally, not by its copy: this spec sits in the + // client TypeScript program, which does not reference the package that + // owns the strings. + const welcome = page.locator('[class*="onboardingOverlay"]') + await welcome.waitFor({ timeout: 15_000 }) + await welcome.getByRole('button').click() + await welcome.waitFor({ state: 'detached', timeout: 15_000 }) // Fresh world: connect a Workspace so the composer starts live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, sessionsDir) const input = page.locator('textarea').first() await input.waitFor({ timeout: 10_000 }) await screen(page, '02-empty-state') diff --git a/apps/web/tests/snapshots/code-mode-round/ui.expected.md b/apps/web/tests/snapshots/code-mode-round/ui.expected.md index 5095ea278d..183bd366a0 100644 --- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md +++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md @@ -22,8 +22,10 @@ - img - text: Code Run bash echo and catch missing file read - img -- text: Bash Echo CODE_ROUND_OK 失败 Read -- button "missing.txt" +- text: Bash Echo CODE_ROUND_OK Failed +- 'button "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"': + - img + - text: "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found" - button "Think The program ran successfully. Let me now reply DONE as instructed.": - img - img diff --git a/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md index 47ba98cf05..1da9b9a45e 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md @@ -1,6 +1,7 @@ - listbox "Trigger suggestions": - text: Commands - - option "goal set or view the goal for a long-running task" [selected] + - option "compact Compact older conversation history" [selected] + - option "goal set or view the goal for a long-running task" - option "permission Switch the permission preset (sandbox mode + approval policy)" - option "plan Enter or leave plan mode" - option "model Select the model for this conversation" diff --git a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md index dc4cbca241..7b6432ef87 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md @@ -7,7 +7,7 @@ - text: Workspaces - button "Group by": - img -- button "Create workspace": +- button "Add workspace": - img - button "Search sessions": - img diff --git a/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md index 7f62e80503..4aad3112e1 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md @@ -7,7 +7,7 @@ - text: Workspaces - button "Group by": - img -- button "Create workspace": +- button "Add workspace": - img - button "Search sessions": - img diff --git a/apps/web/tests/snapshots/message-actions/ui.expected.md b/apps/web/tests/snapshots/message-actions/ui.expected.md index 34ce19a69f..613e9a3605 100644 --- a/apps/web/tests/snapshots/message-actions/ui.expected.md +++ b/apps/web/tests/snapshots/message-actions/ui.expected.md @@ -14,12 +14,16 @@ - img - img - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel. -- img -- text: Read -- button "a.txt" -- img -- text: Read -- button "b.txt" +- button "Read a.txt": + - img + - img + - text: Read + - button "a.txt" +- button "Read b.txt": + - img + - img + - text: Read + - button "b.txt" - button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.": - img - img diff --git a/apps/web/tests/snapshots/search-card/grep-card.expected.txt b/apps/web/tests/snapshots/search-card/grep-card.expected.txt index 3d0efb3ecd..ce95519f0b 100644 --- a/apps/web/tests/snapshots/search-card/grep-card.expected.txt +++ b/apps/web/tests/snapshots/search-card/grep-card.expected.txt @@ -5,7 +5,23 @@ file=packages/client/ui-conversation/src/client/toolviews/search-row.tsx4 line=16: export const DEFAULT_SEARCH_MAX_LINES = 16 line=138: export function SearchBlock(props: SearchBlockProps) { line=141: const [collapsed, setCollapsed] = useState>(() => new Set()) -line=73: const search = searchCardModel(block) -line=90: -line=113: ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep' }, SearchRow) -expand=… 其余 4 行 \ No newline at end of file +line=35: const search = searchCardModel(block) +line=52: search={search} +line=73: ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow) +expand=… 其余 4 行 +recovery=Found 9 of 42 matches + +packages/client/ui-primitives/src/SearchBlock.tsx +Line 16: export const DEFAULT_SEARCH_MAX_LINES = 16 +Line 138: export function SearchBlock(props: SearchBlockProps) { +Line 141: const [collapsed, setCollapsed] = useState>(() => new Set()) +packages/client/ui-conversation/src/client/contract/search-card-model.ts +Line 24: export const CHAT_SEARCH_MAX_LINES = 8 +Line 60: export function searchCardModel(block: ToolCallBlock): SearchCardModel | null { +packages/client/ui-conversation/src/client/toolviews/search-row.tsx +Line 33: export function SearchRow({ toolName, block, inspect, t }: SearchRowProps) { +Line 35: const search = searchCardModel(block) +Line 52: search={search} +Line 73: ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow) + +(Full grep result stored at: fixture://spill/grep-66. Read it to see every match.) \ No newline at end of file diff --git a/apps/web/tests/snapshots/seeded-history/command-row.expected.md b/apps/web/tests/snapshots/seeded-history/command-row.expected.md index bcbac2622e..0173726c38 100644 --- a/apps/web/tests/snapshots/seeded-history/command-row.expected.md +++ b/apps/web/tests/snapshots/seeded-history/command-row.expected.md @@ -13,12 +13,16 @@ - img - img - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel. -- img -- text: Read -- button "a.txt" -- img -- text: Read -- button "b.txt" +- button "Read a.txt": + - img + - img + - text: Read + - button "a.txt" +- button "Read b.txt": + - img + - img + - text: Read + - button "b.txt" - button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.": - img - img diff --git a/apps/web/tests/snapshots/seeded-history/ui.expected.md b/apps/web/tests/snapshots/seeded-history/ui.expected.md index e29d1e8b30..0062b6cfab 100644 --- a/apps/web/tests/snapshots/seeded-history/ui.expected.md +++ b/apps/web/tests/snapshots/seeded-history/ui.expected.md @@ -13,12 +13,16 @@ - img - img - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel. -- img -- text: Read -- button "a.txt" -- img -- text: Read -- button "b.txt" +- button "Read a.txt": + - img + - img + - text: Read + - button "a.txt" +- button "Read b.txt": + - img + - img + - text: Read + - button "b.txt" - button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.": - img - img diff --git a/apps/web/tests/snapshots/steering/mid-steer.expected.md b/apps/web/tests/snapshots/steering/mid-steer.expected.md index b41f6baae2..27b40ef442 100644 --- a/apps/web/tests/snapshots/steering/mid-steer.expected.md +++ b/apps/web/tests/snapshots/steering/mid-steer.expected.md @@ -17,6 +17,7 @@ - img - img - text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that. +- text: Running - button "Ask question waiting": - img - img diff --git a/apps/web/tests/snapshots/web-search-round/ui.expected.md b/apps/web/tests/snapshots/web-search-round/ui.expected.md index 09718300f2..37d53a0df6 100644 --- a/apps/web/tests/snapshots/web-search-round/ui.expected.md +++ b/apps/web/tests/snapshots/web-search-round/ui.expected.md @@ -13,13 +13,10 @@ - img - img - text: Context injection -- img -- text: Search DeepSeek Harness snapshot search -- list: - - listitem: - - link "Snapshot Search Result": - - /url: https://docs.example.test/search - - text: Snapshot search excerpt. 2026-07-31 +- button "Search DeepSeek Harness snapshot search": + - img + - img + - text: Search DeepSeek Harness snapshot search - paragraph: SEARCH_DONE - button "Copy": - img diff --git a/apps/web/tests/startup-auto-selection.e2e.ts b/apps/web/tests/startup-auto-selection.e2e.ts new file mode 100644 index 0000000000..f3a953c1e6 --- /dev/null +++ b/apps/web/tests/startup-auto-selection.e2e.ts @@ -0,0 +1,119 @@ +// Web e2e scenario: startup auto-selection keeps the hero on screen. +// +// A page load with a workspace already registered runs +// `WorkspacesService.startInitialSelection`: it connects the most recent +// workspace and opens its blank session. `openState` flips to `loading` the +// moment `open()` lands, which used to drive `data-phase=settling` on the +// conversation root — `visibility:hidden` over the composer seat and the +// header for the whole `session.history` round-trip, so the center column went +// blank and repainted, reading as a full-page refresh on every launch. +// +// The unit spec pins the phase condition over hand-built stores. What only the +// assembled application can show is that the path a user actually takes +// reaches it: the real selection service, the real client session opening over +// the real /api transport, and a real browser deciding what is painted. +// +// The round-trip against a loopback host is far too fast to observe, so this +// scenario HOLDS the `session.history` response open at the browser's network +// boundary and asserts the visible frame while it is in flight. That gate is +// what makes the assertions non-vacuous: with the exemption reverted the held +// window is exactly when `settling` is painted and the composer is hidden. +// +// Zero model calls: registering a workspace and opening its blank session are +// host RPCs with no model involvement. A stray stream would fail loud with +// NO_ADAPTER. +import type { Browser, Page } from 'playwright' +import { chromium } from 'playwright' +import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' +import { acknowledgeReloadConnectionLoss, launchWebScaffold, watchConsole, type WebScaffold } from './scaffold.ts' +import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts' + +/** Wire path of the history round-trip the conversation root waits out (POST /api/session.history). */ +const HISTORY_ROUTE = '**/api/session.history' + +/** + * The conversation root's own phase attribute. `div` disambiguates it from the + * composer textarea, which carries an unrelated `data-phase` of its own. + */ +const ROOT_PHASE = 'div[data-phase]' + +/** Every distinct `data-phase` the conversation root shows, in order, across one page load. */ +function recordedPhases(page: Page): Promise { + return page.evaluate(() => (window as unknown as { __conversationPhases: string[] }).__conversationPhases) +} + +describe('web e2e: startup auto-selection', () => { + let scaffold: WebScaffold + let browser: Browser + let page: Page + let tripwire: ReturnType + + beforeAll(async () => { + scaffold = await launchWebScaffold({}) + browser = await chromium.launch() + page = await newEnglishPage(browser) + tripwire = watchConsole(page) + await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) + await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) + // A registered workspace is the precondition for auto-selection: the first + // load has nothing to select, so the reload below is the path under test. + await connectFreshWorkspace(page, scaffold.workspaceCwd, 'startup-auto-selection') + }, 180_000) + + afterAll(async () => { + await browser?.close() + await scaffold?.close() + }) + + it('keeps the hero and the composer on screen while the auto-selected blank session opens', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-startup-auto-selection')) + // Runs before any page script on the reload below, so the first phase the + // root ever renders is recorded, not just the ones after a listener attaches. + await page.addInitScript(() => { + const phases: string[] = [] + ;(window as unknown as { __conversationPhases: string[] }).__conversationPhases = phases + setInterval(() => { + const phase = document.querySelector('div[data-phase]')?.getAttribute('data-phase') + if (phase === null || phase === undefined) return + if (phases[phases.length - 1] !== phase) phases.push(phase) + }, 8) + }) + + let releaseHistory = (): void => {} + const historyHeld = new Promise((resolve) => { releaseHistory = resolve }) + let historyRequested = (): void => {} + const historyInFlight = new Promise((resolve) => { historyRequested = resolve }) + let gated = false + await page.route(HISTORY_ROUTE, async (route) => { + // Only the auto-selection's own round-trip is held; later pages must not + // deadlock behind a gate this test has already released. + if (gated) { await route.continue(); return } + gated = true + historyRequested() + await historyHeld + await route.continue() + }) + + const warningsBefore = tripwire.warnings.length + await page.reload({ waitUntil: 'commit' }) + await historyInFlight + + // The frame a user sees while the session is still opening: hero phase, the + // hero title, and a composer that is actually painted (`settling` hides the + // seat with `visibility:hidden`, which Playwright reports as not visible). + await page.waitForSelector(ROOT_PHASE, { timeout: 15_000 }) + expect(await page.locator(ROOT_PHASE).first().getAttribute('data-phase')).toBe('hero') + expect(await page.getByText("Let's start building").isVisible()).toBe(true) + expect(await page.locator('textarea').first().isVisible()).toBe(true) + + releaseHistory() + await page.locator('textarea:enabled[placeholder="Describe what you want to build"]') + .waitFor({ timeout: 15_000 }) + acknowledgeReloadConnectionLoss(tripwire, warningsBefore) + + // Settling is not merely absent from the frame sampled above: the root + // never entered it at any point of the load. + expect(await recordedPhases(page)).toEqual(['hero']) + expect(tripwire.pageErrors).toEqual([]) + }, 120_000) +}) diff --git a/apps/web/tests/steering.e2e.ts b/apps/web/tests/steering.e2e.ts index 3cbae0b9ee..6bd369ea2c 100644 --- a/apps/web/tests/steering.e2e.ts +++ b/apps/web/tests/steering.e2e.ts @@ -72,7 +72,7 @@ describe('web e2e: mid-turn steering lands durably and visibly', () => { await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) // Fresh world: connect a Workspace so the composer scenarios start live. - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/support.ts b/apps/web/tests/support.ts index d03915f851..4ccc18de9f 100644 --- a/apps/web/tests/support.ts +++ b/apps/web/tests/support.ts @@ -1,6 +1,7 @@ // Shared plumbing for the web smoke tests (dist location, free port, failure shots). import { existsSync, mkdirSync } from 'node:fs' import { createServer } from 'node:net' +import { join } from 'node:path' import { fileURLToPath } from 'node:url' import type { Browser, Page } from 'playwright' @@ -55,23 +56,32 @@ export function probeFreePort(): Promise { } /** - * Drive the hero's workspace picker through its create-by-name dialog until - * the live composer unlocks. A fresh world has no Workspace, so the boot + * Drive the hero's workspace picker through the composed directory dialog + * until the live composer unlocks. A fresh world has no Workspace, so the boot * lands in the locked view state (startup auto-selection has nothing to * select); every scenario that types into the composer must connect one - * first. The default name 'workspace' keeps the session header cwd at - * /workspace — the materialization proof several scenarios + * first. With nothing to list, the chip gesture raises the dialog directly — + * adding a workspace is the picker's only entry. The directory is staged here + * and adopted through the path editor, which is idempotent across the repeated + * connects a scenario may make; creating a folder from inside the dialog (the + * product's other half of the same route) is covered by + * workspace-management.e2e.ts. The default name 'workspace' keeps the session + * header cwd at /workspace, the materialization proof several scenarios * assert. * @param page - the page under test. - * @param name - workspace name typed into the create dialog. + * @param root - host directory the workspace folder is staged in (the scaffold's `workspaceCwd`). + * @param name - folder name staged and adopted as the workspace. */ -export async function connectFreshWorkspace(page: Page, name = 'workspace'): Promise { +export async function connectFreshWorkspace(page: Page, root: string, name = 'workspace'): Promise { + mkdirSync(join(root, name), { recursive: true }) await page.getByRole('button', { name: 'Choose workspace' }).click() - await page.getByRole('menuitem', { name: 'Create a new workspace' }).click() - const dialog = page.getByRole('dialog', { name: 'Create a new workspace' }) + const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' }) await dialog.waitFor({ timeout: 10_000 }) - await dialog.getByLabel('New workspace name').fill(name) - await dialog.getByRole('button', { name: 'Create workspace' }).click() + await dialog.getByRole('button', { name: 'Edit path' }).click() + const pathInput = dialog.getByRole('textbox', { name: 'Edit path' }) + await pathInput.fill(join(root, name)) + await pathInput.press('Enter') + await dialog.getByRole('button', { name: 'Open', exact: true }).click() // The pick connected the workspace: the blank session's live composer // replaces the locked placeholder and enables. await page.locator('textarea:enabled[placeholder="Describe what you want to build"]') diff --git a/apps/web/tests/web-search-round.e2e.ts b/apps/web/tests/web-search-round.e2e.ts index 804c7a70ca..e887fb8e35 100644 --- a/apps/web/tests/web-search-round.e2e.ts +++ b/apps/web/tests/web-search-round.e2e.ts @@ -109,7 +109,7 @@ describe('web e2e: shipped default web search', () => { tripwire = watchConsole(page) await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) - await connectFreshWorkspace(page) + await connectFreshWorkspace(page, scaffold.workspaceCwd) }, 120_000) afterAll(async () => { diff --git a/apps/web/tests/workspace-management.e2e.ts b/apps/web/tests/workspace-management.e2e.ts index 48483e512d..95d44d4162 100644 --- a/apps/web/tests/workspace-management.e2e.ts +++ b/apps/web/tests/workspace-management.e2e.ts @@ -1,17 +1,18 @@ -// Web e2e scenarios: workspace management — the create-by-name dialog, the -// rename round trip over the real wire (workspace.rename RPC + durable -// registry), duplicate-name pre-check, the flat "In one list" view with its -// persisted group-by preference, the session hover card, and the session -// archive round trip (row menu → workspace.archiveSession RPC → durable -// global set → row hidden across reload). Zero model calls: -// workspace.create/rename/archiveSession are host RPCs with no model -// involvement, and the one session row the flat/hover/archive scenarios need -// comes from a seeded fixture (the seeded-history seed reused verbatim — no -// new recording). +// Web e2e scenarios: workspace management — adding a workspace through the +// composed directory dialog (its own New folder affordance is the product's +// one creation route), the rename round trip over the real wire +// (workspace.rename RPC + durable registry), duplicate-name pre-check, the +// flat "In one list" view with its persisted group-by preference, the session +// hover card and row action menu, and the session archive round trip (row +// menu → workspace.archiveSession RPC → durable global set → row hidden +// across reload). Zero model calls: workspace.create/rename/archiveSession +// are host RPCs with no model involvement, and the one session row the +// flat/hover/menu/archive scenarios need comes from a seeded fixture (the +// seeded-history seed reused verbatim — no new recording). import { mkdir, readFile, stat, writeFile } from 'node:fs/promises' import { fileURLToPath } from 'node:url' import { join } from 'node:path' -import type { Browser, Page } from 'playwright' +import type { Browser, Locator, Page } from 'playwright' import { chromium } from 'playwright' import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' import { SessionId } from '@deepseek-ai/dsh-session' @@ -28,29 +29,59 @@ const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', impo const MODE = webSnapshotMode() const BROWSER_EXPECTED = join(SNAPSHOT_DIR, 'directory-browser.expected.md') const SEED_ID = 'workspace-management-web-e2e' +// Both waits exceed ui-primitives' 200ms POINTER_GRACE_MS. Keep them coupled +// to that contract if the shared grace tuning changes. +const POINTER_TRANSIT_MS = 300 +const POINTER_HOLD_MS = 600 -describe('web e2e: workspace management (create / rename / flat view / hover card)', () => { +describe('web e2e: workspace management (create / rename / flat view / hover affordances)', () => { let scaffold: WebScaffold let browser: Browser let page: Page let tripwire: ReturnType /** - * Drive the in-app browser to a directory via its path-edit affordance, - * confirm it, and wait for the adoption to settle host-side (workspace - * registered + the flow's New-Session agent up), so later test steps can't - * race the in-flight blank-session attach. + * Raise the region header's directory dialog and drive it to a directory via + * the path-edit affordance. Adding is the header button's only action, so + * the click lands in the dialog with no menu in between. */ - async function openLocalFolder(path: string, options: { waitForAgent?: boolean } = {}): Promise { - const agentsBefore = scaffold.ctx.agents.list().length - await page.getByRole('button', { name: 'Create workspace' }).click() - await page.getByRole('menuitem', { name: 'Open local folder…' }).click() + async function browseTo(path: string): Promise { + await page.getByRole('button', { name: 'Add workspace' }).click() const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' }) await dialog.waitFor({ timeout: 10_000 }) await dialog.getByRole('button', { name: 'Edit path' }).click() await dialog.getByLabel('Edit path').fill(path) await dialog.getByLabel('Edit path').press('Enter') - await dialog.getByRole('button', { name: 'Open' }).click() + return dialog + } + + /** + * Create a folder inside `parent` through the dialog and adopt it — the + * product's only route to a brand-new workspace directory. + */ + async function addNewFolderWorkspace(parent: string, name: string): Promise { + const dialog = await browseTo(parent) + await dialog.getByRole('button', { name: 'New folder' }).click() + await page.getByLabel('Folder name').fill(name) + await page.getByRole('button', { name: 'Create', exact: true }).click() + // Creating selects the new folder in the listing; Open adopts it. + await dialog.getByRole('button', { name: 'Open', exact: true }).click() + await dialog.waitFor({ state: 'hidden', timeout: 10_000 }) + await expect.poll( + () => scaffold.ctx.workspace.resolveByPath(join(parent, name)), + { timeout: 10_000 }, + ).not.toBeUndefined() + } + + /** + * Adopt an existing directory, waiting for the adoption to settle host-side + * (workspace registered + the flow's New-Session agent up), so later test + * steps can't race the in-flight blank-session attach. + */ + async function adoptDirectory(path: string, options: { waitForAgent?: boolean } = {}): Promise { + const agentsBefore = scaffold.ctx.agents.list().length + const dialog = await browseTo(path) + await dialog.getByRole('button', { name: 'Open', exact: true }).click() await dialog.waitFor({ state: 'hidden', timeout: 10_000 }) await expect.poll( () => scaffold.ctx.workspace.resolveByPath(path), @@ -86,22 +117,17 @@ describe('web e2e: workspace management (create / rename / flat view / hover car await scaffold?.close() }) - it('creates two workspaces by name through the region-header dialog', async () => { + it('adds two workspaces through the dialog, each on a folder it created', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-create')) - const createByName = async (name: string): Promise => { - await page.getByRole('button', { name: 'Create workspace' }).click() - await page.getByRole('menuitem', { name: 'Create a new workspace' }).click() - const dialog = page.getByRole('dialog', { name: 'Create a new workspace' }) - await dialog.waitFor({ timeout: 10_000 }) - await dialog.getByLabel('New workspace name').fill(name) - await dialog.getByRole('button', { name: 'Create workspace' }).click() - await expect.poll(() => page.getByRole('dialog', { name: 'Create a new workspace' }).count(), { timeout: 10_000 }).toBe(0) + const add = async (name: string): Promise => { + await addNewFolderWorkspace(scaffold.workspaceCwd, name) // The real workspace materializes in the tree as a group row. await expect.poll(() => page.getByText(name, { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1) } - await createByName('alpha-ws') - await createByName('beta-ws') - // Durable on the host: both registered, newest first (create prepends). + await add('alpha-ws') + await add('beta-ws') + // Durable on the host: both registered, newest first (create prepends), + // each titled after the folder the dialog made. const titles = scaffold.ctx.workspace.list().map(workspace => workspace.title) expect(titles.slice(0, 2)).toEqual(['beta-ws', 'alpha-ws']) expect(tripwire.pageErrors).toEqual([]) @@ -167,7 +193,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car collect() }) // Register the scaffold's existing project directory through the real UI. - await openLocalFolder(scaffold.workspaceCwd, { waitForAgent: true }) + await adoptDirectory(scaffold.workspaceCwd, { waitForAgent: true }) const workspace = await scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd) if (workspace === undefined) throw new Error('GUI did not register the existing project directory') await workspace.attachSession(SessionId(SEED_ID)) @@ -225,7 +251,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car // Re-registering the exact deleted path immediately, without a reload, is // a supported reversible flow. It creates a fresh Workspace id without // re-adopting the retained Session. - await openLocalFolder(scaffold.workspaceCwd) + await adoptDirectory(scaffold.workspaceCwd) await expect.poll( () => scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd), { timeout: 10_000 }, @@ -295,7 +321,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car collect() }) - await openLocalFolder(oldPath) + await adoptDirectory(oldPath) await expect.poll( () => scaffold.ctx.workspace.resolveByPath(oldPath), { timeout: 10_000 }, @@ -311,12 +337,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car .getByRole('button', { name: 'Delete workspace' }).click() await expect.poll(() => scaffold.ctx.workspace.get(oldWorkspace.id), { timeout: 10_000 }).toBeUndefined() - await page.getByRole('button', { name: 'Create workspace' }).click() - await page.getByRole('menuitem', { name: 'Create a new workspace' }).click() - const create = page.getByRole('dialog', { name: 'Create a new workspace' }) - await create.getByLabel('New workspace name').fill(title) - await create.getByRole('button', { name: 'Create workspace' }).click() - await expect.poll(() => create.count(), { timeout: 10_000 }).toBe(0) + await addNewFolderWorkspace(scaffold.workspaceCwd, title) const fresh = scaffold.ctx.workspace.list().find(workspace => workspace.title === title) expect(fresh?.id).toBeDefined() expect(fresh?.id).not.toBe(oldWorkspace.id) @@ -366,13 +387,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car process.env.HOME = scaffold.workspaceCwd process.env.USERPROFILE = scaffold.workspaceCwd try { - await page.getByRole('button', { name: 'Create workspace' }).click() - await page.getByRole('menuitem', { name: 'Open local folder…' }).click() - const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' }) - await dialog.waitFor({ timeout: 10_000 }) - await dialog.getByRole('button', { name: 'Edit path' }).click() - await dialog.getByLabel('Edit path').fill(staged) - await dialog.getByLabel('Edit path').press('Enter') + const dialog = await browseTo(staged) await expect.poll(() => dialog.getByText('alpha', { exact: true }).count(), { timeout: 10_000 }).toBe(1) const snapshot = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd) await compareOrRefreshGolden(BROWSER_EXPECTED, snapshot, MODE) @@ -387,14 +402,17 @@ describe('web e2e: workspace management (create / rename / flat view / hover car expect(tripwire.pageErrors).toEqual([]) }, 60_000) - it('shows the session hover card after a dwell on the row', async () => { - onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-hover')) - // Expand Ungrouped to reveal the seeded session row, then dwell on it - // (the card opens after a 500ms hover delay, portaled to body). + /** + * Expand Ungrouped and return its seeded session row. The only visible child + * is the non-blank persisted Session; the blank Session created while + * adopting the Workspace stays hidden. + * @returns the session row locator, already present. + */ + async function seededSessionRow() { const ungroupedRow = page.getByText('Ungrouped', { exact: true }).locator('..').locator('..') const ungroupedSection = ungroupedRow.locator('..') - // Initial-current auto-expansion can race this following test's gesture; - // converge on expanded rather than assuming which update wins first. + // Initial-current auto-expansion can race this gesture; converge on + // expanded rather than assuming which update wins first. await expect.poll(async () => { if (await ungroupedRow.getAttribute('aria-expanded') !== 'true') { await page.getByText('Ungrouped', { exact: true }).click() @@ -402,17 +420,72 @@ describe('web e2e: workspace management (create / rename / flat view / hover car } return await ungroupedRow.getAttribute('aria-expanded') }, { timeout: 5_000 }).toBe('true') - // The only visible child is the non-blank persisted Session; the blank - // Session created while adopting the Workspace remains hidden. - const sessionRow = ungroupedSection.locator('[role="treeitem"]').nth(1) - await sessionRow.waitFor({ timeout: 10_000 }) + const row = ungroupedSection.locator('[role="treeitem"]').nth(1) + await row.waitFor({ timeout: 10_000 }) + return row + } + + it('shows the session hover card after a dwell on the row', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-hover')) + // Dwell on the seeded row; the card opens after a 500ms hover delay, + // portaled to body. + const sessionRow = await seededSessionRow() + const rowTitle = await sessionRow.locator('[class*="title"]').innerText() await sessionRow.hover() - // Card content: the full title plus the Idle status line (display-only - // card; no aria role — text anchors are the stable selector). + // Card content: the full title plus the Idle status line (no aria role — + // text anchors are the stable selector). await expect.poll(() => page.getByText('Idle', { exact: true }).count(), { timeout: 5_000 }).toBeGreaterThanOrEqual(1) - // Leaving the anchor closes it with no delay. + // The card is REACHABLE: it sits 8px off the row, so getting to it means + // crossing ground that belongs to neither. Hovering it must not dismiss + // it — the regression this scenario guards. + const card = page.getByRole('button', { name: `Copy: ${rowTitle}` }) + await card.hover() + await page.waitForTimeout(POINTER_HOLD_MS) + expect(await page.getByText('Idle', { exact: true }).count()).toBeGreaterThanOrEqual(1) + // The full title is the card's primary value: activating anywhere on the + // card writes it through the browser clipboard and localizes the success + // feedback through the English locale seat. + await page.context().grantPermissions(['clipboard-read', 'clipboard-write']) + const cardHeight = (await card.boundingBox())?.height + await card.click() + const copied = page.getByRole('status').getByText('Copied', { exact: true }) + await copied.waitFor({ timeout: 5_000 }) + await page.waitForTimeout(POINTER_HOLD_MS) + expect((await card.boundingBox())?.height).toBe(cardHeight) + expect(await copied.isVisible()).toBe(true) + expect(await page.evaluate(() => navigator.clipboard.readText())).toBe(rowTitle) + // Leaving anchor and card together closes it after the grace. await page.getByRole('button', { name: 'Settings' }).hover() - await expect.poll(() => page.getByText('Idle', { exact: true }).count(), { timeout: 5_000 }).toBe(0) + await expect.poll(() => card.count(), { timeout: 5_000 }).toBe(0) + expect(tripwire.pageErrors).toEqual([]) + }, 60_000) + + it('keeps an open row menu up while the pointer moves between trigger and list', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-row-menu')) + const sessionRow = await seededSessionRow() + // The trigger is display:none until its row hovers. + await sessionRow.hover() + const trigger = sessionRow.locator('button[aria-label^="Session actions for "]') + await trigger.click() + const item = page.getByRole('menuitem', { name: 'Rename' }) + await item.waitFor({ timeout: 5_000 }) + // Into the list, then back up to the trigger across the 4px gap below it: + // that return trip used to fire the list's pointerleave and close the + // menu, so a hesitating pointer lost it. Order matters — clicking leaves + // the pointer ON the trigger, so entering the list has to come first for + // the return to be a real departure. + await item.hover() + await page.waitForTimeout(POINTER_TRANSIT_MS) + await trigger.hover() + await page.waitForTimeout(POINTER_HOLD_MS) + expect(await page.getByRole('menuitem', { name: 'Rename' }).count()).toBe(1) + // ...and back down into the list, which must still be there to enter. + await item.hover() + await page.waitForTimeout(POINTER_HOLD_MS) + expect(await page.getByRole('menuitem', { name: 'Rename' }).count()).toBe(1) + // Pointer-leave dismissal still applies once the pointer genuinely leaves. + await page.getByRole('button', { name: 'Settings' }).hover() + await expect.poll(() => page.getByRole('menuitem', { name: 'Rename' }).count(), { timeout: 5_000 }).toBe(0) expect(tripwire.pageErrors).toEqual([]) }, 60_000) diff --git a/apps/web/tsconfig.json b/apps/web/tsconfig.json index a4cd2d9121..b3e614c293 100644 --- a/apps/web/tsconfig.json +++ b/apps/web/tsconfig.json @@ -24,6 +24,7 @@ "exclude": [ "tests/scaffold.ts", "tests/scaffold-hermetic.e2e.ts", + "tests/core-web-profile.snapshot.ts", "tests/live-interactions.e2e.ts", "tests/question-composer.e2e.ts", "tests/approval-composer.e2e.ts", @@ -47,7 +48,8 @@ "tests/queue-actions.e2e.ts", "tests/skill-invocation-policy.e2e.ts", "tests/permission-policy-context.e2e.ts", - "tests/access-confirmation.e2e.ts" + "tests/access-confirmation.e2e.ts", + "tests/startup-auto-selection.e2e.ts" ], "references": [ { diff --git a/bin/dsh b/bin/dsh index f85f28a5cd..c578d78e74 100755 --- a/bin/dsh +++ b/bin/dsh @@ -20,6 +20,7 @@ root=$(CDPATH='' cd -- "$(dirname -- "$script")/.." && pwd) # ESM-only and the CJS resolver costs ~0.4s of startup). Absolute paths keep # both the hook and the tsconfig anchored to this checkout when the launcher # runs from any cwd, where bare `tsx/esm` would not resolve. -TSX_TSCONFIG_PATH="$root/tsconfig.json" \ +NODE_USE_ENV_PROXY=1 \ + TSX_TSCONFIG_PATH="$root/tsconfig.json" \ exec node --import "$root/node_modules/tsx/dist/esm/index.mjs" \ "$root/apps/cli/src/bin.ts" "$@" diff --git a/docs/architecture.i18n.yaml b/docs/architecture.i18n.yaml index 1ee5e3a3aa..e305eb5f42 100644 --- a/docs/architecture.i18n.yaml +++ b/docs/architecture.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 docs/architecture.md -architecture.md: 929d2d28fd93d06cf18abeeac968860048657faf -architecture.zh.md: c9e495359d804c49181e78b6099c4aa2b1125d92 +architecture.md: 75340b6fb3e4e109974bcb9d9ccabec004d853e1 +architecture.zh.md: 0955a40f3571fe9146c75a6b1094f945fcc5219c diff --git a/docs/architecture.md b/docs/architecture.md index 929d2d28fd..75340b6fb3 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -130,11 +130,11 @@ Adapter failures close their step before `agent/request-error` receives the exac Other failures use `agent/error`. Cancellation and disposal beat recovery. Before request-header commit, the turn signal cancels asynchronous model-capability preparation; undispatched tools get synthetic `tool/call`/`ABORTED_BEFORE_DISPATCH` pairs. Effective `cancel(cause)` emits its cause before queue clearing and abort; observers cannot veto; idle calls emit nothing. Durability records user or parent cancellation as `aborted`, teardown as `disposed`; teardown awaits quiescence. The cause affects reporting, not late result-context handling ([decision](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)). -Turn and step events are turn-enclosed; idle injected `user/message` events may sit between turns. Reload closes an interrupted tail with a synthetic turn end. After close, only `agent/error` reports failures. Each turn has one [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). +Turn and step events are turn-enclosed. Idle `user/message` and standalone `compact/* { turn: null }` consume no turn; their lock-time markers may interleave with injection. Reload synthesizes interrupted turn ends; `session/end-seed` distinguishes stale compaction orphans from live locks. After close, only `agent/error` reports failures. Each turn has one [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). ### Agent Handles -`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins use full `send()` options or `followup()`, `steer()`, and `inject()` presets; `cancel()` and `whenIdle()` control lifecycle. One awaited disposer coordinates teardown ownership. +`ctx.agents` owns agents, returning `AgentHandle { agent, dispose() }`. Plugins use `send()` or `followup()`, `steer()`, and `inject()` presets; [`reserveTurnAdmission()`](../packages/core/agent/README.md#agent-interface-typests) synchronously reserves idle for durable work without changing queued prompt identity. `cancel()` and `whenIdle()` control lifecycle. Awaited disposal owns teardown. ### Agent Scope @@ -150,7 +150,7 @@ The session log is authoritative. `deriveMessages()` projects model history; raw Durability is a plugin concern. Backends eagerly drain synchronous `session/event` notifications. `session/flush` barriers precede each request and top-level tool dispatch, then follow `turn/end` before another queued turn or idle observation. `SessionPersistence` stores `SessionEvent` directly and metadata in `SessionHeader`; JSONL defaults to checksummed Zstandard, while SQLite shares the contract ([decision](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)). -Log-only events may sit between turns. Owners append through `Session`, flushing only for durability. `session/title` relies on eager persistence and lifecycle drains. Latest title wins with provenance; fallback and provider work never delays responses. Such records are fork boundaries, so forks inherit titles ([decision](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)). +Between turns, owners append log-only events through `Session`, flushing only for durability. `session/title` needs eager persistence and lifecycle drains; manual compaction flushes its bracket before releasing admission. Title work never delays responses; latest wins with provenance. Title records are inherited fork boundaries ([decision](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)). ### Model Content diff --git a/docs/architecture.zh.md b/docs/architecture.zh.md index c9e495359d..0955a40f35 100644 --- a/docs/architecture.zh.md +++ b/docs/architecture.zh.md @@ -130,11 +130,11 @@ idle inject: 其他故障使用 `agent/error`。取消和资源释放优先于恢复。在提交请求头之前,轮次信号会取消异步模型能力准备;尚未分派的工具会得到合成的 `tool/call`/`ABORTED_BEFORE_DISPATCH` 对。实际生效的 `cancel(cause)` 在清空队列和中止前发出原因;观察方不能否决;空闲调用不发事件。持久化层将用户或父级取消记录为 `aborted`,拆卸记录为 `disposed`;拆卸会等待完全停稳。原因只影响报告方式,不影响延迟完成的结果上下文处理([决策](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md))。 -轮次和步骤事件均位于轮次边界内;空闲时注入的 `user/message` 可以位于两个轮次之间。重新加载会用合成的轮次结束事件闭合中断尾部。关闭后仅由 `agent/error` 报告故障。每个轮次有一个 [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap)。 +轮次和步骤事件均位于轮次边界内。空闲 `user/message` 与独立的 `compact/* { turn: null }` 不占用轮次;其锁定时刻标记可以与注入交错。重新加载会为中断的轮次合成结束事件;`session/end-seed` 区分陈旧的压缩遗留项与活跃锁。关闭后仅由 `agent/error` 报告故障。每个轮次有一个 [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap)。 ### Agent 句柄 -`ctx.agents` 拥有活跃 agent,并返回 `AgentHandle { agent, dispose() }`。插件使用全部 `send()` 选项,或 `followup()`、`steer()` 和 `inject()` 预设;`cancel()` 与 `whenIdle()` 控制生命周期。一个需等待完成的 disposer 协调拆卸归属。 +`ctx.agents` 拥有 agent,返回 `AgentHandle { agent, dispose() }`。插件使用 `send()`,或使用 `followup()`、`steer()` 和 `inject()` 预设;[`reserveTurnAdmission()`](../packages/core/agent/README.md#agent-interface-typests) 为持久工作同步预留空闲状态,同时不改变排队提示词身份。`cancel()` 与 `whenIdle()` 控制生命周期。需等待完成的资源释放负责拆卸。 ### Agent 作用域 @@ -150,7 +150,7 @@ idle inject: 持久性由插件负责。后端会尽快排空同步的 `session/event` 通知。`session/flush` 屏障位于每次请求与顶层工具分发之前,并在 `turn/end` 之后、处理另一个已排队轮次或观察到空闲状态之前执行。`SessionPersistence` 直接存储 `SessionEvent`,并将元数据存入 `SessionHeader`;JSONL 默认采用带校验和的 Zstandard,SQLite 遵循同一契约([决策](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md))。 -纯日志事件可以位于轮次之间。事件所有方通过 `Session` 追加,仅为持久性而刷写。`session/title` 依赖尽快持久化与生命周期排空。最新标题按后写覆盖并携带来源信息;回退与提供方工作绝不会延迟响应。这类记录可作为 fork 边界,因此 fork 会继承标题([决策](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md))。 +在轮次之间,事件所有方通过 `Session` 追加纯日志事件,仅为持久性而刷写。`session/title` 需要尽快持久化与生命周期排空;手动压缩会在释放轮次接纳预留前 flush 其标记对。标题工作绝不延迟响应;最新标题按后写覆盖并携带来源信息。标题记录是可继承的 fork 边界([决策](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md))。 ### 模型内容 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 12bde08080..c862dc7f93 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -349,7 +349,7 @@ Source: [`packages/code-runtime/code-runtime-worker/src/index.ts:25`](../package ## `@deepseek-ai/dsh-compact-basic` -Requires: `llm` · `tokenMeter` +Requires: `llm` · `tokenMeter` · `sessions` ```ts config-catalog /** Basic compaction configuration with an optional exact-target policy table. */ @@ -2308,6 +2308,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co - `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts)) - `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts)) - `@deepseek-ai/dsh-client-ui-workspace` ([`packages/client/ui-workspace/src/index.ts`](../packages/client/ui-workspace/src/index.ts)) +- `@deepseek-ai/dsh-command-compact` — requires `commands` · `compact` ([`packages/compact/command-compact/src/index.ts`](../packages/compact/command-compact/src/index.ts)) - `@deepseek-ai/dsh-command-goal` — requires `commands` · `goals` ([`packages/goal/command-goal/src/index.ts`](../packages/goal/command-goal/src/index.ts)) - `@deepseek-ai/dsh-commands` ([`packages/ui/commands/src/index.ts`](../packages/ui/commands/src/index.ts)) - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts)) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 497e0d220d..a7ff21e2f4 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -32,7 +32,7 @@ Effective broad cancellation was requested, before queued/outbox work is cleared Types: [Agent](../core-data-structures/core.md) · [AgentCancelCause](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/created` — emit @@ -54,7 +54,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:264`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -74,7 +74,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence and sco Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:259`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:273`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -96,7 +96,7 @@ A step or turn errored. The machine reports a failure here (plus the logger) eve Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:433`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:447`](../../packages/core/agent/src/types.ts) ### `agent/inbox/dequeue` — emit @@ -117,7 +117,7 @@ The driver claimed one item out of the inbox: a queued item at a turn boundary, Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:297`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:311`](../../packages/core/agent/src/types.ts) ### `agent/inbox/discard` — emit @@ -140,7 +140,7 @@ Pending inbox items were dropped without delivering them, so every enqueue occur Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:309`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:323`](../../packages/core/agent/src/types.ts) ### `agent/inbox/enqueue` — emit @@ -161,7 +161,7 @@ An item entered the queued or steering inbox. `placement` is the acceptance-time Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:278`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:292`](../../packages/core/agent/src/types.ts) ### `agent/inbox/update` — emit @@ -181,7 +181,7 @@ A still-pending queued item changed content. The item id, placement, and positio Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:287`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:301`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -204,7 +204,7 @@ Allow, rewrite, or block one claimed prompt before it becomes a user message or Types: [Agent](../core-data-structures/core.md) · [PromptDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [UserMessage](../core-data-structures/session.md) -Source: [`packages/core/agent/src/types.ts:346`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -228,7 +228,7 @@ Replace the frozen call configuration. `await next()` yields the config the mach Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:372`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:386`](../../packages/core/agent/src/types.ts) ### `agent/request-error` — waterfall @@ -258,7 +258,7 @@ Handle a model-request failure after its failed step has closed but before the f Types: [Agent](../core-data-structures/core.md) · [LlmFailure](../core-data-structures/llm-streaming.md) · [RequestError](../core-data-structures/core.md) · [RequestErrorAction](../core-data-structures/core.md) · [ResolvedRetryPolicy](../core-data-structures/llm-streaming.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:391`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:405`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -280,7 +280,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:332`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:346`](../../packages/core/agent/src/types.ts) ### `agent/settled` — emit @@ -305,7 +305,7 @@ One drain chain reached its terminal turn: that turn's `turn/end` is already com Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SettleReason](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:420`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:434`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -325,7 +325,7 @@ Agent status changed (`idle` ⇄ `running`). `send()` does not enter `running` s Types: [Agent](../core-data-structures/core.md) · [AgentStatus](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:268`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:282`](../../packages/core/agent/src/types.ts) ### `agent/step` — serial @@ -349,7 +349,7 @@ Awaited serial checkpoint before EVERY request of a turn is built (the first as Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:359`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:373`](../../packages/core/agent/src/types.ts) ### `agent/turn-stopping` — serial @@ -375,7 +375,7 @@ The turn is about to close: the model owes no response (no live tool calls, no f Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:406`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:420`](../../packages/core/agent/src/types.ts) ## `agent-loop/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 478a147361..f2c0b9f07e 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -463,6 +463,26 @@ Abstract compaction service. Implementations own trigger policy, retention, and */ abstract compactIfNeeded( agent: CompactAgentContext, trigger: CompactionTrigger, signal: AbortSignal, ): Promise +/** + * Explicitly compact useful history even below automatic pressure thresholds. + * Implementations reserve idle turn admission synchronously before any + * asynchronous work, select a useful range without writing on a no-op, then + * append a standalone `compact/start` before summarization. That durable + * marker is the compaction lock until one `compact/end` attempt. Later waking + * prompts remain accepted in FIFO order and start only after the optional + * durability checkpoint and admission release. Context injected while the + * summary runs may sit between the marker pair; only the selected span must + * remain stable. + * + * @param agent - idle agent whose durable history should be compacted. + * @param signal - command-owned cancellation forwarded to summarization. + * @returns the compaction result, or `null` when no safe useful range exists. + * @throws {@link ManualCompactionError} for expected busy, changed-span, + * summarization/shrink, commit-stage, or persistence failures, and the exact + * abort reason when cancelled. Failed attempts remain visible in the log. + */ +abstract compactNow( agent: ManualCompactAgentContext, signal: AbortSignal, ): Promise + /** * Forcibly compact a range of surface nodes into a single summary node. * `start` and `end` name an inclusive span by surface position, not numeric seq @@ -486,7 +506,7 @@ abstract compactRegion( start: number, end: number, agent: CompactAgentContext, Types: [CompactionResult](../core-data-structures/compaction.md) · [CompactionTrigger](../core-data-structures/compaction.md) -Source: [`packages/compact/compact/src/index.ts:45`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:80`](../../packages/compact/compact/src/index.ts) ## `ctx.credentials` — `Credentials` (abstract seam) diff --git a/docs/core-data-structures/compaction.i18n.yaml b/docs/core-data-structures/compaction.i18n.yaml index a933e793c4..972521f7c0 100644 --- a/docs/core-data-structures/compaction.i18n.yaml +++ b/docs/core-data-structures/compaction.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 docs/core-data-structures/compaction.md -compaction.md: 3ae4d7e50452b549654b7a7162141a4be505d784 -compaction.zh.md: 448c3aaf298b65ebe88565190c5b3978b975f5f3 +compaction.md: 070adc65fb25b2536c88701c375cc0b2a5308559 +compaction.zh.md: 9167882f63b2931ba3ce49697e0c87164394af89 diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 3ae4d7e504..070adc65fb 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -2,7 +2,7 @@ English | [中文](compaction.zh.md) -The compaction seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)). +The compaction seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and human consumer ([dsh-command-compact](../../packages/compact/command-compact)). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)). Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) @@ -12,12 +12,14 @@ Compaction extends [`SessionEventMap`](session.md) with three event types via de | Event | Payload | Role | |---|---|---| -| `compact/start` | `{ turn }` | acquires the log-recorded lock | +| `compact/start` | `{ turn }` | acquires the log-recorded lock; a number identifies the open automatic turn, while `null` identifies a standalone manual attempt | | `compact/summary` | `{ summary, rawOutput?, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens?, usage? }` | provenance: the safe summary projection, optional complete provider output and usage, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability Agent Note) | -| `compact/end` | `{ turn, error? }` | releases the lock (`error` set when summarization threw) | +| `compact/end` | `{ turn, error? }` | releases the lock with the same numeric-or-null owner (`error` records an unsuccessful attempt) | The lock brackets the **whole** operation: `compact/start` is appended first, then summarization, the `compact/summary` provenance record, and the `user/message` replacement all land, and only then `compact/end`. Releasing the lock last turns a crash mid-operation into a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished. +The markers are lock time points, not an exclusive container. An unrelated idle injection can appear between a standalone manual start and end while summarization is pending. The manual path revalidates only its selected positional span, so that injected context survives after the replacement checkpoint. A live unmatched start blocks every entry point; an unmatched start before a newer `session/end-seed` is stale evidence from a prior lifecycle and is ignored. + These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` block, so — unlike the top-level types on the other sub-pages — they are not pasted as a drift-checked ` ```ts type-equiv ` block (the `verify-type-equiv` extractor matches only top-level declarations by name). The payload table above is the catalog entry; follow the source link for the authoritative shapes. ## `CompactionResult` @@ -60,7 +62,16 @@ Automatic callers state why policy is running; implementations may treat confirm type CompactionTrigger = 'pressure' | 'context-overflow' ``` -`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Every backend marks its replacement `user/message` with `COMPACT_CHECKPOINT_SOURCE`; client and wire consumers import that value and `isCompactCheckpointSource()` from the cordis-free `@deepseek-ai/dsh-compact/checkpoint` subpath, while the package root re-exports both for host consumers. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. +`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, `compactNow(agent, signal)` for one useful idle-session reduction even below pressure, and `compactRegion(...)` for an explicit inclusive surface range. `compactNow()` synchronously reserves the agent's next-turn admission, returns `null` without writing when no useful range exists, records a standalone `turn: null` bracket before summarization, flushes a closed attempt, and then releases admission so ordinary queued prompts derive from the new surface. Every backend marks its replacement `user/message` with `COMPACT_CHECKPOINT_SOURCE`; client and wire consumers import that value and `isCompactCheckpointSource()` from the cordis-free `@deepseek-ai/dsh-compact/checkpoint` subpath, while the package root re-exports both for host consumers. The predicate keeps checkpoint recognition independent of any one backend. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. + +Expected manual failures use `ManualCompactionErrorCode`: + +```ts type-equiv +/** Expected failure classes for an explicit idle-session compaction request. */ +type ManualCompactionErrorCode = 'busy' | 'changed' | 'summary' | 'commit' | 'persistence' +``` + +`changed` and `summary` leave the conversation surface unchanged but still close and persist the failed attempt in the log. `commit` may follow partial mutation; `persistence` means the in-memory bracket closed but its flush failed. Cancellation remains separate and throws the exact abort reason after required cleanup. Pressure compaction runs at serial `agent/step` before request derivation. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and returns a retry action only when the surface replacement generation advances, even if later summary work throws after pruning; cancellation still wins. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. diff --git a/docs/core-data-structures/compaction.zh.md b/docs/core-data-structures/compaction.zh.md index 448c3aaf29..9167882f63 100644 --- a/docs/core-data-structures/compaction.zh.md +++ b/docs/core-data-structures/compaction.zh.md @@ -2,7 +2,7 @@ [English](compaction.md) | 中文 -压缩 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md),与 bash 一样分为接口([dsh-compact](../../packages/compact/compact),`ctx.compact`)、实现(例如 [dsh-compact-basic](../../packages/compact/compact-basic) 后端)和消费方(延期实现的 `/compact` 工具)。压缩是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。基于 tokenizer 或模板的后端是实现同一接口的兄弟包(package)。与 bash 不同,该接口必然依赖 `dsh-session` 和 `dsh-llm`:其动词作用于 agent 所有的 `Session`,而其持久摘要事件使用 `ContentBlock` 词汇(见[压缩能力 seam Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md))。 +压缩 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md),与 bash 一样分为接口([dsh-compact](../../packages/compact/compact),`ctx.compact`)、实现(例如 [dsh-compact-basic](../../packages/compact/compact-basic) 后端)和面向用户的消费方([dsh-command-compact](../../packages/compact/command-compact))。压缩是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。基于 tokenizer 或模板的后端是实现同一接口的兄弟包(package)。与 bash 不同,该接口必然依赖 `dsh-session` 和 `dsh-llm`:其动词作用于 agent 所有的 `Session`,而其持久摘要事件使用 `ContentBlock` 词汇(见[压缩能力 seam Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md))。 源码:[`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) @@ -12,12 +12,14 @@ | 事件 | 载荷 | 作用 | |---|---|---| -| `compact/start` | `{ turn }` | 获取日志记录的锁 | +| `compact/start` | `{ turn }` | 获取日志记录的锁;数字标识打开的自动轮次,`null` 标识独立手动尝试 | | `compact/summary` | `{ summary, rawOutput?, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens?, usage? }` | provenance:安全摘要投影、可选的完整 provider 输出与 usage、被遮蔽的 surface 边界对(`start`/`end` seq——位置跨度,而非数值区间)、按 surface 顺序排列的被遮蔽 seq、估算 token 数,以及摘要调用的 envelope(`provider`、`model`,若有生成上限则还包括该上限)——写入日志后,该一次性请求可由日志 + 代码重建(见可重建性 Agent Note) | -| `compact/end` | `{ turn, error? }` | 释放锁(摘要调用抛出异常时设置 `error`) | +| `compact/end` | `{ turn, error? }` | 使用相同的数字或 `null` 归属值释放锁(`error` 记录失败尝试) | 锁括住**整个**操作:先追加 `compact/start`,然后执行摘要生成、写入 `compact/summary` 来源记录与 `user/message` 替换,最后才追加 `compact/end`。最后释放锁意味着操作中途崩溃会表现为可检测的遗留锁(有 `compact/start` 而无匹配的 `compact/end`),而非一个虚假声称压缩已完成的 `compact/end`。 +这些标记表示锁的时间点,而不是排他的容器。摘要等待期间,不相关的空闲注入可以出现在独立的手动 start 与 end 之间。手动路径只重新验证所选位置 span,因此替换检查点之后仍保留该注入上下文。活动的未匹配 start 会阻塞所有入口点;较新 `session/end-seed` 之前的未匹配 start 是先前生命周期留下的陈旧证据,会被忽略。 + 这些变体在 `declare module '@deepseek-ai/dsh-session'` 块内合并,因此——与其他子页面上的顶层类型不同——它们不以漂移检查的 ` ```ts type-equiv ` 块粘贴(`verify-type-equiv` 提取器只按名称匹配顶层声明)。上方的载荷表即为目录条目;权威形状请循源码链接查看。 ## `CompactionResult` @@ -60,7 +62,16 @@ interface CompactionResult { type CompactionTrigger = 'pressure' | 'context-overflow' ``` -`CompactService` 暴露 `compactIfNeeded(agent, trigger, signal)` 以执行自动 `pressure` 或 `context-overflow` 策略;没有可安全执行的工作时返回 `null`。它还针对显式、两端均包含的 surface 范围暴露 `compactRegion(...)`。每个后端都使用 `COMPACT_CHECKPOINT_SOURCE` 标记其替换用的 `user/message`;client 与 wire 消费方从无 cordis 的 `@deepseek-ai/dsh-compact/checkpoint` 子路径导入该值和 `isCompactCheckpointSource()`,包根则为 host 消费方重新导出两者。实现必须把传入的 signal 转发给摘要流程。该 seam 不拥有计价 API:单例 [`ctx.tokenMeter`](token-meter.md) 直接拥有估算与回放,而 `dsh-compact-basic` 拥有保留策略、事件排序、按路由执行的摘要调用及其配置。 +`CompactService` 暴露 `compactIfNeeded(agent, trigger, signal)` 以执行自动 `pressure` 或 `context-overflow` 策略,暴露 `compactNow(agent, signal)` 以便即使未达到压力也对空闲会话进行一次有效缩减,还针对显式、两端均包含的 surface 范围暴露 `compactRegion(...)`。`compactNow()` 会同步预留 agent 的下一轮次接纳;没有有效范围时返回 `null` 且不写入;在摘要前记录独立的 `turn: null` 标记对;flush 已闭合尝试;随后释放接纳预留,使普通排队提示词从新表层派生。每个后端都使用 `COMPACT_CHECKPOINT_SOURCE` 标记其替换用的 `user/message`;client 与 wire 消费方从无 cordis 的 `@deepseek-ai/dsh-compact/checkpoint` 子路径导入该值和 `isCompactCheckpointSource()`,包根则为 host 消费方重新导出两者。该判定函数使检查点识别不依赖任一特定后端。实现必须把传入的 signal 转发给摘要流程。该 seam 不拥有计价 API:单例 [`ctx.tokenMeter`](token-meter.md) 直接拥有估算与回放,而 `dsh-compact-basic` 拥有保留策略、事件排序、按路由执行的摘要调用及其配置。 + +预期的手动失败使用 `ManualCompactionErrorCode`: + +```ts type-equiv +/** Expected failure classes for an explicit idle-session compaction request. */ +type ManualCompactionErrorCode = 'busy' | 'changed' | 'summary' | 'commit' | 'persistence' +``` + +`changed` 和 `summary` 保持会话表层不变,但仍会闭合失败尝试并将其持久化到日志。`commit` 可能发生在部分变更之后;`persistence` 表示内存中的标记对已闭合,但 flush 失败。取消独立于这些失败,并在完成必要清理后抛出原始 abort 原因。 压力压缩在串行 `agent/step` 中运行,先于请求推导。一旦压力或规范化溢出满足条件,compact-basic 会在选择范围前调用可选的 [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md),再通过 `ctx.tokenMeter` 重新测量,并且可以在不生成摘要的情况下推进 surface。失败请求的恢复在失败的步骤关闭后通过 `agent/request-error` 运行;仅当 surface replacement generation 前进时才返回重试动作,即便后续摘要工作在剪枝后抛异常亦如此;取消仍然优先。区域边界保持工具调用/结果配对,但不保持整个轮次,因此一个过大轮次中较早关闭的步骤可以被压缩。`dsh-compact-basic` 拥有阈值、保留尾部策略、溢出上限与失败处理。 diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml index 82ef063bec..b1bdfb1a14 100644 --- a/docs/core-data-structures/core.i18n.yaml +++ b/docs/core-data-structures/core.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 docs/core-data-structures/core.md -core.md: 5ed6a47c5488005d41fdac9349e4c9d1c550d13d -core.zh.md: 1b16b7ec994c6fccd6fedf1508dec6b1b057edf3 +core.md: 70c63d8a84963f56468b5fcdacb580a798de2e10 +core.zh.md: 280529b7de6c3e8546b71791367710c588ad9282 diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 5ed6a47c54..70c63d8a84 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -614,6 +614,20 @@ interface Agent { */ send(message: UserMessage, options: SendOptions): void + /** + * Reserve admission of the next ordinary turn while this agent is idle, so an + * operation can mutate durable history before any queued prompt derives a + * request from it. Already-accepted waking work has right of way, including a + * send whose wake is still a pending microtask. Later sends keep their + * ordinary placement, FIFO order, and `wakeup` facts, and + * {@link acceptsNextStep} stays `false`, so a waking `next-step` send becomes + * a queued follow-up rather than steering; cancellation and disposal may + * still discard them. {@link inject} is not withheld. {@link whenIdle} treats + * a live reservation as activity, while lifecycle teardown does not await it. + * @returns the idempotent release, or `undefined` when the agent is running, already reserved, or already committed to waking work. + */ + reserveTurnAdmission(): (() => void) | undefined + /** * Mutate one still-pending queued occurrence synchronously. Editing preserves * the message identity and queue position; removal publishes its terminal @@ -671,7 +685,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running'`, and `SessionId` is branded. Disposal removes the agent from the registry and emits `agent/disposed`; it is not a terminal status value. `running` describes the driver-wide drain interval and may span consecutive queued turns; it does not prove a turn is still open. `acceptsNextStep` is the narrower routing predicate for callers that must choose between steering the current admission/turn and submitting a fresh admitted prompt. `AgentOptions` is merge-extensible: core declares `provider?`, `model?`, and `maxTokens?` (dispatch requires provider and model after `agent/request`). When present, `maxTokens` must be a positive safe integer and caps every conversation-model request; omission allows the exact-model adapter default to materialize before the request header, or otherwise leaves provider behavior unchanged. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. +`AgentStatus` is `'idle' | 'running'`, and `SessionId` is branded. Disposal removes the agent from the registry and emits `agent/disposed`; it is not a terminal status value. `running` describes the driver-wide drain interval and may span consecutive queued turns; it does not prove a turn is still open. `acceptsNextStep` is the narrower routing predicate for callers that must choose between steering the current admission/turn and submitting a fresh admitted prompt. A live turn-admission reservation is quiescence-relevant without changing `status` or turning later queue entries into steering; its only authority is to defer the next driver claim until release. `AgentOptions` is merge-extensible: core declares `provider?`, `model?`, and `maxTokens?` (dispatch requires provider and model after `agent/request`). When present, `maxTokens` must be a positive safe integer and caps every conversation-model request; omission allows the exact-model adapter default to materialize before the request header, or otherwise leaves provider behavior unchanged. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. The cause is a TypeScript-enforced same-process input. An active `TurnCancellation` holder copies its discriminant into the runtime-only `AbortSignal.reason` and is retired before `turn/end` publication; the frozen `AbortSignal.reason` remains readable after that retirement. Only the loop reads the cause (`user`, `parent`, or lifecycle-only `disposed`) back off its own machine-private signal at settlement — there is no public reader, and a signal grants cooperating listeners no classification authority. Durable `turn/end` retains the coarse `{ kind: 'aborted' }` outcome; request provenance would require a separate durable event rather than overloading the terminal result. diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md index 1b16b7ec99..280529b7de 100644 --- a/docs/core-data-structures/core.zh.md +++ b/docs/core-data-structures/core.zh.md @@ -622,6 +622,20 @@ interface Agent { */ send(message: UserMessage, options: SendOptions): void + /** + * Reserve admission of the next ordinary turn while this agent is idle, so an + * operation can mutate durable history before any queued prompt derives a + * request from it. Already-accepted waking work has right of way, including a + * send whose wake is still a pending microtask. Later sends keep their + * ordinary placement, FIFO order, and `wakeup` facts, and + * {@link acceptsNextStep} stays `false`, so a waking `next-step` send becomes + * a queued follow-up rather than steering; cancellation and disposal may + * still discard them. {@link inject} is not withheld. {@link whenIdle} treats + * a live reservation as activity, while lifecycle teardown does not await it. + * @returns the idempotent release, or `undefined` when the agent is running, already reserved, or already committed to waking work. + */ + reserveTurnAdmission(): (() => void) | undefined + /** * Mutate one still-pending queued occurrence synchronously. Editing preserves * the message identity and queue position; removal publishes its terminal @@ -679,7 +693,7 @@ interface Agent { } ``` -`AgentStatus` 为 `'idle' | 'running'`,`SessionId` 是品牌类型。dispose(资源释放)会把 agent 从注册表移除并发出 `agent/disposed`;它不是一个终态 status 值。`running` 描述整个驱动器的排空区间,可能跨越连续的排队轮次;它不能证明某个轮次仍然打开。对于需要在把输入作为 steering 加入当前提示词准入/轮次,还是提交为一个新的待准入提示词之间做选择的调用方,`acceptsNextStep` 才是更窄且准确的路由判断条件。`AgentOptions` 可合并扩展:core 声明 `provider?`、`model?` 与 `maxTokens?`(在 `agent/request` 后,分发要求 provider 与 model 都存在)。提供 `maxTokens` 时,它必须是正安全整数,并限制每次对话模型请求的输出;省略时,系统会在写入请求 header 前填入确切模型的适配器默认值,否则提供方行为保持不变。Persona 归 `dsh-system-prompt` 所有:agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。 +`AgentStatus` 为 `'idle' | 'running'`,`SessionId` 是品牌类型。dispose(资源释放)会把 agent 从注册表移除并发出 `agent/disposed`;它不是一个终态 status 值。`running` 描述整个驱动器的排空区间,可能跨越连续的排队轮次;它不能证明某个轮次仍然打开。对于需要在把输入作为 steering 加入当前提示词准入/轮次,还是提交为一个新的待准入提示词之间做选择的调用方,`acceptsNextStep` 才是更窄且准确的路由判断条件。活动的轮次接纳预留与完全停稳相关,但不会改变 `status`,也不会把之后的队列项变成 steering;它的唯一权限是将驱动器的下一次认领延迟到释放时。`AgentOptions` 可合并扩展:core 声明 `provider?`、`model?` 与 `maxTokens?`(在 `agent/request` 后,分发要求 provider 与 model 都存在)。提供 `maxTokens` 时,它必须是正安全整数,并限制每次对话模型请求的输出;省略时,系统会在写入请求 header 前填入确切模型的适配器默认值,否则提供方行为保持不变。Persona 归 `dsh-system-prompt` 所有:agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。 cause 是由 TypeScript 强制约束的同进程输入。活跃的 `TurnCancellation` 持有者会把其判别字段复制到仅运行时的 `AbortSignal.reason`,并在发布 `turn/end` 前退役;冻结后的 `AbortSignal.reason` 仍可读取。只有 loop 会在结算时从自己机器私有的 signal 上读回 cause(`user`、`parent` 或仅用于生命周期的 `disposed`)——不存在公开的读取器,signal 也不授予协作监听器任何分类权限。持久 `turn/end` 保留粗粒度 `{ kind: 'aborted' }` 结果;若需记录请求 provenance,应使用单独的持久事件,而不是让终态结果承担额外含义。 diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index c456a02a31..7d71b529fa 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.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 docs/development.md -development.md: f58cad7d361def14667fa66017cb003b74d70749 -development.zh.md: 88ddd8483c234bdf1c1fd0bcda9df3ca02ea6fa4 +development.md: 22eb7915f621883a84688d70e2ccad2fee2dbbba +development.zh.md: 480cd323d4d2325974f472c734edab9ce7459e89 diff --git a/docs/development.md b/docs/development.md index f58cad7d36..22eb7915f6 100644 --- a/docs/development.md +++ b/docs/development.md @@ -83,7 +83,7 @@ DEEPSEEK_BASE_URL=https://... # optional lefthook is configured in `lefthook.yml` as a fast local checkpoint: -- `pre-commit` applies formatting-only ESLint fixes, validates the staged files with Oxlint and applies its native fixes, checks the staged diff for whitespace errors, and runs the vendor manifest guard. +- `pre-commit` applies formatting-only ESLint fixes, validates the staged files with Oxlint and applies its native fixes, regenerates `THIRD_PARTY_NOTICES.md` when a staged file is one of its inputs, checks the staged diff for whitespace errors, and runs the vendor manifest guard. - `pre-push` runs only the incremental repository typecheck (`tsc -b` over the root solution, covering both the host and client aggregates). The vendor manifest guard checks that changes under `vendor/*/src` are staged with the matching `vendor/README.md` manifest update. See `vendor/README.md` before editing vendored code. diff --git a/docs/development.zh.md b/docs/development.zh.md index 88ddd8483c..480cd323d4 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -83,7 +83,7 @@ DEEPSEEK_BASE_URL=https://... # optional lefthook 在 `lefthook.yml` 中配置,作为快速的本地检查点: -- `pre-commit` 应用仅用于格式化的 ESLint 修复,使用 Oxlint 验证暂存文件并应用其原生修复,然后检查暂存 diff 中的空白错误,并运行 vendor manifest(元数据清单)守卫; +- `pre-commit` 应用仅用于格式化的 ESLint 修复,使用 Oxlint 验证暂存文件并应用其原生修复,在暂存文件属于 `THIRD_PARTY_NOTICES.md` 的输入时重新生成该文件,然后检查暂存 diff 中的空白错误,并运行 vendor manifest(元数据清单)守卫; - `pre-push` 只运行仓库增量类型检查(对根 solution 执行 `tsc -b`,覆盖 host 与 client 两个聚合)。 vendor manifest 守卫检查 `vendor/*/src` 下的改动是否连同对应的 `vendor/README.md` manifest 更新一起暂存。请在编辑 vendor 代码前先阅读 `vendor/README.md`。 diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index cce2258651..f2007c814a 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,22 +8,22 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | | `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:157`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`tui`](../packages/ui/tui) | -| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal-session`](../packages/goal/goal-session) | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:259`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:433`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tui`](../packages/ui/tui) | -| `agent/inbox/dequeue` | `emit` | [`packages/core/agent/src/types.ts:297`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | -| `agent/inbox/discard` | `emit` | [`packages/core/agent/src/types.ts:309`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | -| `agent/inbox/enqueue` | `emit` | [`packages/core/agent/src/types.ts:278`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session) | -| `agent/inbox/update` | `emit` | [`packages/core/agent/src/types.ts:287`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy` | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:346`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`tui`](../packages/ui/tui) | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:372`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`agent`](../packages/core/agent) | -| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:391`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:332`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`workspace-context`](../packages/context/workspace-context) | -| `agent/settled` | `emit` | [`packages/core/agent/src/types.ts:420`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`compact-basic`](../packages/compact/compact-basic) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:268`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/step` | `serial` | [`packages/core/agent/src/types.ts:359`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`plan-mode`](../packages/plan/plan-mode), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`time-context`](../packages/context/time-context), [`tmux-context`](../packages/context/tmux-context), [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | -| `agent/turn-stopping` | `serial` | [`packages/core/agent/src/types.ts:406`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal-session`](../packages/goal/goal-session) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:264`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:273`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:447`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tui`](../packages/ui/tui) | +| `agent/inbox/dequeue` | `emit` | [`packages/core/agent/src/types.ts:311`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | +| `agent/inbox/discard` | `emit` | [`packages/core/agent/src/types.ts:323`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | +| `agent/inbox/enqueue` | `emit` | [`packages/core/agent/src/types.ts:292`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session) | +| `agent/inbox/update` | `emit` | [`packages/core/agent/src/types.ts:301`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy` | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`tui`](../packages/ui/tui) | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:386`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`agent`](../packages/core/agent) | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:405`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:346`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`workspace-context`](../packages/context/workspace-context) | +| `agent/settled` | `emit` | [`packages/core/agent/src/types.ts:434`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:282`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/step` | `serial` | [`packages/core/agent/src/types.ts:373`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`plan-mode`](../packages/plan/plan-mode), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`time-context`](../packages/context/time-context), [`tmux-context`](../packages/context/tmux-context), [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | +| `agent/turn-stopping` | `serial` | [`packages/core/agent/src/types.ts:420`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:30`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `apiproxy` | | `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:154`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | `apiproxy`, [`tui`](../packages/ui/tui) | | `credentials/updated` | `emit` | [`packages/credentials/credentials/src/index.ts:67`](../packages/credentials/credentials/src/index.ts) | [`credentials`](../packages/credentials/credentials) (`events.dispatch`) | `apiproxy`, [`credentials`](../packages/credentials/credentials) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 99660d1eab..eb2f7d887d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -57,6 +57,7 @@ flowchart TD pkg_tool_skill["tool-skill"] end subgraph group_compact["packages/compact"] + pkg_command_compact["command-compact"] pkg_compact["compact"] pkg_compact_basic["compact-basic"] pkg_compact_tool_result_prune["compact-tool-result-prune"] @@ -617,6 +618,9 @@ flowchart TD pkg_fs_sandbox --> pkg_invariants pkg_fs_sandbox --> pkg_sandbox pkg_fs_sandbox --> pkg_sandbox_policy + pkg_command_compact --> pkg_commands + pkg_command_compact --> pkg_compact + pkg_command_compact --> pkg_invariants pkg_compact_basic --> pkg_agent pkg_compact_basic --> pkg_compact pkg_compact_basic --> pkg_compact_tool_result_prune @@ -1157,6 +1161,7 @@ flowchart TD | [`goal-session`](../packages/goal/goal-session) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | | [`fs-sandbox`](../packages/fs/fs-sandbox) | `fs` | [`fs`](../packages/fs/fs), [`fs-local`](../packages/fs/fs-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | +| [`command-compact`](../packages/compact/command-compact) | `compact` | [`commands`](../packages/ui/commands), [`compact`](../packages/compact/compact), [`invariants`](../packages/support/invariants) | | [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`compact-tool-result-prune`](../packages/compact/compact-tool-result-prune), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) | | [`session-query`](../packages/session-query/session-query) | `session-query` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-title`](../packages/session-title/session-title) | | [`session-title-llm`](../packages/session-title/session-title-llm) | `session-title` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-title`](../packages/session-title/session-title), [`timeout`](../packages/util/timeout) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index ab62f07184..b02dd1d6be 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -209,20 +209,27 @@ Source: [`packages/ui/commands/src/index.ts:132`](../packages/ui/commands/src/in #### `compact/end` — log-only ```ts persistence-catalog -/** Marks the end of a compaction — log-only, releases the lock. `error` set if summarization failed. */ -'compact/end': { turn: number; error?: string } +/** + * Marks the end of a compaction — log-only, releases the lock. Its owner + * matches `compact/start`; `error` records an unsuccessful attempt. + */ +'compact/end': { turn: number | null; error?: string } ``` -Source: [`packages/compact/compact/src/types.ts:44`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:51`](../packages/compact/compact/src/types.ts) #### `compact/start` — log-only ```ts persistence-catalog -/** Marks the start of a compaction — log-only, holds the lock until `compact/end`. */ -'compact/start': { turn: number } +/** + * Marks the start of a compaction — log-only, holds the lock until + * `compact/end`. A numbered owner is strictly enclosed by that open turn; + * `null` identifies a standalone manual transaction between turns. + */ +'compact/start': { turn: number | null } ``` -Source: [`packages/compact/compact/src/types.ts:15`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:19`](../packages/compact/compact/src/types.ts) #### `compact/summary` — log-only @@ -258,7 +265,7 @@ Source: [`packages/compact/compact/src/types.ts:15`](../packages/compact/compact Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:26`](../packages/compact/compact/src/types.ts) ### `hook/*` diff --git a/examples/README.i18n.yaml b/examples/README.i18n.yaml index 1956f0fd5e..ead468e816 100644 --- a/examples/README.i18n.yaml +++ b/examples/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 examples/README.md -README.md: a502f34128da497586d593f64d0ce1c05f68a067 -README.zh.md: e3c111bb6a8f67899b6f434345baa3b47640b7ee +README.md: 64e9804eb69367588e926791039c453b0a9aede9 +README.zh.md: dd26b9e3f35c2d3350da77ce04bd77b4660ced1b diff --git a/examples/README.md b/examples/README.md index a502f34128..64e9804eb6 100644 --- a/examples/README.md +++ b/examples/README.md @@ -4,6 +4,10 @@ English | [中文](README.zh.md) Runnable demos (not workspaces) that showcase how the harness is wired. Each example is a **thin leaf**: either a `cordis.yml` tree that picks swappable backends and loads one app package, or an **overlay** — a patch list `dsh --config` applies over the shipped composition ([`apps/cli/config/base.cordis.yml`](../apps/cli/config/base.cordis.yml) plus a surface overlay). Bundled compositions live in [`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo), [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo), and their shared [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) bundle; the `dsh` surfaces use flat config trees instead. There is no `start.ts`; the terminal `demo:*` scripts boot through the [`dsh`](../apps/cli/README.md) CLI, and the headless/ACP scripts invoke the `cli-demo`/`acp-demo` bins. +## mcp-memory + +Three default-off reference overlays connect a memory MCP server through the generic MCP client. Pick one file and pass it to `dsh --config`; DSH does not install or configure the upstream memory system. See [mcp-memory/README.md](mcp-memory/README.md) for pinned prerequisites, identity mapping, the shared optional prompt, and the write → fresh-session recall → use verification recipe. + ## headless-agent A non-interactive agent demo that accepts one positional task, runs one complete model/tool turn on the `@deepseek-ai/dsh-cli-demo` app, persists a fresh session, prints `text`, `json`, or `stream-json`, and exits. diff --git a/examples/README.zh.md b/examples/README.zh.md index e3c111bb6a..dd26b9e3f3 100644 --- a/examples/README.zh.md +++ b/examples/README.zh.md @@ -4,6 +4,10 @@ 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**:要么是一份选择可替换后端、加载一个应用包(package)的 `cordis.yml` 配置树,要么是一个 **overlay**——由 `dsh --config` 叠加到交付组合([`apps/cli/config/base.cordis.yml`](../apps/cli/config/base.cordis.yml) 加一份 surface overlay)之上的 patch 列表。成组的组合位于 [`@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;`dsh` 的各 surface 则改用平铺 config tree。没有 `start.ts`;终端 `demo:*` 脚本通过 [`dsh`](../apps/cli/README.md) CLI(命令行界面)启动,无头/ACP(Agent Client Protocol)脚本则调用 `cli-demo`/`acp-demo` bin。 +## mcp-memory + +三份默认关闭的参考 overlay 通过通用 MCP 客户端连接一个记忆 MCP 服务器。选择其中一份文件传给 `dsh --config`;DSH 不负责安装或配置上游记忆系统。版本固定的前置条件、身份映射、可选的共用提示词,以及「写入 → 新会话召回 → 使用」验证流程详见 [mcp-memory/README.md](mcp-memory/README.md)。 + ## 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。 diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl index c8321da3bb..43a87440a2 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl @@ -13,7 +13,7 @@ {"type":"assistant/chunk","seq":11,"time":1785487622703,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":12,"time":1785487622703,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"7c207b09-7f6e-4e53-a5d2-77e0d2bbb474"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[7,8,9,10,11],"surfaceOp":"append"} {"type":"tool/call","seq":13,"time":1785487622703,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}} -{"type":"tool/result","seq":14,"time":1785487622726,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly acceptsNextStep: boolean;\n readonly ctx: Context;\n send(message: UserMessage, options: SendOptions): void;\n updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n adapterDefaults?: LlmCallConfigAdapterDefaults;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export type InboxAction = {\n readonly kind: 'edit';\n readonly content: ContentBlock[];\n } | {\n readonly kind: 'remove';\n };\n export type InboxActionResult = 'applied' | 'not-found';\n export type InboxItemId = Branded<'InboxItemId'>;\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmCallConfigAdapterDefaults {\n reasoningEffort?: true;\n maxTokens?: true;\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReadFileLine {\n number: number;\n text: string;\n }\n export interface ReadResultView {\n card: 'read';\n title?: string;\n path: string;\n offset: number;\n lines: ReadFileLine[];\n totalLines: number;\n lang?: string;\n content?: ContentBlock[];\n }\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export interface RequestContext {\n provider: string;\n model: string;\n contextWindow?: number;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SearchFileMatches {\n path: string;\n matches: SearchLineMatch[];\n }\n export interface SearchLineMatch {\n lineNumber: number;\n line: string;\n }\n export interface SearchMatchesResultView {\n card: 'search';\n shape: 'matches';\n title?: string;\n files: SearchFileMatches[];\n truncated: boolean;\n total: number;\n }\n export interface SearchPathsResultView {\n card: 'search';\n shape: 'paths';\n title?: string;\n paths: string[];\n truncated: boolean;\n total: number;\n }\n export type SearchResultView = SearchMatchesResultView | SearchPathsResultView;\n export interface SendOptions {\n target: SendTarget;\n wakeup: boolean;\n }\n export type SendTarget = 'next-turn' | 'next-step';\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n requestContext(): RequestContext | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': {\n turn: number;\n message: UserMessage;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n 'request/context': RequestContext;\n 'session/end-seed': Record;\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView | SearchResultView | ReadResultView | WebResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n retry: {\n kind: 'retry';\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }\n export interface WebFetchResultView {\n card: 'web';\n kind: 'fetch';\n title?: string;\n url: string;\n statusCode: number;\n truncated: boolean;\n }\n export type WebResultView = WebSearchResultView | WebFetchResultView;\n export interface WebSearchResultView {\n card: 'web';\n kind: 'search';\n title?: string;\n sources: WebSource[];\n answer?: string;\n truncated: boolean;\n }\n export interface WebSource {\n url: string;\n title?: string;\n snippet?: string;\n publishedAt?: string;\n }"}],"isError":false}],"role":"user","id":"a4ec9786-5e3f-45b2-a6de-efdf953287f9"}},"sourceEventSeqs":[13],"surfaceOp":"append"} +{"type":"tool/result","seq":14,"time":1785487622726,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly acceptsNextStep: boolean;\n readonly ctx: Context;\n send(message: UserMessage, options: SendOptions): void;\n reserveTurnAdmission(): (() => void) | undefined;\n updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n adapterDefaults?: LlmCallConfigAdapterDefaults;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export type InboxAction = {\n readonly kind: 'edit';\n readonly content: ContentBlock[];\n } | {\n readonly kind: 'remove';\n };\n export type InboxActionResult = 'applied' | 'not-found';\n export type InboxItemId = Branded<'InboxItemId'>;\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmCallConfigAdapterDefaults {\n reasoningEffort?: true;\n maxTokens?: true;\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReadFileLine {\n number: number;\n text: string;\n }\n export interface ReadResultView {\n card: 'read';\n title?: string;\n path: string;\n offset: number;\n lines: ReadFileLine[];\n totalLines: number;\n lang?: string;\n content?: ContentBlock[];\n }\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export interface RequestContext {\n provider: string;\n model: string;\n contextWindow?: number;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SearchFileMatches {\n path: string;\n matches: SearchLineMatch[];\n }\n export interface SearchLineMatch {\n lineNumber: number;\n line: string;\n }\n export interface SearchMatchesResultView {\n card: 'search';\n shape: 'matches';\n title?: string;\n files: SearchFileMatches[];\n truncated: boolean;\n total: number;\n }\n export interface SearchPathsResultView {\n card: 'search';\n shape: 'paths';\n title?: string;\n paths: string[];\n truncated: boolean;\n total: number;\n }\n export type SearchResultView = SearchMatchesResultView | SearchPathsResultView;\n export interface SendOptions {\n target: SendTarget;\n wakeup: boolean;\n }\n export type SendTarget = 'next-turn' | 'next-step';\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n requestContext(): RequestContext | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': {\n turn: number;\n message: UserMessage;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n 'request/context': RequestContext;\n 'session/end-seed': Record;\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView | SearchResultView | ReadResultView | WebResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n retry: {\n kind: 'retry';\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }\n export interface WebFetchResultView {\n card: 'web';\n kind: 'fetch';\n title?: string;\n url: string;\n statusCode: number;\n truncated: boolean;\n }\n export type WebResultView = WebSearchResultView | WebFetchResultView;\n export interface WebSearchResultView {\n card: 'web';\n kind: 'search';\n title?: string;\n sources: WebSource[];\n answer?: string;\n truncated: boolean;\n }\n export interface WebSource {\n url: string;\n title?: string;\n snippet?: string;\n publishedAt?: string;\n }"}],"isError":false}],"role":"user","id":"a4ec9786-5e3f-45b2-a6de-efdf953287f9"}},"sourceEventSeqs":[13],"surfaceOp":"append"} {"type":"step/end","seq":15,"time":1785487622726,"data":{"turn":1,"step":1}} {"type":"step/start","seq":16,"time":1785487622735,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":17,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/examples/mcp-memory/README.i18n.yaml b/examples/mcp-memory/README.i18n.yaml new file mode 100644 index 0000000000..def44e65e3 --- /dev/null +++ b/examples/mcp-memory/README.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 examples/mcp-memory/README.md +README.md: b5dd7ffc4ad248d38e108d9aa28c7c26e0c76913 +README.zh.md: 1249ae40bb344fc81836cb49d71dd5656457b1b3 diff --git a/examples/mcp-memory/README.md b/examples/mcp-memory/README.md new file mode 100644 index 0000000000..b5dd7ffc4a --- /dev/null +++ b/examples/mcp-memory/README.md @@ -0,0 +1,113 @@ +# Third-party memory MCP examples + +English | [中文](README.zh.md) + +These three **default-off reference configurations** connect one memory system to DSH through [`@deepseek-ai/dsh-mcp-client`](../../packages/mcp/mcp-client/README.md). Pick one, or copy the same generic MCP row for another server. + +These third-party configurations are provided as interoperability examples only. Their inclusion does not imply endorsement, recommendation, partnership, or ongoing support by DeepSeek. + +## What DSH does + +DSH parses the selected Cordis overlay, starts a configured stdio command or connects to a configured Streamable HTTP URL, discovers MCP tools, and exposes them as `mcp____`. DSH does **not** download the server, initialize its database, choose its model or embedding provider, create a cloud account, migrate vendor data, or supervise a separate HTTP service. For stdio, the generic client launches and stops the child with the DSH plugin lifecycle; for HTTP, the upstream service must already be running. + +The stdio bridge deliberately removes ambient credential-shaped and `DSH_*` variables before launching a child; other ambient variables remain inherited. Each example adds only the baseline override it needs. If an optional upstream feature needs another secret, add that variable to the row's `config.env` instead of putting the secret directly in YAML. + +## Choose one + +| System | Tested pin | Transport | Upstream prerequisite | +|---|---:|---|---| +| [Memorix](https://github.com/AVIDS2/memorix) | `memorix@1.3.0` (`500792cad3144142293bfbb20acb4841c9f7fcfa`) | stdio | Node 22.18+ and `npm install --global memorix@1.3.0` | +| [MCP Reference Memory](https://github.com/modelcontextprotocol/servers/tree/main/src/memory) | `@modelcontextprotocol/server-memory@2026.7.4` (`6dd0a683e198783e30feabf7abaf42f925bd18b1`) | stdio | `npm install --global @modelcontextprotocol/server-memory@2026.7.4` | +| [Engram](https://github.com/Gentleman-Programming/engram) | `v1.20.0` (`ba9e46ced152c37a7cb9e576153c41995873e2fc`) | stdio | Go 1.25.10+ and `go install github.com/Gentleman-Programming/engram/cmd/engram@v1.20.0`, or the matching release binary | + +## Enable one + +Pass one overlay to DSH: + +```sh +dsh --config "$PWD/examples/mcp-memory/memorix.cordis.yml" +``` + +Replace the filename with `mcp-reference-memory.cordis.yml` or `engram.cordis.yml`. The path may point to a copied file anywhere on disk. No memory server is present in the shipped composition, so omitting `--config` keeps all three disabled. + +Without a repository checkout, download the selected overlay directly: + +```sh +mkdir -p "${DSH_HOME:-$HOME/.dsh}" +curl --fail --location \ + --output "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml" \ + https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/master/examples/mcp-memory/memorix.cordis.yml +dsh --config "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml" +``` + +Replace `memorix.cordis.yml` in the URL with either of the other filenames to select it. Review a downloaded overlay before running it: Cordis configuration can contain executable `!!js` expressions. + +To keep the selection in personal configuration, merge the chosen file's single `insert` patch into `$DSH_HOME/config.yaml` (normally `~/.dsh/config.yaml`). Do not copy over an existing file: it may already contain unrelated personal patches. + +## Provider setup + +### Memorix + +```sh +npm install --global memorix@1.3.0 +dsh --config "$PWD/examples/mcp-memory/memorix.cordis.yml" +``` + +Memorix works in local heuristic mode without an LLM or embedding service. Configure optional providers in Memorix's own `~/.memorix/config.toml` or project `memorix.toml`. The example keeps Memorix's Git-project identity from the DSH working directory and uses Memorix's own `~/.memorix/data` default. Set `MEMORIX_DATA_DIR` before starting DSH to override it. + +### MCP Reference Memory + +```sh +npm install --global @modelcontextprotocol/server-memory@2026.7.4 +dsh --config "$PWD/examples/mcp-memory/mcp-reference-memory.cordis.yml" +``` + +This reference server stores a local knowledge graph and exposes entity, relation, observation, read, search, and open tools. It needs no model or embedding service. The example stores its JSONL at `$HOME/.dsh-mcp-reference-memory.jsonl` instead of the installed npm package directory. Set `MEMORY_FILE_PATH` before starting DSH to override it. + +Search is case-insensitive substring matching over entity names, types, and observations, not semantic retrieval. The server does not add embeddings, automatic summarization, conflict resolution, or a forgetting policy. + +### Engram + +```sh +go install github.com/Gentleman-Programming/engram/cmd/engram@v1.20.0 +dsh --config "$PWD/examples/mcp-memory/engram.cordis.yml" +``` + +Engram owns storage and project selection: it uses `~/.engram` by default, detects the Git project from the DSH working directory, and accepts `ENGRAM_DATA_DIR` or `ENGRAM_PROJECT` as ambient overrides. + +## Optional shared model instruction + +Add this short, vendor-neutral instruction to your existing model instructions if the server's tool descriptions do not trigger memory use reliably: + +> When the user asks you to remember something, call a memory write tool. When historical information may be relevant, search memory and use relevant results. + +This is additive guidance only. The examples do not replace DSH's system-prompt persona. + +## Verify write, fresh-session recall, and use + +Use one unique value and keep the provider's storage scope unchanged throughout: + +1. In DSH session A, ask: `Remember that my validation drink is lapsang-.` Confirm the model called the provider's write tool and the tool returned success. +2. Create DSH session B in the same running Host. Do not copy session A's conversation. Ask: `What is my validation drink? Check memory.` Confirm the model called the provider's search or recall tool and returned the value. +3. Still in session B, ask: `Use that preference to suggest one drink for the meeting.` Confirm the answer uses the recalled value. + +A new DSH session is required; a Host restart is not. Restart or HMR is needed only after an MCP child crashes because the current generic client does not auto-reconnect; its tool registrations remain until plugin disposal or a successful re-sync, and calls can fail against the closed transport. Initial discovery is asynchronous, so wait for the provider's `mcp__...` tools before sending the first validation prompt. + +## Bring another MCP server + +Copy the same generic shape and use a unique `id` and `serverName`: + +```yaml +- insert: + - id: memory-my-server + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: my-memory + transport: stdio + command: my-memory-mcp + args: [] + env: {} + cwd: !!js process.cwd() +``` + +For a remote server, use `transport: streamable-http`, `url`, and `headers` instead. Provider-specific installation, identity, authentication, models, embeddings, persistence, and licensing remain the provider's responsibility. diff --git a/examples/mcp-memory/README.zh.md b/examples/mcp-memory/README.zh.md new file mode 100644 index 0000000000..1249ae40bb --- /dev/null +++ b/examples/mcp-memory/README.zh.md @@ -0,0 +1,113 @@ +# 第三方记忆 MCP 示例 + +[English](README.md) | 中文 + +这三份**默认关闭的参考配置** 通过 [`@deepseek-ai/dsh-mcp-client`](../../packages/mcp/mcp-client/README.md) 将一个记忆系统连接到 DSH。请选择其中一份,或复制相同的通用 MCP 配置项来连接其他服务器。 + +这些第三方配置仅作为互操作参考;收录不代表 DeepSeek 的认可、推荐、合作关系或持续支持承诺。 + +## DSH 负责什么 + +DSH 解析选中的 Cordis overlay,启动已配置的 stdio 命令或连接已配置的 Streamable HTTP URL,发现 MCP 工具,并以 `mcp____` 的形式公开这些工具。DSH **不负责** 下载服务器、初始化其数据库、选择模型或 embedding 提供方、创建云端账户、迁移提供方数据,也不监管独立的 HTTP 服务。对于 stdio,通用客户端会随 DSH 插件生命周期启动和停止子进程;对于 HTTP,上游服务必须已经运行。 + +stdio 桥接器在启动子进程前会主动移除环境中名称类似凭据的变量和 `DSH_*` 变量;其余环境变量仍会继承。每份示例仅添加其基线所需的覆盖项。如果某个可选的上游功能还需要其他密钥,请将该变量添加到配置项的 `config.env`,不要把密钥直接写进 YAML。 + +## 选择一个 + +| 系统 | 已测试版本 | 传输方式 | 上游前置条件 | +|---|---:|---|---| +| [Memorix](https://github.com/AVIDS2/memorix) | `memorix@1.3.0`(`500792cad3144142293bfbb20acb4841c9f7fcfa`) | stdio | Node 22.18+,并执行 `npm install --global memorix@1.3.0` | +| [MCP Reference Memory](https://github.com/modelcontextprotocol/servers/tree/main/src/memory) | `@modelcontextprotocol/server-memory@2026.7.4`(`6dd0a683e198783e30feabf7abaf42f925bd18b1`) | stdio | `npm install --global @modelcontextprotocol/server-memory@2026.7.4` | +| [Engram](https://github.com/Gentleman-Programming/engram) | `v1.20.0`(`ba9e46ced152c37a7cb9e576153c41995873e2fc`) | stdio | Go 1.25.10+,并执行 `go install github.com/Gentleman-Programming/engram/cmd/engram@v1.20.0`,或安装匹配的发布版二进制文件 | + +## 启用一个 + +将一份 overlay 传给 DSH: + +```sh +dsh --config "$PWD/examples/mcp-memory/memorix.cordis.yml" +``` + +请将文件名替换为 `mcp-reference-memory.cordis.yml` 或 `engram.cordis.yml`。该路径可以指向磁盘任意位置的一份复制文件。交付组合不包含任何记忆服务器,因此不传 `--config` 就会让这三项全部保持关闭。 + +如果本地没有仓库 checkout,可直接下载所选 overlay: + +```sh +mkdir -p "${DSH_HOME:-$HOME/.dsh}" +curl --fail --location \ + --output "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml" \ + https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/master/examples/mcp-memory/memorix.cordis.yml +dsh --config "${DSH_HOME:-$HOME/.dsh}/memory.cordis.yml" +``` + +若要选择另外任一配置,请将 URL 中的 `memorix.cordis.yml` 替换为对应文件名。运行下载的 overlay 前,请先审阅其内容:Cordis 配置可以包含可执行的 `!!js` 表达式。 + +如果要把所选配置保存在个人配置中,请将对应文件中的单个 `insert` patch 合并到 `$DSH_HOME/config.yaml`(通常是 `~/.dsh/config.yaml`)。不要覆盖已有文件,其中可能已经包含无关的个人 patch。 + +## 提供方设置 + +### Memorix + +```sh +npm install --global memorix@1.3.0 +dsh --config "$PWD/examples/mcp-memory/memorix.cordis.yml" +``` + +Memorix 无需 LLM(大语言模型)或 embedding 服务,即可在本地启发式模式下运行。请在 Memorix 自己的 `~/.memorix/config.toml` 或项目 `memorix.toml` 中配置可选提供方。该示例沿用 DSH 工作目录中的 Git 项目标识,并使用 Memorix 自身的默认目录 `~/.memorix/data`。若要覆盖该目录,请在启动 DSH 前设置 `MEMORIX_DATA_DIR`。 + +### MCP Reference Memory + +```sh +npm install --global @modelcontextprotocol/server-memory@2026.7.4 +dsh --config "$PWD/examples/mcp-memory/mcp-reference-memory.cordis.yml" +``` + +该参考服务器存储本地知识图谱,并公开实体、关系、观察、读取、搜索和打开工具。它不需要模型或 embedding 服务。该示例将 JSONL 存储在 `$HOME/.dsh-mcp-reference-memory.jsonl`,而不是已安装的 npm 包(package)目录中。若要覆盖该路径,请在启动 DSH 前设置 `MEMORY_FILE_PATH`。 + +搜索只对实体名称、类型和 observation 进行不区分大小写的子字符串匹配,不是语义检索。该服务器不提供 embedding、自动摘要、冲突消解或遗忘策略。 + +### Engram + +```sh +go install github.com/Gentleman-Programming/engram/cmd/engram@v1.20.0 +dsh --config "$PWD/examples/mcp-memory/engram.cordis.yml" +``` + +Engram 负责存储和项目选择:它默认使用 `~/.engram`,从 DSH 工作目录检测 Git 项目,并接受 `ENGRAM_DATA_DIR` 或 `ENGRAM_PROJECT` 作为环境覆盖项。 + +## 可选的共用模型指令 + +如果服务器的工具描述无法可靠触发记忆使用,请将以下简短、与提供方无关的指令添加到你现有的模型指令中: + +> 用户要求记住时调用写入工具;涉及历史信息时,主动检索并使用相关记忆。 + +这只是附加指导。示例不会替换 DSH 系统提示词中的 persona。 + +## 验证写入、新会话召回和使用 + +请在整个过程中使用一个唯一值,并保持提供方的存储范围不变: + +1. 在 DSH 会话 A 中提出:`Remember that my validation drink is lapsang-.`。确认模型调用了提供方的写入工具,并且工具返回成功。 +2. 在同一个仍在运行的 Host 中创建 DSH 会话 B。不要复制会话 A 的对话。提出:`What is my validation drink? Check memory.`。确认模型调用了提供方的搜索或召回工具,并返回该值。 +3. 继续在会话 B 中提出:`Use that preference to suggest one drink for the meeting.`。确认回答使用了召回的值。 + +必须新建 DSH 会话,但不需要重启 Host。只有 MCP 子进程崩溃后才需要重启或执行 HMR(热模块替换),因为当前的通用客户端不会自动重连;其工具注册会一直保留到插件完成资源释放或成功重新同步,针对已关闭传输的调用可能失败。初始发现过程是异步的,因此发送第一条验证提示词前,请等待提供方的 `mcp__...` 工具出现。 + +## 接入其他 MCP 服务器 + +复制相同的通用结构,并使用唯一的 `id` 和 `serverName`: + +```yaml +- insert: + - id: memory-my-server + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: my-memory + transport: stdio + command: my-memory-mcp + args: [] + env: {} + cwd: !!js process.cwd() +``` + +对于远程服务器,请改用 `transport: streamable-http`、`url` 和 `headers`。提供方专属的安装、身份、认证、模型、embedding、持久化和许可仍由提供方负责。 diff --git a/examples/mcp-memory/engram.cordis.yml b/examples/mcp-memory/engram.cordis.yml new file mode 100644 index 0000000000..018df88b6f --- /dev/null +++ b/examples/mcp-memory/engram.cordis.yml @@ -0,0 +1,11 @@ +# Opt-in reference for Engram 1.20.0. Install the pinned `engram` executable +# first; storage and project selection remain Engram-owned. +- insert: + - id: memory-engram + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: engram + transport: stdio + command: engram + args: [mcp] + cwd: !!js process.cwd() diff --git a/examples/mcp-memory/mcp-reference-memory.cordis.yml b/examples/mcp-memory/mcp-reference-memory.cordis.yml new file mode 100644 index 0000000000..d89fbe2673 --- /dev/null +++ b/examples/mcp-memory/mcp-reference-memory.cordis.yml @@ -0,0 +1,13 @@ +# Opt-in reference for @modelcontextprotocol/server-memory 2026.7.4. Install +# the pinned executable first; DSH starts it but does not run a package manager. +- insert: + - id: memory-mcp-reference + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: reference_memory + transport: stdio + command: mcp-server-memory + cwd: !!js process.cwd() + env: + MEMORY_FILE_PATH: !!js >- + process.env.MEMORY_FILE_PATH?.trim() || process.getBuiltinModule('node:path').join(process.getBuiltinModule('node:os').homedir(), '.dsh-mcp-reference-memory.jsonl') diff --git a/examples/mcp-memory/memorix.cordis.yml b/examples/mcp-memory/memorix.cordis.yml new file mode 100644 index 0000000000..c993581eae --- /dev/null +++ b/examples/mcp-memory/memorix.cordis.yml @@ -0,0 +1,11 @@ +# Opt-in reference for Memorix 1.3.0. Install the pinned `memorix` executable +# first; DSH starts it but does not run a package manager. +- insert: + - id: memory-memorix + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: memorix + transport: stdio + command: memorix + args: [serve] + cwd: !!js process.cwd() diff --git a/lefthook.yml b/lefthook.yml index 1a4e004842..bdab57a9a3 100644 --- a/lefthook.yml +++ b/lefthook.yml @@ -18,6 +18,16 @@ pre-commit: run: node_modules/.bin/tsx scripts/run-oxlint.ts --fix --no-error-on-unmatched-pattern {staged_files} stage_fixed: true + # Regenerate rather than reject: a dependency edit that forgot the notices + # would otherwise fail the test lane long after the commit. The glob matches + # every input the generator reads, including the generator itself and the + # build-time pin source. Deleting a manifest cannot trigger this job — + # lefthook only inspects files present on disk — so that one case still + # falls through to the freshness assertion in the test lane. + - name: third-party notices (staged) + glob: '{package.json,*/package.json,*/*/package.json,*/*/*/package.json,*/*/*/*/package.json,pnpm-workspace.yaml,*/*/pnpm-workspace.yaml,pnpm-lock.yaml,vendor/README.md,python/*/pyproject.toml,scripts/gen-third-party-notices.ts,scripts/build-exe-for-python-sdk.ts}' + run: node_modules/.bin/tsx scripts/gen-third-party-notices.ts && git add THIRD_PARTY_NOTICES.md + - name: whitespace (staged) run: git diff --cached --check diff --git a/package.json b/package.json index 96f72d1c1c..a5f76a0612 100644 --- a/package.json +++ b/package.json @@ -92,6 +92,8 @@ "verify-doc-graphs": "tsx scripts/gen-doc-graphs.ts --check", "gen-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts", "verify-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts --check", + "gen-third-party-notices": "tsx scripts/gen-third-party-notices.ts", + "verify-third-party-notices": "tsx scripts/gen-third-party-notices.ts --check", "gen-module-graph": "tsx scripts/gen-module-graph.ts", "gen-scoped-events": "tsx scripts/gen-scoped-events.ts", "verify-scoped-events": "tsx scripts/gen-scoped-events.ts --check", @@ -120,6 +122,7 @@ "@types/jsdom": "^28.0.3", "@types/mdast": "^4.0.4", "@types/node": "^22.20.0", + "@types/spdx-expression-parse": "^4.0.0", "@typescript-eslint/parser": "8.61.0", "@vitest/coverage-v8": "^4.1.8", "@yarnpkg/cli-dist": "4.17.1", @@ -140,6 +143,8 @@ "oxlint": "1.76.0", "oxlint-tsgolint": "7.0.2001", "publint": "^0.3.21", + "smol-toml": "^1.7.1", + "spdx-expression-parse": "^5.0.0", "tsdown": "^0.22.2", "tsx": "^4.22.4", "typescript": "^6.0.3", diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 4bdeeec7dc..9f091b26c5 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -164,10 +164,10 @@ const SEARCH_MATCHES_FIXTURE: { path: string; matches: { lineNumber: number; lin { path: 'packages/client/ui-conversation/src/client/toolviews/search-row.tsx', matches: [ - { lineNumber: 71, line: 'export function SearchRow({ toolName, block }: ToolRowProps) {' }, - { lineNumber: 73, line: ' const search = searchCardModel(block)' }, - { lineNumber: 90, line: ' ' }, - { lineNumber: 113, line: " ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep' }, SearchRow)" }, + { lineNumber: 33, line: 'export function SearchRow({ toolName, block, inspect, t }: SearchRowProps) {' }, + { lineNumber: 35, line: ' const search = searchCardModel(block)' }, + { lineNumber: 52, line: ' search={search}' }, + { lineNumber: 73, line: " ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow)" }, ], }, ] @@ -197,7 +197,7 @@ const SEARCH_PATHS_FIXTURE = [ 'packages/client/ui-primitives/src/SearchBlock.module.css', 'packages/client/ui-conversation/src/client/contract/search-card-model.ts', 'packages/client/ui-conversation/src/client/toolviews/search-row.tsx', - 'packages/client/ui-conversation/src/client/toolviews/search-row.module.css', + 'packages/client/ui-conversation/tests/search-card.spec.tsx', ] /** diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index e3d86bb196..b022abd659 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/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/runtime/README.md -README.md: e8ba80790307e7123406934c1ab11b86dfc0faf3 -README.zh.md: 6eb69d9cf10959b007f3759378612dbc013a8904 +README.md: 64982c2b5af891b60055a41bc3c30c1ba4041300 +README.zh.md: 2cc2dc30bd4913c52645c76de4bc55d109a40001 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index e8ba807903..64982c2b5a 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -30,6 +30,10 @@ SlotsService gives the renderer separate bare observables for `useSessions` and Because the projection is log-ordered, the node array is seq-monotonic by construction: log-only `command/run` / `command/done` nodes splice in by seq, `Session` merges interrupted frozen nodes by their fractional seqs, and a window whose checkpoint cites a shadowed range outside it renders the marker with nothing logged. The marker's summary text comes from the checkpoint's `compact/summary` provenance; a window cut that left the provenance outside makes the row non-expandable rather than empty, and a later page that supplies it resolves the text. Performance contract: one append materializes at most one node and copies the projection only when it adds that node; an event that changes no node keeps the previous array reference (a chunk storm costs nothing), and unchanged nodes keep their object identity. +## Request inspection + +`SessionHistoryInspection.requests` is one chronological, purpose-discriminated provider-request stream. Assistant requests always carry their numeric `turn` and `step`; compaction requests carry `step: 0` and a `turn` owner that may be `null`. That null owner means a manual compaction ran standalone between turns, not that it belongs to either adjacent turn. A `session/end-seed` boundary closes an unmatched compaction request as an error at the boundary time with `Compaction was interrupted before completion.`; a later start projects as an independent request instead of overwriting the orphan. + ## Code Mode sub-dispatch index `ConversationSnapshot.codeDispatches` groups a `run_code` call's sub-dispatches under their parent callId, in start order, using the native call-block shapes: a `tool/code-dispatch-start` event lands the `RunningToolCall` form (rows derive the running ring from the shape) and its `tool/code-dispatch` settlement replaces it in place with the `ToolResultNode` form, `callTime` carrying the paired start's time. A settle whose start fell outside the replay window appends directly with `callTime: null` (duration unknown — never a fabricated zero). Live mux frames and history replay build the identical index; sub-calls never join the transcript `nodes` flow; per-parent array and map references are memo-stable across unrelated snapshot swaps. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 6eb69d9cf1..2cc2dc30bd 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -30,6 +30,10 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 由于投影按日志顺序,节点数组天然按 seq 单调:仅日志的 `command/run` / `command/done` 节点按 seq 插入,`Session` 按分数 seq 归并被打断的冻结节点,而检查点所引范围落在窗口之外的窗口会渲染出标记且不打印任何日志。标记的摘要文本来自检查点的 `compact/summary` 溯源;窗口切分把溯源留在窗口外时该行不可展开而非空白,后续补上溯源的分页会解析出文本。性能契约:一次追加最多物化一个节点,并且仅在加入该节点时复制投影;不改变任何节点的事件保持上一次的数组引用(分片风暴零成本),未变化的节点保持其对象标识。 +## 请求检查 + +`SessionHistoryInspection.requests` 是一条按时间顺序排列、以用途为判别字段的提供方请求流。助手请求始终携带数值型 `turn` 与 `step`;压缩请求携带 `step: 0`,其 `turn` 所有者可以是 `null`。这个 null 所有者表示手动压缩独立运行在两个轮次之间,并不表示它属于任一相邻轮次。`session/end-seed` 边界会在边界时刻将未匹配的压缩请求以错误状态结束,错误固定为 `Compaction was interrupted before completion.`;后续 start 会投影为独立请求,而不会覆盖这项遗留的未匹配请求。 + ## Code Mode 子调用索引 `ConversationSnapshot.codeDispatches` 按父调用的 callId 和启动顺序,用原生调用块形状组织一个 `run_code` 调用的子调用:`tool/code-dispatch-start` 事件落成 `RunningToolCall` 形状(行组件从该形状推导运行中的转圈状态),其 `tool/code-dispatch` 完结事件原位替换为 `ToolResultNode` 形状,`callTime` 携带成对 start 事件的时间。start 落在回放窗口之外的完结事件则直接追加,`callTime: null`(耗时未知——绝不伪造零耗时)。live mux 帧与历史回放构建相同的索引;子调用永不进入 transcript 的 `nodes` 流;无关快照交换不会改变每个父调用对应的数组引用和映射引用,两者均保持 memo 稳定。 diff --git a/packages/client/runtime/src/client/sessions/request-inspection.ts b/packages/client/runtime/src/client/sessions/request-inspection.ts index e15ad55c8b..e57ff23f58 100644 --- a/packages/client/runtime/src/client/sessions/request-inspection.ts +++ b/packages/client/runtime/src/client/sessions/request-inspection.ts @@ -35,40 +35,55 @@ export interface RequestPromptChange { previous?: ConversationPromptSnapshot } -/** One provider request reconstructed from durable request lifecycle events. */ -export interface RequestView { - /** Request category; compaction is a purpose, not a separate projection. */ - purpose: 'assistant' | 'compaction' +/** Lifecycle fields shared by ordinary generation and compaction requests. */ +interface RequestViewBase { /** Sequence that opened the operation represented by this request. */ startSeq: number - turn: number - /** Agent-loop step, or zero for a direct compaction request. */ - step: number startedAt: number completedAt: number | null status: 'running' | 'complete' | 'error' error?: string - /** Effective ordinary request input, inherited until a later header changes it. */ - prompt?: ConversationPromptSnapshot - /** Prompt change logged while preparing this request. */ - promptChange?: RequestPromptChange provenance?: AssistantProvenanceView requestConfig?: AssistantRequestConfig usage?: unknown /** Assistant message or compaction summary sequence produced by this request. */ resultSeq?: number +} + +/** One ordinary assistant generation reconstructed from durable request events. */ +interface AssistantRequestView extends RequestViewBase { + purpose: 'assistant' + turn: number + /** Agent-loop step that issued this request. */ + step: number + /** Effective ordinary request input, inherited until a later header changes it. */ + prompt?: ConversationPromptSnapshot + /** Prompt change logged while preparing this request. */ + promptChange?: RequestPromptChange + /** Retry ordinal scheduled after a failed ordinary request. */ + retry?: number + maxRetries?: number + retryDelayMs?: number +} + +/** One compaction provider request, either turn-owned or standalone between turns. */ +interface CompactionRequestView extends RequestViewBase { + purpose: 'compaction' + /** Owning turn, or `null` when manual compaction ran between turns. */ + turn: number | null + /** Direct compaction requests do not consume an agent-loop step. */ + step: 0 /** Compaction replacement message sequence, when one was committed. */ replacementSeq?: number /** Safe compaction summary projection. */ summary?: readonly ContentBlock[] /** Complete compaction provider output before the safe projection. */ rawOutput?: readonly ContentBlock[] - /** Retry ordinal scheduled after a failed ordinary request. */ - retry?: number - maxRetries?: number - retryDelayMs?: number } +/** One provider request reconstructed from durable request lifecycle events. */ +export type RequestView = AssistantRequestView | CompactionRequestView + /** Immutable request-centric projection derived from one history window. */ export interface RequestInspectionSnapshot { requests: readonly RequestView[] @@ -110,7 +125,7 @@ interface CompactionStartEvent { type: 'compact/start' seq: number time: number - data: { turn: number } + data: { turn: number | null } } interface CompactionSummaryEvent { @@ -131,7 +146,7 @@ interface CompactionEndEvent { type: 'compact/end' seq: number time: number - data: { turn: number; error?: string } + data: { turn: number | null; error?: string } } function requestKey(turn: number, step: number): string { @@ -228,10 +243,21 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] let activePrompt: ConversationPromptSnapshot | undefined let activeCompaction: number | undefined - const update = (index: number | undefined, change: Partial): void => { + const updateAssistant = ( + index: number | undefined, + change: Partial>, + ): void => { if (index === undefined) return const request = requests[index] - if (request !== undefined) requests[index] = { ...request, ...change } + if (request?.purpose === 'assistant') requests[index] = { ...request, ...change } + } + const updateCompaction = ( + index: number | undefined, + change: Partial>, + ): void => { + if (index === undefined) return + const request = requests[index] + if (request?.purpose === 'compaction') requests[index] = { ...request, ...change } } for (const sourceEvent of events) { @@ -263,7 +289,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } const change = promptChange(activePrompt, prompt, sourceEvent) activePrompt = prompt - update(activeStep === undefined ? undefined : ordinaryByStep.get(activeStep), { + updateAssistant(activeStep === undefined ? undefined : ordinaryByStep.get(activeStep), { prompt, requestConfig: prompt.config, ...(change === undefined ? {} : { promptChange: change }), @@ -278,8 +304,11 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] requestKey(sourceEvent.data.turn, sourceEvent.data.step), ) const request = index === undefined ? undefined : requests[index] - update(index, { - usage: addTokenUsage(request?.usage, sourceEvent.data.chunk.usage), + updateAssistant(index, { + usage: addTokenUsage( + request?.purpose === 'assistant' ? request.usage : undefined, + sourceEvent.data.chunk.usage, + ), }) continue } @@ -288,7 +317,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] requestKey(sourceEvent.data.turn, sourceEvent.data.step), ) const request = index === undefined ? undefined : requests[index] - update(index, { + updateAssistant(index, { completedAt: sourceEvent.time, status: 'complete', resultSeq: sourceEvent.seq, @@ -296,7 +325,9 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] provider: sourceEvent.data.message.source.provider, model: sourceEvent.data.message.source.model, }, - ...(request?.usage !== undefined || sourceEvent.data.usage === undefined + ...(request?.purpose === 'assistant' + && request.usage !== undefined + || sourceEvent.data.usage === undefined ? {} : { usage: sourceEvent.data.usage }), }) @@ -306,8 +337,8 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] const key = requestKey(sourceEvent.data.turn, sourceEvent.data.step) const index = ordinaryByStep.get(key) const request = index === undefined ? undefined : requests[index] - if (request?.status === 'running') { - update(index, { + if (request?.purpose === 'assistant' && request.status === 'running') { + updateAssistant(index, { completedAt: sourceEvent.time, status: 'error', }) @@ -317,7 +348,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } if ((sourceEvent.type as string) === 'llm/retry') { const event = sourceEvent as unknown as RetryEvent - update(ordinaryByStep.get(requestKey(event.data.turn, event.data.step)), { + updateAssistant(ordinaryByStep.get(requestKey(event.data.turn, event.data.step)), { status: 'error', error: event.data.failure.message, retry: event.data.retry, @@ -328,7 +359,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } if (sourceEvent.type === 'turn/end' && sourceEvent.data.reason.kind === 'error') { const reason = sourceEvent.data.reason - update(ordinaryByStep.get(requestKey(sourceEvent.data.turn, reason.step)), { + updateAssistant(ordinaryByStep.get(requestKey(sourceEvent.data.turn, reason.step)), { status: 'error', error: 'failure' in reason ? reason.failure.message : reason.message, }) @@ -336,6 +367,15 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } const type = sourceEvent.type as string + if (type === 'session/end-seed' && activeCompaction !== undefined) { + updateCompaction(activeCompaction, { + completedAt: sourceEvent.time, + status: 'error', + error: 'Compaction was interrupted before completion.', + }) + activeCompaction = undefined + continue + } if (type === 'compact/start') { const event = sourceEvent as unknown as CompactionStartEvent activeCompaction = requests.length @@ -352,7 +392,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } if (type === 'compact/summary' && activeCompaction !== undefined) { const event = sourceEvent as unknown as CompactionSummaryEvent - update(activeCompaction, { + updateCompaction(activeCompaction, { resultSeq: event.seq, summary: event.data.summary, ...(event.data.rawOutput === undefined ? {} : { rawOutput: event.data.rawOutput }), @@ -375,12 +415,12 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] && activeCompaction !== undefined && isCompactionSource(sourceEvent.data.source) ) { - update(activeCompaction, { replacementSeq: sourceEvent.seq }) + updateCompaction(activeCompaction, { replacementSeq: sourceEvent.seq }) continue } if (type !== 'compact/end' || activeCompaction === undefined) continue const event = sourceEvent as unknown as CompactionEndEvent - update(activeCompaction, { + updateCompaction(activeCompaction, { completedAt: event.time, status: event.data.error === undefined ? 'complete' : 'error', ...(event.data.error === undefined ? {} : { error: event.data.error }), diff --git a/packages/client/runtime/tests/request-inspection.spec.ts b/packages/client/runtime/tests/request-inspection.spec.ts index a76036c076..031109ca8c 100644 --- a/packages/client/runtime/tests/request-inspection.spec.ts +++ b/packages/client/runtime/tests/request-inspection.spec.ts @@ -85,6 +85,68 @@ describe('inspectRequests', () => { expect(snapshot.callSchemas.get('call-1')?.name).toBe('read') }) + it('preserves a standalone compaction owner without widening assistant turns', () => { + const snapshot = inspectRequests(entriesOf([ + at(0, 'compact/start', { turn: null }), + at(1, 'compact/summary', { + summary: [{ type: 'text', text: 'standalone summary' }], + provider: 'fake', + model: 'compact-model', + }), + at(2, 'compact/end', { turn: null }), + at(3, 'step/start', { turn: 2, step: 1 }), + ])) + + const [compaction, assistant] = snapshot.requests + expect(compaction).toMatchObject({ + purpose: 'compaction', + turn: null, + step: 0, + status: 'complete', + }) + expect(assistant).toMatchObject({ + purpose: 'assistant', + turn: 2, + step: 1, + status: 'running', + }) + if (assistant?.purpose === 'assistant') { + const turn: number = assistant.turn + expect(turn).toBe(2) + } + }) + + it('interrupts an orphaned compaction at end-seed before projecting a new attempt', () => { + const snapshot = inspectRequests(entriesOf([ + at(0, 'compact/start', { turn: null }), + at(1, 'session/end-seed', {}), + at(2, 'compact/start', { turn: null }), + at(3, 'compact/summary', { + summary: [{ type: 'text', text: 'replacement summary' }], + provider: 'fake', + model: 'compact-model', + }), + at(4, 'compact/end', { turn: null }), + ])) + + expect(snapshot.requests).toMatchObject([ + { + purpose: 'compaction', + startSeq: 0, + status: 'error', + completedAt: 1_700_000_000_001, + error: 'Compaction was interrupted before completion.', + }, + { + purpose: 'compaction', + startSeq: 2, + status: 'complete', + completedAt: 1_700_000_000_004, + summary: [{ type: 'text', text: 'replacement summary' }], + }, + ]) + }) + it('captures schemas for nested tool dispatches from the active request header', () => { const snapshot = inspectRequests(entriesOf([ at(0, 'request/header', { @@ -179,6 +241,7 @@ describe('inspectRequests', () => { ])) expect(snapshot.callSchemas).toEqual(new Map()) - expect(snapshot.requests[0]?.prompt?.tools).toEqual([]) + const [request] = snapshot.requests + expect(request?.purpose === 'assistant' ? request.prompt?.tools : undefined).toEqual([]) }) }) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index db9786931e..ac0bd88de1 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: 66120f222de4b4d4707430a1ec310c6fe801c0c5 -README.zh.md: f5e953f363733341400a292a1946b4e298858b77 +README.md: f7279d2c640d447609c4e9804af633d026b35ed9 +README.zh.md: 2e8f3483c160689cdf5ff283f2955a5c0be4fd8e diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index 66120f222d..f7279d2c64 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -18,13 +18,15 @@ Generic tool rows classify the built-in bash, read, search, write, edit, and run 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. A multi-line command gets one prompt row per line, with the dot marking the call once on the first row — the exit status is the whole call's, so a dot per line would claim a per-line outcome bash does not report. The keyed `BashRow` carries the card resident below its summary row; since tool rows are no longer details-panel click targets, the card's copy and expand controls are the row's only interactions. The render-site fallback row keeps the card 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 per render intent — the terminal and web cards, each with its own bound; 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 `web` render intent renders its web retrieval inline, at both conversation render sites, through ui-primitives' `WebBlock`. `contract/web-card-model.ts` is the single derivation from the snapshot's `resultView`, mirroring the terminal card, so the sites cannot disagree about what a web call shows; it yields null — the generic path — for a running call, a non-web result view, a generic result view, a `card` tag this client version does not know, or a web card whose `kind` this client version does not know (a newer host's value, which the wire cannot be trusted to be `search` or `fetch`). The keyed `WebRow` registers one component under both `web_search` and `web_fetch`, discriminating on the tool name only for its icon and title; a web-declaring tool without a keyed row lands on the `GenericToolCard` fallback, which grows the same resident card, and the details panel renders it at the primitive's full source allowance and, below the card, the flattened model-visible result content — a fetch body is readable only there, since its card carries only the URL and status. Rows cap at `CHAT_WEB_MAX_SOURCES` (8) against the panel's 16, the same summary-versus-reading split the terminal card draws ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md)). +A tool call declaring the `web` render intent renders its web retrieval inline, at both conversation render sites, through ui-primitives' `WebBlock`. `contract/web-card-model.ts` is the single derivation from the snapshot's `resultView`, mirroring the terminal card, so the sites cannot disagree about what a web call shows; it yields null — the generic path — for a running call, a non-web result view, a generic result view, a `card` tag this client version does not know, or a web card whose `kind` this client version does not know (a newer host's value, which the wire cannot be trusted to be `search` or `fetch`). The keyed `WebRow` registers one component under both `web_search` and `web_fetch`, discriminating on the tool name only for its icon and title; it composes the shared `ToolRow`, feeding the card as ToolRow's `web` body, so the retrieval is the row's collapsed-by-default expanded card (the same unified expand every card row has). A web-declaring tool without a keyed row lands on the `GenericToolCard` fallback, which routes the card through ToolRow the same way, and the details panel renders it at the primitive's full source allowance and, below the card, the flattened model-visible result content — a fetch body is readable only there, since its card carries only the URL and status. Rows cap at `CHAT_WEB_MAX_SOURCES` (8) against the panel's 16, the same summary-versus-reading split the terminal card draws ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md)). -A tool call declaring the `diff` render intent (the `write`/`edit` tools) renders its applied change inline through ui-primitives' `DiffBlock`, the same four-layer shape. `contract/diff-card-model.ts` is the single derivation from the `callView`/`resultView` pair; the settled result's hunks replace the call-time diff, and it yields null — the generic path — for any other card tag or a generic result view (write/edit's execution errors). The keyed `FileMutationRow` (registered under both `write` and `edit`) carries the card resident below its summary, whose path link still opens the file through the host; the render-site fallback and the details panel are diff-aware too. Rows cap at `CHAT_DIFF_MAX_LINES` (8) against the panel's 16 ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-diff-card.md)). +A `read` call declaring the `read` render intent renders the returned file window inline, at both conversation render sites, through ui-primitives' `ReadBlock` — the line-numbered, syntax-highlighted content the tool projects. `contract/read-card-model.ts` is the single derivation from the snapshot's `resultView`; the read card is result-side only (a call carries no file content until `execute` returns), so a running read shows its summary alone and it yields null — the generic path — for a non-read result view or a `card` tag this client version does not know. The keyed `ReadRow` composes the shared `ToolRow`, feeding the card as ToolRow's `read` body, so it is the row's collapsed-by-default expanded card; the summary stays a path link that opens the file through the host. The render-site fallback and the details panel are read-aware too. Rows cap at `CHAT_READ_MAX_LINES` (8) against the panel's 16 ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.md)). + +A tool call declaring the `diff` render intent (the `write`/`edit` tools) renders its applied change inline through ui-primitives' `DiffBlock`, the same four-layer shape. `contract/diff-card-model.ts` is the single derivation from the `callView`/`resultView` pair; the settled result's hunks replace the call-time diff, and it yields null — the generic path — for any other card tag or a generic result view (write/edit's execution errors). The keyed `FileMutationRow` (registered under both `write` and `edit`) composes the shared `ToolRow`, feeding the diff as ToolRow's `diff` body, so it is the row's collapsed-by-default expanded card; the summary path link still opens the file through the host, and an errored mutation (no diff card) surfaces its error text through ToolRow's Output section with the first line in the collapsed summary. The render-site fallback and the details panel are diff-aware too. Rows cap at `CHAT_DIFF_MAX_LINES` (8) against the panel's 16 ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-diff-card.md)). The chat flow projects consecutive model-retry nodes across retry turns into one stable, muted status row updated to the latest attempt; every retry event remains in the runtime snapshot and session log. Its frontend countdown anchors the scheduled delay to client receipt, avoiding host/browser clock skew, rounds remaining time up to seconds, and has a one-second floor. The latest unresolved retry uses a left-to-right text shimmer. Subsequent turn facts distinguish an attempt that started from one cancelled during backoff, while the Host running bit only controls the live animation; the row then shows a static completed or cancelled label. Normal policy rows show the finite retry maximum; always policy rows show `∞`. Activating the row reveals the latest exact retry delay and failure message. The client runtime removes each failed step's streaming tail before its retry node arrives, while the status remains visible after a later attempt succeeds. -A `grep`/`glob` call declaring the `search` render intent renders its result inline, at the same render sites, through ui-primitives' `SearchBlock` — grep's matches grouped by file (each a collapsible header of `lineNumber: line` rows), glob's flat path list. `contract/search-card-model.ts` is the single derivation from the snapshot's `resultView`; unlike the terminal card it reads no `callView`, since a search has no matches or paths before `execute`, so a running search shows its summary alone. It yields null — the generic path — for any non-search result view, a `card` or `kind` this client version does not compile, and (because those ride the untrusted wire frame) a known kind whose `files`/`paths` is malformed. The keyed `SearchRow`, registered under both `grep` and `glob` since the derived `kind` decides the shape, carries the card resident below its summary; the render-site fallback keeps it behind the expand control. Both cap at `CHAT_SEARCH_MAX_LINES` (8) against the panel's 16. A capped search drops rows from the card, but the locator to the rest — grep/glob's `Full … stored at …` footer — lives only in the result text, so the derivation surfaces that as a recovery footer below the card when (and only when) the result was truncated; a settled call with no card at all (an errored search, a nested `run_code` sub-dispatch, a legacy generic result) falls back to its flattened result text so nothing is lost behind a bare summary ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-search-card.md)). +A `grep`/`glob` call declaring the `search` render intent renders its result inline, at the same render sites, through ui-primitives' `SearchBlock` — grep's matches grouped by file (each a collapsible header of `lineNumber: line` rows), glob's flat path list. `contract/search-card-model.ts` is the single derivation from the snapshot's `resultView`; unlike the terminal card it reads no `callView`, since a search has no matches or paths before `execute`, so a running search shows its summary alone. It yields null — the generic path — for any non-search result view, a `card` or `kind` this client version does not compile, and (because those ride the untrusted wire frame) a known kind whose `files`/`paths` is malformed. The keyed `SearchRow`, registered under both `grep` and `glob` since the derived `kind` decides the shape, composes the shared `ToolRow`, feeding the card as ToolRow's `search` body, so it is the row's collapsed-by-default expanded card; the render-site fallback routes it the same way. Both cap at `CHAT_SEARCH_MAX_LINES` (8) against the panel's 16. A capped search drops rows from the card, but the locator to the rest — grep/glob's `Full … stored at …` footer — lives only in the result text, so the derivation surfaces that as a recovery footer below the card when (and only when) the result was truncated; a settled call with no card at all (an errored search, a nested `run_code` sub-dispatch, a legacy generic result) surfaces its flattened result text through ToolRow's Output section so nothing is lost behind a bare summary ([decision](../../../.agents/notes/implemented/feature/2026-07-30-web-search-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`/`openFile`) 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 f5e953f363..2e8f3483c1 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -16,13 +16,15 @@ 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。多行命令的每一行各占一个提示行,状态点只在第一行为整次调用标记一次——退出状态属于整次调用,因此每行一枚就会声称一个 bash 并不报告的逐行结果。键控的 `BashRow` 把卡片常驻在摘要行下方;由于工具行已不再是详情面板的点击目标,卡片的复制与展开控件就是该行唯一的交互。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。内联输出按渲染意图开放——终端卡片与 web 卡片,各有自己的上限;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 `web` 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 `WebBlock` 内联渲染其 web 检索。`contract/web-card-model.ts` 是从快照的 `resultView` 推导的唯一位置,镜像终端卡片,因此两个渲染点不可能对一次 web 调用的显示产生分歧;对运行中的调用、非 web 的 result view、generic result view、本客户端版本不认识的 `card` 标签,或本客户端版本不认识 `kind` 的 web 卡片(更新的 host 发来的值,wire 上不可信其为 `search` 或 `fetch`),它返回 null,落回通用路径。键控的 `WebRow` 把一个组件注册在 `web_search` 与 `web_fetch` 两个键下,仅根据工具名判别以选取图标与标题;没有自己键控行的 web 声明工具落到 `GenericToolCard` 兜底,它长出同一张常驻卡片,详情面板则以原语的完整 source 额度渲染它,并在卡片下方渲染摊平的模型可见结果内容——fetch 正文只在此处可读,因为其卡片只携带 URL 和状态。行的上限是 `CHAT_WEB_MAX_SOURCES`(8),面板为 16,与终端卡片所画的摘要面对阅读面的同一划分([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md))。 +声明 `web` 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 `WebBlock` 内联渲染其 web 检索。`contract/web-card-model.ts` 是从快照的 `resultView` 推导的唯一位置,镜像终端卡片,因此两个渲染点不可能对一次 web 调用的显示产生分歧;对运行中的调用、非 web 的 result view、generic result view、本客户端版本不认识的 `card` 标签,或本客户端版本不认识 `kind` 的 web 卡片(更新的 host 发来的值,wire 上不可信其为 `search` 或 `fetch`),它返回 null,落回通用路径。键控的 `WebRow` 把一个组件注册在 `web_search` 与 `web_fetch` 两个键下,仅根据工具名判别以选取图标与标题;它组合共享的 `ToolRow`,把卡片作为 ToolRow 的 `web` body 传入,因此检索成为该行默认折叠的展开卡片(与每个卡片行相同的统一展开交互)。没有自己键控行的 web 声明工具落到 `GenericToolCard` 兜底,它以同样方式经 ToolRow 渲染卡片,详情面板则以原语的完整 source 额度渲染它,并在卡片下方渲染摊平的模型可见结果内容——fetch 正文只在此处可读,因为其卡片只携带 URL 和状态。行的上限是 `CHAT_WEB_MAX_SOURCES`(8),面板为 16,与终端卡片所画的摘要面对阅读面的同一划分([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md))。 -声明 `diff` 渲染意图的工具调用(`write`/`edit` 工具),通过 ui-primitives 的 `DiffBlock` 内联渲染其已应用的改动,采用同一套四层结构。`contract/diff-card-model.ts` 是从 `callView`/`resultView` 对推导的唯一位置;已结算 result 的 hunk 替换 call 时 diff,对任何其他 card 标签或 generic result view(write/edit 的执行错误)它返回 null,落回通用路径。键控的 `FileMutationRow`(在 `write` 与 `edit` 下都注册)把卡片常驻在摘要之下,其路径链接仍经 host 打开文件;渲染点兜底行与详情面板同样感知 diff。行的上限是 `CHAT_DIFF_MAX_LINES`(8),面板为 16([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-diff-card.md))。 +声明 `read` 渲染意图的 `read` 调用,会在两个对话渲染点上都通过 ui-primitives 的 `ReadBlock` 内联渲染返回的文件窗口——工具投影出的带行号、语法高亮的内容。`contract/read-card-model.ts` 是从快照的 `resultView` 推导的唯一位置;read 卡片是仅结果侧的(调用在 `execute` 返回前不携带文件内容),所以运行中的 read 只显示摘要,且对非 read 的 result view 或本客户端版本不认识的 `card` 标签返回 null,落回通用路径。键控的 `ReadRow` 组合共享的 `ToolRow`,把卡片作为 ToolRow 的 `read` body 传入,因此它是该行默认折叠的展开卡片;摘要仍是一个经 host 打开文件的路径链接。渲染点兜底行与详情面板同样感知 read。行的上限是 `CHAT_READ_MAX_LINES`(8),面板为 16([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.md))。 + +声明 `diff` 渲染意图的工具调用(`write`/`edit` 工具),通过 ui-primitives 的 `DiffBlock` 内联渲染其已应用的改动,采用同一套四层结构。`contract/diff-card-model.ts` 是从 `callView`/`resultView` 对推导的唯一位置;已结算 result 的 hunk 替换 call 时 diff,对任何其他 card 标签或 generic result view(write/edit 的执行错误)它返回 null,落回通用路径。键控的 `FileMutationRow`(在 `write` 与 `edit` 下都注册)组合共享的 `ToolRow`,把 diff 作为 ToolRow 的 `diff` body 传入,因此它是该行默认折叠的展开卡片;摘要路径链接仍经 host 打开文件,而出错的改动(没有 diff 卡片)经 ToolRow 的 Output 区呈现其错误文本,首行进入折叠摘要。渲染点兜底行与详情面板同样感知 diff。行的上限是 `CHAT_DIFF_MAX_LINES`(8),面板为 16([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-diff-card.md))。 聊天流会将跨重试轮次连续出现的模型重试节点投影为一个稳定的弱化状态行,并用最新一次尝试更新该行;每个重试事件仍保留在运行时快照与会话日志中。前端倒计时以客户端收到事件的时刻为计划延迟的起点,避免 Host 与浏览器的时钟偏差;剩余时间向上取整到秒,且下限为 1 秒。最近一次尚未完成的重试会显示从左到右的文字渐变动画。后续轮次事实用于区分已开始的尝试与在退避期间取消的尝试,Host 的 running 位只控制实时动画;随后该行会显示静态的已完成或已取消标签。normal 策略行显示有限重试上限;always 策略行显示 `∞`。激活该行会显示最近一次重试的精确延迟和失败消息。客户端运行时会在相应重试节点到达前移除每个失败步骤的流式输出尾部;后续某次尝试成功后,该状态仍保持可见。 -声明 `search` 渲染意图的 `grep`/`glob` 调用,会在同样的渲染点上通过 ui-primitives 的 `SearchBlock` 内联渲染其结果——grep 的匹配按文件分组(每个是一个可折叠的头,下辖 `lineNumber: line` 行),glob 是扁平路径列表。`contract/search-card-model.ts` 是从快照的 `resultView` 推导的唯一位置;与终端卡片不同,它不读 `callView`,因为搜索在 `execute` 前没有匹配或路径,所以运行中的搜索只显示摘要。对任何非搜索的结果视图、当前客户端版本无法编译的 `card` 或 `kind`、以及(因为这些都与不可信的 wire 帧同行)一个 `files`/`paths` 格式错误的已知 kind,它都返回 null,落回通用路径。键控的 `SearchRow` 因推导出的 `kind` 决定形态而同时注册在 `grep` 与 `glob` 下,把卡片常驻在摘要行下方;渲染点兜底行则把它保持在展开控件之后。两者上限都是 `CHAT_SEARCH_MAX_LINES`(8),面板为 16。被截断的搜索会从卡片里丢掉一些行,但通往其余部分的定位符——grep/glob 的 `Full … stored at …` 脚注——只存在于结果文本里,因此推导在(且仅在)结果被截断时把它作为恢复脚注画在卡片下方;一个完全没有卡片的已结算调用(出错的搜索、嵌套 `run_code` 子派发、旧日志的 generic 结果)则回退到其压平后的结果文本,从而不让任何内容丢失在一个光秃秃的摘要之后([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-search-card.md))。 +声明 `search` 渲染意图的 `grep`/`glob` 调用,会在同样的渲染点上通过 ui-primitives 的 `SearchBlock` 内联渲染其结果——grep 的匹配按文件分组(每个是一个可折叠的头,下辖 `lineNumber: line` 行),glob 是扁平路径列表。`contract/search-card-model.ts` 是从快照的 `resultView` 推导的唯一位置;与终端卡片不同,它不读 `callView`,因为搜索在 `execute` 前没有匹配或路径,所以运行中的搜索只显示摘要。对任何非搜索的结果视图、当前客户端版本无法编译的 `card` 或 `kind`、以及(因为这些都与不可信的 wire 帧同行)一个 `files`/`paths` 格式错误的已知 kind,它都返回 null,落回通用路径。键控的 `SearchRow` 因推导出的 `kind` 决定形态而同时注册在 `grep` 与 `glob` 下,组合共享的 `ToolRow`,把卡片作为 ToolRow 的 `search` body 传入,因此它是该行默认折叠的展开卡片;渲染点兜底行以同样方式渲染它。两者上限都是 `CHAT_SEARCH_MAX_LINES`(8),面板为 16。被截断的搜索会从卡片里丢掉一些行,但通往其余部分的定位符——grep/glob 的 `Full … stored at …` 脚注——只存在于结果文本里,因此推导在(且仅在)结果被截断时把它作为恢复脚注画在卡片下方;一个完全没有卡片的已结算调用(出错的搜索、嵌套 `run_code` 子派发、旧日志的 generic 结果)则经 ToolRow 的 Output 区呈现其压平后的结果文本,从而不让任何内容丢失在一个光秃秃的摘要之后([决策](../../../.agents/notes/implemented/feature/2026-07-30-web-search-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`/`openFile`),`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(瀑布式事件)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/src/client/apply.ts b/packages/client/ui-conversation/src/client/apply.ts index 9d569eba29..489ad34e3f 100644 --- a/packages/client/ui-conversation/src/client/apply.ts +++ b/packages/client/ui-conversation/src/client/apply.ts @@ -20,9 +20,9 @@ import { InputBar } from './skeleton/InputBar.tsx' import { ChatView } from './chat/ChatView.tsx' import { StatsLine } from './chat/StatsLine.tsx' import { bashToolviewSample } from './toolviews/bash-sample.tsx' -import { searchToolview } from './toolviews/search-row.tsx' import { readToolview } from './toolviews/read-row.tsx' import { fileMutationToolview } from './toolviews/file-mutation-row.tsx' +import { searchToolview } from './toolviews/search-row.tsx' import { webToolview } from './toolviews/web-row.tsx' import { ApprovalPanel } from './skeleton/ApprovalPanel.tsx' import { todoToolview } from './toolviews/todo-row.tsx' @@ -322,10 +322,6 @@ export function apply(ctx: Context): void { // (ToolRow-matching Bash · {description} chrome; scoped badge in child sessions). ctx.plugin(bashToolviewSample) - // The grep/glob search row rides the same seam: one component registered - // under both tool names, since both declare the same search render intent. - ctx.plugin(searchToolview) - // The read row rides the same seam (a product registration, not a sample): // Read · {path} chrome with the file's read card resident below it. ctx.plugin(readToolview) @@ -334,6 +330,11 @@ export function apply(ctx: Context): void { // diff render intent, so these rows stack the applied diff card under their // path-link summary (the terminal card's posture, applied to diffs). ctx.plugin(fileMutationToolview) + + // The grep/glob search row rides the same seam: one component registered + // under both tool names, since both declare the same search render intent. + ctx.plugin(searchToolview) + // The web rows ride the same seam: one WebRow registered under both // web_search and web_fetch, rendering the completed retrieval's web card // resident under the summary (a product registration, not a sample). diff --git a/packages/client/ui-conversation/src/client/chat/GenericToolCard.module.css b/packages/client/ui-conversation/src/client/chat/GenericToolCard.module.css deleted file mode 100644 index d21f6d3712..0000000000 --- a/packages/client/ui-conversation/src/client/chat/GenericToolCard.module.css +++ /dev/null @@ -1,17 +0,0 @@ -/* GenericToolCard resident cards: a read-declaring or web-declaring tool - without its own keyed row (e.g. web_fetch) grows a resident card under its - summary row. A column around the ToolRow keeps the row's own 24px height, so - the read card renders identically to the keyed ReadRow and the web card to - the web_search/web_fetch WebRow. */ - -.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. */ -.read, -.web { - margin: 4px 0 4px 22px; -} diff --git a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx index 40c209627b..705d1d039f 100644 --- a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx +++ b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx @@ -7,17 +7,16 @@ import type { ReactNode } from 'react' import { IconApiOutline14, IconBrowseOutline16, IconCodeOutline16, IconEditOutline16, IconSearchOutline16, IconSparkle16, - IconThinkOutline14, ReadBlock, WebBlock, + IconThinkOutline14, } from '@deepseek-ai/dsh-client-ui-primitives' import type { ChatViewSlotProps, ToolRowOwnerProps } from '../contract/slots.ts' -import { searchCardModel } from '../contract/search-card-model.ts' -import { CHAT_READ_MAX_LINES, readCardModel } from '../contract/read-card-model.ts' +import { readCardModel } from '../contract/read-card-model.ts' import { diffCardModel } from '../contract/diff-card-model.ts' +import { searchCardModel } from '../contract/search-card-model.ts' import { terminalCardModel, terminalFailed } from '../contract/terminal-card-model.ts' -import { CHAT_WEB_MAX_SOURCES, webCardModel } from '../contract/web-card-model.ts' +import { webCardModel } from '../contract/web-card-model.ts' import { toolRowModel, type ToolRowVariant } from '../contract/tool-call-model.ts' import { ToolRow } from './ToolRow.tsx' -import css from './GenericToolCard.module.css' /** Variant leading icons (figma table); all glyphs render at 14 inside the 16px leading box. */ const VARIANT_ICONS: Record = { @@ -39,9 +38,9 @@ export interface GenericToolCardProps extends ToolRowOwnerProps { export function GenericToolCard({ toolName, block, cwd, openFile, inspect, t }: GenericToolCardProps) { const model = toolRowModel(toolName, block, cwd) const terminal = terminalCardModel(block, cwd) - const search = searchCardModel(block) const read = readCardModel(block, cwd) const diff = diffCardModel(block) + const search = searchCardModel(block) const web = webCardModel(block) // A failing exit status is the terminal card's own error signal (the call // itself settles isError:false), surfaced as the row's red state dot. @@ -49,7 +48,7 @@ export function GenericToolCard({ toolName, block, cwd, openFile, inspect, t }: ? 'error' : model.state const singleFile = model.filePath !== undefined - const row = ( + return ( ) - // A read-declaring tool without its own keyed row lands here (e.g. web_fetch), - // so the file's read card is resident below the summary row exactly as the - // keyed ReadRow draws it. Only wrap when a card is present, so every other - // tool keeps the bare ToolRow. - if (read !== null) { - return ( -
- {row} - -
- ) - } - // A web-declaring tool without its own keyed row lands here; its card is - // resident under the summary, mirroring WebRow (and BashRow's terminal card). - if (web === null) return row - return ( -
- {row} - -
- ) } 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 44511ee03d..81e41b066f 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.module.css +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.module.css @@ -248,13 +248,18 @@ /* The block-shaped expanded bodies: the code variant's run_code program through CodeBlock (shiki-highlighted TypeScript), a terminal card's command - output through TerminalBlock, and a search card's grouped matches or path - list through SearchBlock. All are drawn by the shared primitive, so only the - row's indentation is this file's concern — the margin also replaces each + output through TerminalBlock, a diff card through DiffBlock, a read card's + line-numbered window through ReadBlock, a search card's grouped matches or + path list through SearchBlock, and a web card's citation/source list through + WebBlock. All 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, -.searchBody { +.diffBody, +.readBody, +.searchBody, +.webBody { margin: 4px 0 4px 4px; } @@ -269,12 +274,6 @@ color: var(--dsw-alias-label-tertiary); } -/* A write/edit diff renders through DiffBlock; like the terminal card it draws - its own surface, so only the row indentation is this file's concern. */ -.diffBody { - margin: 4px 0 4px 4px; -} - /* In-row code renders at the smaller code size (12/18) via each primitive's rebindable content-font seam; standalone markdown code blocks keep 13/22. */ .codeBody { @@ -290,3 +289,15 @@ --dsl-terminal-output-max-height: 224px; border: 1px solid var(--dsw-alias-border-l1); } + +/* Visually hidden run-state label for assistive technology: the StateDot and + the running sweep are aria-hidden / colour-only, so the text carries the + running/failed/interrupted state to a screen reader. */ +.visuallyHidden { + position: absolute; + width: 1px; + height: 1px; + overflow: hidden; + clip: rect(0 0 0 0); + white-space: nowrap; +} diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx index 95e14771d5..46cdbda191 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx @@ -3,26 +3,33 @@ // separator dot + FILL-truncated summary, drawn through the shared // DisclosureRow chrome with the whole row as the expand toggle (click / // Enter / Space, icon→chevron hover preview). The collapsed row is always -// one line; every row with body, output, terminal, or search material is -// expandable; the summary stays inline while open, except Think, whose body -// opens with the same first line and would repeat it. +// one line; every row with body, output, or a card material (terminal, diff, +// read, search, web) is expandable; the summary stays inline while open, +// except Think, whose body opens with the same first line and would repeat it. // The expanded body — an IN/OUT gutter-labeled card (figma 1249:35657) for -// text input/output, the run_code program through CodeBlock, a terminal -// card's command output through TerminalBlock, or a search card's grouped -// matches / path list through SearchBlock (capped at CHAT_SEARCH_MAX_LINES) — -// lives in a max-height scroll container so a long payload scrolls internally -// instead of taking over the message flow; Think's prose is the exception and -// flows uncapped like message text. Expand state is component-local view state. -// File-tool summaries are path links that open through the host (stopPropagation -// keeps the two gestures independent); an error row's collapsed summary is the -// failure's first line in the error color. +// text input/output, the run_code program through CodeBlock, or a card +// primitive (TerminalBlock, DiffBlock, ReadBlock, SearchBlock, WebBlock) for a +// call that declared that render intent — lives in a max-height scroll +// container so a long payload scrolls internally instead of taking over the +// message flow; Think's prose is the exception and flows uncapped like message +// text. Every card kind starts collapsed, so a run of tool calls stays +// scannable; the details panel is the single-call full-height reading surface. +// Expand state is component-local view state. File-tool summaries are path +// links that open through the host (stopPropagation keeps the two gestures +// independent); an error row's collapsed summary is the failure's first line in +// the error color. -import { useState, type MouseEvent, type ReactNode } from 'react' +import { useState, type KeyboardEvent, type MouseEvent, type ReactNode } from 'react' import clsx from 'clsx' -import { CodeBlock, DiffBlock, SearchBlock, StateDot, TerminalBlock } from '@deepseek-ai/dsh-client-ui-primitives' +import { + CodeBlock, DiffBlock, ReadBlock, SearchBlock, StateDot, TerminalBlock, WebBlock, +} from '@deepseek-ai/dsh-client-ui-primitives' +import type { WebBlockProps } from '@deepseek-ai/dsh-client-ui-primitives' import type { TranslateNS } from '@deepseek-ai/dsh-client-ui-slots' -import { CHAT_SEARCH_MAX_LINES, type SearchCardModel } from '../contract/search-card-model.ts' import { CHAT_DIFF_MAX_LINES, type DiffCardModel } from '../contract/diff-card-model.ts' +import { CHAT_READ_MAX_LINES, type ReadCardModel } from '../contract/read-card-model.ts' +import { CHAT_SEARCH_MAX_LINES, type SearchCardModel } from '../contract/search-card-model.ts' +import { CHAT_WEB_MAX_SOURCES } from '../contract/web-card-model.ts' import { terminalBlockLabels, type TerminalCardModel } from '../contract/terminal-card-model.ts' import type { ToolRowState, ToolRowVariant } from '../contract/tool-call-model.ts' import { DisclosureRow } from './DisclosureRow.tsx' @@ -47,24 +54,34 @@ export interface ToolRowProps { /** * Terminal-card material for a call whose render intent is a terminal card * (derived by `terminalCardModel`); it replaces the text sections when - * present. A row with no body, no output, and no terminal material is not - * expandable. + * present. A call carries at most one card kind, so the card props below are + * mutually exclusive. */ terminal?: TerminalCardModel | null | undefined + /** + * Diff-card material for a call whose render intent is a diff card (derived by + * `diffCardModel`); it replaces the text body when present, the same way + * `terminal` does. + */ + diff?: DiffCardModel | null | undefined + /** + * Read-card material for a call whose render intent is a read card (derived by + * `readCardModel`); it replaces the text body with the file's line-numbered, + * syntax-highlighted window when present. + */ + read?: ReadCardModel | null | undefined /** * Search-card material for a call whose render intent is a search card - * (derived by `searchCardModel`); it replaces the text body when present. - * Null or absent leaves the text body. A call carries at most one card kind, - * so `terminal`, `search`, and `diff` are never both present on the same row. + * (derived by `searchCardModel`); it replaces the text body with grouped + * matches or a path list when present. */ search?: SearchCardModel | null | undefined /** - * Diff-card material for a call whose render intent is a diff card (derived by - * `diffCardModel`); it replaces the text body when present, the same way - * `terminal` does. A call carries at most one card intent, so the cards are - * never both set. + * Web-card material for a call whose render intent is a web card (derived by + * `webCardModel`); it replaces the text body with the retrieval's citation + * list or fetched-source card when present. */ - diff?: DiffCardModel | null | undefined + web?: WebBlockProps | null | undefined state: ToolRowState /** * Filesystem path from tool args; when set with onOpenFile, the summary @@ -101,6 +118,19 @@ function leadingFor(state: ToolRowState, icon: ReactNode): ReactNode { } } +/** Visually hidden run-state label: the StateDot and the CSS sweep are both + * aria-hidden / colour-only, so assistive technology needs this text to know a + * row is running, failed, or interrupted. null in the ok state (the icon and + * summary already describe a settled row). */ +function stateStatus(state: ToolRowState, t: TranslateNS<'conversation'>): string | null { + switch (state) { + case 'running': return t('row.running') + case 'error': return t('row.failed') + case 'stopped': return t('row.stopped') + default: return null + } +} + export function ToolRow({ t, variant, @@ -112,8 +142,10 @@ export function ToolRow({ output, errorSummary, terminal, - search, diff, + read, + search, + web, state, filePath, onOpenFile, @@ -121,13 +153,20 @@ export function ToolRow({ }: ToolRowProps) { const [expanded, setExpanded] = useState(false) const terminalBody = terminal ?? null - const searchBody = search ?? null const diffBody = diff ?? null + const readBody = read ?? null + const searchBody = search ?? null + const webBody = web ?? null const outputText = output ?? null - // A search or diff card replaces the text body; a call carries at most one - // card kind, so terminal, search, and diff are never both present on a row. - const expandable = body !== null || outputText !== null || terminalBody !== null || searchBody !== null || diffBody !== null + // A card replaces the text body; a call carries at most one card kind, so the + // card props are mutually exclusive. Any of them, or a text body/output, + // makes the row expandable. + const card = terminalBody ?? diffBody ?? readBody ?? searchBody ?? webBody + const expandable = body !== null || outputText !== null || card !== null const open = expanded && expandable + // The run-state label AT needs: the StateDot and the running sweep are both + // aria-hidden / colour-only, so a stopped or running row is otherwise silent. + const status = stateStatus(state, t) // An error row's collapsed summary IS the failure: the first error line in // the error color outranks both the args summary and a terminal description. const failureLine = state === 'error' ? errorSummary ?? null : null @@ -141,6 +180,13 @@ export function ToolRow({ event.stopPropagation() if (filePath !== undefined) onOpenFile?.(filePath) } + // Keep Enter/Space on the focused path link from bubbling to the row's + // keydown handler, which would preventDefault() the key and toggle expand + // instead of activating the link — the keyboard analogue of openFile's + // stopPropagation. The native button still fires its own onClick from the key. + const fileLinkKeyDown = (event: KeyboardEvent) => { + if (event.key === 'Enter' || event.key === ' ') event.stopPropagation() + } // Think reasoning is prose, not an input payload: expanded, it renders as // plain indented text (no IN/OUT card) and the inline summary — the body's // own first line — yields to avoid repeating itself. @@ -153,6 +199,7 @@ export function ToolRow({ // of losing it with the icon. return (
+ {status !== null && {status}} {summaryText} @@ -198,51 +246,55 @@ export function ToolRow({ className={css.terminalBody} /> ) - : searchBody !== null - ? ( - <> - - {/* A capped search's recovery locator lives only in the result - text; show it below the card so the dropped rows survive. */} - {searchBody.recovery !== undefined && ( -
{searchBody.recovery}
- )} - - ) - : diffBody !== null - ? - : isThink - ?
{body}
- : ( + : diffBody !== null + ? + : readBody !== null + ? + : searchBody !== null + ? ( <> - {variant === 'code' && body !== null && ( -
- -
- )} - {(cardBody !== null || outputText !== null) && ( -
- {cardBody !== null && ( -
- IN - {cardBody} -
- )} - {cardBody !== null && outputText !== null && ( - - )} - {outputText !== null && ( -
- OUT - - {outputText} - -
- )} -
+ + {/* A capped search's recovery locator lives only in the result + text; show it below the card so the dropped rows survive. */} + {searchBody.recovery !== undefined && ( +
{searchBody.recovery}
)} - )} + ) + : webBody !== null + ? + : isThink + ?
{body}
+ : ( + <> + {variant === 'code' && body !== null && ( +
+ +
+ )} + {(cardBody !== null || outputText !== null) && ( +
+ {cardBody !== null && ( +
+ IN + {cardBody} +
+ )} + {cardBody !== null && outputText !== null && ( + + )} + {outputText !== null && ( +
+ OUT + + {outputText} + +
+ )} +
+ )} + + )} {inspect !== undefined && ( - ) : ( - {model.summary} - )} -
- {diff !== null && ( - - )} - {failure !== null &&
{failure}
} -
+ } + title={model.title} + summary={model.summary} + body={null} + output={model.output} + errorSummary={model.errorSummary} + diff={diff} + state={model.state} + filePath={model.filePath} + onOpenFile={openFile} + inspect={inspect} + /> ) } @@ -87,7 +67,7 @@ export const fileMutationToolview = { * @param ctx - registrant context (disposal rides ctx.effect inside slots.register). */ apply(ctx: Context): void { - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'edit' }, FileMutationRow) - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'write' }, FileMutationRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'edit', locale: NS }, FileMutationRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'write', locale: NS }, FileMutationRow) }, } diff --git a/packages/client/ui-conversation/src/client/toolviews/read-row.module.css b/packages/client/ui-conversation/src/client/toolviews/read-row.module.css deleted file mode 100644 index a03a949451..0000000000 --- a/packages/client/ui-conversation/src/client/toolviews/read-row.module.css +++ /dev/null @@ -1,119 +0,0 @@ -/* Read toolview: same geometry/tokens as ToolRow (figma Read · {path}), plus - the read card the row stacks under its summary line. */ - -/* Summary line over the read 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. */ -.read { - margin: 4px 0 4px 22px; -} - -.root { - position: relative; /* sweep-glare overlay anchor */ - overflow: hidden; - display: flex; - align-items: center; - height: 24px; - min-width: 0; -} - -/* Running sweep glare — same pattern as BashRow/ToolRow, so a running read row - gives the same executing feedback a running command row does. The leading - read icon stays static (a read has no per-step state to animate); the sweep - is the row-level running signal. */ -.root[data-state='running']::after { - content: ''; - position: absolute; - top: 0; - bottom: 0; - left: 0; - width: 300px; - background: linear-gradient( - 90deg, - transparent 0%, - color-mix(in srgb, var(--dsw-alias-bg-base) 60%, transparent) 55%, - transparent 100% - ); - animation: dsh-read-row-sweep 2.6s ease-out infinite; - pointer-events: none; -} - -@keyframes dsh-read-row-sweep { - 0% { left: -300px; } - 90%, 100% { left: 100%; } -} - -.leading { - flex: none; - width: 16px; - height: 16px; - display: inline-flex; - align-items: center; - justify-content: center; - margin-right: 6px; - color: var(--dsw-alias-label-tertiary); -} - -.title { - flex: none; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-secondary); -} - -.sep { - flex: none; - width: 2px; - height: 2px; - border-radius: 1px; - margin: 0 8px; - background: var(--dsw-alias-label-caption); -} - -.summary { - flex: 1 1 auto; - min-width: 0; - overflow: hidden; - text-overflow: ellipsis; - white-space: nowrap; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-tertiary); -} - -/* File path: same geometry as .summary; hover underline + pointer. */ -.fileLink { - flex: 1 1 auto; - min-width: 0; - overflow: hidden; - text-overflow: ellipsis; - white-space: nowrap; - margin: 0; - padding: 0; - border: none; - background: none; - text-align: left; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-tertiary); - cursor: pointer; -} - -.fileLink:hover { - text-decoration: underline; -} - -.visuallyHidden { - position: absolute; - width: 1px; - height: 1px; - overflow: hidden; - clip: rect(0 0 0 0); - white-space: nowrap; -} diff --git a/packages/client/ui-conversation/src/client/toolviews/read-row.tsx b/packages/client/ui-conversation/src/client/toolviews/read-row.tsx index 4527f85537..8d3694eeef 100644 --- a/packages/client/ui-conversation/src/client/toolviews/read-row.tsx +++ b/packages/client/ui-conversation/src/client/toolviews/read-row.tsx @@ -1,88 +1,49 @@ -// Read toolview registrant: the keyed toolview hole for the read tool -// (ctx.slots.register + ToolRowProps only — never imports the chat domain). -// Product chrome matches ToolRow (figma: Read · {path}); the summary is the -// file path as an openable link, exactly as the generic read row draws it. -// -// A read RESULT declares the read render intent, so this row renders the file's -// own line-numbered, syntax-highlighted content through ReadBlock resident -// below its summary line — the same posture BashRow gives a terminal card. The -// card is capped at CHAT_READ_MAX_LINES (the chat flow's tighter cap over the -// block's own default of 16) with the block's internal expander keeping a long -// read from taking over the message flow. A running read (no result yet) and a -// non-read result both render the summary row alone. The read intent is +// Read toolview registrant: the keyed toolview hole for the read tool. The row +// composes the shared ToolRow (chrome, running sweep, whole-row expand) and +// feeds it the file's line-numbered, syntax-highlighted content as ToolRow's +// `read` card material, so it renders through ReadBlock in the collapsed-by- +// default expanded body — the same unified interaction every other card row +// has. The summary path is an openable host link. A running read (no result +// yet) and a non-read result render the summary row alone: the read intent is // result-side only, so there is no running-state read card to draw. import type { Context } from 'cordis' -import { IconBrowseOutline16, ReadBlock, StateDot } from '@deepseek-ai/dsh-client-ui-primitives' +import { IconBrowseOutline16 } from '@deepseek-ai/dsh-client-ui-primitives' +import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' import type { ToolRowProps } from '../contract/slots.ts' -import { CHAT_READ_MAX_LINES, readCardModel } from '../contract/read-card-model.ts' -import { toolRowModel, type ToolRowState } from '../contract/tool-call-model.ts' -import css from './read-row.module.css' +import { readCardModel } from '../contract/read-card-model.ts' +import { toolRowModel } from '../contract/tool-call-model.ts' +import { ToolRow } from '../chat/ToolRow.tsx' +import { NS } from '../locales.ts' -/** Leading-slot state substitution: the tool icon yields to the state dot - * (error = red, interrupted = amber). Running keeps the icon. */ -function leadingFor(state: ToolRowState) { - switch (state) { - case 'error': return - case 'stopped': return - default: return - } -} - -/** Visually hidden status — StateDot is aria-hidden; AT needs a text label. */ -function stateStatus(state: ToolRowState): string | null { - switch (state) { - case 'running': return '运行中' - case 'error': return '失败' - case 'stopped': return '已停止' - default: return null - } -} +/** Full row props: the toolview runtime share plus the standard locale seat. */ +type ReadRowProps = ToolRowProps & PropsLocale<'conversation'> /** * Read row: icon + Read · {path} in the shared ToolRow chrome, with the file's - * read card resident below it. The summary path is an openable host link when - * the row names a single file; the card's copy and expand controls plus that - * link are the row's only interactions (tool rows are not details-panel - * targets). + * read card as the row's collapsed-by-default card body. The summary path is an + * openable host link when the row names a single file. */ -export function ReadRow({ toolName, block, sessionId, useSessions, openFile }: ToolRowProps) { - // Session workspace root: the read view's path relativizes against it (a - // workspace-rooted absolute path shows its short form), which the pure - // presenter cannot do. - const cwd = useSessions(list => list.byId[sessionId]?.cwd) +export function ReadRow({ toolName, block, cwd, openFile, inspect, t }: ReadRowProps) { const model = toolRowModel(toolName, block, cwd) const read = readCardModel(block, cwd) - const status = stateStatus(model.state) - const filePath = model.filePath return ( -
- {/* jscpd:ignore-start — the summary-line chrome (leading, status, title, - sep, path-link/summary) is the shared ToolRow row shape every keyed - toolview draws; extracting it into one component is a separate change - tracked for all rows at once, not this read-card PR. */} -
- {leadingFor(model.state)} - {status !== null && {status}} - {model.title} - - {filePath !== undefined ? ( - - ) : ( - {model.summary} - )} -
- {/* jscpd:ignore-end */} - {read !== null && ( - - )} -
+ } + title={model.title} + summary={model.summary} + body={null} + output={model.output} + errorSummary={model.errorSummary} + read={read} + state={model.state} + filePath={model.filePath} + onOpenFile={openFile} + inspect={inspect} + /> ) } @@ -100,6 +61,6 @@ export const readToolview = { * @param ctx - registrant context (disposal rides ctx.effect inside slots.register). */ apply(ctx: Context): void { - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'read' }, ReadRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'read', locale: NS }, ReadRow) }, } diff --git a/packages/client/ui-conversation/src/client/toolviews/search-row.module.css b/packages/client/ui-conversation/src/client/toolviews/search-row.module.css deleted file mode 100644 index 21908bd9e1..0000000000 --- a/packages/client/ui-conversation/src/client/toolviews/search-row.module.css +++ /dev/null @@ -1,117 +0,0 @@ -/* Search toolview: same geometry/tokens as ToolRow and BashRow (figma - Search · summary), plus the search card the row stacks resident under its - summary line. */ - -/* Summary line over the search 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. */ -.search { - margin: 4px 0 4px 22px; -} - -.root { - position: relative; /* sweep-glare overlay anchor */ - overflow: hidden; - display: flex; - align-items: center; - height: 24px; - min-width: 0; -} - -/* Running sweep glare — same deepsuite ShimmerText pattern as ToolRow / BashRow. */ -.root[data-state='running']::after { - content: ''; - position: absolute; - top: 0; - bottom: 0; - left: 0; - width: 300px; - background: linear-gradient( - 90deg, - transparent 0%, - color-mix(in srgb, var(--dsw-alias-bg-base) 60%, transparent) 55%, - transparent 100% - ); - animation: dsh-search-row-sweep 2.6s ease-out infinite; - pointer-events: none; -} - -@keyframes dsh-search-row-sweep { - 0% { left: -300px; } - 90%, 100% { left: 100%; } -} - -.leading { - flex: none; - width: 16px; - height: 16px; - display: inline-flex; - align-items: center; - justify-content: center; - margin-right: 6px; - color: var(--dsw-alias-label-tertiary); -} - -.title { - flex: none; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-secondary); -} - -.sep { - flex: none; - width: 2px; - height: 2px; - border-radius: 1px; - margin: 0 8px; - background: var(--dsw-alias-label-caption); -} - -.summary { - flex: 1 1 auto; - min-width: 0; - overflow: hidden; - text-overflow: ellipsis; - white-space: nowrap; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-tertiary); -} - -.visuallyHidden { - position: absolute; - width: 1px; - height: 1px; - overflow: hidden; - clip: rect(0 0 0 0); - white-space: nowrap; -} - -/* The result text for an errored search, indented to the card's own column and - in the error tone, standing in for the search card the failure path does not - produce. */ -.failure { - margin: 4px 0 4px 22px; - white-space: pre-wrap; - overflow-wrap: anywhere; - font: var(--dsw-font-xs-13); - color: var(--dsw-alias-state-error-primary); -} - -/* The recovery footer for a capped search: the model-facing result text (its - `Full … stored at …` locator) shown below the card in the muted tone, since - the card holds only the retained rows. Same column indent as the card body. */ -.recovery { - margin: 4px 0 4px 22px; - white-space: pre-wrap; - overflow-wrap: anywhere; - font: var(--dsw-font-xs-13); - color: var(--dsw-alias-label-tertiary); -} diff --git a/packages/client/ui-conversation/src/client/toolviews/search-row.tsx b/packages/client/ui-conversation/src/client/toolviews/search-row.tsx index 5ea72e4a25..0e8a90ed7a 100644 --- a/packages/client/ui-conversation/src/client/toolviews/search-row.tsx +++ b/packages/client/ui-conversation/src/client/toolviews/search-row.tsx @@ -1,76 +1,62 @@ -// Search toolview registrant: the keyed toolview hole (ctx.slots.register + -// ToolRowProps only — never imports the chat domain). One SearchRow component -// registered under both `grep` and `glob`, since both tools declare the same -// `card: 'search'` render intent and render as one visual object; the row reads -// the `kind` discriminant off the derived model to draw grouped matches or a -// path list. Product chrome matches ToolRow / BashRow (Search · {summary}). -// -// A search call declares its render intent result-time only, so this row's -// search card is resident below the summary rather than expand-gated: the row -// itself has no expand control, and the card's own copy, per-file collapse, and -// head/tail expand are the row's only interactions. CHAT_SEARCH_MAX_LINES is -// passed as `maxLines` — the chat flow's tighter cap over the block's own -// default of 16 — so a large result stays bounded in the message flow. +// Search toolview registrant: the keyed toolview hole for the `grep` and `glob` +// tools. One SearchRow component registered under both, since both declare the +// same `card: 'search'` render intent and render as one visual object; the +// derived model's `kind` decides the card shape (grouped matches or a path +// list). The row composes the shared ToolRow (chrome, running sweep, whole-row +// expand) and feeds it the completed search as ToolRow's `search` card +// material, so it renders through SearchBlock in the collapsed-by-default +// expanded body — with a capped search's recovery footer below the card. A +// search declares its render intent result-time only, so a running row is the +// summary line alone; a settled call with no search card (an errored search, a +// nested run_code sub-dispatch, a legacy generic result) surfaces its +// model-facing text through ToolRow's Output section instead. import type { Context } from 'cordis' -import { IconSearchOutline16, SearchBlock, StateDot } from '@deepseek-ai/dsh-client-ui-primitives' +import { IconSearchOutline16 } from '@deepseek-ai/dsh-client-ui-primitives' +import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' import type { ToolRowProps } from '../contract/slots.ts' -import { CHAT_SEARCH_MAX_LINES, searchCardModel } from '../contract/search-card-model.ts' -import { toolRowModel, type ToolRowState } from '../contract/tool-call-model.ts' -import { rowResultText, rowStateStatus } from '../contract/toolview-status.ts' -import css from './search-row.module.css' +import { searchCardModel } from '../contract/search-card-model.ts' +import { toolRowModel } from '../contract/tool-call-model.ts' +import { ToolRow } from '../chat/ToolRow.tsx' +import { NS } from '../locales.ts' -/** Leading-slot glyph substitution: the search icon yields to the terminal - * state semantic (error = red, interrupted = amber). Running keeps the icon — - * the row sweep carries the in-flight signal. */ -function leadingFor(state: ToolRowState) { - switch (state) { - case 'error': return - case 'stopped': return - default: return - } -} +/** Full row props: the toolview runtime share plus the standard locale seat. */ +type SearchRowProps = ToolRowProps & PropsLocale<'conversation'> /** * Search row: icon + Search · {summary} in the shared ToolRow chrome, with the - * completed search's card resident below it, and — when the result was capped — - * the recovery footer below the card. The summary row is not a details-panel - * control, so the card's copy, per-file collapse, and expand controls are the - * row's only interactions. Registered under both `grep` and `glob`; the derived - * model's `kind` decides the card shape. + * completed search's card as the row's collapsed-by-default card body (a capped + * search's recovery footer rides below it, inside ToolRow). Registered under + * both `grep` and `glob`; the derived model's `kind` decides the card shape. A + * settled call with no search card surfaces its model-facing text through + * ToolRow's Output section, since the keyed SearchRow owns this render slot. */ -export function SearchRow({ toolName, block }: ToolRowProps) { +export function SearchRow({ toolName, block, inspect, t }: SearchRowProps) { const model = toolRowModel(toolName, block) const search = searchCardModel(block) - const status = rowStateStatus(model.state) - // A settled call with no search card — an errored search (grep/glob emit no - // result view on error), a successful nested run_code sub-dispatch, or a - // legacy generic result — has its model-facing text nowhere else to go, since - // the keyed SearchRow owns this render slot. Surface it as the fallback body. - // A running call ('kind' absent) has no result to flatten; rowResultText - // returns null for it, so the arm stays closed until settle. - const settled = 'kind' in block - const fallback = search === null && settled ? rowResultText(block) : null return ( -
-
- {leadingFor(model.state)} - {status !== null && {status}} - {model.title} - - {/* The result view's replacement title outranks the args-derived - summary, matching the terminal card's description precedence. */} - {search?.title ?? model.summary} -
- {search !== null && ( - - )} - {/* A capped search drops rows from the card; its recovery locator (the - `Full … stored at …` footer) lives only in the result text, so show it - below the card so the one path to the dropped rows survives. */} - {search?.recovery !== undefined &&
{search.recovery}
} - {fallback !== null &&
{fallback}
} -
+ } + title={model.title} + // The result view's replacement title outranks the args-derived summary, + // matching the terminal card's description precedence. + summary={search?.title ?? model.summary} + body={null} + // A settled call with no search card (errored search, nested run_code + // sub-dispatch, legacy generic result) has its text nowhere else to go; + // ToolRow's Output section carries it, and errorSummary its first line. + // When a card is present ToolRow renders it instead of the output, so + // passing model.output unconditionally is safe and keeps the four card + // rows symmetric. + output={model.output} + errorSummary={model.errorSummary} + search={search} + state={model.state} + inspect={inspect} + /> ) } @@ -90,7 +76,7 @@ export const searchToolview = { * @param ctx - registrant context (disposal rides ctx.effect inside slots.register). */ apply(ctx: Context): void { - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep' }, SearchRow) - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'glob' }, SearchRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'glob', locale: NS }, SearchRow) }, } diff --git a/packages/client/ui-conversation/src/client/toolviews/web-row.module.css b/packages/client/ui-conversation/src/client/toolviews/web-row.module.css deleted file mode 100644 index 0b1519e218..0000000000 --- a/packages/client/ui-conversation/src/client/toolviews/web-row.module.css +++ /dev/null @@ -1,95 +0,0 @@ -/* Web toolview: same geometry/tokens as ToolRow (figma icon · summary), plus - the web card the row stacks under its summary line, mirroring the bash row's - resident terminal card. */ - -/* Summary line over the web 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. */ -.web { - margin: 4px 0 4px 22px; -} - -.root { - position: relative; /* sweep-glare overlay anchor */ - overflow: hidden; - display: flex; - align-items: center; - height: 24px; - min-width: 0; -} - -/* Running sweep glare — same deepsuite ShimmerText pattern as ToolRow. */ -.root[data-state='running']::after { - content: ''; - position: absolute; - top: 0; - bottom: 0; - left: 0; - width: 300px; - background: linear-gradient( - 90deg, - transparent 0%, - color-mix(in srgb, var(--dsw-alias-bg-base) 60%, transparent) 55%, - transparent 100% - ); - animation: dsh-web-row-sweep 2.6s ease-out infinite; - pointer-events: none; -} - -@keyframes dsh-web-row-sweep { - 0% { left: -300px; } - 90%, 100% { left: 100%; } -} - -.leading { - flex: none; - width: 16px; - height: 16px; - display: inline-flex; - align-items: center; - justify-content: center; - margin-right: 6px; - color: var(--dsw-alias-label-tertiary); -} - -.title { - flex: none; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-secondary); -} - -.sep { - flex: none; - width: 2px; - height: 2px; - border-radius: 1px; - margin: 0 8px; - background: var(--dsw-alias-label-caption); -} - -.summary { - flex: 1 1 auto; - min-width: 0; - overflow: hidden; - text-overflow: ellipsis; - white-space: nowrap; - font-size: 14px; - line-height: 24px; - color: var(--dsw-alias-label-tertiary); -} - -.visuallyHidden { - position: absolute; - width: 1px; - height: 1px; - overflow: hidden; - clip: rect(0 0 0 0); - white-space: nowrap; -} diff --git a/packages/client/ui-conversation/src/client/toolviews/web-row.tsx b/packages/client/ui-conversation/src/client/toolviews/web-row.tsx index b86c523a26..4d8ab5f59f 100644 --- a/packages/client/ui-conversation/src/client/toolviews/web-row.tsx +++ b/packages/client/ui-conversation/src/client/toolviews/web-row.tsx @@ -1,24 +1,25 @@ -// Web toolview registrant: third-party posture over the keyed toolview hole -// (ctx.slots.register + ToolRowProps only — never imports the chat domain). -// Registered under BOTH web_search and web_fetch, since both declare the one -// `web` render intent and render through the one WebBlock family; the row -// discriminates on the toolName only to pick its icon and title. -// -// A web tool declares the `web` render intent at result time, so this row -// renders the completed retrieval through WebBlock resident below its summary, -// the same posture BashRow uses for the terminal card: no expand control on the -// row itself, not a details-panel target, and the block's own expander keeps a -// long source list from taking over the message flow (CHAT_WEB_MAX_SOURCES is -// passed as maxSources — the chat flow's tighter cap over the block's default -// of 16). Until the call settles there is no web card (the tools keep a generic -// pending view), so a running row is the summary line alone. +// Web toolview registrant: the keyed toolview hole for the `web_search` and +// `web_fetch` tools. Registered under BOTH, since both declare the one `web` +// render intent and render through the one WebBlock family; the row +// discriminates on the toolName only to pick its icon and title. The row +// composes the shared ToolRow (chrome, running sweep, whole-row expand) and +// feeds it the completed retrieval as ToolRow's `web` card material, so it +// renders through WebBlock in the collapsed-by-default expanded body — the same +// unified interaction every other card row has. Until the call settles there is +// no web card (the tools keep a generic pending view), so a running row is the +// summary line alone. import type { Context } from 'cordis' -import { IconBrowseOutline16, IconSearchOutline16, StateDot, WebBlock } from '@deepseek-ai/dsh-client-ui-primitives' +import { IconBrowseOutline16, IconSearchOutline16 } from '@deepseek-ai/dsh-client-ui-primitives' +import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' import type { ToolRowProps } from '../contract/slots.ts' -import { CHAT_WEB_MAX_SOURCES, webCardModel } from '../contract/web-card-model.ts' -import { toolRowModel, type ToolRowState } from '../contract/tool-call-model.ts' -import css from './web-row.module.css' +import { webCardModel } from '../contract/web-card-model.ts' +import { toolRowModel } from '../contract/tool-call-model.ts' +import { ToolRow } from '../chat/ToolRow.tsx' +import { NS } from '../locales.ts' + +/** Full row props: the toolview runtime share plus the standard locale seat. */ +type WebRowProps = ToolRowProps & PropsLocale<'conversation'> /** web_fetch reads one URL; web_search queries. Titles are figma literals. */ const WEB_TITLES: Record = { @@ -26,49 +27,30 @@ const WEB_TITLES: Record = { web_fetch: 'Fetch', } -/** Leading icon per tool, yielding to the state semantic while failed/stopped. */ -function leadingFor(toolName: string, state: ToolRowState) { - switch (state) { - case 'error': return - case 'stopped': return - // Running keeps the icon — the row sweep carries the in-flight signal. - default: return toolName === 'web_fetch' ? : - } -} - -/** Visually hidden status — StateDot is aria-hidden; AT needs a text label. */ -function stateStatus(state: ToolRowState): string | null { - switch (state) { - case 'running': return '运行中' - case 'error': return '失败' - case 'stopped': return '已停止' - default: return null - } -} - /** * Web row: icon + Search/Fetch · {summary} in the shared ToolRow chrome, with - * the completed retrieval's web card resident below it. The summary row is not - * a details-panel control (tool rows stopped being one), so the card's own - * links and expander are the row's only interactions. + * the completed retrieval's web card as the row's collapsed-by-default card + * body. The row discriminates on `toolName` only to pick its icon and title. */ -export function WebRow({ toolName, block }: ToolRowProps) { +export function WebRow({ toolName, block, inspect, t }: WebRowProps) { const model = toolRowModel(toolName, block) const web = webCardModel(block) - const status = stateStatus(model.state) + const icon = toolName === 'web_fetch' ? : return ( -
-
- {leadingFor(toolName, model.state)} - {status !== null && {status}} - {WEB_TITLES[toolName] ?? model.title} - - {model.summary} -
- {web !== null && ( - - )} -
+ ) } @@ -86,7 +68,7 @@ export const webToolview = { * @param ctx - registrant context (disposal rides ctx.effect inside slots.register). */ apply(ctx: Context): void { - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'web_search' }, WebRow) - ctx.slots.register({ name: 'conversation.chat.toolview', key: 'web_fetch' }, WebRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'web_search', locale: NS }, WebRow) + ctx.slots.register({ name: 'conversation.chat.toolview', key: 'web_fetch', locale: NS }, WebRow) }, } diff --git a/packages/client/ui-conversation/tests/chat-apply.spec.tsx b/packages/client/ui-conversation/tests/chat-apply.spec.tsx index 33342a49e5..d3fabd9bee 100644 --- a/packages/client/ui-conversation/tests/chat-apply.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-apply.spec.tsx @@ -88,15 +88,15 @@ describe('apply wiring', () => { await b.runtime.dispose() }) - it('mounts the bash sample, the search rows, the read row, the file-mutation rows, the web rows, and the product rows as keyed entries through the load-order seam', async () => { + it('mounts the bash sample, the read row, the file-mutation rows, the search rows (grep + glob), the web rows, and the product rows as keyed entries through the load-order seam', async () => { const b = await bench() // Every registrant plugin's inject: ['slots', 'conversation'] resolved — the // service being present implies the chat entry declared the hole first. The - // one search row registers under both grep and glob; the file-mutation - // registrant claims both write and edit for the diff card; the web rows - // register one component under both web tool names. + // file-mutation registrant claims both write and edit for the diff card; the + // one search row registers under both grep and glob; the web rows register + // one component under both web tool names. const entries = b.slots.entries('conversation.chat.toolview') - expect(entries.map(e => e.options.key)).toEqual(['bash', 'grep', 'glob', 'read', 'edit', 'write', 'web_search', 'web_fetch', 'todo_write', 'ask_user_question']) + expect(entries.map(e => e.options.key)).toEqual(['bash', 'read', 'edit', 'write', 'grep', 'glob', 'web_search', 'web_fetch', 'todo_write', 'ask_user_question']) // Stats stick with the composer (not inside ChatView). expect(b.slots.entries('conversation.composer.dock').map(e => e.options.id)).toEqual(['stats']) await b.runtime.dispose() diff --git a/packages/client/ui-conversation/tests/diff-card.spec.tsx b/packages/client/ui-conversation/tests/diff-card.spec.tsx index 4b23ff6f20..8744e6b802 100644 --- a/packages/client/ui-conversation/tests/diff-card.spec.tsx +++ b/packages/client/ui-conversation/tests/diff-card.spec.tsx @@ -12,7 +12,7 @@ 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, ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { SelectionTarget } from '@deepseek-ai/dsh-client-ui-conversation/client' import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime' import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts' import { CHAT_DIFF_MAX_LINES, diffCardModel } from '../src/client/contract/diff-card-model.ts' @@ -24,6 +24,9 @@ import { zh } from '../src/client/locales.ts' afterEach(cleanup) +/** FileMutationRow's full prop shape (ToolRow runtime share + conversation locale seat). */ +type FileMutationRowProps = Parameters[0] + const SID = 's1' as SessionId const t = makeTranslate(zh, commonZh) @@ -155,14 +158,23 @@ describe('FileMutationRow diff card', () => { phase: 'ready', }) - const rowProps = (block: RunningToolCall | ToolResultNode, toolName = 'edit'): ToolRowProps => ({ + const rowProps = (block: RunningToolCall | ToolResultNode, toolName = 'edit'): FileMutationRowProps => ({ callId: 'c1', toolName, block, openFile: vi.fn(), cwd: '/w/app', sessionId: SID, useSessions: bindSnapshotSelector(list()), - } as unknown as ToolRowProps) + t, + } as unknown as FileMutationRowProps) - it('renders the applied diff under the summary row, without an expand gesture', () => { + /** The whole summary row is the expand toggle (ToolRow's unified interaction). */ + const toggleRow = (view: { container: HTMLElement }) => { + fireEvent.click(view.container.querySelector('[data-expandable]')!) + } + + it('collapses to the summary row; expanding reveals the applied diff card', () => { const view = render() - // The diff card is resident (no expand toggle needed). + // The diff card is collapsed by default — not in the DOM until expanded. + expect(view.container.querySelector('[data-diff]')).toBeNull() + expect(view.queryByText('hello fixture')).toBeNull() + toggleRow(view) expect(view.container.querySelector('[data-diff]')).not.toBeNull() expect(view.getByText('hello fixture')).toBeTruthy() expect(view.getByText('复制')).toBeTruthy() @@ -171,6 +183,7 @@ describe('FileMutationRow diff card', () => { it('the summary is a path link that opens the tool path through the host', () => { const openFile = vi.fn() const view = render() + // The path link rides the collapsed summary, so it opens without expanding. fireEvent.click(view.getByRole('button', { name: 'notes/demo.txt' })) // The row passes the tool's own path; the injected openFile resolves it // against the session cwd (apply.ts), so the row must not resolve twice. @@ -184,6 +197,8 @@ describe('FileMutationRow diff card', () => { callView: { card: 'diff', title: 'Write notes/new.txt', diffs: [{ path: 'notes/new.txt', oldText: null, newText: 'hello fixture' }] }, resultView: { card: 'diff', title: 'Write notes/new.txt', diffs: [{ path: 'notes/new.txt', oldText: null, newText: 'hello fixture' }] }, }), 'write')} />) + // The footer counts live inside the collapsed diff card. + toggleRow(view) expect(view.getByText('└ +1 -0 · 1 file')).toBeTruthy() }) @@ -197,13 +212,16 @@ describe('FileMutationRow diff card', () => { it('a mutation call with no diff view renders the summary row alone', () => { const view = render() + // No diff material: expanding shows the args-JSON body, never a diff card. + expect(view.container.querySelector('[data-diff]')).toBeNull() + toggleRow(view) expect(view.container.querySelector('[data-diff]')).toBeNull() }) it('surfaces the result text when an errored mutation has no diff card', () => { // write/edit return undefined from presentResult on isError, so the failure - // has no diff — the row shows the model-facing error text instead of a bare - // red dot. + // has no diff — ToolRow shows the model-facing error text as the collapsed + // summary's first line (errorSummary) instead of a bare red dot. const view = render( { expect(view.getByText('ToolError: sandbox_denied')).toBeTruthy() }) - it('shows no failure text for a successful diff or a running call', () => { + it('shows no error summary for a successful diff or a running call', () => { + // ToolRow's error-color summary line is set only on the error state. const ok = render() - expect(ok.container.querySelector('[class*="_failure_"]')).toBeNull() + expect(ok.container.querySelector('[class*="_errorSummary_"]')).toBeNull() cleanup() const run = render() - expect(run.container.querySelector('[class*="_failure_"]')).toBeNull() + expect(run.container.querySelector('[class*="_errorSummary_"]')).toBeNull() }) it('shows the stopped state when the call was interrupted', () => { @@ -234,7 +253,8 @@ describe('FileMutationRow diff card', () => { error: { name: 'ToolError', code: 'interrupted' }, }))} />) expect(view.container.querySelector('[data-state="stopped"]')).not.toBeNull() - // The visually-hidden status label carries the stopped semantic for AT. + // The amber StateDot is aria-hidden, so ToolRow carries the state to AT as + // visually-hidden text; without it a stopped row is a colour-only signal. expect(view.getByText('已停止')).toBeTruthy() }) @@ -250,12 +270,12 @@ describe('FileMutationRow diff card', () => { describe('fileMutationToolview registration', () => { it('registers one component under both edit and write, and each disposes', () => { - const registered: { key: string; disposed: boolean }[] = [] + const registered: { key: string; locale: unknown; disposed: boolean }[] = [] const disposers: (() => void)[] = [] const ctx = { slots: { - register: ({ key }: { name: string; key: string }) => { - const entry = { key, disposed: false } + register: ({ key, locale }: { name: string; key: string; locale?: string }) => { + const entry = { key, locale, disposed: false } registered.push(entry) const dispose = () => { entry.disposed = true } disposers.push(dispose) @@ -265,6 +285,8 @@ describe('fileMutationToolview registration', () => { } fileMutationToolview.apply(ctx as never) expect(registered.map(r => r.key).sort()).toEqual(['edit', 'write']) + // Both keys claim the conversation locale seat ToolRow's body copy needs. + expect(registered.map(r => r.locale)).toEqual(['conversation', 'conversation']) // The registrant's inject seam is the load-order contract the row relies on. expect(fileMutationToolview.inject).toEqual(['slots', 'conversation']) // Disposal removes each contribution (packages/AGENTS.md registry contract). diff --git a/packages/client/ui-conversation/tests/read-card.spec.tsx b/packages/client/ui-conversation/tests/read-card.spec.tsx index 11354413b7..b8c08a2bb6 100644 --- a/packages/client/ui-conversation/tests/read-card.spec.tsx +++ b/packages/client/ui-conversation/tests/read-card.spec.tsx @@ -2,8 +2,9 @@ // The read render intent on the web side: the pure readCardModel derivation // over the settled result view, and both conversation render sites that consume // it — the chat tool row (the keyed ReadRow and the GenericToolCard fallback, -// each with the read card resident under the summary) and the details panel's -// Output section. Also pins the keyed 'read' toolview registration. +// each composing ToolRow with the read card as its collapsed-by-default expanded +// body) and the details panel's Output section (resident, full height). Also +// pins the keyed 'read' toolview registration. import { afterEach, describe, expect, it, vi } from 'vitest' import { cleanup, fireEvent, render } from '@testing-library/react' @@ -16,7 +17,7 @@ import type { ConversationSnapshot, RunningToolCall, SessionId, SessionListState, ToolResultNode, WorkspaceListState, } from '@deepseek-ai/dsh-client-runtime/client' import type { ToolResultView } from '@deepseek-ai/dsh-client-connection/client' -import type { SelectionTarget, ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { SelectionTarget } from '@deepseek-ai/dsh-client-ui-conversation/client' import { CHAT_READ_MAX_LINES, readCardModel } from '../src/client/contract/read-card-model.ts' import { createChatStore } from '../src/client/stores.ts' import { GenericToolCard, type GenericToolCardProps } from '../src/client/chat/GenericToolCard.tsx' @@ -128,11 +129,19 @@ describe('GenericToolCard read body', () => { callId: 'c1', toolName: 'web_fetch', block, openFile: vi.fn(), t, }) - it('renders the read card resident under the summary, capped tighter than the panel', () => { + /** The whole summary row is the expand toggle (ToolRow's unified interaction). */ + const toggleRow = (view: { container: HTMLElement }) => { + fireEvent.click(view.container.querySelector('[data-expandable]')!) + } + + it('expands to the read card, capped tighter than the panel', () => { expect(CHAT_READ_MAX_LINES).toBeLessThan(16) // web_fetch lands on the read variant without its own keyed row, so the - // fallback card owns the resident read block. + // fallback card owns the read block once expanded. const view = render() + // Collapsed: no read card in the DOM yet. + expect(view.container.querySelector('[data-read]')).toBeNull() + toggleRow(view) expect(view.container.querySelector('[data-read]')).not.toBeNull() expect(contentTexts(view.container)).toContain('export const a = 1') // The gutter keeps the file's own line numbers. @@ -145,6 +154,7 @@ describe('GenericToolCard read body', () => { call: { name: 'echo', argsRaw: '{"text":"x"}' }, callView: null, resultView: null, }), openFile: vi.fn(), t, })} />) + toggleRow(view) expect(view.container.querySelector('[data-read]')).toBeNull() }) @@ -162,19 +172,34 @@ describe('ReadRow keyed toolview', () => { phase: 'ready', }) - const rowProps = (block: RunningToolCall | ToolResultNode): ToolRowProps => ({ + const rowProps = (block: RunningToolCall | ToolResultNode): Parameters[0] => ({ callId: 'c1', toolName: 'read', block, openFile: vi.fn(), sessionId: SID, useSessions: bindSnapshotSelector(list()), - } as unknown as ToolRowProps) + t, + } as unknown as Parameters[0]) - it('renders the file path summary and the resident read card', () => { + /** The whole summary row is the expand toggle (ToolRow's unified interaction). */ + const toggleRow = (view: { container: HTMLElement }) => { + fireEvent.click(view.container.querySelector('[data-expandable]')!) + } + + it('collapses to the path summary; the whole row toggles the read card', () => { const view = render() expect(view.getByText('Read')).toBeTruthy() - // The path appears twice: the row summary link and the card's banner label. + // Collapsed: the path is the summary link alone, and the card is absent. + expect(view.getAllByText('src/a.ts').length).toBe(1) + expect(view.container.querySelector('[data-read]')).toBeNull() + toggleRow(view) + // Expanded: the summary link stays inline and the card's banner label adds a + // second occurrence of the path. expect(view.getAllByText('src/a.ts').length).toBe(2) expect(view.container.querySelector('[data-read]')).not.toBeNull() expect(contentTexts(view.container)).toContain('export const a = 1') expect(view.getByText('显示 3 / 180 行')).toBeTruthy() + // Collapse back in place: the card unmounts, the summary link returns. + toggleRow(view) + expect(view.container.querySelector('[data-read]')).toBeNull() + expect(view.getAllByText('src/a.ts').length).toBe(1) }) it('the path summary opens the file through the host', () => { @@ -212,7 +237,8 @@ describe('ReadRow keyed toolview', () => { const registered: { name: unknown; key?: unknown }[] = [] const ctx = { slots: { register: (options: { name: unknown; key?: unknown }) => { registered.push(options) } } } as unknown as Context readToolview.apply(ctx) - expect(registered).toEqual([{ name: 'conversation.chat.toolview', key: 'read' }]) + // The row composes ToolRow, so it declares its locale namespace at the seat. + expect(registered).toEqual([{ name: 'conversation.chat.toolview', key: 'read', locale: 'conversation' }]) expect(readToolview.inject).toContain('conversation') }) }) diff --git a/packages/client/ui-conversation/tests/search-card.spec.tsx b/packages/client/ui-conversation/tests/search-card.spec.tsx index 4856a7ff1e..75114ae9a2 100644 --- a/packages/client/ui-conversation/tests/search-card.spec.tsx +++ b/packages/client/ui-conversation/tests/search-card.spec.tsx @@ -1,9 +1,10 @@ // @vitest-environment jsdom // The search render intent on the web side: the pure searchCardModel derivation // over resultView, and the conversation render sites that consume it — the chat -// tool row (GenericToolCard's expand-gated body and SearchRow's resident card) -// and the details panel's Output section. The keyed registration under both grep -// and glob is pinned here too. +// tool row (GenericToolCard's fallback body and SearchRow, both composing the +// shared ToolRow with the search card collapsed by default) and the details +// panel's Output section (resident, full height). The keyed registration under +// both grep and glob is pinned here too. import { afterEach, describe, expect, it, vi } from 'vitest' import { cleanup, fireEvent, render } from '@testing-library/react' @@ -13,7 +14,7 @@ import type { ConversationSnapshot, RunningToolCall, SessionId, SessionListState, ToolResultNode, WorkspaceListState, } from '@deepseek-ai/dsh-client-runtime/client' import type { ToolResultView } from '@deepseek-ai/dsh-client-connection/client' -import type { SelectionTarget, ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { SelectionTarget } from '@deepseek-ai/dsh-client-ui-conversation/client' import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime' import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts' import { CHAT_SEARCH_MAX_LINES, searchCardModel } from '../src/client/contract/search-card-model.ts' @@ -23,6 +24,9 @@ import { GenericToolCard, type GenericToolCardProps } from '../src/client/chat/G import { DetailsPanel } from '../src/client/skeleton/DetailsPanel.tsx' import { SearchRow, searchToolview } from '../src/client/toolviews/search-row.tsx' +/** SearchRow now composes ToolRow, so its props include the locale `t` seat. */ +type SearchRowProps = Parameters[0] + afterEach(cleanup) /** Conversation-locale translate stub for the render sites' `t` seat. */ @@ -228,21 +232,32 @@ describe('chat row search body (GenericToolCard fallback)', () => { }) describe('SearchRow keyed card', () => { - const rowProps = (block: RunningToolCall | ToolResultNode, toolName: string): ToolRowProps => ({ - callId: 'c1', toolName, block, openFile: vi.fn(), sessionId: SID, - } as unknown as ToolRowProps) + const rowProps = (block: RunningToolCall | ToolResultNode, toolName: string): SearchRowProps => ({ + callId: 'c1', toolName, block, openFile: vi.fn(), sessionId: SID, t, + } as unknown as SearchRowProps) - it('renders the grep card resident under the summary row, without an expand gesture', () => { + /** The whole summary row is the expand toggle (ToolRow's unified interaction). */ + const toggleRow = (view: { container: HTMLElement }) => { + fireEvent.click(view.container.querySelector('[data-expandable]')!) + } + + it('collapses to the summary row; expanding reveals the grep card', () => { const view = render() expect(view.getByText('Search')).toBeTruthy() + // Collapsed: the card is not in the DOM until the row is expanded. + expect(searchKindOf(view.container)).toBeNull() + expect(view.queryByText(/const foo = 1/)).toBeNull() + toggleRow(view) expect(searchRows(view.container)).toContain('12: const foo = 1') expect(searchKindOf(view.container)).toBe('matches') - // The card's controls are the row's only interactions. + // The card's copy control lives inside the expanded body. expect(view.getByText('复制')).toBeTruthy() }) - it('renders the glob path card resident', () => { + it('expands to the glob path card', () => { const view = render() + expect(searchKindOf(view.container)).toBeNull() + toggleRow(view) expect(view.getByText('src/a.ts')).toBeTruthy() expect(searchKindOf(view.container)).toBe('paths') }) @@ -250,7 +265,7 @@ describe('SearchRow keyed card', () => { it('agrees with the summary row about the run state', () => { const runningView = render() expect(runningView.container.querySelector('[data-variant="search"]')?.getAttribute('data-state')).toBe('running') - // No result view yet, so no resident card. + // No result view yet, so no card even once material could expand. expect(searchKindOf(runningView.container)).toBeNull() cleanup() const errorView = render( { expect(errorView.container.querySelector('[data-variant="search"]')?.getAttribute('data-state')).toBe('error') }) - it('surfaces the result text when an errored search has no card', () => { + it('surfaces the result text through the Output section when an errored search has no card', () => { // grep/glob return no presentResult on error → no card; the row shows the - // model-facing error text instead of a bare red dot. + // first error line as the collapsed summary and the full text once expanded. const view = render() expect(searchKindOf(view.container)).toBeNull() + // Error state: the first line is the collapsed summary. expect(view.getByText('grep: invalid regular expression')).toBeTruthy() + toggleRow(view) + // Now in ToolRow's Output section too (the kept summary makes it appear twice). + expect(view.container.querySelector('[data-error]')?.textContent).toBe('grep: invalid regular expression') }) - it('surfaces the result text for a settled non-error call with no card', () => { + it('surfaces the result text for a settled non-error call with no card once expanded', () => { // A successful nested run_code sub-dispatch (backend computes no // presentationMeta, so resultView is null) or a legacy generic result settles // with search === null and state ok. The keyed SearchRow owns the slot, so - // without the widened arm the content would be lost behind a bare summary. + // ToolRow's Output section carries the text; it is only visible expanded. const view = render() expect(view.container.querySelector('[data-variant="search"]')?.getAttribute('data-state')).toBe('ok') expect(searchKindOf(view.container)).toBeNull() + // Collapsed: the ok row shows its args summary, not the output text. + expect(view.queryByText('nested run_code output line')).toBeNull() + toggleRow(view) expect(view.getByText('nested run_code output line')).toBeTruthy() }) @@ -290,12 +312,15 @@ describe('SearchRow keyed card', () => { content: [{ type: 'text', text: recovery }], resultView: resultMatches({ truncated: true, total: 42 }), }), 'grep')} />) + toggleRow(view) expect(searchKindOf(view.container)).toBe('matches') expect(view.getByText(/Full grep result stored at: spill:\/\/grep-1/)).toBeTruthy() }) it('shows no recovery footer for an uncapped search', () => { const view = render() + toggleRow(view) + expect(searchKindOf(view.container)).toBe('matches') expect(view.container.textContent).not.toMatch(/stored at/) }) @@ -304,6 +329,7 @@ describe('SearchRow keyed card', () => { isError: true, resultView: null, content: [], error: { name: 'ToolError', code: 'timeout' }, }), 'grep')} />) + // Error state: the derived name/code line is the collapsed summary. expect(view.getByText('ToolError: timeout')).toBeTruthy() }) @@ -320,16 +346,18 @@ describe('SearchRow keyed card', () => { }) it('registers the one row component under both grep and glob keys', () => { - const registered: { key: unknown; component: unknown }[] = [] + const registered: { key: unknown; locale: unknown; component: unknown }[] = [] const ctx = { slots: { - register: (options: { name: string; key: string }, component: unknown) => { - registered.push({ key: options.key, component }) + register: (options: { name: string; key: string; locale?: string }, component: unknown) => { + registered.push({ key: options.key, locale: options.locale, component }) }, }, } as never searchToolview.apply(ctx) expect(registered.map(r => r.key)).toEqual(['grep', 'glob']) + // Both keys claim the conversation locale seat ToolRow's body copy needs. + expect(registered.map(r => r.locale)).toEqual(['conversation', 'conversation']) // One component, two keys. expect(registered[0]!.component).toBe(SearchRow) expect(registered[1]!.component).toBe(SearchRow) diff --git a/packages/client/ui-conversation/tests/skeleton.spec.tsx b/packages/client/ui-conversation/tests/skeleton.spec.tsx index eeb8404fd5..ebc263b712 100644 --- a/packages/client/ui-conversation/tests/skeleton.spec.tsx +++ b/packages/client/ui-conversation/tests/skeleton.spec.tsx @@ -80,16 +80,25 @@ function mount( snapshot: ConversationSnapshot, workspaceRows: WorkspaceView[] = [{ ...workspace('one'), sessionIds: [SID] }], retargetWorkspace = vi.fn(async (_workspaceId: WorkspaceId) => {}), - /** When true, mimic overlay:true chain siblings (hidden fallback + takeover). */ - overlayTakeover = false, + options: { + /** When true, mimic overlay:true chain siblings (hidden fallback + takeover). */ + overlayTakeover?: boolean + /** The session list summary's `blank` flag — independent of the snapshot's. */ + summaryBlank?: boolean + /** Drop the session's summary row entirely (a session the list has not caught up with). */ + omitSummaryRow?: boolean + } = {}, ) { const root = sid('root') + const rootRow = { id: root, displayTitle: 'Root', running: false, waitingApproval: false, blank: false, updatedAt: 1 } + const childRow = { + id: SID, displayTitle: 'Child', parentId: root, cwd: '/projects/one', + running: false, waitingApproval: false, blank: options.summaryBlank ?? false, updatedAt: 2, + } + const listed = options.omitSummaryRow !== true const sessions = createSnapshotStore({ - ids: [root, SID], - byId: { - [root]: { id: root, displayTitle: 'Root', running: false, waitingApproval: false, blank: false, updatedAt: 1 }, - [SID]: { id: SID, displayTitle: 'Child', parentId: root, cwd: '/projects/one', running: false, waitingApproval: false, blank: false, updatedAt: 2 }, - }, + ids: listed ? [root, SID] : [root], + byId: { [root]: rootRow, ...listed && { [SID]: childRow } }, current: SID, phase: 'ready', }) @@ -167,7 +176,7 @@ function mount( return
}) as ConversationRootProps['renderSlot'] const renderSlotChain = ((_key, _owner, opts) => ( - overlayTakeover + options.overlayTakeover === true ? ( <>
@@ -229,7 +238,7 @@ describe('ConversationRoot resident composer', () => { }) it('sticky composer seat wraps the whole overlay chain, not only the fallback stack', () => { - const b = mount(conversationSnapshot(), undefined, undefined, true) + const b = mount(conversationSnapshot(), undefined, undefined, { overlayTakeover: true }) const seat = b.view.container.querySelector('[data-composer-seat]') const takeover = b.view.getByTestId('composer-takeover') const fallback = b.view.container.querySelector('[data-chain-overlay-fallback="conversation.composer"]') @@ -270,6 +279,39 @@ describe('ConversationRoot resident composer', () => { expect(b.view.getByText('Selected Folder')).toBeTruthy() }) + it('settling phase: a summary that does not prove the session blank hides the composer while it opens', () => { + const b = mount(conversationSnapshot({ composerPhase: 'blank', blank: true, openState: 'loading' })) + const root = b.view.container.querySelector('[data-phase]') + expect(root?.getAttribute('data-phase')).toBe('settling') + expect(b.view.queryByText('开始构建吧')).toBeNull() + }) + + it('settling phase: a session the list has no row for settles conservatively', () => { + const b = mount( + conversationSnapshot({ composerPhase: 'blank', blank: true, openState: 'loading' }), + undefined, + undefined, + { omitSummaryRow: true }, + ) + const root = b.view.container.querySelector('[data-phase]') + expect(root?.getAttribute('data-phase')).toBe('settling') + }) + + it('startup auto-selection: a summary-proven blank session opens straight into the hero', () => { + const b = mount( + conversationSnapshot({ composerPhase: 'blank', blank: true, openState: 'loading' }), + undefined, + undefined, + { summaryBlank: true }, + ) + // The summary already proves the outcome, so the settling hide would only + // blank the column for the history round-trip. + const root = b.view.container.querySelector('[data-phase]') + expect(root?.getAttribute('data-phase')).toBe('hero') + expect(b.view.getByText('开始构建吧')).toBeTruthy() + expect(b.view.getByRole('textbox')).toBeTruthy() + }) + it('same textarea DOM node survives the hero → active flip into the sticky scrollport', () => { const b = mount(conversationSnapshot({ composerPhase: 'blank', blank: true })) const before = b.view.getByRole('textbox') diff --git a/packages/client/ui-conversation/tests/web-card.spec.tsx b/packages/client/ui-conversation/tests/web-card.spec.tsx index 0cb4f93f92..42dc729e41 100644 --- a/packages/client/ui-conversation/tests/web-card.spec.tsx +++ b/packages/client/ui-conversation/tests/web-card.spec.tsx @@ -4,17 +4,19 @@ // WebRow (registered under both web_search and web_fetch), the GenericToolCard // render-site fallback, and the details panel's Output section. Mirrors // terminal-card.spec.tsx: model derivation + null arms, both kinds, the chat -// row's resident card, the panel arm, and the keyed registration. +// row's collapsed-by-default ToolRow card, the panel arm, and the keyed +// registration. WebRow now composes the shared ToolRow, so its web card is +// collapsed by default and appears only once the whole row is expanded. import { afterEach, describe, expect, it, vi } from 'vitest' -import { cleanup, render } from '@testing-library/react' +import { cleanup, fireEvent, render } from '@testing-library/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 { ToolResultView } from '@deepseek-ai/dsh-client-connection/client' import { bindSnapshotSelector } from '@deepseek-ai/dsh-client-web-react' -import type { SelectionTarget, ToolRowOwnerProps, ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { SelectionTarget, ToolRowOwnerProps } from '@deepseek-ai/dsh-client-ui-conversation/client' import { CHAT_WEB_MAX_SOURCES, webCardModel } from '../src/client/contract/web-card-model.ts' import { createChatStore } from '../src/client/stores.ts' import { GenericToolCard } from '../src/client/chat/GenericToolCard.tsx' @@ -122,36 +124,49 @@ describe('chat row web body', () => { const ownerProps = (block: RunningToolCall | ToolResultNode, toolName: string): ToolRowOwnerProps => ({ callId: block.callId, toolName, block, openFile: vi.fn(), }) - // WebRow reads only toolName/block off the full runtime share; the standard - // kit is unused, so the cast supplies the owner slice alone (as BashRow's - // tests do for the terminal card). - const rowProps = (block: RunningToolCall | ToolResultNode, toolName: string): ToolRowProps => - ownerProps(block, toolName) as unknown as ToolRowProps + // WebRow reads only toolName/block off the full runtime share plus the locale + // seat; the standard kit is unused, so the cast supplies the owner slice and + // `t` alone (as BashRow's tests do for the terminal card). + const rowProps = (block: RunningToolCall | ToolResultNode, toolName: string): Parameters[0] => + ({ ...ownerProps(block, toolName), t } as unknown as Parameters[0]) - it('the WebRow renders the search card resident under the summary, capped tighter than the panel', () => { + /** The whole summary row is the expand toggle (ToolRow's unified interaction). */ + const toggleRow = (view: { container: HTMLElement }) => { + fireEvent.click(view.container.querySelector('[data-expandable]')!) + } + + it('the WebRow collapses to the summary row, expanding to the search card capped tighter than the panel', () => { expect(CHAT_WEB_MAX_SOURCES).toBeLessThan(16) const view = render() - // The summary row plus the resident card, without any expand gesture on the row itself. + // Collapsed: the summary row alone, no card in the DOM. expect(view.getByText('Search')).toBeTruthy() + expect(view.queryByText('Titled')).toBeNull() + expect(view.container.querySelector('[data-web]')).toBeNull() + toggleRow(view) + // Expanded: the resident search card with every source field. expect(view.getByText('Titled')).toBeTruthy() expect(view.getByText('excerpt')).toBeTruthy() // hostname fallback for the source with no title expect(view.getByText('plain.example.org')).toBeTruthy() }) - it('the WebRow renders the fetch card resident, titled Fetch', () => { + it('the WebRow expands to the fetch card, titled Fetch', () => { const view = render() expect(view.getByText('Fetch')).toBeTruthy() - // The url shows in the summary row and as the card's link; scope to the card. + expect(view.container.querySelector('[data-web]')).toBeNull() + toggleRow(view) + // The url shows as the card's link; scope to the card. const card = view.container.querySelector('[data-web="fetch"]') expect(card?.querySelector('a')?.getAttribute('href')).toBe('https://example.com/page') expect(view.getByText('HTTP 200')).toBeTruthy() }) - it('a running web call is the summary row alone (no card until it settles)', () => { + it('a running web call is the summary row alone, with nothing to expand', () => { const view = render() expect(view.getByText('Search')).toBeTruthy() expect(view.queryByText('Titled')).toBeNull() + // No card material and no expandable body: clicking the row reveals nothing. + expect(view.container.querySelector('[data-expandable]')).toBeNull() expect(view.container.querySelector('[data-web]')).toBeNull() }) @@ -165,12 +180,14 @@ describe('chat row web body', () => { expect(view.container.querySelector('[data-state="error"]')).not.toBeNull() }) - it('the GenericToolCard fallback also renders a resident web card for a web-declaring tool', () => { + it('the GenericToolCard fallback also expands to a web card for a web-declaring tool', () => { // A web-declaring tool without its own keyed row lands on the fallback; its - // card is resident there too. + // card routes through the same collapsed-by-default ToolRow. const view = render() + expect(view.container.querySelector('[data-web]')).toBeNull() + toggleRow(view) expect(view.getByText('Titled')).toBeTruthy() expect(view.container.querySelector('[data-web="search"]')).not.toBeNull() }) @@ -250,17 +267,19 @@ describe('DetailsPanel web Output section', () => { describe('web toolview registration', () => { it('registers one WebRow under both web_search and web_fetch', () => { - const registered: { key: string; component: unknown }[] = [] + const registered: { key: string; locale: unknown; component: unknown }[] = [] const ctx = { slots: { - register: (options: { name: string; key: string }, component: unknown) => { - registered.push({ key: options.key, component }) + register: (options: { name: string; key: string; locale?: string }, component: unknown) => { + registered.push({ key: options.key, locale: options.locale, component }) return () => {} }, }, } as unknown as import('cordis').Context webToolview.apply(ctx) expect(registered.map(r => r.key)).toEqual(['web_search', 'web_fetch']) + // Both keys claim the conversation locale seat ToolRow's body copy needs. + expect(registered.map(r => r.locale)).toEqual(['conversation', 'conversation']) // One component under both keys, not two thin rows. expect(registered[0]?.component).toBe(WebRow) expect(registered[1]?.component).toBe(WebRow) diff --git a/packages/client/ui-primitives/README.i18n.yaml b/packages/client/ui-primitives/README.i18n.yaml index af576fed26..b5bb7f0adb 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: 6430a789c15634538a38d6581df50a489522db55 -README.zh.md: 78249612cce3148fcececded40c529682450460a +README.md: f06e8c014c19d17197980a232e8b42080aac2901 +README.zh.md: feb97ee9fa834fbff10052909630ffcbbce9c78a diff --git a/packages/client/ui-primitives/README.md b/packages/client/ui-primitives/README.md index 6430a789c1..f06e8c014c 100644 --- a/packages/client/ui-primitives/README.md +++ b/packages/client/ui-primitives/README.md @@ -2,7 +2,11 @@ English | [中文](README.zh.md) -Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/Input, the markdown family (MessageText/MarkdownText/JsonBlock), the read-only JsonTree inspector, the `useAnchoredMaxHeight` hook that clamps a bottom-anchored overlay to the viewport space above its anchor (re-measured on resize, scroll, and a caller-supplied dependency), TerminalBlock, SearchBlock, DiffBlock, and WebBlock. Contract: api-contracts v3 §8. +Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/Input, the markdown family (MessageText/MarkdownText/JsonBlock), the read-only JsonTree inspector, the `useAnchoredMaxHeight` hook that clamps a bottom-anchored overlay to the viewport space above its anchor (re-measured on resize, scroll, and a caller-supplied dependency), TerminalBlock, DiffBlock, ReadBlock, SearchBlock, and WebBlock. Contract: api-contracts v3 §8. + +## Hover cards + +`HoverCard` keeps its portaled preview reachable across the anchor gap with a pointer-leave grace. A consumer may also pass `copyText`: the card then exposes button semantics for pointer and keyboard activation, includes that value after the `copyLabel` prefix in its accessible name, writes the exact value through the package clipboard helper, and temporarily replaces its content with `copiedLabel` only after the host accepts the write. A non-collapsed text selection intersecting the card suppresses pointer-click activation, while success feedback retains the original card height and clears when the card closes or after one second. `copyLabel` and `copiedLabel` are label props because this zero-cordis atom cannot read the application locale; omitting `copyText` preserves the read/select-only card. Rationale: [the hover-card copy note](../../../.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md). ## Markdown rendering @@ -12,14 +16,18 @@ Pure React atoms (zero cordis): StateDot, ic_ds_* icons, Button/Pill/Menu/Modal/ `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 the card reserves as its own left padding, so the dot sits inside the card box yet left of the prompt text. 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; cursor movements replay into a per-line column buffer before inert controls are stripped, since carriage return and backspace only MOVE the cursor: `100%` + CR + `OK` alone shows `OK0%`, while the `\x1b[K` a spinner writes with its redraw erases the tail so `100%\r\x1b[KOK` shows `OK`. Erase-in-line is honored in all three parameter forms, the cursor advances by terminal columns (8-column tab stops, two for emoji and CJK, none for a combining mark), and SGR state is normalized per cell as a terminal stores it, threading across lines and closing at the state the line ended in; 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). -## Search results +## Read rendering -`SearchBlock` renders a completed search, one component for both kinds (discriminated by `kind`). A `matches` (grep) shows each file as a bold path header with its `lineNumber: line` rows, the per-file group collapsible; a `paths` (glob) shows a flat path list. Both flatten to one row list the height cap slices head/tail over (default 16, the TerminalBlock split arithmetic), and neither soft-wraps — a long match line or path scrolls horizontally instead of folding. The banner summary folds the pre-cap total in when the tool capped the result (`显示 X / 共 N 处匹配 · K 个文件` for grep, `显示 X / 共 N 个路径` for glob), so the card never presents a capped result as complete; a copy control writes the whole structured result regardless of the cap or which groups are collapsed. Geometry mirrors CodeBlock/TerminalBlock. Rationale: [the web search card note](../../../.agents/notes/implemented/feature/2026-07-30-web-search-card.md). +`ReadBlock` renders a returned file window as a line-numbered, syntax-highlighted code surface: a bold path (or presenter-supplied title) banner with a copy control, then the content lines with their file line numbers in a gutter (a windowed read keeps the file's own numbering, so a read past an offset starts above 1). A `totalLines` exceeding the window count draws a `showing N of M` note, and the body collapses to a head slice plus a tail slice past `maxLines` (default 16, the TerminalBlock split arithmetic) behind an expand button. Highlighting runs through the same shiki path as `CodeBlock`. Rationale: [the web read card note](../../../.agents/notes/implemented/feature/2026-07-30-web-read-card.md). ## Diff rendering `DiffBlock` renders a file mutation as an inline diff surface: one bold path header per file, the removed lines (`- `, error token) above the added lines (`+ `, success token), a `⋯` gap before a same-file second hunk, and a dim `└ +A -R · N file(s)` footer. Lines are `white-space: pre` with horizontal scrolling, so a source line holds its indentation instead of soft-wrapping, and the body collapses to a head slice plus a tail slice past `maxLines` (default 16, `TerminalBlock`'s split arithmetic) behind an expand button. A create (`oldText: null`) has no removed side. The copy control writes the prefixed diff text (path headers, `- `/`+ ` lines, the gap) so a multi-file copy stays attributable, and floats in the top-right corner rather than on a banner row of its own. Geometry mirrors `CodeBlock`/`TerminalBlock`. The `+`/`-` block form mirrors the TUI transcript's diff card so a diff reads the same across front ends. Rationale: [the web diff card note](../../../.agents/notes/implemented/feature/2026-07-30-web-diff-card.md). +## Search results + +`SearchBlock` renders a completed search, one component for both kinds (discriminated by `kind`). A `matches` (grep) shows each file as a bold path header with its `lineNumber: line` rows, the per-file group collapsible; a `paths` (glob) shows a flat path list. Both flatten to one row list the height cap slices head/tail over (default 16, the TerminalBlock split arithmetic), and neither soft-wraps — a long match line or path scrolls horizontally instead of folding. The banner summary folds the pre-cap total in when the tool capped the result (`显示 X / 共 N 处匹配 · K 个文件` for grep, `显示 X / 共 N 个路径` for glob), so the card never presents a capped result as complete; a copy control writes the whole structured result regardless of the cap or which groups are collapsed. Geometry mirrors CodeBlock/TerminalBlock. Rationale: [the web search card note](../../../.agents/notes/implemented/feature/2026-07-30-web-search-card.md). + ## Web retrieval `WebBlock` renders a completed web retrieval, one component for both kinds of the `web` render intent (discriminated by `kind`). A `search` shows an optional provider answer (through `MarkdownText`) above an ordered citation list: each source is a safe external link labelled by its title, or its hostname, falling back to the raw URL when the URL does not parse or has no hostname (a `file:`/`data:` URL) so a label is never blank; its snippet and publication date render below it. Only http(s) URLs become anchors (`target`/`rel` set) — the http(s) subset of the allowlist `MarkdownText` applies to untrusted links (it also permits `mailto:`, excluded here); any other URL renders as plain text. A long list caps at `maxSources` (default 16, the TerminalBlock split arithmetic) with a head/tail collapse; the collapsed tail keeps each source's original citation number via `
  • `, and the expand control is a marker-less `
  • ` so the `
      ` stays valid HTML. When a search legitimately returns no answer and no sources, the card shows an explicit empty-state note rather than a blank `
        ` (the chat row does not surface the raw result content). A `fetch` shows a compact summary: the linked final URL and its HTTP status. Both mark a capped retrieval. Rationale: [the web result card note](../../../.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md). @@ -37,5 +45,5 @@ 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. -- **User-facing copy localizes through label props, defaulting to the original Chinese literals** — the atoms are zero-cordis and cannot reach `ctx.locale`, so `TerminalBlock` (`labels`), `JsonTree` (`labels`), `CodeBlock` (`copyLabel`/`copiedLabel`), `MarkdownText` (`codeLabels`), `JsonBlock` (`truncatedLabel`), `ConnectionBanner` (`label`), and `Modal` (`closeLabel`) take their copy as optional props with the previous hardcoded strings as defaults. Localized plugins pass dictionary-driven labels from their own `t` seat; a consumer that passes nothing renders exactly the pre-localization output. `WebBlock` does not yet follow this pattern: its source expand/collapse controls, source-list and fetch truncation notes, and empty-search note stay inline Chinese, pending the same label-prop treatment. +- **User-facing copy localizes through label props, defaulting to the original Chinese literals** — the atoms are zero-cordis and cannot reach `ctx.locale`, so `HoverCard` (`copyLabel`/`copiedLabel`), `TerminalBlock` (`labels`), `JsonTree` (`labels`), `CodeBlock` (`copyLabel`/`copiedLabel`), `MarkdownText` (`codeLabels`), `JsonBlock` (`truncatedLabel`), `ConnectionBanner` (`label`), and `Modal` (`closeLabel`) take their copy as optional props with the previous hardcoded strings as defaults. Localized plugins pass dictionary-driven labels from their own `t` seat; a consumer that passes nothing renders exactly the pre-localization output. `WebBlock` does not yet follow this pattern: its source expand/collapse controls, source-list and fetch truncation notes, and empty-search note stay inline Chinese, pending the same label-prop treatment. - **`TerminalBlock` is not a terminal emulator** — it renders settled or still-running command output, not an interactive session: SGR color and attributes are honored, and so are the in-line cursor movements a progress line uses — carriage return, backspace, erase-in-line, tab stops and character width. Absolute cursor positioning, 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 78249612cc..feb97ee9fa 100644 --- a/packages/client/ui-primitives/README.zh.md +++ b/packages/client/ui-primitives/README.zh.md @@ -2,23 +2,32 @@ [English](README.md) | 中文 -纯 React 原子组件(零 cordis):StateDot、ic_ds_* 图标、Button/Pill/Menu/Modal/Input、markdown 家族(MessageText/MarkdownText/JsonBlock)、只读 JsonTree 检查器、`useAnchoredMaxHeight` hook(把底部锚定的浮层高度收敛到锚点上方的视口空间,并在 resize、scroll 与调用方提供的依赖变化时重新测量)、TerminalBlock、SearchBlock、DiffBlock,以及 WebBlock。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)、只读 JsonTree 检查器、`useAnchoredMaxHeight` hook(把底部锚定的浮层高度收敛到锚点上方的视口空间,并在 resize、scroll 与调用方提供的依赖变化时重新测量)、TerminalBlock、DiffBlock、ReadBlock、SearchBlock,以及 WebBlock。契约:api-contracts v3 §8。 + +## 悬浮卡片 + +`HoverCard` 通过指针离开宽限期,让采用 portal 渲染的预览在跨越与锚点之间的间隙时仍可抵达。消费方还可传入 `copyText`:此时卡片为指针与键盘激活提供按钮语义,其无障碍名称会在 `copyLabel` 前缀后包含该值,通过包内剪贴板辅助函数原样写入该值,并且只有宿主接受写入后,才会临时将内容替换为 `copiedLabel`。与卡片相交的非折叠文本选区会阻止指针点击激活;成功反馈保持卡片原有高度,并随卡片关闭或在一秒后清除。`copyLabel` 和 `copiedLabel` 采用 label prop,是因为这个 zero-cordis 原子组件无法读取应用 locale;省略 `copyText` 时,卡片维持只读且可选择文本的行为。理由见[悬浮卡片复制 Agent Note](../../../.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md)。 ## 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。`extractMarkdownPlainText` 会移除 Markdown 呈现标记以用于紧凑标签,同时将原始 HTML 保留为字面文本。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: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以自身左内边距预留的落区中,因此它位于卡片盒之内、提示文字之左。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;光标移动在剥除无显示意义控制符之前先重放进逐行的列缓冲,因为回车与退格**只移动**光标:单是 `100%` 加回车再加 `OK` 显示为 `OK0%`,而 spinner 随重绘写出的 `\x1b[K` 会擦掉尾巴,因此 `100%\r\x1b[KOK` 显示为 `OK`。行内擦除的三种参数形式都被遵循,光标按终端列推进(8 列制表位;emoji 与 CJK 占两列;组合标记不占列),SGR 状态按单元格归一化存储,与终端一致,并跨行延续、在行结束时的状态处收束;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)。 -## 搜索结果 +## Read 渲染 -`SearchBlock` 渲染一次已完成的搜索,一个组件绘制两种 kind(由 `kind` 判别)。`matches`(grep)把每个文件渲染为粗体路径头加其 `lineNumber: line` 行,每个文件组可折叠;`paths`(glob)渲染扁平路径列表。两者都摊平成一个行列表,由高度上限做头/尾切片(默认 16,与 TerminalBlock 相同的切分算法),且都不软换行——长匹配行或路径横向滚动而非折行。当工具截断结果时,banner 摘要把截断前总数折入(grep 为 `显示 X / 共 N 处匹配 · K 个文件`,glob 为 `显示 X / 共 N 个路径`),使卡片绝不把截断结果呈现为完整;复制控件写入完整结构化结果,无论是否触及上限或哪些组被折叠。几何镜像 CodeBlock/TerminalBlock。原理:[Web 搜索卡片笔记](../../../.agents/notes/implemented/feature/2026-07-30-web-search-card.md)。 +`ReadBlock` 将返回的文件窗口渲染为带行号、语法高亮的代码表层:一个粗体路径(或 presenter 提供的标题)横幅加复制控件,其下是内容行,行号槽里是文件自身的行号(窗口化的 read 保留文件本身的编号,因此偏移之后的 read 从大于 1 处起始)。`totalLines` 超过窗口行数时画出 `showing N of M` 提示;超过 `maxLines`(默认 16,与 TerminalBlock 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。高亮走与 `CodeBlock` 相同的 shiki 路径。原理:[Web read 卡片笔记](../../../.agents/notes/implemented/feature/2026-07-30-web-read-card.md)。 ## Diff 渲染 `DiffBlock` 将一次文件改动渲染为内联 diff 表层:每个文件一个粗体路径头、删除行(`- `,error token)在新增行(`+ `,success token)之上、同文件第二个 hunk 前一个 `⋯` gap,以及暗色 `└ +A -R · N file(s)` 页脚。各行使用 `white-space: pre` 并横向滚动,因此源码行保留其缩进而不软换行;超过 `maxLines`(默认 16,与 `TerminalBlock` 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。新建(`oldText: null`)没有删除侧。复制控件写入带前缀的 diff 文本(路径头、`- `/`+ ` 行、gap),使多文件复制保持可归属,并浮在右上角而非占据自己的 banner 行。几何镜像 `CodeBlock`/`TerminalBlock`。`+`/`-` 块形式镜像 TUI 转录的 diff 卡片,使 diff 在两个前端读起来一致。原理:[Web diff 卡片笔记](../../../.agents/notes/implemented/feature/2026-07-30-web-diff-card.md)。 +## 搜索结果 + +`SearchBlock` 渲染一次已完成的搜索,并通过 `kind` 判别,由一个组件处理两种结果。`matches`(grep)将每个文件显示为粗体路径头及其 `lineNumber: line` 行,各文件组均可折叠;`paths`(glob)显示扁平的路径列表。两者都摊平成一个行列表,由高度上限对其做头尾切片(默认 16,与 `TerminalBlock` 相同的切分算法),且都不软换行:较长的匹配行或路径会横向滚动而非折行。当工具截断结果时,banner 摘要会包含截断前的总数(grep 为 `显示 X / 共 N 处匹配 · K 个文件`,glob 为 `显示 X / 共 N 个路径`),使卡片绝不把截断后的结果呈现为完整结果;无论是否触及上限或哪些组处于折叠状态,复制控件都会写入完整的结构化结果。几何结构与 `CodeBlock`/`TerminalBlock` 一致。原理:[Web 搜索卡片笔记](../../../.agents/notes/implemented/feature/2026-07-30-web-search-card.md)。 + ## Web 检索 `WebBlock` 渲染一次已完成的 web 检索,用一个组件绘制 `web` 渲染意图的两种 kind(由 `kind` 判别)。`search` 在有序引用列表上方显示可选的 provider answer(通过 `MarkdownText`):每个 source 是一个安全外链,以其标题为标签,或以其主机名为标签,当 URL 无法解析或没有主机名(`file:`/`data:` URL)时回退到原始 URL,因此标签绝不为空;其下渲染 snippet 与发布日期。只有 http(s) URL 会成为锚点(设置 `target`/`rel`)——这是 `MarkdownText` 对不受信任链接所用 allowlist 的 http(s) 子集(该 allowlist 还允许 `mailto:`,此处排除);任何其他 URL 渲染为纯文本。长列表在 `maxSources`(默认 16,即 TerminalBlock 的切分算术)处折叠为头部/尾部;折叠的尾部通过 `
      1. ` 保留每个 source 原始的引用编号,展开控件是无 marker 的 `
      2. `,使 `
          ` 保持为合法 HTML。当一次 search 合法地返回无 answer 且无 source 时,卡片显示一个明确的空状态提示,而不是空的 `
            `(chat 行不呈现原始 result content)。`fetch` 显示一个紧凑摘要:带链接的最终 URL 及其 HTTP 状态。两者都会标记一次被截断的检索。原理:[Web result 卡片笔记](../../../.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md)。 @@ -36,5 +45,5 @@ - **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。 -- **面向用户的文案经 label props 本地化,默认值为原中文字面量**:这些原子组件是 zero-cordis 的,拿不到 `ctx.locale`,因此 `TerminalBlock`(`labels`)、`JsonTree`(`labels`)、`CodeBlock`(`copyLabel`/`copiedLabel`)、`MarkdownText`(`codeLabels`)、`JsonBlock`(`truncatedLabel`)、`ConnectionBanner`(`label`)和 `Modal`(`closeLabel`)都把文案作为可选 props 接收,默认值即此前的硬编码字符串。已本地化的插件用自己的 `t` 席位传入字典驱动的 label;什么都不传的消费者渲染与本地化之前逐字节一致。`WebBlock` 尚未跟进这一模式:它的来源展开/收起控件、来源列表与 fetch 截断提示、以及空搜索提示仍是内联中文,待同样的 label-prop 处理。 +- **面向用户的文案经 label props 本地化,默认值为原中文字面量**:这些原子组件是 zero-cordis 的,拿不到 `ctx.locale`,因此 `HoverCard`(`copyLabel`/`copiedLabel`)、`TerminalBlock`(`labels`)、`JsonTree`(`labels`)、`CodeBlock`(`copyLabel`/`copiedLabel`)、`MarkdownText`(`codeLabels`)、`JsonBlock`(`truncatedLabel`)、`ConnectionBanner`(`label`)和 `Modal`(`closeLabel`)都把文案作为可选 props 接收,默认值即此前的硬编码字符串。已本地化的插件用自己的 `t` 席位传入字典驱动的 label;什么都不传的消费者渲染与本地化之前逐字节一致。`WebBlock` 尚未跟进这一模式:它的来源展开/收起控件、来源列表与 fetch 截断提示、以及空搜索提示仍是内联中文,待同样的 label-prop 处理。 - **`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,进度行所用的行内光标移动同样被遵循——回车、退格、行内擦除、制表位与字符宽度。绝对光标定位、清屏与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/HoverCard.module.css b/packages/client/ui-primitives/src/HoverCard.module.css index 8d8a52100e..8d425ca85c 100644 --- a/packages/client/ui-primitives/src/HoverCard.module.css +++ b/packages/client/ui-primitives/src/HoverCard.module.css @@ -7,7 +7,9 @@ /* Preview card (figma session hover card): 244 wide, r12, pad 12/16, the * menu card's elevation. Surface is #2C2C2E in both themes (figma value, - * light/dark identical), so a component-level variable, not a theme token. */ + * light/dark identical), so a component-level variable, not a theme token. + * Hit-testable on purpose: resting the pointer on the card holds it open + * (HoverCard's grace close), which a `pointer-events: none` card cannot do. */ .card { --dsw-hovercard-bg: #2C2C2E; position: fixed; @@ -18,5 +20,35 @@ border-radius: 12px; background: var(--dsw-hovercard-bg); box-shadow: var(--dsw-shadow-lv3); - pointer-events: none; +} + +.copyable { + cursor: pointer; +} + +.copyable:focus-visible { + outline: 2px solid var(--dsw-alias-state-business-primary); + outline-offset: 2px; +} + +.feedback { + display: flex; + align-items: center; + justify-content: center; +} + +.copied { + color: #FFFFFF; + font-size: 14px; + line-height: 20px; + text-align: center; +} + +.status { + position: absolute; + width: 1px; + height: 1px; + overflow: hidden; + clip: rect(0 0 0 0); + white-space: nowrap; } diff --git a/packages/client/ui-primitives/src/HoverCard.tsx b/packages/client/ui-primitives/src/HoverCard.tsx index 1720a0b79c..ea14afad1f 100644 --- a/packages/client/ui-primitives/src/HoverCard.tsx +++ b/packages/client/ui-primitives/src/HoverCard.tsx @@ -1,33 +1,73 @@ // HoverCard: delayed hover-preview card portaled to document.body. // Same portal mechanics as Menu: the wrapper span supplies the anchor rect, // the card is fixed-positioned at its right edge and repositions on -// scroll/resize while open. Display-only — the card ignores pointer events -// and closes the instant the pointer leaves the anchor (no close delay). +// scroll/resize while open. The card is reachable: it takes pointer events, +// and leaving the anchor only arms a grace-delayed close, so the pointer can +// cross the 8px gap and settle on the card to read a clipped path or title. +// The portaled card is a React child of the wrapper, so React's enter/leave +// traversal already treats it as inside — one pair of wrapper handlers covers +// anchor and card alike. -import { useEffect, useLayoutEffect, useRef, useState } from 'react' +import { useCallback, useEffect, useLayoutEffect, useRef, useState } from 'react' import type { ReactNode } from 'react' import { createPortal } from 'react-dom' +import { writeClipboard } from './clipboard.ts' +import { usePointerGrace } from './pointer-grace.ts' import css from './HoverCard.module.css' /** * Render an anchor with a hover-triggered preview card. * @param props.anchor - the hover target (rendered in place inside a wrapper span). - * @param props.content - card content (display-only, no pointer interaction). + * @param props.content - card content; the pointer may rest on it, so it is + * readable and selectable, but it carries no dismissal affordance of its own. * @param props.openDelayMs - hover dwell before the card shows (default 500). * @param props.disabled - suppress opening; turning true closes an open card. + * @param props.copyText - optional primary value copied by activation and + * included in the card's accessible name. + * @param props.copyLabel - accessible activation-label prefix (default "复制"). + * @param props.copiedLabel - visible success label (default "复制成功"). * @returns anchor wrapper with the conditional portaled card. */ -export function HoverCard({ anchor, content, openDelayMs = 500, disabled = false }: { +export function HoverCard({ + anchor, content, openDelayMs = 500, disabled = false, + copyText, copyLabel = '复制', copiedLabel = '复制成功', +}: { anchor: ReactNode content: ReactNode openDelayMs?: number disabled?: boolean + copyText?: string | undefined + copyLabel?: string | undefined + copiedLabel?: string | undefined }) { const rootRef = useRef(null) const cardRef = useRef(null) const timerRef = useRef | null>(null) + const copyTimerRef = useRef | null>(null) + const copyHeightRef = useRef(null) + const copyEpochRef = useRef(0) + const copyingRef = useRef(false) + const mountedRef = useRef(true) const [open, setOpen] = useState(false) const [pos, setPos] = useState<{ left: number; top: number } | null>(null) + const [copied, setCopied] = useState(false) + + const clearCopied = useCallback(() => { + if (copyTimerRef.current !== null) { + clearTimeout(copyTimerRef.current) + copyTimerRef.current = null + } + copyHeightRef.current = null + setCopied(false) + }, []) + + const close = useCallback(() => { + copyEpochRef.current += 1 + clearCopied() + setOpen(false) + }, [clearCopied]) + + const { arm: armClose, cancel: cancelClose } = usePointerGrace(close) const clearTimer = () => { if (timerRef.current !== null) { @@ -40,10 +80,22 @@ export function HoverCard({ anchor, content, openDelayMs = 500, disabled = false useEffect(() => { if (!disabled) return clearTimer() - setOpen(false) - }, [disabled]) + cancelClose() + close() + }, [disabled, cancelClose, close]) - useEffect(() => clearTimer, []) + useEffect(() => { + mountedRef.current = true + return () => { + mountedRef.current = false + copyEpochRef.current += 1 + clearTimer() + if (copyTimerRef.current !== null) { + clearTimeout(copyTimerRef.current) + copyTimerRef.current = null + } + } + }, []) // Fixed-position from the anchor rect before paint; track the anchor while // open (capture-phase scroll catches nested panes), as in Menu portal mode. @@ -79,9 +131,49 @@ export function HoverCard({ anchor, content, openDelayMs = 500, disabled = false } }, [open, pos]) + const copy = async (text: string): Promise => { + if (copied || copyingRef.current) return + copyingRef.current = true + const copyEpoch = copyEpochRef.current + const accepted = await writeClipboard(text) + copyingRef.current = false + const card = cardRef.current + if (!accepted || !mountedRef.current || copyEpoch !== copyEpochRef.current || card === null) return + const height = card.offsetHeight + copyHeightRef.current = height > 0 ? height : null + setCopied(true) + copyTimerRef.current = setTimeout(clearCopied, 1000) + } + + const copyable = copyText !== undefined const card = open && pos !== null && ( -
            - {content} +
            { + const selection = window.getSelection() + if (selection !== null && !selection.isCollapsed) { + for (let i = 0; i < selection.rangeCount; i += 1) { + if (selection.getRangeAt(i).intersectsNode(e.currentTarget)) return + } + } + void copy(copyText) + } + : undefined} + onKeyDown={copyable + ? (e) => { + if (e.key !== 'Enter' && e.key !== ' ') return + e.preventDefault() + void copy(copyText) + } + : undefined} + > + {copied ? : content}
            ) @@ -91,21 +183,33 @@ export function HoverCard({ anchor, content, openDelayMs = 500, disabled = false className={css.root} onPointerEnter={() => { if (disabled) return + // Coming back inside during the grace (the gap, or the card itself) + // keeps the current card rather than restarting the dwell. + cancelClose() + if (open) return clearTimer() timerRef.current = setTimeout(() => { setOpen(true) }, openDelayMs) }} onPointerLeave={() => { clearTimer() - setOpen(false) + // Leaving a closed card schedules a no-op close; only arm while + // open, matching Menu's shape. + if (open) armClose() }} - // Any press inside the anchor (row click, menu trigger) dismisses the + // A press inside the anchor (row click, menu trigger) dismisses the // card immediately, without waiting for the owner to flip `disabled`. - onPointerDownCapture={() => { + // Capture presses reach this handler from the card too — it is a React + // child of the wrapper — but a press there starts a selection, so the + // card must stay mounted under it (and the browser's click with it). + onPointerDownCapture={(e) => { + if (cardRef.current?.contains(e.target as Node)) return clearTimer() - setOpen(false) + cancelClose() + close() }} > {anchor} + {open && copyable && {copied ? copiedLabel : ''}} {card !== false && createPortal(card, document.body)} ) diff --git a/packages/client/ui-primitives/src/Menu.tsx b/packages/client/ui-primitives/src/Menu.tsx index 747750363d..ea7e51b478 100644 --- a/packages/client/ui-primitives/src/Menu.tsx +++ b/packages/client/ui-primitives/src/Menu.tsx @@ -13,6 +13,7 @@ import type { CSSProperties, ReactNode } from 'react' import { createPortal } from 'react-dom' import clsx from 'clsx' import { IconCheckOutline16 } from './icons/index.tsx' +import { usePointerGrace } from './pointer-grace.ts' import css from './Menu.module.css' /** Selectable row (optionally with a nested submenu). */ @@ -69,8 +70,10 @@ const MEASURE_STYLE: CSSProperties = { visibility: 'hidden', left: 0, top: 0 } * from the anchor rect (repositions on scroll/resize while open). Use when an * ancestor's overflow clipping would crop the in-place list; default false * keeps the pure-CSS in-place behavior. - * @param props.closeOnPointerLeave - close the list when the pointer leaves - * it (default false keeps it open until outside click/Escape/selection). + * @param props.closeOnPointerLeave - close the list once the pointer has left + * both trigger and list for the pointer grace (default false keeps it open + * until outside click/Escape/selection). The grace makes the 4px trigger->list + * gap and a brief overshoot survivable; coming back cancels the close. * @param props.compact - use reduced menu typography and spacing. * @param props.getAnchorRect - portal mode only: supply the anchor rect * directly (e.g. from a host-owned trigger button) instead of measuring the @@ -102,6 +105,7 @@ export function Menu({ open, anchor, items, selectedId, onSelect, onClose, align const listRef = useRef(null) const [openSubmenuId, setOpenSubmenuId] = useState(null) const [fixedPos, setFixedPos] = useState(null) + const { arm: armClose, cancel: cancelClose } = usePointerGrace(onClose) // Portal mode: fixed-position the list from the anchor rect before paint; // track the anchor while open (capture-phase scroll catches nested panes). @@ -179,6 +183,14 @@ export function Menu({ open, anchor, items, selectedId, onSelect, onClose, align } }, [open, onClose]) + // A close from selection/Escape/outside click outruns a pending grace close; + // left armed it would shut a list reopened inside the grace window. Its own + // effect, not the listener effect above: that one re-runs on every `onClose` + // identity change and would cancel the grace mid-transit. + useEffect(() => { + if (!open) cancelClose() + }, [open, cancelClose]) + // The submenu card is absolutely positioned outside the list box; the // scroll clip would crop it, so only submenu-free menus get the height cap. const scrollable = !items.some(entry => !isSeparator(entry) && !isLabel(entry) && entry.submenu !== undefined && entry.submenu.length > 0) @@ -251,7 +263,6 @@ export function Menu({ open, anchor, items, selectedId, onSelect, onClose, align className={clsx(css.list, compact && css.compactList, scrollable && css.scrollable, portal && css.portal, side === 'top' && !portal && css.sideTop, align === 'end' && !portal && css.alignEnd)} style={portal ? fixedPos ?? MEASURE_STYLE : undefined} role="menu" - onPointerLeave={closeOnPointerLeave ? () => { onClose() } : undefined} // React portals bubble synthetic events through the REACT tree: without // this stop, an item click re-fires the anchor row's own onClick // (open/toggle) after onSelect. @@ -268,8 +279,17 @@ export function Menu({ open, anchor, items, selectedId, onSelect, onClose, align
            ) + // Pointer-leave dismissal watches the WRAPPER, not the list: React's + // enter/leave traversal runs over the React tree, so trigger and portaled + // list are one region here. Aiming back at the trigger, or crossing the 4px + // gap between them, therefore never counts as leaving. return ( - + { if (open) armClose() } : undefined} + > {anchor} {portal ? (list !== false && createPortal(list, document.body)) : list} diff --git a/packages/client/ui-primitives/src/index.ts b/packages/client/ui-primitives/src/index.ts index e5100b2db5..b19147a1cc 100644 --- a/packages/client/ui-primitives/src/index.ts +++ b/packages/client/ui-primitives/src/index.ts @@ -24,14 +24,14 @@ export { JsonTree } from './JsonTree.tsx' export type { JsonTreeProps, JsonTreeLabels } from './JsonTree.tsx' export { TerminalBlock, DEFAULT_TERMINAL_MAX_LINES } from './TerminalBlock.tsx' export type { TerminalBlockProps, TerminalBlockLabels } from './TerminalBlock.tsx' -export { SearchBlock, DEFAULT_SEARCH_MAX_LINES } from './SearchBlock.tsx' -export type { - SearchBlockProps, SearchMatchesBlockProps, SearchPathsBlockProps, SearchFileGroup, SearchBlockLineMatch, -} from './SearchBlock.tsx' export { ReadBlock, DEFAULT_READ_MAX_LINES } from './ReadBlock.tsx' export type { ReadBlockProps, ReadBlockLine } from './ReadBlock.tsx' export { DiffBlock, DEFAULT_DIFF_MAX_LINES } from './DiffBlock.tsx' export type { DiffBlockProps, DiffHunk } from './DiffBlock.tsx' +export { SearchBlock, DEFAULT_SEARCH_MAX_LINES } from './SearchBlock.tsx' +export type { + SearchBlockProps, SearchMatchesBlockProps, SearchPathsBlockProps, SearchFileGroup, SearchBlockLineMatch, +} from './SearchBlock.tsx' export { WebBlock, DEFAULT_WEB_MAX_SOURCES } from './WebBlock.tsx' export type { WebBlockProps, WebSearchBlockProps, WebFetchBlockProps, WebSourceView } from './WebBlock.tsx' export { CodeBlock } from './markdown/CodeBlock.tsx' diff --git a/packages/client/ui-primitives/src/pointer-grace.ts b/packages/client/ui-primitives/src/pointer-grace.ts new file mode 100644 index 0000000000..1619cfe66e --- /dev/null +++ b/packages/client/ui-primitives/src/pointer-grace.ts @@ -0,0 +1,53 @@ +// Shared close timing for pointer-dismissed popups (HoverCard, hover-closing +// Menu). Both float free of their anchor, so the pointer has to cross ground +// that belongs to neither on its way in; closing on the first pointerleave +// makes the popup unreachable. The grace turns that transit into a cancelable +// pending close. + +import { useCallback, useEffect, useRef } from 'react' + +/** + * Grace before a pointer-dismissed popup closes. Covers the anchor->popup gap + * (8px for HoverCard, 4px for Menu) at a hand's travel speed without leaving a + * popup lingering once the pointer has genuinely moved on. + */ +export const POINTER_GRACE_MS = 200 + +/** Cancelable delayed close for a pointer-dismissed popup. */ +export interface PointerGrace { + /** Schedule the close {@link POINTER_GRACE_MS} from now, replacing any pending one. */ + arm: () => void + /** Abort a pending close (the pointer came back). */ + cancel: () => void +} + +/** + * Delay a pointer-dismissed popup's close so the pointer can cross the gap + * between anchor and popup. A pending close is dropped on unmount. + * @param close - runs when the grace elapses with no re-entry; read at fire + * time, so callers may pass a fresh closure each render. + * @returns the {@link PointerGrace} handle. + */ +export function usePointerGrace(close: () => void): PointerGrace { + const timerRef = useRef | null>(null) + const closeRef = useRef(close) + closeRef.current = close + + const cancel = useCallback(() => { + if (timerRef.current === null) return + clearTimeout(timerRef.current) + timerRef.current = null + }, []) + + const arm = useCallback(() => { + cancel() + timerRef.current = setTimeout(() => { + timerRef.current = null + closeRef.current() + }, POINTER_GRACE_MS) + }, [cancel]) + + useEffect(() => cancel, [cancel]) + + return { arm, cancel } +} diff --git a/packages/client/ui-primitives/tests/atoms.spec.tsx b/packages/client/ui-primitives/tests/atoms.spec.tsx index 4349e2ddce..568853d0cb 100644 --- a/packages/client/ui-primitives/tests/atoms.spec.tsx +++ b/packages/client/ui-primitives/tests/atoms.spec.tsx @@ -1,7 +1,8 @@ // @vitest-environment jsdom -import { cleanup, fireEvent, render, screen } from '@testing-library/react' +import { act, cleanup, fireEvent, render, screen } from '@testing-library/react' import { afterEach, describe, expect, it, vi } from 'vitest' import { Button, ConnectionBanner, Input, Menu, Modal, Pill } from '@deepseek-ai/dsh-client-ui-primitives' +import { POINTER_GRACE_MS } from '../src/pointer-grace.ts' afterEach(cleanup) @@ -160,16 +161,77 @@ describe('Menu', () => { expect(onSelect).toHaveBeenCalledWith('del') }) - it('closeOnPointerLeave closes when the pointer leaves the list; default stays open', () => { - const onClose = vi.fn() - const { rerender } = render( - trigger} items={items} onSelect={() => {}} onClose={onClose} />) - fireEvent.pointerLeave(screen.getByRole('menu')) - expect(onClose).toHaveBeenCalledTimes(1) - rerender( - trigger} items={items} onSelect={() => {}} onClose={onClose} />) - fireEvent.pointerLeave(screen.getByRole('menu')) - expect(onClose).toHaveBeenCalledTimes(1) + it('closeOnPointerLeave closes a grace after the pointer leaves trigger and list; default never does', () => { + vi.useFakeTimers() + try { + const onClose = vi.fn() + const { rerender } = render( + trigger} items={items} onSelect={() => {}} onClose={onClose} />) + const wrapper = screen.getByText('trigger').parentElement as HTMLElement + fireEvent.pointerLeave(wrapper) + // Still open through the grace: the pointer may be crossing the gap. + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS - 1) }) + expect(onClose).not.toHaveBeenCalled() + act(() => { vi.advanceTimersByTime(1) }) + expect(onClose).toHaveBeenCalledTimes(1) + rerender( + trigger} items={items} onSelect={() => {}} onClose={onClose} />) + fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS * 10) }) + expect(onClose).toHaveBeenCalledTimes(1) + } finally { + vi.useRealTimers() + } + }) + + it('coming back inside the grace keeps the list open (trigger and list are one region)', () => { + vi.useFakeTimers() + try { + const onClose = vi.fn() + render( + trigger} items={items} onSelect={() => {}} onClose={onClose} />) + const wrapper = screen.getByText('trigger').parentElement as HTMLElement + fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS - 50) }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS * 10) }) + expect(onClose).not.toHaveBeenCalled() + } finally { + vi.useRealTimers() + } + }) + + it('a close from selection disarms the pending grace close', () => { + vi.useFakeTimers() + try { + const onClose = vi.fn() + const { rerender } = render( + trigger} items={items} onSelect={() => {}} onClose={onClose} />) + const wrapper = screen.getByText('trigger').parentElement as HTMLElement + fireEvent.pointerLeave(wrapper) + // The owner closes for its own reason (selection/Escape) mid-grace; the + // armed timer must not survive to shut a list reopened right after. + rerender( + trigger} items={items} onSelect={() => {}} onClose={onClose} />) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS * 10) }) + expect(onClose).not.toHaveBeenCalled() + } finally { + vi.useRealTimers() + } + }) + + it('leaving a closed list arms nothing', () => { + vi.useFakeTimers() + try { + const onClose = vi.fn() + render( + trigger} items={items} onSelect={() => {}} onClose={onClose} />) + fireEvent.pointerLeave(screen.getByText('trigger').parentElement as HTMLElement) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS * 10) }) + expect(onClose).not.toHaveBeenCalled() + } finally { + vi.useRealTimers() + } }) it('a list click does not bubble to the anchor row (portal synthetic-event path)', () => { diff --git a/packages/client/ui-primitives/tests/hover-card.spec.tsx b/packages/client/ui-primitives/tests/hover-card.spec.tsx index ce599c0258..d5b580045a 100644 --- a/packages/client/ui-primitives/tests/hover-card.spec.tsx +++ b/packages/client/ui-primitives/tests/hover-card.spec.tsx @@ -2,6 +2,7 @@ import { act, cleanup, fireEvent, render, screen } from '@testing-library/react' import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' import { HoverCard } from '@deepseek-ai/dsh-client-ui-primitives' +import { POINTER_GRACE_MS } from '../src/pointer-grace.ts' afterEach(cleanup) beforeEach(() => { vi.useFakeTimers() }) @@ -16,7 +17,13 @@ function stubAnchorRect(anchor: HTMLElement, rect: { top: number; right: number }) } -function mount(props: { openDelayMs?: number; disabled?: boolean } = {}) { +function mount(props: { + openDelayMs?: number + disabled?: boolean + copyText?: string + copyLabel?: string + copiedLabel?: string +} = {}) { const view = render( row} content={
            card body
            } {...props} />, ) @@ -25,6 +32,19 @@ function mount(props: { openDelayMs?: number; disabled?: boolean } = {}) { return { view, anchor, wrapper: anchor.parentElement as HTMLElement } } +/** Install the async browser clipboard and restore its prior host shape. */ +function installClipboard(writeText: (text: string) => Promise): () => void { + const prior = Object.getOwnPropertyDescriptor(navigator, 'clipboard') + Object.defineProperty(navigator, 'clipboard', { + configurable: true, + value: { writeText }, + }) + return () => { + if (prior === undefined) Reflect.deleteProperty(navigator, 'clipboard') + else Object.defineProperty(navigator, 'clipboard', prior) + } +} + describe('HoverCard', () => { it('opens after the dwell delay, positioned right of the anchor', () => { const { wrapper } = mount() @@ -54,18 +74,47 @@ describe('HoverCard', () => { expect(screen.queryByText('card body')).toBeNull() }) - it('pointerleave closes an open card immediately; re-enter restarts the dwell', () => { + it('pointerleave closes an open card a grace later; re-enter after that restarts the dwell', () => { const { wrapper } = mount() fireEvent.pointerEnter(wrapper) act(() => { vi.advanceTimersByTime(500) }) expect(screen.getByText('card body')).toBeTruthy() fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS - 1) }) + expect(screen.getByText('card body')).toBeTruthy() + act(() => { vi.advanceTimersByTime(1) }) expect(screen.queryByText('card body')).toBeNull() fireEvent.pointerEnter(wrapper) act(() => { vi.advanceTimersByTime(500) }) expect(screen.getByText('card body')).toBeTruthy() }) + it('reaching the card inside the grace keeps it open without restarting the dwell', () => { + // The portaled card is a React child of the wrapper, so the pointer + // arriving on it re-enters the wrapper — the gesture the 8px anchor gap + // used to make impossible. + const { wrapper } = mount() + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS - 50) }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS * 10) }) + expect(screen.getByText('card body')).toBeTruthy() + }) + + it('re-entering while open does not queue a second dwell', () => { + const { wrapper } = mount() + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + fireEvent.pointerEnter(wrapper) + fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS) }) + // A dwell restarted by the redundant enter would reopen the card here. + act(() => { vi.advanceTimersByTime(500) }) + expect(screen.queryByText('card body')).toBeNull() + }) + it('a press inside the anchor dismisses the card without waiting for disabled', () => { const { wrapper } = mount() fireEvent.pointerEnter(wrapper) @@ -78,6 +127,237 @@ describe('HoverCard', () => { expect(screen.queryByText('card body')).toBeNull() }) + it('a press on the card starts a selection instead of dismissing it', () => { + // The card is a React child of the wrapper, so capture-phase presses on + // it reach the wrapper's dismissal handler too; they must not close it, + // or the first pointerdown of a text-selection drag would kill the card. + const { wrapper } = mount() + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + fireEvent.pointerDown(screen.getByText('card body')) + // Still mounted after a grace's worth of time: no close was armed either. + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS) }) + expect(screen.getByText('card body')).toBeTruthy() + }) + + it('keeps a completed card selection instead of treating its click as copy', async () => { + const writeText = vi.fn(async () => {}) + const restoreClipboard = installClipboard(writeText) + const selection = window.getSelection() + if (selection === null) throw new Error('jsdom selection API unavailable') + try { + const { wrapper } = mount({ copyText: 'card body', copyLabel: 'Copy' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + const card = screen.getByRole('button', { name: 'Copy: card body' }) + const selectedText = screen.getByText('card body') + const cardRange = document.createRange() + cardRange.selectNodeContents(selectedText) + selection.addRange(cardRange) + await act(async () => { fireEvent.click(card) }) + expect(writeText).not.toHaveBeenCalled() + expect(selection.toString()).toBe('card body') + expect(screen.getByText('card body')).toBeTruthy() + + // Firefox supports multiple selection ranges: any range intersecting + // this card wins, not only the first. + selection.removeAllRanges() + const getSelection = vi.spyOn(window, 'getSelection').mockReturnValue({ + isCollapsed: false, + rangeCount: 2, + getRangeAt: vi.fn((index: number) => ({ + intersectsNode: () => index === 1, + })), + } as unknown as Selection) + await act(async () => { fireEvent.click(card) }) + expect(writeText).not.toHaveBeenCalled() + getSelection.mockRestore() + + // A non-collapsed selection elsewhere does not block this card. + const anchorRange = document.createRange() + anchorRange.selectNodeContents(screen.getByText('row')) + selection.addRange(anchorRange) + await act(async () => { fireEvent.click(card) }) + expect(writeText).toHaveBeenCalledWith('card body') + } finally { + selection.removeAllRanges() + restoreClipboard() + } + }) + + it('a press while closed leaves the card closed', () => { + mount() + fireEvent.pointerDown(screen.getByText('row')) + act(() => { vi.advanceTimersByTime(1000) }) + expect(screen.queryByText('card body')).toBeNull() + }) + + it('copies its configured value and shows success only for the feedback window', async () => { + const writeText = vi.fn(async () => {}) + const restoreClipboard = installClipboard(writeText) + try { + const { wrapper } = mount({ + copyText: '/full/path', + copyLabel: 'Copy path', + copiedLabel: 'Copied', + }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + const card = screen.getByRole('button', { name: 'Copy path: /full/path' }) + const status = screen.getByRole('status') + expect(status.textContent).toBe('') + expect(card.contains(status)).toBe(false) + Object.defineProperty(card, 'offsetHeight', { configurable: true, value: 96 }) + await act(async () => { fireEvent.click(card) }) + expect(writeText).toHaveBeenCalledWith('/full/path') + expect(status.textContent).toBe('Copied') + expect(screen.getByRole('button', { name: 'Copy path: /full/path' })).toBe(card) + expect(card.style.minHeight).toBe('96px') + // Repeated activation while feedback is visible neither rewrites nor + // extends the one-second success window. + await act(async () => { fireEvent.click(card) }) + expect(writeText).toHaveBeenCalledOnce() + act(() => { vi.advanceTimersByTime(999) }) + expect(status.textContent).toBe('Copied') + act(() => { vi.advanceTimersByTime(1) }) + expect(screen.getByRole('button', { name: 'Copy path: /full/path' })).toBe(card) + expect(card.style.minHeight).toBe('') + expect(status.textContent).toBe('') + expect(screen.getByText('card body')).toBeTruthy() + } finally { + restoreClipboard() + } + }) + + it('supports button keys and ignores unrelated keys', async () => { + const writeText = vi.fn(async () => {}) + const restoreClipboard = installClipboard(writeText) + try { + const { wrapper } = mount({ copyText: 'value', copiedLabel: 'Copied' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + const card = screen.getByRole('button') + fireEvent.keyDown(card, { key: 'Escape' }) + expect(writeText).not.toHaveBeenCalled() + await act(async () => { fireEvent.keyDown(card, { key: 'Enter' }) }) + expect(writeText).toHaveBeenCalledOnce() + act(() => { vi.advanceTimersByTime(1000) }) + await act(async () => { fireEvent.keyDown(card, { key: ' ' }) }) + expect(writeText).toHaveBeenCalledTimes(2) + } finally { + restoreClipboard() + } + }) + + it('keeps its content when the clipboard rejects the write', async () => { + const writeText = vi.fn(async () => { throw new Error('denied') }) + const restoreClipboard = installClipboard(writeText) + try { + const { wrapper } = mount({ copyText: 'value', copiedLabel: 'Copied' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + await act(async () => { fireEvent.click(screen.getByRole('button')) }) + expect(screen.queryByText('Copied')).toBeNull() + expect(screen.getByText('card body')).toBeTruthy() + } finally { + restoreClipboard() + } + }) + + it('unmount clears copied feedback', async () => { + const writeText = vi.fn(async () => {}) + const restoreClipboard = installClipboard(writeText) + try { + const { view, wrapper } = mount({ copyText: 'value' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + await act(async () => { fireEvent.click(screen.getByRole('button')) }) + expect(vi.getTimerCount()).toBe(1) + view.unmount() + expect(vi.getTimerCount()).toBe(0) + } finally { + restoreClipboard() + } + }) + + it('clears copied feedback when the card closes', async () => { + const writeText = vi.fn(async () => {}) + const restoreClipboard = installClipboard(writeText) + try { + const { wrapper } = mount({ copyText: 'value', copiedLabel: 'Copied' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + await act(async () => { fireEvent.click(screen.getByRole('button')) }) + expect(screen.getByRole('status').textContent).toBe('Copied') + fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS) }) + expect(screen.queryByText('Copied')).toBeNull() + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + expect(screen.getByText('card body')).toBeTruthy() + } finally { + restoreClipboard() + } + }) + + it('does not create copied feedback after an in-flight write unmounts', async () => { + let acceptWrite: (() => void) | undefined + const writeText = vi.fn(() => new Promise((resolve) => { acceptWrite = resolve })) + const restoreClipboard = installClipboard(writeText) + try { + const { view, wrapper } = mount({ copyText: 'value' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + fireEvent.click(screen.getByRole('button')) + expect(writeText).toHaveBeenCalledOnce() + view.unmount() + await act(async () => { acceptWrite?.() }) + expect(vi.getTimerCount()).toBe(0) + } finally { + restoreClipboard() + } + }) + + it('does not restore copied feedback after an in-flight card closes', async () => { + let acceptWrite: (() => void) | undefined + const writeText = vi.fn(() => new Promise((resolve) => { acceptWrite = resolve })) + const restoreClipboard = installClipboard(writeText) + try { + const { wrapper } = mount({ copyText: 'value', copiedLabel: 'Copied' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + fireEvent.click(screen.getByRole('button')) + fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS) }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + await act(async () => { acceptWrite?.() }) + expect(vi.getTimerCount()).toBe(0) + expect(screen.getByText('card body')).toBeTruthy() + } finally { + restoreClipboard() + } + }) + + it('coalesces activations while the clipboard write is in flight', async () => { + let acceptWrite: (() => void) | undefined + const writeText = vi.fn(() => new Promise((resolve) => { acceptWrite = resolve })) + const restoreClipboard = installClipboard(writeText) + try { + const { wrapper } = mount({ copyText: 'value', copiedLabel: 'Copied' }) + fireEvent.pointerEnter(wrapper) + act(() => { vi.advanceTimersByTime(500) }) + const card = screen.getByRole('button') + fireEvent.click(card) + fireEvent.click(card) + expect(writeText).toHaveBeenCalledOnce() + await act(async () => { acceptWrite?.() }) + expect(screen.getByRole('status').textContent).toBe('Copied') + } finally { + restoreClipboard() + } + }) + it('disabled suppresses opening entirely', () => { const { wrapper } = mount({ disabled: true }) fireEvent.pointerEnter(wrapper) @@ -135,6 +415,7 @@ describe('HoverCard', () => { expect(card.style.left).toBe('308px') expect(card.style.top).toBe('90px') fireEvent.pointerLeave(wrapper) + act(() => { vi.advanceTimersByTime(POINTER_GRACE_MS) }) expect(screen.queryByText('card body')).toBeNull() }) diff --git a/packages/client/ui-trajectory/README.i18n.yaml b/packages/client/ui-trajectory/README.i18n.yaml index 51ff03c8af..41c954adc0 100644 --- a/packages/client/ui-trajectory/README.i18n.yaml +++ b/packages/client/ui-trajectory/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-trajectory/README.md -README.md: b9c8b849b3454fe46e1fc37713d9d3b9449734cf -README.zh.md: 6ddc32f2f27c93f8ccc80b3d9b31d56d3cf4dd94 +README.md: a65c11aed9dd74f9b0b60795441f876c1d64b3ad +README.zh.md: 6e25d24c6b65673b3d003e624b6e0727be60c0e1 diff --git a/packages/client/ui-trajectory/README.md b/packages/client/ui-trajectory/README.md index b9c8b849b3..a65c11aed9 100644 --- a/packages/client/ui-trajectory/README.md +++ b/packages/client/ui-trajectory/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. A fixed Overview above the ledger projects real record start/duration timing from left to right; dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full branch. The runtime's independent history source supplies raw context lineage and projects cancellation-frozen Assistant and Tool records, so Trajectory neither reads nor changes the Chat conversation snapshot. The package remains a pure-consumer plugin (registers one view tab into the conversation's `'conversation.view'` slot ring, provides no service, declares no Context merge). Contract: api-contracts v3 §8. +Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. A standalone compaction request appears chronologically in its own `Between turns` section, while a numbered compaction remains inside its owning turn. A fixed Overview above the ledger projects real record start/duration timing from left to right; dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full branch. The runtime's independent history source supplies raw context lineage and projects cancellation-frozen Assistant and Tool records, so Trajectory neither reads nor changes the Chat conversation snapshot. The package remains a pure-consumer plugin (registers one view tab into the conversation's `'conversation.view'` slot ring, provides no service, declares no Context merge). Contract: api-contracts v3 §8. ## Model Experience diff --git a/packages/client/ui-trajectory/README.zh.md b/packages/client/ui-trajectory/README.zh.md index 6ddc32f2f2..6e25d24c6b 100644 --- a/packages/client/ui-trajectory/README.zh.md +++ b/packages/client/ui-trajectory/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -Trajectory 渲染按轮次组织的事件记录表,其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界,紧凑的行内标记标识步骤,主记录表仅保留索引、事件和内容;选择记录则会打开局部检查器,查看 token 用量、耗时、输入、输出和计时。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时;拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录,清除选择则恢复完整分支。运行时的独立历史数据源提供原始上下文谱系,并投影因取消而冻结的助手和工具记录,因此 Trajectory 既不读取也不改变 Chat 会话快照。该包(package)保持为纯消费方插件(向会话的 `'conversation.view'` slot 环注册一个视图标签页,不提供服务,也不声明 Context 合并)。契约:api-contracts v3 §8。 +Trajectory 渲染按轮次组织的事件记录表,其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界,紧凑的行内标记标识步骤,主记录表仅保留索引、事件和内容;选择记录则会打开局部检查器,查看 token 用量、耗时、输入、输出和计时。独立运行的压缩(compaction)请求会按时间顺序显示在自己的 `Between turns` 区段中,而带数值所有者的压缩仍位于其所属轮次内。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时;拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录,清除选择则恢复完整分支。运行时的独立历史数据源提供原始上下文谱系,并投影因取消而冻结的助手和工具记录,因此 Trajectory 既不读取也不改变 Chat 会话快照。该包(package)保持为纯消费方插件(向会话的 `'conversation.view'` slot 环注册一个视图标签页,不提供服务,也不声明 Context 合并)。契约:api-contracts v3 §8。 ## 模型体验 diff --git a/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx b/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx index 5a78e95a40..53db32efca 100644 --- a/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx +++ b/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx @@ -104,7 +104,8 @@ const KIND_ICON: Record = { } interface TableRecord { - turn: number + turn: number | null + section: number group: string groupStart: boolean turnStart: boolean @@ -146,7 +147,8 @@ interface ToolCallTextParts { } interface SelectedRequest { - turn: number + turn: number | null + section: number number: number group: string } @@ -320,15 +322,12 @@ export interface TrajectoryTableProps { onInspectApplied?: (() => void) | undefined } -/** One request identity paired with its session-global number. */ -export interface TrajectoryRequestNumber { +/** Request-inspector fields shared by ordinary generation and compaction. */ +interface TrajectoryRequestNumberBase { /** Request anchor event sequence; absent for the currently streaming ordinary request. */ seq?: number - turn: number - step: number group: string number: number - purpose?: 'compaction' status?: 'complete' | 'running' | 'error' startedAt?: number completedAt?: number | null @@ -344,6 +343,20 @@ export interface TrajectoryRequestNumber { cumulativeUsage?: TrajectoryUsage } +/** One purpose-discriminated request identity paired with its session-global number. */ +export type TrajectoryRequestNumber = TrajectoryRequestNumberBase & ( + | { + purpose?: 'assistant' + turn: number + step: number + } + | { + purpose: 'compaction' + turn: number | null + step: 0 + } +) + /** Disjoint provider token buckets for one request or a session prefix. */ export interface TrajectoryUsage { input?: number @@ -354,17 +367,18 @@ export interface TrajectoryUsage { } function flattenRecords(turns: readonly TrajectoryTurnModel[]): TableRecord[] { - return turns.flatMap((turn) => { - let firstInTurn = true + return turns.flatMap((turn, section) => { + let firstInSection = true const records = turn.groups.flatMap((group) => { return group.cells.map((cell, index) => { - const turnStart = firstInTurn + const turnStart = firstInSection && cell.requestOnly !== true && cell.kind !== 'system' - && cell.kind !== 'compacted' - if (turnStart) firstInTurn = false + && (cell.kind !== 'compacted' || turn.turn === null) + if (turnStart) firstInSection = false return { turn: turn.turn, + section, group: group.title, groupStart: index === 0, turnStart, @@ -388,18 +402,18 @@ function filterRecords( record.cell.requestOnly !== true && matches.has(record.cell.index), ) .map(record => ({ ...record, groupStart: false, turnStart: false, turnEnd: false })) - const startedTurns = new Set() + const startedSections = new Set() for (const [index, record] of filtered.entries()) { const previous = filtered[index - 1] const next = filtered[index + 1] record.groupStart = previous === undefined - || previous.turn !== record.turn + || previous.section !== record.section || previous.group !== record.group - record.turnStart = !startedTurns.has(record.turn) + record.turnStart = !startedSections.has(record.section) && record.cell.kind !== 'system' - && record.cell.kind !== 'compacted' - if (record.turnStart) startedTurns.add(record.turn) - record.turnEnd = next === undefined || next.turn !== record.turn + && (record.cell.kind !== 'compacted' || record.turn === null) + if (record.turnStart) startedSections.add(record.section) + record.turnEnd = next === undefined || next.section !== record.section } return filtered } @@ -410,10 +424,14 @@ function requestStep(group: string): number | undefined { return Number.isInteger(value) && value > 0 ? value : undefined } -function requestKey(turn: number, group: string): string { +function requestKey(turn: number | null, group: string): string { return `${turn}\u0000${group}` } +function sectionLabel(turn: number | null): string { + return turn === null ? 'Between turns' : `Turn ${turn}` +} + function indexRequestNumbers( records: readonly TableRecord[], sessionNumbers: readonly TrajectoryRequestNumber[] | undefined, @@ -455,12 +473,13 @@ function collapseTurnRecords( if (collapsedTurns.size === 0) return [...records] const recordsByTurn = new Map() for (const record of records) { + if (record.turn === null) continue const turnRecords = recordsByTurn.get(record.turn) ?? [] turnRecords.push(record) recordsByTurn.set(record.turn, turnRecords) } return records.flatMap((record) => { - if (!collapsedTurns.has(record.turn)) return [record] + if (record.turn === null || !collapsedTurns.has(record.turn)) return [record] const turnRecords = recordsByTurn.get(record.turn) ?? [record] if (record.cell.requestOnly === true || record.cell.kind === 'system') return [record] const contentRecords = turnRecords.filter(candidate => @@ -1537,6 +1556,7 @@ export function TrajectoryTable({ ? [] : allRecords.filter(record => record.turn === selectedRequest.turn + && record.section === selectedRequest.section && record.group === selectedRequest.group, ) const selectedRequestAssistant = selectedRequestRecords.find( @@ -1588,7 +1608,8 @@ export function TrajectoryTable({ const selectedRequestCumulativeUsage = selectedRequestInfo?.cumulativeUsage ?? selectedRequestUsage const selectedRequestOptions = selectedRequestInfo?.requestConfig - const activeTurn = selectedRequest?.turn ?? selected?.turn + const activeTurn = selectedRequest === null ? selected?.turn : selectedRequest.turn + const activeSection = selectedRequest === null ? selected?.section : selectedRequest.section const selectedTabs = selectedRequest !== null ? REQUEST_TABS.filter(tab => tab.id !== 'options' || selectedRequestOptions !== undefined) : selected === undefined ? [] : detailTabs(selected) @@ -1604,6 +1625,7 @@ export function TrajectoryTable({ selected !== undefined && selectedAssistantRequest !== undefined ? { turn: selected.turn, + section: selected.section, number: selectedAssistantRequest, group: selected.group, } @@ -1664,7 +1686,7 @@ export function TrajectoryTable({ const openRecordSummary = (target: TableRecord) => { const targetAt = allRecords.findIndex(record => record.cell.index === target.cell.index) - if (collapsedTurns.has(target.turn)) onToggleTurn(target.turn) + if (target.turn !== null && collapsedTurns.has(target.turn)) onToggleTurn(target.turn) if (target.cell.kind === 'tool' || target.cell.kind === 'subtool') { for (let i = targetAt - 1; i >= 0; i--) { const candidate = allRecords[i] @@ -1739,7 +1761,7 @@ export function TrajectoryTable({ && record.cell.index === allRecords[0]?.cell.index const request = record.groupStart && !isCollapsedSummary - && !collapsedTurns.has(record.turn) + && (record.turn === null || !collapsedTurns.has(record.turn)) ? requestNumbers.get(requestKey(record.turn, record.group)) : undefined const requestInfo = request === undefined @@ -1750,7 +1772,11 @@ export function TrajectoryTable({ : `Request #${request}${requestInfo?.purpose === 'compaction' ? ' · Compaction' : ''}` const requestSelected = request !== undefined && selectedRequest?.turn === record.turn + && selectedRequest.section === record.section && selectedRequest.number === request + const sectionActive = record.turn === null + ? activeSection === record.section + : activeTurn === record.turn return ( { - if (record.collapsedSummaryKind === 'turn') onToggleTurn(record.turn) - else onToggleAssistant(record.cell.index) + if (record.collapsedSummaryKind === 'turn' && record.turn !== null) { + onToggleTurn(record.turn) + } else onToggleAssistant(record.cell.index) } : () => { selectRecord(record.cell.index) }} onDoubleClick={(event) => { if (isCollapsedSummary || isRequestOnly) return - if (collapsedTurns.has(record.turn)) { + if (record.turn !== null && collapsedTurns.has(record.turn)) { event.preventDefault() onToggleTurn(record.turn) return @@ -1800,6 +1827,7 @@ export function TrajectoryTable({ return } if (!record.turnStart) return + if (record.turn === null) return if (allRecords.filter(candidate => candidate.turn === record.turn && candidate.cell.requestOnly !== true @@ -1812,8 +1840,9 @@ export function TrajectoryTable({ if (event.key !== 'Enter' && event.key !== ' ') return event.preventDefault() if (isCollapsedSummary) { - if (record.collapsedSummaryKind === 'turn') onToggleTurn(record.turn) - else onToggleAssistant(record.cell.index) + if (record.collapsedSummaryKind === 'turn' && record.turn !== null) { + onToggleTurn(record.turn) + } else onToggleAssistant(record.cell.index) return } selectRecord(record.cell.index) @@ -1833,6 +1862,7 @@ export function TrajectoryTable({ event.stopPropagation() selectRequest({ turn: record.turn, + section: record.section, number: request, group: record.group, }) @@ -1840,7 +1870,9 @@ export function TrajectoryTable({ onDoubleClick={(event) => { event.stopPropagation() }} /> )} - {activeTurn === record.turn && !isInitialSystem && ( + {record.turn !== null + && activeTurn === record.turn + && !isInitialSystem && (