diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml index 0d6a23bebe..8193e5e839 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-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/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md -2026-06-21-bounded-llm-request-recovery.md: 83d47e3a7d91bbcd2ceaf7b11cf13316142eb3ed -2026-06-21-bounded-llm-request-recovery.zh.md: 00dcbad3d1023ad33a22297bfe938b94bce839d4 +2026-06-21-bounded-llm-request-recovery.md: 5c76ed5d754ea40f41dff78cb56ee7fc139a32b1 +2026-06-21-bounded-llm-request-recovery.zh.md: 1fa56f3fe0405cab663c2843d423a78d910170dd diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md index 83d47e3a7d..5c76ed5d75 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md @@ -60,11 +60,11 @@ For an eligible failure with budget remaining, the one-based transient retry cou The plugin owns a lifetime `AbortController` and tracks every active recovery callback, including delegated waterfall work and backoff. Effect cleanup first unregisters the listener, then aborts and awaits the active callbacks; abort wins over a late delegated retry decision, and a captured callback can neither retry nor enter the rest of its waterfall after disposal. This makes HMR disposal quiescent even though Cordis has already captured the listener. -Before sleeping, `dsh-llm-retry` appends one non-surface `llm/retry` session event containing the turn, failed step, provider, policy mode, complete resolved-policy key, provider-policy retry number, mode-specific finite maximum when present, scheduled delay, and `LlmFailure`. The key sorts the code set and separates retry histories when a provider route is replaced by a behaviorally different same-mode policy. The plugin owns the `SessionEventMap` augmentation; `dsh-session` remains generic persistence and does not absorb the optional policy's vocabulary. The event says what was scheduled, not that the next request completed; cancellation during the delay is subsequently visible on `turn/end`. The event ships only with a production renderer and replay/snapshot coverage, because its purpose is operational state rather than trace collection. +Before sleeping, `dsh-llm-retry` appends one non-surface `llm/retry` session event containing the turn, failed step, provider, policy mode, complete resolved-policy key, provider-policy retry number, mode-specific finite maximum when present, scheduled delay, and `LlmFailure`. The key sorts the code set and separates retry histories when a provider route is replaced by a behaviorally different same-mode policy. The plugin owns the `SessionEventMap` augmentation and exports the payload through its browser-safe `./types` subpath; `dsh-session` remains generic persistence and does not absorb the optional policy's vocabulary. The event says what was scheduled, not that the next request completed; cancellation during the delay is subsequently visible on `turn/end`. The event ships with production renderers and replay/snapshot coverage, because its purpose is operational state rather than trace collection. The listener calls `next()` for a non-transient code, an exhausted policy budget, or an over-cap provider delay. This preserves composition with context-overflow recovery and later policy plugins. For an owned failure it records and awaits the delay, then returns `{ kind: 'retry' }` without delegating. Turn cancellation and plugin disposal end the wait without returning a retry; the loop's cancellation/disposal checks remain authoritative. -The agent-spine demo bundle loads the plugin so the shared stdio/TUI, one-shot CLI, and ACP example compositions use the same provider-routed policy. Library consumers retain explicit plugin composition: omitting the plugin leaves request failures terminal. +The agent-spine demo bundle loads the plugin so the shared stdio/TUI, one-shot CLI, ACP, and headless example compositions use the same provider-routed policy. The shipped Web composition also loads it, so browser and command-line requests use the same provider defaults. Library consumers retain explicit plugin composition: omitting the plugin leaves request failures terminal. ### Make one layer own visible attempts @@ -82,7 +82,7 @@ Boundary tests prove termination at both actual transports. The hand-written ada ### Keep attempts separate in the existing log -A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure; message derivation continues to ignore the failed chunks. +A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects consecutive retry-turn events into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from subsequent turn facts. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows. If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. If transient recovery continues, `llm/retry` is the durable home for that attempt's failure and delay. No standalone final-error event or response-id vocabulary is added. @@ -116,7 +116,7 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason` - Pure unit tests cover transient-code selection, exponential backoff and jitter bounds, valid and over-cap `Retry-After`, exhausted budgets, deterministic timer/random seams, and abort during backoff. - Real agent-loop tests cover failure before chunks, partial chunks then failure, thrown and in-band failures, retry to success in a new turn, exhaustion to structured `turn/end.reason`, and composition with `dsh-compact-basic` context-overflow recovery. - The partial-chunk integration test proves failed chunks remain attributed to the failed step, no assistant message or tool side effect is committed for that step, and the successful retry has distinct provenance. -- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI retraction plus scheduled-retry rendering. Keyless snapshots cover scheduling, cancellation, success, and exhaustion; ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted. +- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Client tests cover complete wire validation, clock-independent countdown, cancellation versus completed retry labels, and trajectory attribution; keyless UI snapshots cover Web scheduling and success, a real Web composition test covers partial transport failure through recovery, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted. - Idle-watchdog tests prove the stable signal is rearmed only while `next()` is outstanding, disarmed during consumer think time and in `finally`, and classified separately from a total-call deadline and an earlier caller abort; adapter tests prove the signal stops the underlying request rather than merely detaching it. - Direct `ctx.llm.stream()` callers remain single-attempt and receive the same structured failure facts. diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md index 00dcbad3d1..1fa56f3fe0 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md @@ -60,11 +60,11 @@ agent loop（智能体循环）会保留 `RequestError` 作为该精确的错误 插件拥有一个全生命期 `AbortController`，并跟踪每个活跃的恢复回调，包括委托的 waterfall（瀑布式事件）工作与退避。effect 清理会先注销监听器，再中止并等待活跃回调；中止会胜过较晚到达的委托重试决策，被捕获的回调在插件释放后既不能重试，也不能进入其 waterfall 的剩余部分。尽管 Cordis 已捕获该监听器，此设计仍能使 HMR（热模块替换）释放达到完全停稳。 -休眠前，`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件，其中包含轮次、失败步骤、提供方、策略 mode、完整的解析策略 key、提供方策略重试编号、该 mode 存在时的有限上限、计划延迟和 `LlmFailure`。该 key 会对 code 集排序，并在提供方路由被行为不同但 mode 相同的策略替换时分隔重试历史。该插件拥有 `SessionEventMap` 声明合并；`dsh-session` 继续负责通用持久化，不会吸收可选策略的词汇。事件记录已安排的内容，而不是下一个请求已完成；延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态，而不是收集跟踪数据，所以它仅与生产渲染器及回放／快照覆盖一起交付。 +休眠前，`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件，其中包含轮次、失败步骤、提供方、策略 mode、完整的解析策略 key、提供方策略重试编号、该 mode 存在时的有限上限、计划延迟和 `LlmFailure`。该 key 会对 code 集排序，并在提供方路由被行为不同但 mode 相同的策略替换时分隔重试历史。该插件拥有 `SessionEventMap` 声明合并，并通过其浏览器安全的 `./types` 子路径导出载荷；`dsh-session` 继续负责通用持久化，不会吸收可选策略的词汇。事件记录已安排的内容，而不是下一个请求已完成；延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态，而不是收集跟踪数据，所以它会与生产渲染器及回放／快照覆盖一起交付。 对非暂时性 code、耗尽的策略预算或超出上限的提供方延迟，监听器会调用 `next()`。这保留了与上下文溢出恢复及后续策略插件的组合能力。对自身处理的失败，它会记录并等待延迟，然后在不委托的情况下返回 `{ kind: 'retry' }`。轮次取消和插件释放会结束等待且不返回重试动作，此后仍以循环的取消／释放检查为准。 -agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次性 CLI（命令行界面）和 ACP（Agent Client Protocol）示例组合使用同一套按提供方路由的策略。库消费方仍需显式组合插件：省略该插件时，请求失败保持终态。 +agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次性 CLI（命令行界面）、ACP（Agent Client Protocol）和 headless 示例组合使用同一套按提供方路由的策略。随产品交付的 Web 组合也会加载该插件，因此浏览器请求与命令行请求使用相同的提供方默认值。库消费方仍需显式组合插件：省略该插件时，请求失败保持终态。 ### 由单一层负责可见的尝试 @@ -82,7 +82,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 ### 在现有日志中分隔尝试 -一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会关闭失败轮次，开启下一个编号轮次，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。消息派生仍会忽略失败分片。 +一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会关闭失败轮次，开启下一个编号轮次，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷契约，在 `llm/retry` 到达时清除失败的部分输出，将连续重试轮次的事件投影为稳定的一行，并用最新一次尝试更新该行，再从后续轮次事实派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点，而不是使用 Host 事件时钟；它按向上取整且不低于 1 秒的秒数显示，仅在重试尚未结束时显示动画，并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点，重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片；Web 在重建历史时也会应用同一投影，因此刷新页面不会让已丢弃的部分输出重新出现，也不会生成重复的重试行。 如果恢复预算耗尽，最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。如果暂时性恢复继续，`llm/retry` 就是该次尝试的失败与延迟的持久归属位置。本决策不增加独立的最终错误事件或响应 id 词汇。 @@ -116,7 +116,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 - 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器／随机数 seam，以及退避期间中止。 - 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新轮次中重试至成功、耗尽后写入结构化 `turn/end.reason`，以及与 `dsh-compact-basic` 上下文溢出恢复的组合。 - 部分分片集成测试证明：失败分片仍归属于失败步骤，该步骤不会提交 assistant 消息或工具副作用，成功的重试具有不同的来源信息。 -- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 撤回和计划重试渲染。无密钥快照覆盖调度、取消、成功和耗尽；ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。 +- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 和 Web 撤回及计划重试渲染。客户端测试覆盖完整的 wire 验证、独立于时钟的倒计时、已取消与已完成重试标签的区别以及轨迹归属；无密钥 UI 快照覆盖 Web 的调度与成功，真实 Web 组合测试覆盖部分传输失败直至恢复，ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。 - 空闲看门狗测试证明：只有 `next()` 尚未完成时才会重新布防稳定信号；在消费方思考期间及 `finally` 中会解除布防；它与总调用 deadline 以及更早发生的调用方中止分开分类。适配器测试证明该信号会终止底层请求，而不只是与其脱离。 - `ctx.llm.stream()` 的直接调用方仍只尝试一次，并收到相同的结构化失败事实。 diff --git a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml index f140786632..451dcd1fca 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.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/2026-07-23-client-plugin-loading-model.md -2026-07-23-client-plugin-loading-model.md: b0873b7aa7bccd3d613f3113fa18207770952e5d -2026-07-23-client-plugin-loading-model.zh.md: f3472dbfc5a78924e77337bf92ce5983c8492c4c +2026-07-23-client-plugin-loading-model.md: 02347f2964942b89ec1f0a6ec483f4c2b2f9e68c +2026-07-23-client-plugin-loading-model.zh.md: ea927d35860fbbba567c47cea0ee3a45133ce0f4 diff --git a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md index b0873b7aa7..02347f2964 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md +++ b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md @@ -56,8 +56,8 @@ What happens between `dsh web` starting and the UI appearing? Three stages: the **Host side — compose the graph.** -1. The composing app (`apps/cli`) ships the roster as ordinary rows in its `cordis.yml` config tree — client plugin packages are entry rows like every host plugin, and `--dev` appends the `client-hmr` row in code (`AppCLIEntry`) before the settle/sweep so the fail-loud triple covers it. A roster row that fails to import is caught by the boot's `assertEntriesLoaded`. -2. The `dsh-client-modules` node half (the package is dual-face: its browser half is the module table) scans loader entries' package.json `dshClient` declarations and composes `window.__DSH_BOOT__`: `{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`. The `inject` edges and the `immediately` mark come from manifests, never hand-copied. It refuses a declared plugin without a built `./client` bundle, and any malformed declaration field — activation-time fail loud (a FAILED fiber the sweep reports). +1. The composing app (`apps/cli`) ships the roster as ordinary rows in its `cordis.yml` config tree — client plugin packages are entry rows like every host plugin, and `--dev` appends the `client-hmr` row in code (`AppCLIEntry`) before the host activation audit so the same check covers it. A roster row that fails to import is caught by `assertEntriesLoaded`; a row whose fiber rejects is reported with its original stack by `assertEntriesActivated` ([host boot decision](2026-07-24-web-config-tree-boot-and-transport-layering.md)). +2. The `dsh-client-modules` node half (the package is dual-face: its browser half is the module table) scans loader entries' package.json `dshClient` declarations and composes `window.__DSH_BOOT__`: `{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`. The `inject` edges and the `immediately` mark come from manifests, never hand-copied. It refuses declared plugins without built `./client` bundles and groups their package/path rows under one required source-build instruction; malformed declaration fields also fail activation, and the host audit reports either error from the FAILED fiber. 3. Scanning is incremental per package — there is no full-rescan code path. Each cordis `internal/plugin` emission marks the fiber's entry name dirty (entry-less fibers drop O(1)); a microtask flush reconciles each dirty name against live loader entries, with package metadata (including the negative "not a client package" verdict) cached per name forever and bundle re-hashing reachable only through `rebuilt(id)`. The activation pass seeds the same dirty set from current entries and flushes synchronously, so first scan and steady state share one implementation. Each bundle's content hash is its `rev` (cache busting + HMR diff anchor), the row set hashes into `graph.rev`, and every row is fetch-served: `/plugins//client.js?rev=…`. The graph types are single-sourced in the modules package's `./impl` export — the webserver knows nothing about the graph (it is a plain route-registration plugin; modules registers the bundle route and taps the index render itself). Why is the roster yml rows and not a scan? Because which plugins compose into a deployment is a composition decision, not a package property — a dshClient package existing in the repo does not mean this deployment mounts it, so discovery-by-scan cannot make that call; the node half scans only what the tree actually mounted. diff --git a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.zh.md b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.zh.md index f3472dbfc5..ea927d3586 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.zh.md @@ -56,8 +56,8 @@ vendored Loader 经其 `internal` seam 消费模块系统——唯一调用点 **host 侧——组合这张图。** -1. 负责组合的 app（`apps/cli`）把名册作为普通行放进它的 `cordis.yml` 配置树——client 插件包与每个 host 插件一样是 entry 行，`--dev` 由代码（`AppCLIEntry`）在 settle/sweep 之前追加 `client-hmr` 行，使 fail-loud 三件套一并覆盖它。名册行 import 失败由 boot 的 `assertEntriesLoaded` 捕获。 -2. `dsh-client-modules` 的 node 半（该包是双面的：浏览器半就是模块表）扫描 loader entry 的 package.json `dshClient` 声明，组合出 `window.__DSH_BOOT__`：`{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`。`inject` 边与 `immediately` 标记都来自 manifest，永不人肉抄写。它拒绝声明了插件却没有已构建 `./client` bundle 的包，也拒绝任何畸形的声明字段——激活期大声失败（FAILED fiber，由 sweep 上报）。 +1. 负责组合的 app（`apps/cli`）把名册作为普通行放进它的 `cordis.yml` 配置树——client 插件包与每个 host 插件一样是 entry 行，`--dev` 由代码（`AppCLIEntry`）在 host 激活检查之前追加 `client-hmr` 行，使同一项检查覆盖它。名册行 import 失败由 `assertEntriesLoaded` 捕获；fiber reject 的行则由 `assertEntriesActivated` 报告原始 stack（[host boot 决策](2026-07-24-web-config-tree-boot-and-transport-layering.md)）。 +2. `dsh-client-modules` 的 node 半（该包是双面的：浏览器半就是模块表）扫描 loader entry 的 package.json `dshClient` 声明，组合出 `window.__DSH_BOOT__`：`{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`。`inject` 边与 `immediately` 标记都来自 manifest，永不人肉抄写。它会拒绝没有已构建 `./client` bundle 的已声明插件，并把它们的 package/path 行归到一条源码构建要求下；畸形声明字段同样会让激活失败，host 检查会从 FAILED fiber 报告这两类错误。 3. 扫描是单包增量——不存在全量重扫代码路径。每次 cordis `internal/plugin` 发射把该 fiber 的 entry 名标脏（无 entry 的 fiber O(1) 丢弃）；微任务 flush 把每个脏名对账 live loader entries，包元数据（含「非 client 包」的否定结论）按名永久缓存，bundle 重哈希只经 `rebuilt(id)` 可达。激活趟从当前 entries 灌同一脏集合并同步 flush，初扫与稳态共享一条实现。每个 bundle 的内容哈希是其 `rev`（缓存失效 + HMR diff 锚点），行集合哈希进 `graph.rev`，每一行都经 fetch 供给：`/plugins//client.js?rev=…`。图类型单源在 modules 包的 `./client` 出口——webserver 对图一无所知（它是朴素路由注册插件；bundle 路由和 index 渲染 tap 都由 modules 自己注册）。 为什么名册是 yml 行而不是扫描？因为哪些插件组合进一次部署是组合决策，不是包属性——一个 dshClient 包存在于仓库里，不代表这次部署要挂载它，扫描发现无从替人做这个决定；node 半只扫描配置树实际挂载了的东西。 diff --git a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.i18n.yaml index aa927a2e7d..d50428d5ed 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.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/2026-07-24-web-config-tree-boot-and-transport-layering.md -2026-07-24-web-config-tree-boot-and-transport-layering.md: a2080024d36d54162f4f4aa79896e51efd708f59 -2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 1c430bf2939f9f556f378bdeb78872a0091a592d +2026-07-24-web-config-tree-boot-and-transport-layering.md: 88f94b1f58ae7a3451c7772f4a9ff7d6564254c0 +2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: ea2a8f70a6c2d4207d4388a9303fbc6ce6e94238 diff --git a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md index a2080024d3..88f94b1f58 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md +++ b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md @@ -12,9 +12,9 @@ English | [中文](2026-07-24-web-config-tree-boot-and-transport-layering.zh.md) ## Decision -**Composition is one flat assembled tree.** `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` holds every row — the host runtime (32 rows), the `api-gateway` row, the `webserver` row, and the `dshClient` rows (the browser roster; the modules row is simultaneously a host row). No spine bundle: every plugin is one row and every config field is yml-editable. That stance later became repository-wide, with the rows both surfaces share factored into `apps/cli/config/base.cordis.yml` and each surface reduced to an overlay ([shared-base overlays](../simplification/2026-07-29-shared-base-config-overlays.md)). `--dev` appends the `dsh-client-hmr` row in code before the settle sweep — prod and dev differ by exactly that row. Row order carries no load semantics; activation is service-availability driven, and the boot compensates with a fail-loud triple: `assertEntriesLoaded` (import failures), `installFailLoud` (late apply rejections), and an all-ACTIVE sweep (PENDING fibers — cordis inject waiting has no timeout). +**Composition is one flat assembled tree.** `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` holds every row — the host runtime (32 rows), the `api-gateway` row, the `webserver` row, and the `dshClient` rows (the browser roster; the modules row is simultaneously a host row). No spine bundle: every plugin is one row and every config field is yml-editable. That stance later became repository-wide, with the rows both surfaces share factored into `apps/cli/config/base.cordis.yml` and each surface reduced to an overlay ([shared-base overlays](../simplification/2026-07-29-shared-base-config-overlays.md)). `--dev` appends the `dsh-client-hmr` row in code before the settle audit — prod and dev differ by exactly that row. Row order carries no load semantics; activation is service-availability driven. The shared audit rejects imports with no fiber, awaits only failed fibers to recover original activation errors, and reports services that leave a fiber `PENDING`; before throwing, it marks those exact rejection reasons through one process checkpoint so `installFailLoud` coalesces Loader's duplicate notification while unrelated unhandled rejections remain fatal. The Node app-boot artifact embeds `@cordisjs/plugin-include` while leaving `@cordisjs/plugin-loader` external, so the include's `EntryTree` and the host bind to one Loader peer instead of splitting a config tree across two Loader implementations. -**Boot glue is a class pair.** `AppCLIEntry` (apps/cli) and `AppWebEntry` (the shell kernel) hold only what must exist independently of cordis: argv facts, the composed patch set, the parsed boot manifest, the module system instance, loading-page handles — everything else lives in plugins. `AppCLIEntry.run()` is three stages: layered env (ambient > cwd `.env` > `$DSH_HOME/.env`, closing the defect above) → patch composition → Loader include boot plus the triple. `AppWebEntry.run()` mirrors it browser-side: parse `window.__DSH_BOOT__` into a `BootManifest` (two views: npm-package rows for the module table, cordis-plugin rows for entry composition; malformed wire throws), build the module system, render the loading page, prefetch the `immediately` tier in parallel with Context/Loader setup, **await the prefetch before creating entries** (materialization is `tree.import`'s synchronous require, unprotected by fiber inject waiting; cross-package require edges such as i18n → runtime/client need every immediately-tier factory registered first — an empirically found 10–25% boot race otherwise), adopt the modules entry, create the graph rows, settle, sweep. +**Boot glue is a class pair.** `AppCLIEntry` (apps/cli) and `AppWebEntry` (the shell kernel) hold only what must exist independently of cordis: argv facts, the composed patch set, the parsed boot manifest, the module system instance, loading-page handles — everything else lives in plugins. `AppCLIEntry.run()` is three stages: layered env (ambient > cwd `.env` > `$DSH_HOME/.env`, closing the defect above) → patch composition → Loader include boot plus the activation audit. `AppWebEntry.run()` mirrors it browser-side: parse `window.__DSH_BOOT__` into a `BootManifest` (two views: npm-package rows for the module table, cordis-plugin rows for entry composition; malformed wire throws), build the module system, render the loading page, prefetch the `immediately` tier in parallel with Context/Loader setup, **await the prefetch before creating entries** (materialization is `tree.import`'s synchronous require, unprotected by fiber inject waiting; cross-package require edges such as i18n → runtime/client need every immediately-tier factory registered first — an empirically found 10–25% boot race otherwise), adopt the modules entry, create the graph rows, settle, sweep. **Config sources have one declaration place each.** yml static values are engineering defaults; the profile json (`./.dsh-tmp-profile/config.json`, read-only, never created, cwd-anchored until the `$DSH_HOME` migration) is user config mapped through a static `PROFILE_MAPPINGS` table onto target rows (`provider`/`model` → the `api-gateway` row, `persistenceRoot` → the jsonl row); CLI flags map onto the `webserver` row with a field set disjoint from the json's; env values enter through yml `!!js` expressions, never through the mapping table. Patches replace a row's config wholesale, so the entry class re-reads the yml row's static values (bypass parse) and merges overrides on top. An unmapped json key fails loud. The resolved frontend `distIndex` rides the same patch channel — an assembly fact, not user config. diff --git a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md index 1c430bf293..ea2a8f70a6 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.zh.md @@ -12,9 +12,9 @@ Status: implemented ## 决策 -**组合结果是一棵平铺配置树。** `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 共同持有全部行——host runtime（32 行）、`api-gateway` 行、`webserver` 行、`dshClient` 行（浏览器 roster；modules 行同时是 host 行）。不做 spine bundle：每插件一行、每个 config 字段 yml 可改。这一立场后来推广到全仓：两个 surface 共享的配置项被抽取进 `apps/cli/config/base.cordis.yml`，各 surface 则收敛为一份 overlay（[共享 base overlay](../simplification/2026-07-29-shared-base-config-overlays.md)）。`--dev` 在 settle sweep 之前由代码追加 `dsh-client-hmr` 行——prod 与 dev 的全部差异就是这一行。行序无装载语义；激活由服务可用性驱动，boot 以 fail-loud 三件套补偿：`assertEntriesLoaded`（import 失败）、`installFailLoud`（迟到的 apply 拒绝）、all-ACTIVE sweep（PENDING fiber——cordis inject 等待没有超时）。 +**组合结果是一棵平铺配置树。** `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 共同持有全部行——host runtime（32 行）、`api-gateway` 行、`webserver` 行、`dshClient` 行（浏览器 roster；modules 行同时是 host 行）。不做 spine bundle：每插件一行、每个 config 字段 yml 可改。这一立场后来推广到全仓：两个 surface 共享的配置项被抽取进 `apps/cli/config/base.cordis.yml`，各 surface 则收敛为一份 overlay（[共享 base overlay](../simplification/2026-07-29-shared-base-config-overlays.md)）。`--dev` 在 settle audit 之前由代码追加 `dsh-client-hmr` 行——prod 与 dev 的全部差异就是这一行。行序无装载语义；激活由服务可用性驱动。共享 audit 会拒绝没有 fiber 的 import、仅等待失败的 fiber 以恢复原始激活错误，并报告让 fiber 停在 `PENDING` 的服务；抛出错误前，审计会通过一个进程级检查点标记这些 rejection 的确切原因，从而让 `installFailLoud` 将 Loader 的重复通知合并为一次，而无关的未处理 rejection 仍然致命。Node app-boot 产物内嵌 `@cordisjs/plugin-include`，但将 `@cordisjs/plugin-loader` 保持为外部依赖，因此 include 的 `EntryTree` 与 host 会绑定到同一个 Loader peer，而不会让一棵配置树横跨两个 Loader 实现。 -**boot 胶水是一对 class。** `AppCLIEntry`（apps/cli）与 `AppWebEntry`（壳内核）只持有独立于 cordis 必须提前存在的东西：argv 事实、合成的 patch 集、解析出的 boot manifest、模块系统实例、loading 页句柄——其余一律进插件。`AppCLIEntry.run()` 三段：分层 env（ambient > cwd `.env` > `$DSH_HOME/.env`，顺手关掉上述缺陷）→ patch 合成 → Loader include boot 加三件套。`AppWebEntry.run()` 在浏览器侧镜像它：把 `window.__DSH_BOOT__` 解析成 `BootManifest`（双视角：npm 包行给模块表、cordis 插件行给 entry 组合；畸形 wire 大声抛）、建模块系统、渲染 loading 页、immediately 层预取与 Context/Loader 准备并行、**create entry 之前等预取齐**（物化是 `tree.import` 的同步 require，不受 fiber inject 等待保护；i18n → runtime/client 这类跨包 require 边要求 immediately 层工厂全部注册完——否则有实测 10–25% 的 boot 竞态）、收编 modules entry、逐图行 create、settle、sweep。 +**boot 胶水是一对 class。** `AppCLIEntry`（apps/cli）与 `AppWebEntry`（壳内核）只持有独立于 cordis 必须提前存在的东西：argv 事实、合成的 patch 集、解析出的 boot manifest、模块系统实例、loading 页句柄——其余一律进插件。`AppCLIEntry.run()` 三段：分层 env（ambient > cwd `.env` > `$DSH_HOME/.env`，顺手关掉上述缺陷）→ patch 合成 → Loader include boot 加 activation audit。`AppWebEntry.run()` 在浏览器侧镜像它：把 `window.__DSH_BOOT__` 解析成 `BootManifest`（双视角：npm 包行给模块表、cordis 插件行给 entry 组合；畸形 wire 大声抛）、建模块系统、渲染 loading 页、immediately 层预取与 Context/Loader 准备并行、**create entry 之前等预取齐**（物化是 `tree.import` 的同步 require，不受 fiber inject 等待保护；i18n → runtime/client 这类跨包 require 边要求 immediately 层工厂全部注册完——否则有实测 10–25% 的 boot 竞态）、收编 modules entry、逐图行 create、settle、sweep。 **每个配置源有唯一声明位置。** yml 静态值是工程默认；profile json（`./.dsh-tmp-profile/config.json`，只读、绝不创建、暂锚 cwd 直至 `$DSH_HOME` 迁移）是用户配置，经静态 `PROFILE_MAPPINGS` 表映射到目标行（`provider`/`model` → `api-gateway` 行，`persistenceRoot` → jsonl 行）；CLI flags 映射到 `webserver` 行、字段集与 json 不相交；env 值经 yml `!!js` 表达式进入，绝不进映射表。patch 整体替换行 config，故 entry 类旁路 parse 重读 yml 行静态值再叠加覆盖。未映射的 json 键 fail loud。解析出的前端 `distIndex` 走同一 patch 通道——装配事实，不是用户配置。 diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml index 98423a8c7d..09ab4376b5 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.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/2026-07-25-web-input-machine-and-slash-pipeline.md -2026-07-25-web-input-machine-and-slash-pipeline.md: 92bb91c3e892d928cedf18ec57c725a116b6ffc8 -2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 5bee6df52f16d935aa4f4ccff8627a2d43d44c8c +2026-07-25-web-input-machine-and-slash-pipeline.md: c3deadb34d3a633525dde701c92bcc98c05e5d6e +2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 7a6988423dcdffebb0a28735146439c8ade0a862 diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md index 92bb91c3e8..c3deadb34d 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md +++ b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md @@ -63,7 +63,7 @@ Calls that stay un-evented (registry registration → explicit call → await): A trigger/menu/pick pipeline with zero knowledge of "commands": - The service holds only the source registry (`SlashSource{trigger: '/'|'@', name, order?, candidates, onPick, matchSpace?, matchEnter?}`; (trigger,name) unique; the optional `order` sorts the roster — lower first, default 0, ties keep registration order — and that sorted roster is both group order and polling order) and `sessionOf(sctx)`. Implementing a match hook IS the declaration of participation in space/enter adjudication; the pipeline polls in roster order, the first non-undefined answer wins, and no claimant means the default sink. matchSpace is synchronous (space fires mid-keystroke; hot cache only); matchEnter is asynchronous (it may await the source's own warmup, and a warmup failure rejects). -- The controller holds the single authoritative hit (span included; retained for Space after the menu closes), the per-session menu store, the candidate-fetch generation, keyboard arbitration (combobox mode: focus stays in the textarea, ↑↓/Enter/Escape are intercepted and all pass the IME composition guard, with the single exception Shift+Enter unconditionally going first), and pick orchestration (outcome → self-dispatched bail events); a `dismiss()` verb backs MenuView's injected `onDismiss` (a pointer down outside both the menu and the surrounding composer card closes the menu; MenuView also localizes group titles through the `slash.menu` locale namespace and clamps its height to the viewport space above the composer via ui-primitives' `useAnchoredMaxHeight`); at each session scope's birth it runs `warm(projection)` once over the source roster — within that scope the projection holds only the stable sessionId, with no published/capability transitions; the scope disposer tears down the controller. +- The controller holds the single authoritative hit (span included; retained for Space after the menu closes), the per-session menu store, the candidate-fetch generation, keyboard arbitration (combobox mode: focus stays in the textarea, ↑↓/Enter/Escape are intercepted and all pass the IME composition guard, with the single exception Shift+Enter unconditionally going first), and pick orchestration (outcome → self-dispatched bail events). `toggleSource(name, syntheticHit)` is the chrome-launch path: it seeds only that registered source over the caller's textarea selection and publishes `launcher = name` until close; ordinary typed tracking clears the launcher and restores the full trigger roster. Both paths render the same MenuView and execute the same `onPick` chain. A `dismiss()` verb backs MenuView's injected `onDismiss` (a pointer down outside both the menu and the surrounding composer card closes the menu; MenuView also localizes group titles through the `slash.menu` locale namespace and clamps its height to the viewport space above the composer via ui-primitives' `useAnchoredMaxHeight`); at each session scope's birth it runs `warm(projection)` once over the source roster — within that scope the projection holds only the stable sessionId, with no published/capability transitions; the scope disposer tears down the controller. - Trigger-detection word boundaries (`user@host` and URL `/` never trigger) and the guard tiers (plain: `/` everywhere + `@` inline / claimed: `/` suppressed, `@` live / frozen: none) are the frozen pure core. ### hub / facade: the resident shell and the strict-session input body @@ -101,7 +101,7 @@ skill/@subagent references skip the placeholder + occurrence identity chain — - `conversation.input.dock` — the stacked strip above the input (QueueDock's read-only queue list lands here), ordered by `order`. - `conversation.composer.dock` — the stats band on the composer's top edge. - `conversation.input.left` / `conversation.input.right` — the tool-row left and right regions. -- `conversation.input.plan` / `conversation.input.model` (single) — the tool row's two named control seats; the bar passes only `locked` (owner props), each stays empty until its owning plugin registers, no placeholder fallback. +- `conversation.input.plan` / `conversation.input.model` (single) — the tool row's two named control seats; the bar passes only `locked` (owner props), each stays empty until its owning plugin registers, no placeholder fallback. The plan seat stays empty while inactive because the shared Command source owns entry; an effective plan target renders the warn-state `Plan ×` status button, whose only action is `/plan off`. - `conversation.hero.workspace` (root scope) — the Workspace picker shared by the no-session and blank Hero; a pick reuses or creates the target blank session through `connectWorkspace`, moving the draft where necessary before switching current. ### Testing discipline @@ -122,6 +122,8 @@ The state machine's entire behavior is covered by pure-JS unit tests (event sequ | Space adjudication also claiming execute-kind commands | The misfire defense: after a space the whole line is an ordinary prompt; irreversible side effects keep explicit entry points only | | A generic tokenPattern decoration mechanism | Structured occurrence records replace pattern scanning | | A placeholder select resident in the tool row | Named seats stay empty until registration; a placeholder clashing with the real implementation is two sources of truth | +| An always-visible Plan on/off toggle | The shared Command source already owns entry; a second entry point turns a status seat into redundant mode chrome | +| A second plus-menu component/controller, or an Add/File group above Command | It would duplicate async candidates, keyboard highlight, focus retention, and pick state; the plus control is only a source-filtered launcher for the existing MenuView, and this scope has no file capability | | All references through U+FFFC chips (the pre-Decision-21 line) | Plain text + derived decoration carries zero identity state; the literal text IS the model projection, sparing undo/clipboard any special cases; the chip chain is kept for scenarios needing indivisible atomicity | ## Consequences diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md index 5bee6df52f..7a6988423d 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md @@ -63,7 +63,7 @@ occurrence 表与 chip 三投影： 对"命令"零知识的触发/菜单/pick 管线： - service 只有 source 注册表（`SlashSource{trigger: '/'|'@', name, order?, candidates, onPick, matchSpace?, matchEnter?}`；(trigger,name) 唯一；可选 `order` 对 roster 排序——越小越靠前、默认 0、同值保持注册序——排序后的 roster 同时是组序与轮询序）与 `sessionOf(sctx)`。实现 match 钩子即参与空格/回车裁决的声明；管线按 roster 序轮询，首个非 undefined 应答胜出，无人认领落 default sink。matchSpace 同步（空格在击键中触发，只许热缓存）；matchEnter 异步（可 await 源自身预热，预热失败即 reject）。 -- controller 持有唯一权威 hit（含 span；菜单关闭后为 Space 保留）、per-session menu store、候选 fetch generation、键盘仲裁（combobox 模式：焦点始终在 textarea，↑↓/Enter/Escape 拦截且全程过 IME composition 守卫，唯一例外 Shift+Enter 无条件先行）、pick 编排（outcome → 自派 bail 事件）；`dismiss()` 动词支撑 MenuView 注入的 `onDismiss`（指针落在菜单与所在 composer 卡片之外即关闭菜单；MenuView 还经 `slash.menu` locale 命名空间本地化组标题，并经 ui-primitives 的 `useAnchoredMaxHeight` 把高度收敛到 composer 上方的视口空间）；每个 session scope 出生时对 source roster 做一次 `warm(projection)`，projection 在该 scope 内只有稳定的 sessionId，无 published/能力跃迁；scope disposer 拆除 controller。 +- controller 持有唯一权威 hit（含 span；菜单关闭后为 Space 保留）、per-session menu store、候选 fetch generation、键盘仲裁（combobox 模式：焦点始终在 textarea，↑↓/Enter/Escape 拦截且全程过 IME composition 守卫，唯一例外 Shift+Enter 无条件先行），以及 pick 编排（outcome → 自派 bail 事件）。`toggleSource(name, syntheticHit)` 是 chrome launcher 路径：它基于调用方的 textarea selection，只 seed 对应的已注册 source，并发布 `launcher = name` 直至关闭；普通的键入式 tracking 会清除 launcher 并恢复完整的 trigger roster。两条路径渲染同一个 MenuView，并执行同一条 `onPick` 链。`dismiss()` 动词支撑 MenuView 注入的 `onDismiss`（指针落在菜单与所在 composer 卡片之外即关闭菜单；MenuView 还经 `slash.menu` locale 命名空间本地化组标题，并经 ui-primitives 的 `useAnchoredMaxHeight` 把高度收敛到 composer 上方的视口空间）；每个 session scope 出生时对 source roster 做一次 `warm(projection)`，projection 在该 scope 内只有稳定的 sessionId，无 published/能力跃迁；scope disposer 拆除 controller。 - 触发检测词边界（`user@host`、URL `/` 永不触发）、守卫分档（plain：`/` 到处 + `@` 行内 / claimed：`/` 抑制、`@` 活 / frozen：全无）为冻结纯核。 ### hub / facade：常驻外壳与严格 session 输入体 @@ -101,7 +101,7 @@ skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把 - `conversation.input.dock`——输入上方堆叠条（QueueDock 的队列只读列表落此），order 定序。 - `conversation.composer.dock`——composer 上沿统计带。 - `conversation.input.left` / `conversation.input.right`——工具行左右区。 -- `conversation.input.plan` / `conversation.input.model`（single）——工具行两具名控制位；bar 只传 `locked`（owner props），空到 owning 插件注册为止，无占位 fallback。 +- `conversation.input.plan` / `conversation.input.model`（single）——工具行两具名控制位；bar 只传 `locked`（owner props），空到 owning 插件注册为止，无占位 fallback。plan seat 未激活时保持为空，因为入口归共享 Command source 所有；有效 plan 目标会渲染 warn 状态的 `Plan ×` 状态按钮，其唯一动作是 `/plan off`。 - `conversation.hero.workspace`（root scope）——无 session / blank Hero 共用的 Workspace picker；pick 经 `connectWorkspace` 复用或创建目标 blank session，必要时搬运 draft 后切 current。 ### 测试纪律 @@ -122,6 +122,8 @@ skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把 | 空格裁决也认领即执行型命令 | 误触发防线：空格后整行是普通 prompt；不可逆副作用只留显式入口 | | 通用 tokenPattern 装饰机制 | 结构化 occurrence 记录取代模式扫描 | | 占位 select 常驻工具行 | 具名坑位空到注册为止；占位件与真实现冲突时是双真相源 | +| 始终可见的 Plan 开／关切换 | 入口已归共享 Command source 所有；第二个入口会把状态 seat 变成冗余的 mode chrome | +| 第二套加号菜单组件／controller，或在 Command 上方增加 Add/File 分组 | 这会重复异步候选、键盘高亮、焦点保留与 pick 状态；加号控件只是既有 MenuView 按 source 过滤的 launcher，且此 scope 没有文件能力 | | 引用一律走 U+FFFC chip（决策 21 前旧线） | 纯文本 + 派生装饰零身份状态；原文即模型投影，undo/剪贴板免特判；chip 链保留给需要不可分原子性的场景 | ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.i18n.yaml new file mode 100644 index 0000000000..752dc0f1aa --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.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/architecture/2026-07-30-adapter-owned-max-token-defaults.md +2026-07-30-adapter-owned-max-token-defaults.md: a522848fd4482f84859e587505b6a5e6f5c72d60 +2026-07-30-adapter-owned-max-token-defaults.zh.md: 8db6a06199fc1c4e73c86492d12dc86edafe8c7e diff --git a/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.md b/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.md new file mode 100644 index 0000000000..a522848fd4 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.md @@ -0,0 +1,33 @@ +# Agent Note: Adapter-owned max-token defaults + +Status: implemented + +English | [中文](2026-07-30-adapter-owned-max-token-defaults.zh.md) + +## Problem + +An LLM adapter could serialize an explicit `GenerateOptions.maxTokens`, but its Cordis configuration could not establish a reconstructable conversation default. Applying a fallback only inside provider serialization would make the wire request differ from the durable `request/header`; putting every provider's default in Agent Loop would instead transfer deployment and model policy into the provider-neutral driver. + +## Decision + +`LlmResolvedModelInfo.defaultMaxTokens` carries an optional adapter-configured per-request output cap for one exact provider/model route. `LlmService` validates it as a positive safe integer and materializes it into `LlmCallConfig.maxTokens` only when the caller omitted a value. A prepared call identifies materialized `maxTokens` and `reasoningEffort` fields as adapter defaults; explicit request or Agent options remain unmarked and therefore win without clamping. + +The agent loop continues to prepare calls before logging `request/header`, so the effective config and its adapter-default provenance become durable request facts before dispatch. Before the next `agent/request` waterfall, the loop removes marked fields from the proposal; exact-model resolution then materializes the current route's defaults again. A provider/model switch therefore cannot mistake a previous adapter's default for an explicit override, while explicit conversation values persist. Direct `LlmService.stream()` calls resolve the same default at the final adapter boundary. The field is a request default rather than a hard model output limit; adapters that preserve provider-owned defaults omit it. + +The native DeepSeek adapter exposes `maxTokens` in Cordis config with a 256,000-token default and maps the effective value to `max_tokens`. Its default context capacity is 1,000,000 tokens: both built-in V4 entries publish that exact capacity, while configured entries without capacity and unlisted pass-through ids inherit the same adapter-wide fallback. + +## Alternatives considered + +**Apply the default only in DeepSeek serialization.** Rejected because the provider wire would contain a model-visible value absent from the durable request header. + +**Set `AgentOptions.maxTokens` in every shipped application.** Rejected because applications would duplicate adapter deployment policy, direct LLM calls would behave differently, and selecting another provider would retain a DeepSeek-specific cap. + +**Represent 256,000 as a hard per-model maximum.** Rejected because the configured value is the desired request budget, not evidence that every configured endpoint rejects larger outputs. Explicit callers remain authoritative. + +**Leave the provider default in control.** Rejected for the native DeepSeek deployment because the product requires a stable 256,000-token conversation budget across compatible endpoints. + +## Consequences + +DeepSeek conversations send `max_tokens: 256000` by default, and the same value plus its adapter provenance appear in the session request header. Deployments can change the adapter default through `llm-deepseek.config.maxTokens`; per-agent and per-request values override it. Changing the route rematerializes the new exact adapter's default instead of carrying DeepSeek's derived value forward. Other adapters retain their existing behavior until they intentionally publish `defaultMaxTokens`. + +The 256,000-token output budget reserves a large part of the one-million-token context on endpoints that pre-allocate requested output. Deployments whose gateway or model supports a smaller budget must lower `maxTokens`; the explicit configuration is preferable to an undocumented provider fallback. diff --git a/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.zh.md b/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.zh.md new file mode 100644 index 0000000000..8db6a06199 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 适配器持有的最大 token 默认值 + +Status: implemented + +[English](2026-07-30-adapter-owned-max-token-defaults.md) | 中文 + +## Problem + +LLM（大语言模型）适配器可以序列化显式的 `GenerateOptions.maxTokens`，但无法通过 Cordis 配置建立可重建的对话默认值。仅在提供方序列化中应用回退，会导致协议请求与持久 `request/header` 不一致；若将各提供方默认值都放进 agent loop（智能体循环），则会把部署与模型策略转移到提供方无关的驱动器中。 + +## Decision + +`LlmResolvedModelInfo.defaultMaxTokens` 携带一条确切提供方／模型路由的可选单次请求输出上限，该值由适配器配置。`LlmService` 将其校验为正安全整数，并且仅在调用方省略值时才填入 `LlmCallConfig.maxTokens`。准备后的调用会将已填入的 `maxTokens` 和 `reasoningEffort` 字段标记为适配器默认值；显式请求值或 Agent 选项不带该标记，因此优先且不会被自动调整。 + +agent loop 仍在记录 `request/header` 前准备调用，因此生效配置及其适配器默认值来源会在分派前成为持久请求事实。下一次 `agent/request` waterfall（瀑布式事件）前，agent loop 会从提议中移除带标记字段，随后精确模型解析会再次填入当前路由的默认值。因此，切换提供方／模型不会把前一个适配器的默认值误当成显式覆盖，而显式对话值则会保留。直接调用 `LlmService.stream()` 时，也会在最终适配器边界解析同一默认值。该字段是请求默认值，而非模型输出硬上限；保留提供方持有默认值的适配器会省略它。 + +原生 DeepSeek 适配器在 Cordis 配置中公开 `maxTokens`，默认值为 256,000 token，并将生效值映射为 `max_tokens`。其默认上下文容量为 1,000,000 token：两个内置 V4 配置项均公布这一精确容量；不含容量的已配置项和未列出的原样传递 id 则继承同一个适配器级回退值。 + +## Alternatives considered + +**仅在 DeepSeek 序列化中应用默认值。** 不予采纳，因为提供方协议会包含持久请求 header 中缺失的模型可见值。 + +**在每个已发布应用中设置 `AgentOptions.maxTokens`。** 不予采纳，因为应用会重复适配器部署策略，直接 LLM 调用的行为将不同，而且选择另一个提供方后仍会保留 DeepSeek 专用上限。 + +**将 256,000 表示为每模型硬上限。** 不予采纳，因为配置值是所需请求预算，无法证明每个已配置端点都会拒绝更大的输出。显式调用方仍具有最终决定权。 + +**由提供方默认值控制。** 对原生 DeepSeek 部署不予采纳，因为产品要求各兼容端点都采用稳定的 256,000 token 对话预算。 + +## Consequences + +DeepSeek 对话默认发送 `max_tokens: 256000`，会话请求 header 中也会出现相同的值及其适配器来源。部署可以通过 `llm-deepseek.config.maxTokens` 更改适配器默认值；每个 agent 和每次请求的值都会覆盖它。更改路由会重新填入新的精确适配器默认值，而不是继续沿用 DeepSeek 派生出的值。其他适配器会保留现有行为，直至主动公布 `defaultMaxTokens`。 + +对于预分配请求输出的端点，256,000 token 的输出预算会占用 1,000,000 token 上下文中的很大部分。如果部署使用的 gateway 或模型仅支持较小预算，则必须调低 `maxTokens`；显式配置优于未记录的提供方回退值。 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 new file mode 100644 index 0000000000..a56a91c980 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.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/architecture/2026-07-30-client-locale-full-rollout.md +2026-07-30-client-locale-full-rollout.md: c080d9f240d4533ecd9694ceecfada8662c46425 +2026-07-30-client-locale-full-rollout.zh.md: 062d982e3d7ea62f3ca4c8fedb842e8336f0852c 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 new file mode 100644 index 0000000000..c080d9f240 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md @@ -0,0 +1,45 @@ +# Agent Note: Full client copy rollout onto the typed locale seat, and the non-translation boundary + +Status: implemented + +English | [中文](2026-07-30-client-locale-full-rollout.zh.md) + +## Problem + +After the typed locale standard seat landed (`locale:` on register → framework-injected typed `t`), only four early adopters rode it; every other client package still shipped hardcoded, mixed-language literals. Migrating the rest required mechanisms and boundary decisions the early adopters never touched: how registration-time text (nav rows, view-tab labels) refreshes on a language switch; how the zero-cordis ui-primitives atoms receive copy; and which strings deliberately stay untranslated — an unrecorded boundary invites a future agent to "complete" the localization. + +## Decision + +**Registration-time text rides a label thunk.** A list registration's `label` accepts `SlotLabel = string | (() => string)`; owners projecting ledger rows resolve through `resolveSlotLabel` (never reading `options.label` raw) and make the read point follow the locale revision (outlets subscribe to the revision themselves; off-ledger projections such as the ui-settings nav fold the revision into their cache key and subscribe to both sources). Thunks evaluate per read, so a language switch causes zero ledger churn — no re-registration, versions stay put, and every `locale/change` re-registration wiring is deleted. + +**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). + +**The non-translation boundary (deliberate decisions, not debt):** + +- **Error/failure strings stay English**: client-authored fallbacks (`command failed`, plan-toggle failures), RpcError messages, and wire `error.message (code)` pass-throughs render verbatim. +- **Design literals stay out of the dictionaries**: tool-row variant titles (Think/Bash/…), SYSTEM/USER-style kind badges, the Plan chip wordmark, the whole StatsLine — identical in both languages. +- **ui-trajectory is deferred wholesale** (a developer inspection surface, terminology-dense, ruled separately). +- **Boot copy stays hardcoded** (AppRoot renders before the locale service exists). + +**Derivation layers stay pure; localization happens at render.** ui-workspace's `relativeTime` returns structured `{unit, n}` composed with dictionary templates by the renderer; blank sessions and the Ungrouped bucket keep their stored titles, with the renderer substituting localized copy off the `blank` flag / absent `workspaceId`; **blank rows are excluded from search entirely** (a bilingual display title cannot match a single-language query stably). Dates use no Intl: format templates live in the dictionaries (message clock `clock.md`/`clock.ymd`, workspace hover `date.ymd`) and the formatters take `t` as a parameter, staying pure. + +**Test and e2e doctrine**: `makeTranslate(...dicts)` (dsh-client-test-runtime) mirrors the service lookup chain (first-dict-wins, key fallback, `{name}` interpolation); component specs stub the `t` seat with it, typed against real props seats. Web e2e uniformly opens through `newEnglishPage` (pins `dsh.locale=en` before boot) and the built-boot snapshot pins the same — goldens are immune to localization migrations; the settings language-switch scenario deliberately bypasses the helper to cover the zh default. + +The "apply layer subscribes to `locale/change` and re-registers for fresh labels" mechanism in the [settings/locale/theme layering note](../../proposed/architecture/2026-07-25-client-settings-locale-theme.md) is superseded by this decision (thunk + revision lifecycle). + +## Alternatives considered + +- **Keep labels as strings and re-register on switch** (the early adopters' original shape): boot already registers once per package, and `locale/change` listeners re-registering amplifies into a storm; ledger version churn also busts every version-keyed projection cache. Thunks move the refresh cost to read points that already follow the revision. +- **A locale context/injection channel for ui-primitives**: breaks the zero-cordis boundary (atoms would depend on the runtime) and drags unlocalized consumers (ui-trajectory) along. Props let each consumer decide independently. +- **Error strings in the dictionaries**: the error surface is a debugging surface — verbatim English is what gets searched and compared in reports; wire pass-throughs are untranslatable anyway, and half-translation manufactures mixed-language text. +- **`toLocaleString()`/Intl for dates**: follows the browser/OS language, not the app locale, guaranteeing mixed text after a switch; the dictionary templates are tiny and isomorphic to the message clock. +- **Blank rows matching search (against localized or stored titles)**: either choice yields "visible but unfindable" in one language; placeholder rows carry no information, so whole-row exclusion is the stable semantic. + +## Consequences + +- A language switch refreshes the whole UI instantly with zero re-registration; adopting a new package is three steps (dictionary + declare-merge + `locale: NS`), no hand-written glue. +- Cost: list-label consumers must know `resolveSlotLabel` (a raw `options.label` read can now hold a function); the `SlotLabel` type catches most misuse statically. +- ui-primitives' Chinese defaults still render Chinese under the English locale **until a consumer passes labels** — the unmigrated JsonTree consumer (ui-trajectory) showing its English defaults happens to match that package's all-English status quo. +- Pinning e2e to English means the zh default is covered mainly by package-level component specs and the settings language-switch scenario; browser e2e no longer asserts zh copy. 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 new file mode 100644 index 0000000000..062d982e3d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md @@ -0,0 +1,45 @@ +# Agent Note: client 文案全量接入 typed locale 席位与不翻译边界 + +Status: implemented + +[English](2026-07-30-client-locale-full-rollout.md) | 中文 + +## Problem + +typed locale 标准席位（`locale:` 注册声明 → 框架注入强类型 `t`）落地后，只有四个先行包接入；其余 client 包的文案仍是硬编码的中英混杂字面量。全量迁移需要几个先行包没有触及的机制与边界决定：注册期文本（导航行、视图 tab 的 label）在语言切换时如何刷新；zero-cordis 的 ui-primitives 原子组件如何拿到文案；哪些字符串**刻意不**本地化——没有记录的边界会诱使后来者"补完"翻译。 + +## Decision + +**注册期文本走 label thunk。** ui-slots 的 list 注册项 `label` 接受 `SlotLabel = string | (() => string)`；owner 投影 ledger 行时必须经 `resolveSlotLabel` 解析（不裸读 `options.label`），并让读取点跟随 locale revision（outlet 自身订阅 revision；ledger 外的投影如 ui-settings 导航把 revision 并进缓存键、订阅双源）。thunk 每次读取时求值，语言切换零 ledger churn——没有重注册、version 不动，`locale/change` 重注册接线全部删除。 + +**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）。 + +**不翻译边界（刻意决定，不是欠账）：** + +- **错误/失败类字符串一律英文**：client 自产的兜底串（`command failed`、plan 切换失败）、RpcError message、wire 透出的 `error.message (code)` 原样呈现。 +- **设计字面量不进字典**：tool 行 variant 标题（Think/Bash/…）、SYSTEM/USER 类 kind 徽标、Plan chip 字标、StatsLine 全部指标——中英界面显示一致。 +- **ui-trajectory 整包缓做**（开发者检查面，术语密集，单独裁决）。 +- **boot 文案保持硬编码**（AppRoot 渲染早于 locale 服务可用）。 + +**派生层保持纯函数，本地化只在渲染层**：ui-workspace 的 `relativeTime` 返回结构化 `{unit, n}` 由渲染组合字典模板；blank 会话/未分组桶的存储标题不变，渲染按 `blank` 标志/`workspaceId` 缺席替换本地化文案；**搜索态 blank 行一律排除**（双语标题无法与单语查询稳定匹配）。日期不引 Intl：格式模板进字典（消息时钟 `clock.md`/`clock.ymd`，workspace hover `date.ymd`），格式化函数吃 `t` 参数保持纯。 + +**测试与 e2e 口径**：`makeTranslate(...dicts)`（dsh-client-test-runtime）镜像服务查找链（首个命中字典胜出、key 兜底、`{name}` 插值），组件测试的 `t` 桩统一用它并以真实 props 席位定型。web e2e 统一 `newEnglishPage`（boot 前钉 `dsh.locale=en`），built-boot snapshot 同样钉 en——golden 对语言迁移免疫；settings 语言切换用例刻意绕开该 helper 覆盖 zh 默认态。 + +[settings/locale/theme 分层 Note](../../proposed/architecture/2026-07-25-client-settings-locale-theme.md) 中"apply 层订阅 `locale/change` 重注册刷新 label"的机制已被本决定取代（thunk + revision 生命周期）。 + +## Alternatives considered + +- **label 保持 string、语言切换时重注册**（先行包的旧形态）：boot 每包一次注册已很重，`locale/change` 监听者重注册会放大成风暴；ledger version 抖动还会击穿一切按 version 缓存的投影。thunk 把刷新成本移到读取点，读取点本来就跟随 revision。 +- **给 ui-primitives 造 locale context/注入通道**：破坏 zero-cordis 边界（原子组件从此依赖运行时），且强迫未本地化消费者（ui-trajectory）陪跑。props 化让每个消费者独立决定。 +- **错误串进字典**：错误面是排障面，英文原样最利于搜索与上报比对；且 wire 透出串本就不可译，半译反而制造混合语言。 +- **日期用 `toLocaleString()`/Intl**：跟随浏览器/OS 语言而非应用语言，切换后必然产生混合文本；字典模板量小且与消息时钟同构。 +- **blank 行参与搜索（匹配本地化标题或存储标题）**：任一选择都在某个语言下"看得见搜不到"；占位行本无信息量，整体排除语义最稳。 + +## Consequences + +- 语言切换全 UI 即时刷新且零重注册；新包接入 = 字典 + declare-merge + `locale: NS` 三步，无手写胶水。 +- 代价：list label 的消费方必须知道 `resolveSlotLabel`（裸读 `options.label` 拿到函数）；类型上 `SlotLabel` 已挡住多数误用。 +- ui-primitives 的中文默认值在英文语言下依旧是中文，**直到消费点传 label**——未迁移包（ui-trajectory 的 JsonTree）显示英文默认恰好符合其整包英文现状。 +- e2e 英文钉死意味着 zh 默认态主要靠包级组件测试与 settings 语言切换用例覆盖，浏览器 e2e 不再验证 zh 文案。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.i18n.yaml index fa54d657a9..3c04e9b255 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.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-settings-write-path-integrity.md -2026-07-30-settings-write-path-integrity.md: 07bd095162879c8e7866846cf562f6a13307e5fc -2026-07-30-settings-write-path-integrity.zh.md: 5d02177073d482b61750d7bdfbbd0866bc227a6a +2026-07-30-settings-write-path-integrity.md: 7bd50adc8a812759c3ae3f80a50978d75baa712a +2026-07-30-settings-write-path-integrity.zh.md: da07745ef1de1b694fc3fd1ee3d04322cdadc992 diff --git a/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.md b/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.md index 07bd095162..7bd50adc8a 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.md +++ b/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.md @@ -14,7 +14,7 @@ Review found the provider's write path could destroy state it never observed, an **One operation chain, and every write is a read-modify-write.** Watcher refreshes and persists from every namespace queue share a single settled chain, and `persistSection` begins by reconciling the on-disk text into the seam — publishing any unobserved difference first — before rendering against that fresh text. A write can no longer resurrect a stale document, and an on-disk document that turned invalid fails the write loud rather than being overwritten (the reload path keeps its warn-and-keep-last-good policy; the shared `reconcileFromDisk` throws and each caller picks its policy). The watcher's `ready` signal queues one extra reconcile, closing the startup gap between the initial load and the watcher becoming active. -**Writes hold a `wx`-created `.lock` sibling.** The read-render-rename cycle runs under a cross-process writer lock with exponential backoff, a 2 s acquisition deadline, and stale takeover after 5 s (a crashed holder, broken with a warning). Readers never lock — the rename commit is atomic — so contention is writer-only and resolves in milliseconds. The lock constants are protocol invariants, not config: a holder rewrites one small document, so the deadline and stale age derive from that bound, not from deployment taste. +**Writes hold a `wx`-created `.lock` sibling.** The read-render-rename cycle runs under a cross-process writer lock with exponential backoff and a 2 s acquisition deadline. A contender times out without removing the existing lock because age cannot distinguish a crashed owner from a paused live writer; orphan recovery is an operator action. Readers never lock — the rename commit is atomic — so contention is writer-only. The retry and deadline constants are protocol invariants, not deployment config. **Observer disposal is quiescent.** Watchers carry an `active` flag checked when a queued invocation would start, so a disposer that ran while the invocation waited prevents the start entirely; started invocations register in a service-level `pendingTails` set that the dispose drain awaits beside the write queues. The `settings/updated` fan-out contains a returned thenable's rejection through the same listener diagnostic as a sync throw, and the event contract now states that the `INVARIANT` rethrow serves synchronous listeners only — invariant companions must stay sync, which the shipped companion already is. @@ -24,7 +24,7 @@ Review found the provider's write path could destroy state it never observed, an ## Alternatives considered -- **`proper-lockfile` instead of a hand-rolled lock** — the dependency-over-hand-rolling policy was weighed: the library is barely maintained, its stale/retry policy is broader than this one-file protocol needs, and the shipped lock is ~40 lines with deterministic tests (including injected `EEXIST`/`stat` races). The policy favors dependencies that delete owned code; this one would replace 40 explained lines with an opaque peer. +- **`proper-lockfile` instead of a hand-rolled lock** — the dependency-over-hand-rolling policy was weighed: the library is barely maintained, its ownership and retry policy is broader than this one-file protocol needs, and the shipped lock is a small exclusive-create loop with deterministic contention tests. The policy favors dependencies that delete owned code; this one would replace a narrow protocol with an opaque peer. - **Revision/CAS instead of a lock** — rename cannot express compare-and-swap, so a CAS needs a version sidecar or content re-hash and a retry loop in every writer; the lock achieves the same serialization with one primitive and keeps readers free. - **Merging external edits into the in-flight write's own section** — the seam merges patches over the state visible at call time, so a same-namespace external edit racing a write still resolves last-write-wins; folding it in would need three-way merge semantics no consumer has asked for. The write publishes the external state first, so the loser is at least observed before being superseded. - **Declaring async `settings/updated` listeners unsupported** — the typed signature is `void` and lint flags misused promises, but an unlinted JS plugin can still register an async listener; a contract note cannot un-throw an unhandled rejection, so containment is the only defense that holds at runtime. @@ -32,4 +32,4 @@ Review found the provider's write path could destroy state it never observed, an ## Consequences -`update()` gained a documented failure mode (lock deadline, invalid on-disk document) and the rejection messages carry `$`-rooted paths. Remaining, documented in the provider README: same-namespace concurrent edits stay last-write-wins (no per-value merge or revision check), a watcher event the OS never delivers leaves the cache stale until the next signal or write, and comments inside replaced arrays or attached inline to changed scalar values go with the value they described. The [user-settings seam note](2026-07-28-user-settings-seam.md)'s deferred-lockfile alternative is superseded by this note. The same defect classes exist in `dsh-credentials-local` (two chains over one `.env`, cached whole-file write-back, post-persist emit) and in the `llm/adapters-updated` fan-out on the stacked branches; those fixes belong to the PRs that introduce the packages and follow this template on merge-up. +`update()` has documented failure modes for the lock deadline and an invalid on-disk document, and rejection messages carry `$`-rooted paths. A crashed holder can leave a lock that requires verified operator removal; automatic age-based takeover would permit overlapping writers. Remaining, documented in the provider README: same-namespace concurrent edits stay last-write-wins (no per-value merge or revision check), a watcher event the OS never delivers leaves the cache stale until the next signal or write, and comments inside replaced arrays or attached inline to changed scalar values go with the value they described. The [user-settings seam note](2026-07-28-user-settings-seam.md)'s deferred-lockfile alternative is superseded by this note. The same defect classes exist in `dsh-credentials-local` (two chains over one `.env`, cached whole-file write-back, post-persist emit) and in the `llm/adapters-updated` fan-out on the stacked branches; those fixes belong to the PRs that introduce the packages and follow this template on merge-up. diff --git a/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.zh.md b/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.zh.md index 5d02177073..da07745ef1 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.zh.md @@ -18,7 +18,7 @@ YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删 **单一操作链，且每次写入都是读-改-写。**watcher 的刷新与来自各 namespace 队列的持久化共享同一条结算链；`persistSection` 会先把磁盘上的文本对账进 seam——任何未被观察到的差异都先发布出去——然后才对照这份新鲜文本渲染。写入不再可能复活一份陈旧文档；磁盘上已变非法的文档会让写入响亮失败，而不是被覆盖（重载路径保持其“告警并保留最后可用值”策略；共享的 `reconcileFromDisk` 抛错，各调用方自选策略）。watcher 的 `ready` 信号会额外排入一次对账，弥合初始加载与 watcher 生效之间的启动缺口。 -**写入持有以 `wx` 创建的同目录 `.lock`。**读-渲染-rename 循环在一把跨进程写锁下运行：指数退避、2 s 获取截止时间、5 s 后陈旧接管（持有者已崩溃；打破旧锁时给出告警）。读方从不加锁——rename 提交是原子的——因此竞争只发生在写方之间，毫秒级即可化解。锁的各项常量是协议不变式，不是配置：持有者只是重写一份小文档，截止时间与陈旧时限都从这一上界推得，而非出自部署偏好。 +**写入持有以 `wx` 创建的同目录 `.lock`。**读-渲染-rename 循环在一把跨进程写锁下运行，采用指数退避与 2 s 获取期限。竞争者会超时，但不会移除现有锁，因为锁龄无法区分已经崩溃的所有者与被暂停但仍存活的写入方；遗留锁恢复须由操作者执行。读方从不加锁——rename 提交是原子的——因此竞争只发生在写方之间。重试与期限常量是协议不变式，而非部署配置。 **观察者 dispose 达到完全停稳。**watcher 携带一个 `active` 标志，排队的调用即将启动时先检查它，因此在调用等待期间已经运行过的释放器能让这次启动彻底不发生；已启动的调用会登记进服务级的 `pendingTails` 集合，dispose 排空除了等待各写队列，还会等待该集合。`settings/updated` 扇出会把监听器返回的 thenable 的 rejection 收容进与同步抛错相同的监听器诊断；事件契约现已写明 `INVARIANT` 重抛只服务同步监听器——不变式配套插件必须保持同步，而已交付的那个配套插件本就是同步的。 @@ -28,7 +28,7 @@ YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删 ## 曾考虑的替代方案 -- **用 `proper-lockfile` 取代手写锁**——按“依赖优先于手写”政策做过权衡：该库几乎无人维护，其陈旧／重试策略比这个单文件协议所需的更宽泛，而已交付的锁约 40 行并带确定性测试（含注入的 `EEXIST`/`stat` 竞态）。该政策偏向能删除自有代码的依赖；这个依赖只会把 40 行带解释的代码换成一个不透明的等价物。 +- **用 `proper-lockfile` 取代手写锁**——按“依赖优先于手写”政策做过权衡：该库几乎无人维护，其所有权与重试策略比这个单文件协议所需的更宽泛，而已交付的锁只是一个小型独占创建循环，带确定性的竞争测试。该政策偏向能删除自有代码的依赖；这个依赖只会把一个窄协议换成不透明的等价物。 - **用修订号/CAS 取代锁**——rename 表达不了 compare-and-swap，因此 CAS 需要一个版本伴随文件或内容重哈希，外加每个写方里的一个重试循环；锁用一个原语实现同样的串行化，还让读方完全免锁。 - **把外部编辑合并进正在进行的写入自身的分节**——seam 是在调用时刻可见的状态之上合并 patch 的，因此与写入竞态的同 namespace 外部编辑仍按后写胜出解决；要把外部编辑并进来，需要三方合并语义，而没有任何消费方提出过这种需求。写入会先发布外部状态，落败一方至少在被取代之前被观察到。 - **宣布不支持异步 `settings/updated` 监听器**——类型签名是 `void`，lint 也会标记误用的 promise，但未经 lint 的 JS 插件仍能注册异步监听器；契约里的一句说明无法收回已经抛出的 unhandled rejection，收容是唯一在运行时守得住的防线。 @@ -36,6 +36,6 @@ YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删 ## 后果 -`update()` 有了成文的失败模式（锁截止时间到期、磁盘文档非法），rejection 消息携带以 `$` 为根的路径。仍然存在、且已记录在提供方 README 中的有：同 namespace 并发编辑仍是后写胜出（没有逐值合并，也没有修订号检查）；OS 从未投递的 watcher 事件会让缓存保持陈旧，直到下一个信号或下一次写入；被替换数组内部的注释、以及行内附着在被改标量值上的注释，会随其描述的值一起消失。 +`update()` 对锁获取期限与磁盘文档非法都有成文的失败模式，rejection 消息携带以 `$` 为根的路径。持有者崩溃后可能留下锁，需要操作者核实后移除；若按锁龄自动接管，则会允许多个写入方重叠。仍然存在、且已记录在提供方 README 中的有：同 namespace 并发编辑仍是后写胜出（没有逐值合并，也没有修订号检查）；OS 从未投递的 watcher 事件会让缓存保持陈旧，直到下一个信号或下一次写入；被替换数组内部的注释、以及行内附着在被改标量值上的注释，会随其描述的值一起消失。 [用户设置 seam note](2026-07-28-user-settings-seam.md)里“延后锁文件”那条替代方案已被本 note 取代。同类缺陷还存在于 `dsh-credentials-local`（两条链共用一个 `.env`、按缓存整文件写回、持久化之后才发事件）与堆叠分支上的 `llm/adapters-updated` 扇出；这些修复归引入相应包（package）的那些 PR（Pull Request）所有，向上合并时按本模板处理。 diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-search.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-web-session-search.i18n.yaml new file mode 100644 index 0000000000..0aed75f807 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-search.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/2026-07-27-web-session-search.md +2026-07-27-web-session-search.md: 9a634c586a4793d1c6986a7e7c0b0c1157b5b687 +2026-07-27-web-session-search.zh.md: 5ec2baf7443aaaaa75abc348ee426df9c14fbaa2 diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-search.md b/.agents/notes/implemented/feature/2026-07-27-web-session-search.md new file mode 100644 index 0000000000..9a634c586a --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-search.md @@ -0,0 +1,44 @@ +# Agent Note: Web past-session search + +Status: implemented + +English | [中文](2026-07-27-web-session-search.zh.md) + +## Problem + +The Web sidebar exposes session titles and Workspace membership but cannot retrieve a past conversation from words that appear only inside its messages. Scanning histories in the browser would require attaching or loading every session, duplicate the existing indexed-search service, and make cold persisted sessions both slow and easy to omit. The product also needs a predictable failure path: an unavailable derived index must not erase title matches that the client can compute locally. + +## Decision + +The shared Web/headless composition mounts [`@deepseek-ai/dsh-session-query-sqlite`](../../../../packages/session-query/session-query-sqlite/README.md) with `openAt: first-search` and an in-memory database. The service is ACTIVE at boot, while its `node:sqlite` module and connection-private handle open only on the first content query. This keeps Node 22 startup output free of SQLite's experimental warning before search is used without promising to suppress the warning when search first imports the module. Each service instance owns its index, preserving the SQLite backend's single-owner contract across parallel CLI or Web invocations without leaving process-scoped derived files behind. The database starts empty and lazily reconciles live and persisted sessions on that first query. It remains a disposable derived index, separate from canonical JSONL persistence. + +The host gateway exposes `session.search` through the existing typed RPC stack. It derives the authorization set from the same visible summaries as `session.list`, asks `ctx.sessionQuery.searchSessions` for globally ranked current-surface `user/message`, `assistant/message`, and `steering/message` matches, and consumes provider pages until it has 20 authorized sessions plus one lookahead or exhausts the stream. The first provider page requests 20 hits; a first-page `SESSION_QUERY_INVALID_LIMIT` halves that size through 10, 5, 2, and 1, retaining the learned size across continuations and stale-generation restarts. Every hit's session id, best-match session id, surface, and event type are revalidated before its snippet leaves the Host. Emitted snippets contain at most 240 Unicode code points; the Host and wire schema share the protocol bounds and code-point-safe truncation helper, while the wire schema independently enforces the snippet bound at client parse. Keeping the potentially large authorization set out of SQLite bindings avoids the portable variable ceiling while preserving global ranking. The response remains one bounded page; `hasMore` tells the UI to ask for a narrower query rather than exposing pagination. A stale continuation discards the current attempt's partial results, deduplication entries, and cursors, then restarts from the first page against the original visibility snapshot. Limit probes and stale retries share the limit of 100 provider calls (and therefore at most 2,000 inspected hits); a page larger than its requested limit, a repeated continuation cursor, or a still-unexhausted stream at that call budget fails closed as an `internal` business error. The carrier signal cancels superseded work, including persistence listing, bounded batches of cold-session metadata stats, and each provider call, and wins over a concurrent limit or stale rejection. A missing query service or an unrecovered indexing/query failure remains a business error and does not mutate the canonical session store. + +[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) keeps metadata and content search deliberately separate. Its default copy is English, and its input plus defensive request path remove NUL and cap queries at the request schema's 500 UTF-16 code units without splitting a surrogate pair. A non-blank query immediately computes case-insensitive title and Workspace substring matches from the Session list, starts a 250 ms debounced content request, aborts the preceding request when the query changes, and ignores stale completions. It merges local matches first in recency order with backend-ranked content-only matches, deduplicates by session id, and renders a flat list regardless of the normal grouping mode. Each row shows the title, Workspace, and an available one-line snippet. Selecting a row opens the Session only and preserves the query; it does not navigate to an exact event. + +The result bound is one protocol constant, not per-connection state. `SESSION_SEARCH_RESULT_LIMIT` lives beside the response schema that enforces it in `dsh-host-apiproxy`, and `SessionsService.searchResultLimit` re-exposes that constant for presentation plugins. Reaching it from a feature is an explicit widening of the sessions domain: `ISessions` — the face injected as `ctx.sessions`, and therefore what the test runtime's sessions double must implement — declares the search verb next to that bound. The connection handle does not carry it: a per-connection field would imply a transport-varying or server-negotiated bound that the schema's fixed `max` forbids, and would leave the same fact with two homes in the same module. + +Content matching inherits the SQLite backend's normalized literal token/phrase semantics. The shared semantic projection excludes reasoning blocks, so UI search never returns a model's private reasoning as a hit or snippet; the derived-index schema version advances so existing persistent indexes rebuild without the former documents. FTS5 operators are inert data, and this surface adds no typo, fuzzy, prefix, or arbitrary-substring expansion. In particular, the `unicode61` tokenizer may treat an uninterrupted Chinese sequence as one token, so a shorter query such as `搜索` is not guaranteed to match inside `会话搜索功能`. Title and Workspace matching remains ordinary client-side substring matching. + +## Failure and visibility contract + +Search never widens session visibility: cold sessions without a servable cwd are absent for the same reason they are absent from `session.list`, and only provider hits whose ids occur in that baseline can leave the Host. Shadowed and log-only events, tool events outside message content, errors, todos, and other trace records do not produce UI hits. + +While the first or a later content request is pending, the UI keeps immediate metadata matches and shows a history-search status. If the backend fails, the same rows remain and a warning explains that content search is unavailable. Zero merged rows produce an explicit empty state. More than 20 candidate rows produce a refine-query hint. + +## Alternatives considered + +- **Scan every session history in the browser** — rejected because it attaches transport and fold cost to the UI, misses cold logs unless they are loaded, and duplicates the semantic extraction and source reconciliation already owned by `ctx.sessionQuery`. +- **Make trigram or fuzzy search part of the first release** — rejected because it changes index size, ranking, short-query behavior, and product expectations. Trigrams also do not by themselves solve two-character queries. The first release uses the existing backend contract and leaves recall expansion as a separate measured decision. +- **Return event addresses and jump to the exact match** — rejected for this release because conversation virtualization and stable event navigation need a separate UI contract. Session-level navigation is useful without coupling search to that work. +- **Expose cursor pagination in the sidebar** — rejected in favor of a fixed top-20 surface and a narrow-query hint; this keeps the interaction and cancellation state bounded. + +## Consequences + +Past persisted conversations become discoverable without opening them first, while the host retains one visibility boundary and one semantic-index implementation. Immediate local results hide most request latency, cancellation prevents obsolete queries from repainting the list, and backend failure degrades to the behavior available before content search. + +The first content query can take longer because it imports and opens SQLite before paying lazy reconciliation. Search quality is token/phrase recall rather than fuzzy or arbitrary substring recall, including the documented continuous-Chinese limitation. Results are session-level, capped at 20, and have no paging or exact-message navigation. A valid but pathologically unselective or repeatedly stale provider attempt that does not complete within 100 calls takes the metadata-only failure path instead of consuming unbounded work. + +## Testing + +Host tests pin request and response validation, visible-session filtering, event/surface filters, result and snippet bounds, adaptive provider limits inside the shared call budget, learned-limit stale restarts, cursor and cross-page deduplication behavior, cancellation precedence, and failure mapping. SQLite lifecycle tests pin eager activation, first-search opening and failure, shared readiness, and unopened disposal; semantic extraction and SQLite/fixture search tests pin exclusion of reasoning-only text. The Node 22 compatibility gate builds the CLI and Web artifacts, boots the shipped `dsh web`/`AppCLIEntry` composition under plain Node with ambient warning suppression removed and an isolated temporary home/provider environment, waits for settled startup, and disposes it through the shipped signal path. Fixture, runtime, and UI tests pin match-centered bounded snippets, stateless delegation, the 500-code-unit query boundary, debounce/abort/stale-response behavior, local fallback, merge order, deduplication, English copy, ARIA tree membership, row rendering, and navigation semantics. A keyless assembled Web test preserves the lazy-open config while seeding an unopened persisted conversation, finds it by visible message content through the SQLite index, captures the sidebar result, opens it, and verifies that the query remains. diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md b/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md new file mode 100644 index 0000000000..5ec2baf744 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md @@ -0,0 +1,44 @@ +# Agent Note: Web 历史会话搜索 + +Status: implemented + +[English](2026-07-27-web-session-search.md) | 中文 + +## 问题 + +Web 侧边栏会展示会话标题及其 Workspace 归属，但无法根据只出现在消息中的词语检索历史对话。在浏览器中扫描历史记录，需要附加或加载每个会话，重复实现现有的索引搜索服务，也会让冷态持久化会话的检索既缓慢又容易遗漏。产品还需要一条可预测的故障路径：派生索引不可用时，不得抹去客户端能够在本地计算出的标题匹配结果。 + +## 决策 + +Web 与 headless 共用的组合会使用 `openAt: first-search` 和内存数据库挂载 [`@deepseek-ai/dsh-session-query-sqlite`](../../../../packages/session-query/session-query-sqlite/README.md)。服务启动时处于 ACTIVE 状态，而其 `node:sqlite` 模块与连接私有句柄分别要到首次内容查询才会导入和打开。这让 Node 22 的启动输出在使用搜索前不会出现 SQLite 实验性警告，但并不承诺在首次搜索导入该模块时抑制警告。每个服务实例都独占自己的索引，因此并行 CLI 或 Web 调用可维持 SQLite 后端的单一所有者契约，又不会留下进程级派生文件。数据库从空状态启动，并在该首次查询时惰性对齐实时会话与持久化会话。它仍是与规范 JSONL 持久化相互独立的可丢弃派生索引。 + +宿主网关通过现有的类型化 RPC 栈公开 `session.search`。它根据 `session.list` 使用的同一组可见摘要推导授权集合，向 `ctx.sessionQuery.searchSessions` 请求全局排序后的当前 surface `user/message`、`assistant/message` 和 `steering/message` 匹配项，并持续消费提供方分页，直到获得 20 个已授权会话及一个前瞻项，或结果流耗尽。首个提供方页面请求 20 个命中；如果第一页返回 `SESSION_QUERY_INVALID_LIMIT`，页面大小会依次折半为 10、5、2、1，并在续传和陈旧世代重启中沿用探测所得的大小。每个命中的会话 id、最佳匹配会话 id、surface 和事件类型都会经过重新校验，其 snippet 才能离开宿主。发出的 snippet 最多包含 240 个 Unicode 码点；宿主与传输 schema 共用协议边界及码点安全的截断辅助函数，而传输 schema 会在客户端解析时独立强制执行 snippet 上限。将可能很大的授权集合排除在 SQLite 绑定之外，可避开可移植变量上限，同时保持全局排序。响应仍只有一个有界页面；`hasMore` 会指示 UI 提示用户缩小查询范围，而不是公开分页能力。陈旧的续传会丢弃当前尝试的部分结果、去重条目和游标，然后依据原始可见性快照从第一页重新开始。上限探测与陈旧重试共用 100 次提供方调用的限制（因此最多检查 2,000 个命中）；如果某页命中数超过其请求的上限、续传游标重复，或用尽该调用预算后结果流仍未耗尽，都会直接返回 `internal` 业务错误，不返回部分结果。载体信号会取消已被取代的工作，包括持久化列表枚举、分批受限执行的冷会话元数据 stat，以及每一次提供方调用；即使同时收到上限拒绝或陈旧拒绝，也以取消为准。查询服务缺失或索引／查询故障无法恢复时，仍作为业务错误处理，不会修改规范会话存储。 + +[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) 有意将元数据搜索与内容搜索保持独立。其默认界面文案为英文；输入框及防御性请求路径会移除 NUL，将查询限制在请求 schema 规定的 500 个 UTF-16 code unit 内且不会拆分 surrogate pair。非空白查询会立即从会话列表中计算不区分大小写的标题和 Workspace 子串匹配，在 250 ms 防抖后发起内容请求，在查询变化时中止前一请求，并忽略陈旧的完成结果。它先按新近程度排列本地匹配，再合并由后端排序且仅匹配内容的结果，按会话 id 去重；无论常规分组模式如何，最终都渲染为扁平列表。每一行显示标题、Workspace，并在存在时显示一行摘要片段。选择某一行只会打开对应会话，并保留查询条件；不会跳转至确切事件。 + +结果上限是单一协议常量，而非逐连接状态。`SESSION_SEARCH_RESULT_LIMIT` 位于 `dsh-host-apiproxy` 中强制执行它的响应 schema 旁边，`SessionsService.searchResultLimit` 则把该常量重新公开给呈现插件。功能包要取用它，必须显式扩展 sessions 域的对外面：`ISessions`（即注入为 `ctx.sessions` 的那个面，也因此是测试运行时的 sessions 替身必须实现的面）在该上限旁声明了搜索动作。连接 handle 不携带它：逐连接字段会暗示该上限随传输层变化或由服务端协商，而 schema 固定的 `max` 恰恰禁止这一点，并且会让同一事实在同一模块内拥有两处归属。 + +内容匹配沿用 SQLite 后端经过规范化的字面 token／短语语义。共享语义投影会排除推理（reasoning）块，因此 UI 搜索绝不会将模型的私有推理作为命中或 snippet 返回；派生索引的 schema 版本会随之前进，使现有持久化索引重建并移除先前的这些文档。FTS5 运算符只作为数据处理，此搜索界面不提供拼写错误纠正、模糊匹配、前缀匹配或任意子串扩展。特别是，`unicode61` 分词器可能将一段连续中文视作单个 token，因此不保证 `搜索` 之类的较短查询能匹配 `会话搜索功能` 的内部片段。标题与 Workspace 匹配仍采用普通的客户端子串匹配。 + +## 故障与可见性契约 + +搜索绝不会扩大会话可见范围：没有可供服务的 cwd 的冷会话会被排除，原因与它们不出现在 `session.list` 中相同；只有 id 位于这条基线中的提供方命中才能离开宿主。被遮蔽事件和纯日志事件、消息内容之外的工具事件、错误、待办事项及其他追踪记录都不会产生 UI 命中结果。 + +首个或后续内容请求仍在处理期间，UI 会保留即时元数据匹配结果，并显示历史搜索状态。如果后端失败，这些行会保持不变，并显示警告说明内容搜索不可用。合并后没有任何行时，界面会显示明确的空状态。候选行超过 20 条时，界面会提示用户缩小查询范围。 + +## 曾考虑的替代方案 + +- **在浏览器中扫描每个会话的历史记录**：不予采纳，因为这会让 UI 承担传输与折叠开销；除非加载冷态日志，否则还会漏掉这些日志；并会重复实现已经由 `ctx.sessionQuery` 负责的语义提取与源对齐。 +- **首版即加入 trigram 或模糊搜索**：不予采纳，因为这会改变索引大小、排序、短查询行为与产品预期。trigram 本身也无法解决双字查询。首版沿用现有后端契约，将召回扩展留作另一项基于度量结果的决策。 +- **返回事件地址并跳转至确切匹配位置**：本版不予采纳，因为对话虚拟化与稳定的事件导航需要单独的 UI 契约。会话级导航本身已有价值，无需让搜索与这项工作耦合。 +- **在侧边栏公开游标分页**：不予采纳，改为固定显示前 20 条结果并提示缩小查询范围；这样可使交互与取消状态保持有界。 + +## 后果 + +无需预先打开，即可检索到历史持久化对话，同时宿主仍只保留一条可见性边界和一套语义索引实现。即时本地结果掩盖了大部分请求延迟，取消机制可防止已作废查询重新渲染列表，后端故障则会降级为内容搜索尚不可用时已有的行为。 + +首次内容查询可能耗时更长，因为它要先导入并打开 SQLite，再承担惰性对齐的开销。搜索质量采用 token／短语召回，而不是模糊召回或任意子串召回，并受上述连续中文限制。结果粒度为会话，最多 20 条，不支持分页，也不能跳转到具体消息。如果有效但选择性极差或反复陈旧的提供方尝试未能在 100 次调用内完成，系统会进入仅保留元数据匹配的故障路径，而不是无限制地继续处理。 + +## 测试 + +宿主测试将请求与响应校验、可见会话过滤、事件和 surface 过滤、结果与 snippet 边界、共享调用预算内的自适应提供方上限、沿用探测所得上限的陈旧世代重启、游标与跨页去重行为、取消优先级及故障映射固定为契约。SQLite 生命周期测试将启动时激活、首次搜索时的打开与失败、共享就绪状态以及未打开状态下的处置固定为契约；语义提取测试与 SQLite／fixture 搜索测试将排除仅存在于推理中的文本固定为契约。Node 22 兼容性门禁会构建 CLI 与 Web 产物，在移除环境级警告抑制并采用隔离的临时 home／提供方环境后，以普通 Node 启动随产品交付的 `dsh web`／`AppCLIEntry` 组合，等待启动完成并稳定，再沿随产品交付的信号路径对其执行 dispose（资源释放）。fixture（测试前置数据）、运行时与 UI 测试将以匹配位置为中心的有界 snippet、无状态委托、500 个 code unit 的查询边界、防抖／中止／陈旧响应行为、本地回退、合并顺序、去重、英文文案、ARIA 树成员关系、行渲染与导航语义固定为契约。无密钥的组装层 Web 测试会在保留惰性打开配置的同时，播种一段尚未打开的持久化对话，通过 SQLite 索引按可见消息内容找到它，捕获侧边栏结果，打开该会话，并验证查询条件仍然保留。 diff --git a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.i18n.yaml index bdec24c41a..887b18118d 100644 --- a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.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-sdk-max-output-tokens.md -2026-07-28-sdk-max-output-tokens.md: 5db48f21892d56addea7b72f73319f9dbfd1e71f -2026-07-28-sdk-max-output-tokens.zh.md: 38b172718716d100726188163ff22be9ea0a7325 +2026-07-28-sdk-max-output-tokens.md: 3ba3e226d64b7d3d192d67bd88af463d2b0d9dc5 +2026-07-28-sdk-max-output-tokens.zh.md: aec566011d2d7a311b4de509c47ebba383c3b0d7 diff --git a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md index 5db48f2189..3ba3e226d6 100644 --- a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md +++ b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md @@ -12,7 +12,7 @@ The Python and TypeScript SDKs could select a provider and model but could not b The high-level SDKs expose one optional process-wide output cap: Python names it `max_tokens`, TypeScript names it `maxTokens`, and the shared `initialize` wire payload carries `maxTokens`. The JSON-RPC server rejects values that are not positive safe integers and stores the accepted cap with its provider/model route. -Each SDK-created root Agent receives the cap through `AgentOptions.maxTokens`. Agent Loop places that value in the initial `LlmCallConfig`, logs it in the request header, and reconstructs every dispatched conversation request from that durable header. Omitting the option leaves `maxTokens` absent so the selected provider retains its default. +Each SDK-created root Agent receives the cap through `AgentOptions.maxTokens`. Agent Loop places that value in the initial `LlmCallConfig`; final call preparation preserves the explicit value or materializes an exact-model adapter default, logs the effective cap in the request header, and reconstructs every dispatched conversation request from that durable header. Omitting the SDK option therefore allows the selected adapter or provider route default to apply. In-process subagents inherit the parent's provider, model, and output cap. An explicit `SubagentStartRequest.agentOptions.maxTokens`, including one configured by `dsh-tool-subagent`, overrides the inherited value for that child and its descendants. Out-of-process providers own the configuration of their separate runtime; `subagent-dsh-sdk` therefore exposes its own optional `maxTokens` and forwards it through that child runtime's SDK handshake. @@ -20,7 +20,7 @@ Compaction, session-title generation, web search, and other auxiliary calls keep ## Alternatives considered -**Set an adapter environment variable.** This would be DeepSeek-adapter-specific, invisible in the session request header, ineffective for intercepted or alternate adapters, and easy to confuse with a provider default. The cap belongs in provider-neutral request configuration. +**Set only an adapter environment variable.** A serializer-private fallback would be DeepSeek-adapter-specific, invisible in the session request header, ineffective for intercepted or alternate adapters, and easy to confuse with a provider default. Adapter-owned defaults may instead be exposed as exact-model metadata and materialized into provider-neutral request configuration before logging. **Add `maxTokens` to every `session/prompt`.** Per-turn mutation would enlarge the wire and introduce request-config transitions that callers do not need for the current evaluation use case. A runtime initialization option gives every session in one SDK process the same reproducible budget. diff --git a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md index 38b1727187..aec566011d 100644 --- a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md @@ -12,7 +12,7 @@ Python 与 TypeScript SDK 可以选择提供方和模型，却无法限制对话 高层 SDK 公开一个可选的进程级输出上限：Python 命名为 `max_tokens`，TypeScript 命名为 `maxTokens`，共享的 `initialize` 线载荷使用 `maxTokens`。JSON-RPC 服务端拒绝非正安全整数，并将通过校验的上限与提供方／模型路由一同保存。 -每个由 SDK 创建的根 Agent 都通过 `AgentOptions.maxTokens` 获得该上限。Agent Loop 将它放入初始 `LlmCallConfig`、记录到请求 header，并从该持久化 header 重建每次分派的对话请求。省略该选项时，`maxTokens` 保持缺失，由所选提供方保留默认值。 +每个由 SDK 创建的根 Agent 都通过 `AgentOptions.maxTokens` 获得该上限。Agent Loop 将它放入初始 `LlmCallConfig`；最终调用准备会保留显式值，或填入确切模型的适配器默认值，再将生效上限记录到请求 header，并从该持久化 header 重建每次分派的对话请求。因此，省略 SDK 选项时会应用所选适配器或提供方路由的默认值。 进程内 subagent 继承父级的提供方、模型和输出上限。显式的 `SubagentStartRequest.agentOptions.maxTokens`（包括通过 `dsh-tool-subagent` 配置的值）会覆盖该子级及其后代的继承值。进程外提供方自行持有其独立运行时的配置；因此 `subagent-dsh-sdk` 公开独立的可选 `maxTokens`，并通过该子运行时自己的 SDK 握手传入。 @@ -20,7 +20,7 @@ Python 与 TypeScript SDK 可以选择提供方和模型，却无法限制对话 ## Alternatives considered -**设置适配器环境变量。** 这种方式仅适用于 DeepSeek 适配器，不会出现在会话请求 header 中，对被拦截请求或其他适配器无效，也容易与提供方默认值混淆。该上限属于提供方无关的请求配置。 +**仅设置适配器环境变量。** 序列化器私有回退仅适用于 DeepSeek 适配器，不会出现在会话请求 header 中，对被拦截请求或其他适配器无效，也容易与提供方默认值混淆。适配器持有的默认值可以改为通过确切模型元数据公开，并在记录前填入提供方无关的请求配置。 **在每个 `session/prompt` 上增加 `maxTokens`。** 按轮次修改会扩大线协议，并引入当前评测用例不需要的请求配置转换。运行时初始化选项可让一个 SDK 进程中的每个会话拥有相同、可重现的预算。 diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml index f2e1183fe5..9cb40d0bbc 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.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-web-message-icon-actions-and-clock.md -2026-07-29-web-message-icon-actions-and-clock.md: ccc9b127d2fcf276fa415ec0ede8b062e45f3df5 -2026-07-29-web-message-icon-actions-and-clock.zh.md: fb4b82a22478b2de38755368ec48a5dca420e79d +2026-07-29-web-message-icon-actions-and-clock.md: f43f7f9c9687e4494993d7e225d11cf6446a9954 +2026-07-29-web-message-icon-actions-and-clock.zh.md: 866fae79f6ad3ea2cb80e5443d2cf5f763562d29 diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md index ccc9b127d2..f43f7f9c96 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md +++ b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md @@ -10,9 +10,9 @@ The web chat user bubble already had copy / branch / edit IconActions but no clo ## Decision -**User bubbles prepend a date-aware local clock to the existing IconActions row; finalized assistant *content* nodes (non-empty text blocks) append a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.** +**User bubbles prepend a date-aware local clock to the existing IconActions row; the last content-text assistant of each turn appends a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.** -Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `AssistantMarkdown` places it after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content; Think-only nodes and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`. +Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `ChatView` derives turn-tail seqs via `assistantActionsSeqs` and withholds `time` for mid-turn content; `AssistantMarkdown` places the row after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content. Think-only nodes, mid-turn narration, and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`. ## Alternatives considered @@ -20,6 +20,8 @@ Both seats format `node.time` through `formatMessageClock`: same calendar day **Put IconActions under every finalized assistant node (including Think-only).** Rejected: copy has nothing useful to write without text content, and repeating the chrome under every step/Think row clutters the flow; only content output owns the seat. +**Put IconActions under every content-text assistant in a multi-step turn.** Rejected: mid-turn narration (text before tools) is not the settled answer; repeating copy/branch/clock under each step clutters the flow. Only the last content assistant of the turn owns the seat. + **Hover-reveal the action row on hover-capable pointers.** Rejected: once the row exists it should stay discoverable; opacity hiding made the chrome easy to miss and required parent hover selectors that duplicated the mount gate. **Let the IconActions decision also define session fork semantics.** Rejected: this note owns only message chrome, clocks, and mount gating; boundary selection, failure behavior, and switching semantics belong to the separate [Web session fork actions](2026-07-27-web-session-fork-actions.md), keeping presentation components from becoming a second home for session mutation. @@ -28,4 +30,4 @@ Both seats format `node.time` through `formatMessageClock`: same calendar day ## Consequences -Settled assistant content answers expose copy, branch, and the event clock as soon as the row mounts; Think-only nodes stay chrome-free. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, the content-only assistant gate, and the respective event `seq` values passed by the user and assistant branch buttons; the web e2e scenario pins the assembled IconActions chrome. +Each turn's last settled content answer exposes copy, branch, and the event clock as soon as the row mounts; mid-turn content and Think-only nodes stay chrome-free. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, the content-only assistant gate, the turn-tail seq gate, and the respective event `seq` values passed by the user and assistant branch buttons; the web e2e scenario pins the assembled IconActions chrome. diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md index fb4b82a224..866fae79f6 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md +++ b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md @@ -10,9 +10,9 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有 ## 决策 -**用户气泡在既有 IconActions 行前追加感知日期的本地时钟；已定稿的 assistant *内容*节点（非空 text 块）在正文下追加带 `margin-top: 16px` 的复制／分支／时钟；两边只要挂载就保持可见，并在下一个本地午夜重新格式化。** +**用户气泡在既有 IconActions 行前追加感知日期的本地时钟；每个轮次中最后一条带 text 内容的 assistant 在正文下追加带 `margin-top: 16px` 的复制／分支／时钟；两边只要挂载就保持可见，并在下一个本地午夜重新格式化。** -两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`AssistantMarkdown` 把它放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染；纯 Think 节点与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调；真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。 +两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`ChatView` 通过 `assistantActionsSeqs` 推导轮次尾部的 seq，并不为轮次中间的内容传入 `time`；`AssistantMarkdown` 把该行放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染。纯 Think 节点、轮次中间的叙述与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调；真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。 ## 曾考虑的方案 @@ -20,6 +20,8 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有 **给每个已定稿 assistant 节点（含纯 Think）都挂 IconActions。** 否决：没有 text 内容时复制没有可写内容，且在每一步／Think 下重复 chrome 会打乱流程；只有内容输出拥有该座位。 +**给多步骤轮次中的每一条带 text 内容的 assistant 都挂 IconActions。** 否决：轮次中间的叙述（工具调用前的 text）不是已定稿答案；在每一步下重复复制／分支／时钟会打乱流程。只有该轮次中最后一条内容 assistant 拥有该座位。 + **在具备 hover 能力的指针上用 hover 才揭示操作行。** 否决：行一旦存在就应保持可发现；用 opacity 隐藏容易漏看，且需要父级 hover 选择器重复挂载门控。 **由 IconActions 决策同时定义 session fork 语义。** 否决：本笔记只拥有消息 chrome、时钟与挂载门控；边界选择、失败行为和切换语义属于独立的 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)，避免展示组件成为 session mutation 的第二正家。 @@ -28,4 +30,4 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有 ## 后果 -已定稿的 assistant 内容回答在行挂载后立刻暴露复制、分支与事件时钟；纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控，以及 user/assistant 分支按钮各自传递的事件 `seq`；Web e2e 场景钉住组装后的 IconActions chrome。 +每个轮次中最后一条已定稿的内容回答在行挂载后立刻暴露复制、分支与事件时钟；轮次中间的内容与纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控、轮次尾部 seq 门控，以及 user/assistant 分支按钮各自传递的事件 `seq`；Web e2e 场景钉住组装后的 IconActions chrome。 diff --git a/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.i18n.yaml new file mode 100644 index 0000000000..dae8f18b4d --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.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-web-result-card-frontend.md +2026-07-30-web-result-card-frontend.md: d6f4785e83335ca2dd5295516baf47c845ebf5bd +2026-07-30-web-result-card-frontend.zh.md: ed95cbe39f4f0bf77ba5da64d664705a0841863f diff --git a/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md b/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md new file mode 100644 index 0000000000..d6f4785e83 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md @@ -0,0 +1,49 @@ +# Agent Note: Web result card frontend — rendering the web render intent in the browser + +Status: implemented + +English | [中文](2026-07-30-web-result-card-frontend.zh.md) + +## Problem + +The `web_search` and `web_fetch` tools declare a `card: 'web'` result view ([web result card](2026-07-30-web-result-card.md)): a `kind`-tagged union carrying either the structured cited sources plus an optional provider answer (`kind: 'search'`) or the fetched URL and its HTTP status (`kind: 'fetch'`). That view already reaches the browser — host, connection, and runtime deliver it onto `ConversationSnapshot` as `resultView` — but the Web client ignored it: a completed web call rendered only as its flattened model-facing text, the same lossy render the contract note explains the structured view exists to replace. A `web_search` reached the reader as one free-text markdown line per source rather than a citation list of clickable sources, and a `web_fetch` as its markdown body with no retrieval summary. + +## Decision + +`WebBlock` is a `ui-primitives` component that renders a completed web retrieval, and every Web render site for a web call consumes the `web` render intent through it: the keyed chat tool rows (`web_search`/`web_fetch`), the `GenericToolCard` render-site fallback, and the details panel's Output section. `ui-conversation/src/client/contract/web-card-model.ts` is the single place that turns the snapshot's `resultView` into the component's props, mirroring `terminal-card-model.ts`, so no two sites disagree about what a web call shows. It returns null — the generic path — for a running call (the web card is result-only, since the tools keep a generic pending view), for a settled call whose result view is not a web card including a `card` value this client version does not know (which arrives over the wire and so cannot be trusted to be a compiled variant), for a generic result view (a web tool's error path returns the generic card, whose text the generic path preserves), and for a web card whose `kind` this client version does not know (a newer host's value off the wire, which reading as a fetch would draw as an empty URL and `HTTP undefined`). + +One component draws both kinds, discriminated by `kind`. A `search` shows the answer as markdown above a citation list; each source is a safe external link labelled by its title, or its hostname when the provider gave none, with the snippet and publication date below it, and a `来源列表已截断` indicator when the tool capped the list. A `fetch` shows a compact summary: the linked final URL, its HTTP status, and a `内容已截断` indicator. One component rather than two because both are web retrieval rendered as one card family, which is exactly the reason the contract carries them under one `card` tag with a `kind` discriminant. + +**Links are safe by the http(s) subset of the allowlist MarkdownText applies to untrusted assistant-authored links** — MarkdownText also permits `mailto:`, deliberately excluded here since a retrieval URL is never a mail address. A source or fetch URL becomes a navigable anchor only when its protocol is `http:` or `https:`, with `target="_blank"` and `rel="noopener noreferrer"`; a `javascript:`/`data:`/`file:`/`mailto:` URL or an unparseable string renders as plain text with no href. The result content a web tool returns is model-authored and reaches this component unverified, so it is treated as untrusted exactly as assistant markdown is. The label falls back from title to hostname to the raw URL, so a source always reads as something even when both the title is absent and the URL does not parse. + +**Geometry mirrors CodeBlock/TerminalBlock** (12px radius, code-block surface, 16px vertical margin) so a web card reads as one family with them. A long source list caps at `maxSources` with a head/tail collapse using TerminalBlock's exact split arithmetic (`ceil(max/2)` head lines plus the remaining tail), so a long body's slices agree between the two cards. A source list is prose rather than column-aligned output, so it wraps normally instead of scrolling horizontally the way a terminal card's output does — that is the one deliberate divergence from TerminalBlock. + +The card is **resident** under the summary row in the chat rows, capped at `CHAT_WEB_MAX_SOURCES` (8) — half the primitive's own default of 16, which the details panel keeps — the same summary-surface-versus-reading-surface split `CHAT_TERMINAL_MAX_LINES` draws for the terminal card, and the same resident posture `BashRow` uses. The keyed rows register one `WebRow` component under both `web_search` and `web_fetch`; the row discriminates on the tool name only to pick its icon (search vs. browse) and its title (`Search`/`Fetch`). A web-declaring tool without its own keyed row lands on `GenericToolCard`, which grows the same resident card. The details panel renders the card at the primitive's full source allowance and, below it, the flattened model-visible result content: a `web_fetch` card carries only the URL and status, so its fetched body is readable only here. + +## Consequences + +`WebBlock` reads only the web view's fields, so it stays a pure function of what the render intent carries — no session lookups, replay-safe like the presenters that produce the view, and unlike the terminal card it needs no cwd resolution because a web view carries no path. A UI without the `web` capability (the TUI) still gets the contract's fallback `content`; nothing about the tools' result shape changed. `MarkdownText` is reused for the answer, so the answer's own untrusted-link handling and GFM rendering come for free. + +A separate later PR unifies the whole-row collapse/expand interaction and will flip every resident card (terminal, diff, web) to expand-gated at once; this card follows the current resident convention rather than pre-empting that change. + +## Alternatives considered + +**Two components, one per kind.** Rejected: the two shapes share their card chrome, their safe-link handling, and their truncation indicator, and the contract already expresses their difference as a `kind` discriminant under one `card` tag; two components would duplicate the shared surface and split the safe-link logic. + +**Reparse the model-facing render text instead of consuming the structured view.** Rejected for the same reason the contract note gives: `web_search`'s render collapses each source's fields into one free-text line labelled by title OR hostname, so reparsing cannot recover `{url, title?, snippet?, publishedAt?}`. The structured `resultView` is the only faithful source, which is why the backend PR added it. + +**Render plain anchors without the protocol allowlist.** Rejected: the URL is model-authored and unverified at this seam, so an unfiltered href would let a `javascript:` URL execute on click. The allowlist is the http(s) subset of MarkdownText's (which also permits `mailto:`), so untrusted retrieval links behave identically wherever they render. + +## Testing + +`packages/client/ui-primitives/tests/web-block.spec.tsx` pins the component per-file to the 100% gate: both kinds; the title-or-hostname-or-raw-URL label fallback; the safe-link attributes on both kinds (an http(s) URL becoming an external anchor with `target`/`rel`, a `javascript:`/`file:`/unparseable URL rendering as a plain span with no href); the snippet and date shown or omitted on present/empty/absent; the truncation indicator gated on the flag; and the source-list height cap with its head/tail slice and expand/collapse control including the default cap. + +`packages/client/ui-conversation/tests/web-card.spec.tsx` mirrors `terminal-card.spec.tsx` at every wiring seam: `webCardModel`'s derivation projecting every source field, its truncation and absent-answer arms, the fetch derivation, and each null arm (running, null result view, generic result view, unknown card tag, unknown web `kind`); the keyed `WebRow`'s resident card for both kinds capped tighter than the panel, its summary-row-alone running and failed arms; the `GenericToolCard` fallback growing the resident card for a web-declaring tool and keeping the plain row for a non-web call; the details panel's Output section for both kinds — including a `web_fetch`'s body flattened below its URL/status card — and its flattened fallback for a non-web result; and the keyed registration under both `web_search` and `web_fetch` with one component. That file sits on the coverage `exclude` list (`ui-conversation/src/*`), so a coverage run measures none of it. + +The fixture (`packages/client/connection/src/client/fixture.ts`) adds turns 66 (`web_search`) and 67 (`web_fetch`), authored inline because the client-side fixture cannot import the web tool: turn 66's result view carries an answer and three sources exercising the citation list (a titled source with a snippet and date, a source with no title so its hostname labels the link, and a source with a date but no snippet) with the capped indicator on; turn 67's carries the fetched URL and a 200 status. Both keep a generic pending call view and add the `web` card only at result time, matching the contract's result-only web shape, and are named after the real tools so they hit the keyed `WebRow`. They are ordered before the todo turn (renumbered to 68) for the same reason the terminal turn is: the standing plan retires at the next `turn/start`, so a turn appended after it would empty the dock's plan strip. This drives the built-boot snapshot and a live `?fixture` server. + +## Related + +- [Web result card](2026-07-30-web-result-card.md) — the backend PR that added the `card: 'web'` result arm and made the two tools emit it; this is its deferred frontend consumer. +- [Web terminal card](2026-07-28-web-terminal-card.md) — the precedent this mirrors: a `ui-primitives` block, a single card-model derivation, keyed and fallback chat rows, and a details-panel arm, for the `terminal` render intent. +- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md) — the `card`-tagged vocabulary; the Web client is now a full consumer of the `web` arm. diff --git a/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.zh.md b/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.zh.md new file mode 100644 index 0000000000..ed95cbe39f --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.zh.md @@ -0,0 +1,49 @@ +# Agent Note: Web result 卡片前端 —— 在浏览器渲染 web 渲染意图 + +Status: implemented + +[English](2026-07-30-web-result-card-frontend.md) | 中文 + +## Problem + +`web_search` 和 `web_fetch` 工具声明了 `card: 'web'` result view（[web result card](2026-07-30-web-result-card.md)）：一个 `kind` 标签联合,携带结构化的被引用 sources 加可选的 provider answer（`kind: 'search'`),或抓取的 URL 及其 HTTP 状态（`kind: 'fetch'`）。该视图早已抵达浏览器 —— host、connection、runtime 将它作为 `resultView` 投递到 `ConversationSnapshot` —— 但 Web 客户端忽略了它:一次已完成的 web 调用只渲染为摊平的模型可见文本,正是契约笔记所解释的、结构化视图要替代的那种有损渲染。`web_search` 到达读者时是每个 source 一行自由文本 markdown,而非可点击 source 的引用列表;`web_fetch` 是它的 markdown 正文,没有检索摘要。 + +## Decision + +`WebBlock` 是一个 `ui-primitives` 组件,渲染一次已完成的 web 检索,web 调用的每个 Web 渲染点都通过它消费 `web` 渲染意图:键控的 chat 工具行（`web_search`/`web_fetch`）、`GenericToolCard` 渲染点兜底,以及详情面板的 Output 区。`ui-conversation/src/client/contract/web-card-model.ts` 是唯一把快照的 `resultView` 转成组件 props 的地方,镜像 `terminal-card-model.ts`,因此没有两个渲染点会对一次 web 调用的显示产生分歧。它返回 null —— 走通用路径 —— 对运行中的调用（web 卡片是 result-only 的,因为工具保留 generic pending 视图）、对 result view 不是 web 卡片的已结算调用（包括本客户端版本不认识的 `card` 值,它经 wire 抵达因而不能被信任为已编译的变体）、对 generic result view（web 工具的错误路径返回 generic 卡片,其文本由通用路径保留）、以及对本客户端版本不认识 `kind` 的 web 卡片（更新的 host 经 wire 发来的值,读作 fetch 会画出空 URL 和 `HTTP undefined`）。 + +一个组件绘制两种 kind,由 `kind` 判别。`search` 把 answer 作为 markdown 显示在引用列表上方;每个 source 是一个安全外链,以其标题为标签,provider 未给标题时以其主机名为标签,下方是 snippet 与发布日期,工具截断列表时显示 `来源列表已截断` 提示。`fetch` 显示一个紧凑摘要:带链接的最终 URL、其 HTTP 状态、以及 `内容已截断` 提示。用一个组件而非两个,因为两者都是渲染为同一卡片族的 web 检索 —— 这正是契约把它们放在一个 `card` 标签下、用 `kind` 判别的原因。 + +**链接的安全性沿用 MarkdownText 对不受信任的 assistant 链接所用 allowlist 的 http(s) 子集。** MarkdownText 还允许 `mailto:`，此处刻意排除，因为检索 URL 绝不会是邮件地址。一个 source 或 fetch URL 仅当其协议为 `http:` 或 `https:` 时才成为可导航锚点，带 `target="_blank"` 和 `rel="noopener noreferrer"`；`javascript:`/`data:`/`file:`/`mailto:` URL 或无法解析的字符串渲染为纯文本、无 href。web 工具返回的 result content 是模型创作的,未经验证抵达本组件,因此像 assistant markdown 一样被当作不受信任处理。标签从标题回退到主机名再回退到原始 URL,因此即便标题缺失且 URL 无法解析,source 也总能读作某个东西。 + +**几何镜像 CodeBlock/TerminalBlock**（12px 圆角、code-block 表面、16px 垂直外边距）,使 web 卡片与它们读作一家。长 source 列表在 `maxSources` 处折叠,用 TerminalBlock 完全相同的分割算术做头/尾折叠（`ceil(max/2)` 头部行加剩余尾部）,使长正文的切片在两张卡之间一致。source 列表是散文而非按列对齐的输出,所以它正常换行,而不像终端卡片的输出那样横向滚动 —— 这是与 TerminalBlock 唯一刻意的分歧。 + +卡片在 chat 行中**常驻**于摘要行之下,上限 `CHAT_WEB_MAX_SOURCES`（8）—— 原语自身默认 16 的一半,面板保留 16 —— 与 `CHAT_TERMINAL_MAX_LINES` 为终端卡片所画的摘要面对阅读面的同一划分,以及 `BashRow` 所用的同一常驻姿态。键控行把一个 `WebRow` 组件注册在 `web_search` 与 `web_fetch` 两个键下;行仅根据工具名判别以选取其图标（search 对 browse）与标题（`Search`/`Fetch`）。没有自己键控行的 web 声明工具落到 `GenericToolCard`,它长出同一张常驻卡片。详情面板以原语的完整 source 额度渲染卡片,并在其下方渲染摊平的模型可见结果内容:`web_fetch` 卡片只携带 URL 与状态,因此其抓取正文只在此处可读。 + +## Consequences + +`WebBlock` 只读 web view 的字段,因此它是渲染意图所携带内容的纯函数 —— 无会话查找,与产出该视图的 presenter 一样回放安全,且不同于终端卡片它不需要 cwd 解析,因为 web view 不携带路径。没有 `web` 能力的 UI（TUI）仍得到契约的回退 `content`;工具的 result 形状没有任何改变。answer 复用 `MarkdownText`,因此 answer 自身的不受信任链接处理与 GFM 渲染免费获得。 + +一条独立的后续 PR 会统一整行折叠/展开交互,并把每张常驻卡片（terminal、diff、web）一次性翻成 expand-gated;本卡片遵循当前的常驻约定,而非抢先做那次改动。 + +## Alternatives considered + +**两个组件,每种 kind 一个。** 拒绝:两种形状共享卡片外框、安全链接处理、截断提示,而契约已经把它们的差异表达为一个 `card` 标签下的 `kind` 判别;两个组件会重复共享表面并拆分安全链接逻辑。 + +**重解析模型可见的渲染文本,而非消费结构化视图。** 因契约笔记给出的同一理由拒绝:`web_search` 的渲染把每个 source 的字段压缩成一行自由文本、以标题或主机名为标签,所以重解析无法恢复 `{url, title?, snippet?, publishedAt?}`。结构化的 `resultView` 是唯一忠实来源,这正是后端 PR 添加它的原因。 + +**不加协议 allowlist 直接渲染裸锚点。** 拒绝:URL 在此接缝处是模型创作、未经验证的,所以未过滤的 href 会让 `javascript:` URL 在点击时执行。该 allowlist 是 MarkdownText allowlist（它还允许 `mailto:`）的 http(s) 子集,因此不受信任的检索链接无论在何处渲染都行为相同。 + +## Testing + +`packages/client/ui-primitives/tests/web-block.spec.tsx` 把组件钉到 per-file 100% 门槛:两种 kind;标题-或-主机名-或-原始 URL 的标签回退;两种 kind 上的安全链接属性（http(s) URL 成为带 `target`/`rel` 的外链,`javascript:`/`file:`/无法解析的 URL 渲染为无 href 的纯 span）;snippet 与日期在存在/为空/缺失时的显示或省略;由标志位控制的截断提示;以及 source 列表高度上限及其头/尾切片与展开/收起控件,含默认上限。 + +`packages/client/ui-conversation/tests/web-card.spec.tsx` 在每个接线接缝镜像 `terminal-card.spec.tsx`:`webCardModel` 的派生投影每个 source 字段、其截断与缺失 answer 的支路、fetch 派生、以及每个 null 支路（运行中、null result view、generic result view、未知 card 标签、未知 web `kind`）;键控 `WebRow` 对两种 kind 的常驻卡片、比面板收得更紧、其仅摘要行的运行中与失败支路;`GenericToolCard` 兜底为 web 声明工具长出常驻卡片、并为非 web 调用保持纯行;详情面板 Output 区对两种 kind —— 含 `web_fetch` 正文摊平在其 URL/状态卡片下方 —— 及其对非 web 结果的摊平回退;以及在 `web_search` 与 `web_fetch` 两键下用一个组件的键控注册。该文件位于覆盖率 `exclude` 列表（`ui-conversation/src/*`）,因此覆盖率运行不度量它。 + +fixture（`packages/client/connection/src/client/fixture.ts`）添加 turn 66（`web_search`）与 67（`web_fetch`）,内联撰写,因为客户端 fixture 无法 import web 工具:turn 66 的 result view 携带一个 answer 与三个 source,演练引用列表（一个带 snippet 与日期的有标题 source、一个无标题因而以主机名标注链接的 source、一个有日期无 snippet 的 source）并开启截断提示;turn 67 携带抓取的 URL 与一个 200 状态。两者都保留 generic pending call view,仅在 result 时添加 `web` 卡片,匹配契约的 result-only web 形状,且以真实工具命名,使其命中键控 `WebRow`。它们被排在 todo turn（重编号为 68）之前,理由与终端 turn 相同:待定计划在下一个 `turn/start` 退休,所以排在其后的 turn 会清空 dock 的 plan strip。这驱动 built-boot snapshot 与一个实时 `?fixture` 服务。 + +## Related + +- [Web result card](2026-07-30-web-result-card.md) —— 添加 `card: 'web'` result 支路并让两个工具发出它的后端 PR;本条是它推迟的前端消费者。 +- [Web terminal card](2026-07-28-web-terminal-card.md) —— 本条所镜像的先例:一个 `ui-primitives` block、一处 card-model 派生、键控与兜底 chat 行、以及一个详情面板支路,用于 `terminal` 渲染意图。 +- [工具调用呈现的标签化 render-intent union](../architecture/2026-07-02-tool-render-intent-union.md) —— `card` 标签词汇;Web 客户端现在是 `web` 支路的完整消费者。 diff --git a/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.i18n.yaml new file mode 100644 index 0000000000..455c89ebcd --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.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-web-tool-row-unified-expand-and-inspect.md +2026-07-30-web-tool-row-unified-expand-and-inspect.md: ba2f4ead8023772fad578ca0b647241ecc332905 +2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md: ac4835c7429a3ff7d3042f73d26d267911533132 diff --git a/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.md b/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.md new file mode 100644 index 0000000000..ba2f4ead80 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.md @@ -0,0 +1,34 @@ +# Agent Note: Web tool-row unified expand and trajectory Inspect + +Status: implemented + +English | [中文](2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md) + +## Problem + +The chat view's tool rows had drifted into per-surface interaction dialects: ToolRow expanded through a leading-icon toggle and only for calls with an args body, the bash sample had its own expand affordance, todo/ask-question rows expanded raw args only, single-file tools were not expandable at all, and a call's OUTPUT was reachable only through the details panel. A failing bash command (exit≠0 settles `isError:false`) showed no collapsed-row failure signal. There was also no path from a chat row to its trajectory record, and switching chat → trajectory → chat lost the reader's scroll position because the tab ring unmounts inactive views. + +## Decision + +**Every expandable tool row shares one interaction — the whole row toggles (click / Enter / Space) with an icon→chevron hover preview — and one expanded body: an IN/OUT gutter-labeled card with per-section scroll caps; a hover-revealed Inspect pill jumps to the call's trajectory record through a one-shot store handoff; the chat view preserves its scroll offset across view switches through an in-memory per-session map.** + +- `toolRowModel` now derives result material alongside args: `output` (the `resultText` flatten, moved from DetailsPanel into the contract), and `errorSummary` (the failure's first line, shown as the collapsed summary in the error color). A row with body, output, or terminal material is expandable; the row itself is the toggle (`role="button"`, `aria-expanded`), and file-path summaries stay independent links via `stopPropagation`. +- The expanded card (figma 1249:35657) is a column of IN/OUT sections: each section is its own scrollport (max-height 150px) with a sticky gutter label, and the l2 divider spans the full card width. Think prose and the run_code CodeBlock keep their non-card bodies; context injection reuses the row with a label-less `plainBody` card. +- `terminalFailed` reads a settled terminal card's exit status so BashRow and GenericToolCard surface a failing command as the row's red state dot — the only failure signal the collapsed row has, since the call itself settles `isError:false`. +- TerminalBlock's banner joins the same reading model: it shares the card surface (no banner token), an l2 hairline separates it from the body, the command column caps at 150px and scrolls with sticky copy/status controls top-aligned to the first prompt row. +- Inspect: `ToolRowOwnerProps.inspect` (absent for rows without a call identity) renders a pill in real flow under the expanded body's bottom-left, revealed by hovering anywhere on the tool call. Clicking writes `{ callId }` to the chat store's one-shot `inspect` field and switches to the trajectory view; TrajectoryTable finds the record, opens its summary, and acknowledges by clearing the field. +- Scroll preservation: the chat view saves its offset on every scroll (null when pinned to bottom) into an apply-scope `Map` exposed as `chatScroll` on the injected props; the open-jump branch restores it on remount. Deliberately not persisted — a fresh page load keeps the open-jump-to-bottom default. + +## Alternatives considered + +**Keeping the leading-icon toggle and per-registrant expand affordances.** Rejected: three surfaces had already diverged; the registrant posture (bash sample replicates CSS locally) makes drift permanent unless the interaction contract itself is uniform and small — whole-row toggle plus hover preview. + +**Routing Inspect through a URL or a trajectory-view prop.** Rejected: the view ring renders through the slot registry, so the two views share no parent that could carry a prop; the chat store already crosses that boundary and the one-shot field keeps the handoff replay-safe (persisted snapshots from before the field rehydrate with `?? null`). + +**Persisting the chat scroll offset.** Rejected: restoring a days-old offset into a conversation that has since grown reads as a bug; the in-memory map scopes the memory to exactly the view-switch case that loses it. + +**A per-row expanded OUTPUT fetched from the details panel's material.** Unnecessary: the settled result node already rides the snapshot's frozen call slice, so the contract-level `resultText` flatten serves both the row and the panel from one derivation. + +## Consequences + +Any registered toolview gets input AND output inspection in place, with the details panel and trajectory remaining the deep-dive surfaces. The unified interaction is contract-visible (`ToolRowProps.output/errorSummary/inspect`), so third-party rows opt in by passing model fields through. The bash sample intentionally re-replicates the new CSS (registrant posture), so future interaction changes still touch it by hand. `--dsw-font-markdown-code-block-small` (12/18) is a hand-added token pending a design-platform export. The web-cordis `distIndex` fix (plain concatenation, not URL.pathname) unblocks preview boots from a cwd with spaces. diff --git a/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md b/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md new file mode 100644 index 0000000000..ac4835c742 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md @@ -0,0 +1,34 @@ +# Agent Note：Web 工具行统一展开交互与 trajectory Inspect + +状态：已实现 + +[English](2026-07-30-web-tool-row-unified-expand-and-inspect.md) | 中文 + +## 问题 + +聊天视图的工具行交互已经分裂成多种方言：ToolRow 通过前导图标切换展开、且仅限有 args body 的调用，bash 示例有自己的一套展开方式，todo / ask-question 行只能展开原始 args，单文件工具完全不可展开，而调用的 OUTPUT 只能通过右侧详情面板查看。失败的 bash 命令（exit≠0 但结算为 `isError:false`）在折叠行上没有任何失败信号。此外聊天行没有跳转到 trajectory 记录的入口，且 chat → trajectory → chat 切换会丢失阅读位置（标签环会卸载非活跃视图）。 + +## 决定 + +**所有可展开工具行共享同一交互——整行即开关（点击 / Enter / 空格），图标 hover 时渐变为 chevron 预览——以及同一展开体：带 IN/OUT 侧栏标签的卡片，各分区独立滚动上限；hover 显示的 Inspect 胶囊通过 store 的一次性交接跳到该调用的 trajectory 记录；聊天视图用内存态的按会话 Map 在视图切换间保留滚动位置。** + +- `toolRowModel` 在 args 之外同时派生结果材料：`output`（`resultText` 拍平逻辑从 DetailsPanel 移入 contract）和 `errorSummary`（失败首行，以错误色作为折叠摘要）。有 body、output 或 terminal 材料的行即可展开；行本身是开关（`role="button"`、`aria-expanded`），文件路径摘要通过 `stopPropagation` 保持独立链接。 +- 展开卡片（figma 1249:35657）是 IN/OUT 分区列：每个分区是独立滚动区（max-height 150px），侧栏标签 sticky 固定，l2 分割线横贯整卡宽度。Think 的推理文本和 run_code 的 CodeBlock 保持非卡片体；上下文注入复用此行并以无标签的 `plainBody` 卡片展开。 +- `terminalFailed` 读取已结算 terminal 卡片的退出状态，让 BashRow 和 GenericToolCard 把失败命令显示为行的红色状态点——这是折叠行唯一的失败信号，因为调用本身结算为 `isError:false`。 +- TerminalBlock 的横幅并入同一阅读模型：与卡片共用同一表面（不再用 banner token），与正文之间是 l2 细线，命令列上限 150px 内部滚动，复制/状态控件 sticky 且顶对齐第一行提示符。 +- Inspect：`ToolRowOwnerProps.inspect`（无调用身份的行不提供）在展开体左下角以真实布局位置渲染胶囊，hover 整个 tool call 任意位置显示。点击将 `{ callId }` 写入 chat store 的一次性 `inspect` 字段并切换到 trajectory 视图；TrajectoryTable 找到记录、打开其摘要，并通过清空字段确认。 +- 滚动保留：聊天视图在每次滚动时保存偏移（贴底时为 null）到 apply 作用域的 `Map`，经注入 props 的 `chatScroll` 暴露；重挂载时 open-jump 分支恢复它。刻意不持久化——新页面加载保持打开即贴底的默认行为。 + +## 曾考虑的替代方案 + +**保留前导图标开关和各注册方自有的展开方式。** 否决：三个表面已经分化；注册方姿态（bash 示例本地复刻 CSS）意味着除非交互契约本身统一且足够小——整行开关加 hover 预览——否则漂移会永久存在。 + +**通过 URL 或 trajectory 视图 prop 传递 Inspect。** 否决：视图环经由 slot 注册表渲染，两个视图没有可携带 prop 的共同父级；chat store 本就跨越该边界，一次性字段让交接可安全重放（字段出现之前的持久化快照以 `?? null` 复水）。 + +**持久化聊天滚动偏移。** 否决：把几天前的偏移恢复到已经增长的会话里读起来像 bug；内存 Map 把记忆精确限定在会丢位置的视图切换场景。 + +**从详情面板的材料为每行单独取展开 OUTPUT。** 不必要：已结算结果节点本就在快照的冻结调用切片上，contract 层的 `resultText` 拍平让行和面板共用一份派生。 + +## 后果 + +任何已注册 toolview 都能就地查看输入与输出，详情面板和 trajectory 仍是深查表面。统一交互契约可见（`ToolRowProps.output/errorSummary/inspect`），第三方行透传模型字段即可接入。bash 示例有意重新复刻新 CSS（注册方姿态），未来交互变更仍需手动同步它。`--dsw-font-markdown-code-block-small`（12/18）是手工补充的 token，待设计平台导出后替换。web-cordis 的 `distIndex` 修复（纯拼接而非 URL.pathname）解除了含空格 cwd 下预览无法启动的问题。 diff --git a/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.i18n.yaml new file mode 100644 index 0000000000..97793a906a --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.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-telemetry-default-mount.md +2026-07-31-web-telemetry-default-mount.md: 6c1fdaa8719ee01726b51db9a469ff659cbac476 +2026-07-31-web-telemetry-default-mount.zh.md: b447832527ba9731097cd0776060db11ee4dfc30 diff --git a/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md b/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md new file mode 100644 index 0000000000..6c1fdaa871 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md @@ -0,0 +1,39 @@ +# Agent Note: Default session-telemetry mount (OTel reporting) in the dsh web composition + +Status: implemented + +English | [中文](2026-07-31-web-telemetry-default-mount.zh.md) + +## Problem + +The telemetry seam and OTel backend ([revival Note](2026-07-23-session-telemetry-otel-revival.md)) had never been wired into any deployment composition since completion: no roster row, no switch, no cadence ruling, and zero observability over user sessions for the internal deployment. A deployment decision was needed: which surfaces report, to where, on what cadence, how to opt out, and how CI stays isolated. + +## Decision + +The shared `dsh` core (`apps/cli/config/base.cordis.yml`) mounts the `telemetry-otel` row by default with a baked-in production endpoint, so every surface — TUI, web, and headless — reports; this is the **internal-testing deployment stance** — reporting is on when an endpoint exists, and users opt out through the environment. Each surface's exit path drains the queue: web/headless dispose on SIGINT/SIGTERM (headless gained those handlers in this change), and the TUI's normal exit runs `disposeRootAndExit` (root dispose, 5s bounded — above the ~1s drain ceiling configured here) while its `/resume` handoff disposes the root before `execve`. + +| Ruling | Value | Rationale | +|---|---|---| +| Mount surface | base.cordis.yml (TUI + web + headless) | One deployment stance for every surface; per-surface divergence would need a reason, and none exists | +| Endpoint | `DSH_TELEMETRY_OTLP_URL`, default `https://harness-telemetry.deepseeksvc.com/v1/logs` | Internal collector; the env override serves local/dev runs | +| Opt-out switch | any non-empty `DSH_TELEMETRY_DISABLED` (including `0`/`false`) disables | A privacy switch prefers off-by-mistake over on-by-mistake; a row can only be disabled at AppCLIEntry's patch layer (config has no disable semantic, and the switch must precede the load-time `exporter.url` validation) | +| Cadence | `processor.scheduledDelayMillis: 10000` (10s/batch) | Streaming while the session runs, never exit-time-only; a crash loses at most the last unexported interval | +| Exit-drain bound | `exporter.timeoutMillis: 1000` + `maxExportBatchSize: 2048` (== maxQueueSize) + `exportTimeoutMillis: 1500` | Dispose must release within ~1s against an unreachable collector: timeoutMillis doubles as the per-attempt socket timeout and the retry deadline (1s effectively disables the SDK's 5-try backoff), and aligning batch size with the queue cap makes the drain a single batch; SDK defaults can stall 40s+ | +| Compression | `compression: gzip` | Event bodies carry full content; cross-datacenter bandwidth | +| CI isolation | top-level `env: DSH_TELEMETRY_DISABLED: '1'` in all 8 GitHub workflows | Every CI channel that boots the web composition (e2e/snapshot/built smokes) must not stream test sessions to the production endpoint | + +The keyless integration test `apps/cli/tests/telemetry-web.e2e.ts` pins the deployment-level behavior: an in-test OTLP collector plus a mock LLM server, a real `dsh web` boot, asserting ledger coverage, seq monotonicity, the first-of-step chunk projection, and the ops `shutdown` marker arriving through the SIGINT drain. + +## Alternatives considered + +**No default mount; deployments add the row themselves (continuing the SDK stance).** Rejected for this stage: this repo's web/headless composition IS the internal deployment, and default-on reporting is that deployment's product requirement; the SDK stance survives in the seam packages (unmounted = nothing leaves). + +**A config field instead of an env patch for the switch.** Infeasible: cordis rows have no config-level disable semantic, and `exporter.url` validation fails loud at plugin construction, so the switch must take effect before the Loader — AppCLIEntry's patch layer is the only seat. + +**A `Promise.race` timeout backstop around exit.** Deferred: the parameter set already bounds the worst-case drain to ~1.5-3s (typically <100ms), measured SIGINT-to-exit 110ms-1.1s; the unbounded drip-feed-response risk stays under observation, and on real evidence the race lands inside the backend's `shutdown()` (never the coordinator — that would decide loss semantics for every backend). + +## Consequences + +- A developer running `dsh web` without a local collector POSTs to the production endpoint every 10s (silent failure when unreachable; no OTel diag logger is registered); local development sets `DSH_TELEMETRY_DISABLED=1` or points `DSH_TELEMETRY_OTLP_URL` locally. +- **No redaction rule is mounted yet**: exports are the raw captured copy (full user/assistant message text, tool arguments and results, the system prompt, the local `session.cwd` path). Crossing a trust boundary requires `telemetry/record` rules first — the redaction rule, identity Resource attributes (hostname / anonymous user id / surface), and the usage-metrics track are the explicit follow-ups of this decision. +- Test rigs reusing this tree (e.g. `apps/web/tests/scaffold.ts`) must explicitly disable the row, or fixture sessions stream to whatever collector the environment happens to name. diff --git a/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.zh.md b/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.zh.md new file mode 100644 index 0000000000..b447832527 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.zh.md @@ -0,0 +1,39 @@ +# Agent Note: dsh web 组合默认挂载会话遥测（OTel 上报） + +Status: implemented + +[English](2026-07-31-web-telemetry-default-mount.md) | 中文 + +## Problem + +遥测 seam 与 OTel backend（[revival Note](2026-07-23-session-telemetry-otel-revival.md)）自完成以来从未接入任何部署组合：没有 roster 行、没有开关、没有节奏口径，内部部署对用户会话零可观测。需要一个部署决策：哪些 surface 上报、报到哪、什么节奏、怎么关、CI 怎么隔离。 + +## Decision + +`dsh` 共享核心（`apps/cli/config/base.cordis.yml`）默认挂载 `telemetry-otel` 行，内置生产 endpoint，因此所有 surface——TUI、web、headless——都上报；这是**内部测试期的部署立场**——有 endpoint 就报，用户可经环境变量退出。各 surface 的退出路径都会排空队列：web/headless 在 SIGINT/SIGTERM 上 dispose（headless 的信号处理是本次补上的），TUI 的正常退出走 `disposeRootAndExit`（根 dispose，5s 兜底——高于此处配置的 ~1s drain 上界），其 `/resume` 移交也在 `execve` 前 dispose 根。 + +| 决策项 | 取值 | 理由 | +|---|---|---| +| 挂载面 | base.cordis.yml（TUI + web + headless） | 所有 surface 一个部署立场；按 surface 分化需要理由，而当前没有 | +| endpoint | `DSH_TELEMETRY_OTLP_URL`，缺省 `https://harness-telemetry.deepseeksvc.com/v1/logs` | 内部 collector；env 覆盖供本地/联调 | +| 退出开关 | `DSH_TELEMETRY_DISABLED` 非空（含 `0`/`false`）即关 | 隐私向开关取「宁关勿误开」；行级 disable 只能在 AppCLIEntry 的 patch 层做（config 无 disable 语义，且必须先于 `exporter.url` 的加载期校验生效） | +| 上报节奏 | `processor.scheduledDelayMillis: 10000`（10s/批） | 流式回流，非退出才报；崩溃至多丢最后一个未导出间隔 | +| 退出 drain 上界 | `exporter.timeoutMillis: 1000` + `maxExportBatchSize: 2048（== maxQueueSize）` + `exportTimeoutMillis: 1500` | collector 不可达时 dispose 必须 ~1s 内放行：timeoutMillis 同时是单次 socket 超时与重试 deadline（1s 等效关掉 SDK 5 次 backoff），批大小对齐队列上限使 drain 恒为单批；默认参数下最坏可卡 40s+ | +| 压缩 | `compression: gzip` | 事件 body 含全文，跨机房带宽 | +| CI 隔离 | 全部 8 个 GitHub workflow 顶层 `env: DSH_TELEMETRY_DISABLED: '1'` | CI 启动 web 组合的所有通道（e2e/snapshot/built smoke）不得向生产 endpoint 泄测试会话 | + +集成测试 `apps/cli/tests/telemetry-web.e2e.ts`（keyless）钉住部署级行为：测试内 OTLP collector + mock LLM，真启动 `dsh web`，断言 ledger 覆盖、seq 单调、chunk 首条投影、以及 SIGINT drain 后 ops `shutdown` 标记到达。 + +## Alternatives considered + +**默认不挂载，部署方自行加行（SDK 立场的延续）。** 否决于当前阶段：本仓的 web/headless 组合就是内部部署本身，「上报默认开」是这个部署的产品要求；SDK 立场仍由 seam 包保持（不挂 = 零外发）。 + +**开关做成 config 字段而非 env patch。** 不可行：cordis 行没有 config 层的 disable 语义，且 `exporter.url` 校验在插件构造期 fail-loud，开关必须在 Loader 之前生效——AppCLIEntry patch 层是唯一落点。 + +**退出时 `Promise.race` 兜底超时。** 暂缓：参数组合已把最坏 drain 压到 ~1.5-3s（典型 <100ms），实测 SIGINT→退出 110ms-1.1s；drip-feed 慢滴响应的无界等待风险留观，出现实证再在 backend `shutdown()` 内加 race（不放 coordinator——那会替所有 backend 决定丢失语义）。 + +## Consequences + +- 无本地 collector 的开发者跑 `dsh web` 会对生产 endpoint 每 10s 发一次 POST（联不通则静默失败，OTel diag logger 未注册）；本地开发设 `DSH_TELEMETRY_DISABLED=1` 或 `DSH_TELEMETRY_OTLP_URL` 指本地。 +- **当前零脱敏规则挂载**：导出即原始捕获副本（用户/助手消息全文、工具参数与结果、system prompt、`session.cwd` 本地路径）。跨信任边界前必须挂 `telemetry/record` 规则——脱敏规则、身份 Resource 维度（hostname/匿名 user id/surface）、使用数据 metrics 轨三件是本决策明确的后续工作。 +- 复用这棵树的测试载具（如 `apps/web/tests/scaffold.ts`）须显式关停该行，否则 fixture 会话会流向 env 里碰巧存在的 collector。 diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml index 2cb7f1009d..50d3e498a5 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.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 -2026-07-06-node-engine-floor.md: f1754ea7ca32452a04c6cd8a0599568f602e47dd -2026-07-06-node-engine-floor.zh.md: 9d376a639378d3a0b9b645aa36c1a5d320d1d147 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-06-node-engine-floor.md +2026-07-06-node-engine-floor.md: ef047d885a442106a35922f4716d2996d8a98ca7 +2026-07-06-node-engine-floor.zh.md: a0281addf7d4327d7f6ea30e3a3f0f40d6782bd0 diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md index f1754ea7ca..ef047d885a 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md @@ -10,7 +10,7 @@ The Node 22 branch of the root `engines.node` range is a contract for the instal ## Decision -Set `engines.node` to `^22.19.0 || >=24.0.0` and test the keyless CI compatibility matrix on `['22.19', 24, 26]`. Every matrix leg runs the TypeScript typecheck plus a keyless source-mode worker smoke, so the floor is exercised through both a complete source typecheck and a real unbuilt runtime path. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor. +Set `engines.node` to `^22.19.0 || >=24.0.0` and test keyless CI on `['22.19', 24, 26]`. The primary Node 24 jobs own the complete typecheck and unit coverage inventory; every version runs focused source-worker, Zstandard, source-launch, and [jsdom storage](../testing/2026-07-30-vitest-jsdom-webstorage-ownership.md) smokes without repeating that inventory. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor. Two Node features gate the source runtime: @@ -24,7 +24,7 @@ Those source features clear on the 22.x line at **22.18**, but the installed Pi ## Consequences - The advertised LTS branch no longer undercuts the Pi adapter dependency floor. -- CI proves the Node 22 LTS floor directly with Node 22.19, keeps the Node 24 branch on `node: 24`, and keeps Node 26 for the next even line; each leg typechecks the source graph and launches the unbuilt workflow worker for real. +- CI proves the Node 22 LTS floor directly with Node 22.19, keeps primary coverage on `node: 24`, and exercises Node 26 as the next even line; focused compatibility smokes run on all three versions. - The built-bin smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the test stays the plain `node lib/bin.js` path it documents. - A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this Agent Note in the same change. diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md index 9d376a6393..a0281addf7 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -将 `engines.node` 设为 `^22.19.0 || >=24.0.0`，并在 keyless CI 兼容性矩阵中测试 `['22.19', 24, 26]`。每条矩阵分支都运行 TypeScript 类型检查加一次 keyless 的源码模式 worker 冒烟测试，因此引擎下限通过完整的源码类型检查和真实的未构建运行时路径两条路径得到验证。真实 API 的 e2e 工作流保持在 Node 24 上，因为它验证的是 API 集成而非运行时下限。 +将 `engines.node` 设为 `^22.19.0 || >=24.0.0`，并在 `['22.19', 24, 26]` 上运行 keyless CI。主要的 Node 24 任务负责整套类型检查和单元测试覆盖率任务；三个版本均运行 source-worker、Zstandard、source-launch 和 [jsdom 存储](../testing/2026-07-30-vitest-jsdom-webstorage-ownership.md) 专项冒烟测试，不重复这套类型检查和覆盖率任务。真实 API 的 e2e 工作流保持在 Node 24 上，因为它验证的是 API 集成而非运行时下限。 两个 Node 特性决定了源码运行时的门槛： @@ -24,7 +24,7 @@ Status: implemented ## 后果 - 宣传的 LTS 分支不再低于 Pi 适配器依赖的下限。 -- CI 通过 Node 22.19 直接验证 Node 22 LTS 下限，Node 24 分支保持 `node: 24`，Node 26 用于下一个偶数线；每条分支都对源码图执行类型检查，并实际启动未构建的工作流 worker。 +- CI 通过 Node 22.19 直接验证 Node 22 LTS 下限，将主要覆盖率任务保留在 `node: 24`，并用 Node 26 验证下一个偶数线；三个版本均运行聚焦的兼容性冒烟测试。 - built-bin 冒烟测试无需版本条件标志：在 22.19 上类型剥离已是默认行为，因此测试保持其文档所述的纯 `node lib/bin.js` 路径。 - 未来若依赖或源码 API 提高运行时下限，必须在同一变更中同步调整 `engines.node`、兼容性矩阵和本 Agent Note（agent 决策记录）。 diff --git a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.i18n.yaml new file mode 100644 index 0000000000..70c5ce5a90 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-22-product-first-root-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 .agents/notes/implemented/process/2026-07-22-product-first-root-readme.md +2026-07-22-product-first-root-readme.md: 32542a45019d64ed1826d4eb21e68c67c3c3d52e +2026-07-22-product-first-root-readme.zh.md: 1c4d5fa53854bfcade9742da1fb74d9636909f84 diff --git a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md new file mode 100644 index 0000000000..32542a4501 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.md @@ -0,0 +1,33 @@ +# Agent Note: Product-first root README + +Status: implemented + +English | [中文](2026-07-22-product-first-root-readme.zh.md) + +## Problem + +The root README is the repository's product front door. Its product-first structure and established voice remain useful, but concrete entry points and capability claims drift as the runtime grows. Rewriting sections whose facts remain correct increases the review surface and discards language that already works. + +## Decision + +The root README preserves its existing structure, order, and wording wherever the underlying fact remains correct. A refresh changes only stale claims and adds material needed to represent shipped surfaces; it does not use repository growth as a reason to reframe the whole page. + +A note before installation thanks internal testers, states that features and experience remain unfinished, and asks for direct reports of failures, confusion, and friction through the WeCom group. The existing development-stage statement identifies DeepSeek Harness as being in internal testing. + +The user-surface section adds the ACP automation server and Python/JSON-RPC SDK beside the existing Web, TUI, and headless entries. The installed TUI remains the single `dsh` command; the Web instructions build the active checkout before running `dsh web`, and custom or reused checkout paths stay explicit. These launch paths must remain executable through a real PTY and a production build/HTTP smoke, respectively. The capability paragraph keeps its compact inventory style while adding the shipped PTY, LSP, web, goal, planning, task, sandbox, approval, settings, credentials, session-query, and telemetry families and stating that compositions select subsets. One adjacent bullet records the authoritative-session-log rule because persistence, replay, queries, telemetry, and interfaces depend on it. + +Detailed package and service inventories remain at their owning documentation. The English and Chinese README sides share the same technical structure, while their community sections continue to point to the primary channel for each language audience. The documentation website keeps its separate user-guide landing page. + +## Alternatives considered + +**Rewrite the README around a new product narrative.** A complete rewrite can make every current surface prominent, but it replaces accurate, reviewed copy and creates unnecessary churn. Current facts fit the established product-first structure. + +**Present the repository as an SDK and package catalog.** This exposes implementation breadth immediately but makes a new reader reconstruct the product from package names. The package map and generated capability graph remain the authoritative inventories. + +**Use a long marketing page with screenshots, badges, and duplicated tutorials.** Rich media can demonstrate a stable product journey, but it ages separately from commands and source contracts. The root stays compact and links to runnable examples and owned guides. + +**Project the root README as the documentation website home page.** A single landing page avoids two narratives, but the website's user guide and the repository's product/developer front door have different navigation and maintenance needs. + +## Consequences + +Reviewers can distinguish factual refreshes from editorial rewrites, and future updates retain established wording unless its meaning becomes false or incomplete. The README must still change with affected commands, entry points, release-stage claims, or high-level capability families, while exhaustive detail remains linked rather than copied. diff --git a/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md new file mode 100644 index 0000000000..1c4d5fa538 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-22-product-first-root-readme.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 产品优先的根 README + +Status: implemented + +[English](2026-07-22-product-first-root-readme.md) | 中文 + +## 问题 + +根 README 是仓库的产品入口。其产品优先的结构和既有语气仍然有效，但随着运行时不断扩展，具体入口和能力声明会逐渐陈旧。重写事实仍然正确的章节，会扩大评审范围，也会丢弃已经行之有效的措辞。 + +## 决策 + +只要背后的事实仍然正确，根 README 就保留既有结构、顺序和措辞。刷新时只修正陈旧声明，并补充呈现已交付内容所需的信息；不会因为仓库规模增长就重构整篇叙事。 + +安装说明之前的一则文字感谢内测用户，说明功能和体验仍待完善，并邀请大家通过企业微信群直接反馈失败、困惑和不顺手之处。既有的开发阶段声明明确说明 DeepSeek Harness 处于内测阶段。 + +用户入口章节在已有的 Web、TUI 和 Headless 入口旁补充 ACP（Agent Client Protocol）自动化服务器和 Python/JSON-RPC SDK。安装后的 TUI 仍只需执行一条 `dsh` 命令；Web 说明要求先构建当前检出，再运行 `dsh web`，并明确处理自定义或复用的检出路径。这两条启动路径必须分别能在真实 PTY 与生产构建／HTTP 冒烟中原样执行。能力段落沿用简洁清单的写法，补充已经交付的 PTY、LSP、Web、目标、规划、任务、沙箱、审批、设置、凭据、会话查询和遥测等能力类别，并说明不同组合只选用其中一部分。相邻的一条列表项说明权威会话日志规则，因为持久化、回放、查询、遥测和各类接口都依赖它。 + +包（package）与服务的完整清单仍由各自的归属文档维护。中英文 README 采用相同的技术结构，但社区章节仍分别指向各自语言受众的主要交流渠道。文档网站继续使用独立的用户指南首页。 + +## 考虑过的替代方案 + +**围绕新的产品叙事重写 README。** 完整重写能够突出所有现有入口和能力，但也会替换准确且已经过评审的文案，造成不必要的变动。现有事实能够纳入既有的产品优先结构。 + +**将仓库呈现为 SDK 和包清单。** 这样能立即展现实现广度，却会迫使新读者从包名反推出产品。包索引与生成的能力图仍是权威清单。 + +**使用包含截图、徽章和重复教程的长篇营销页面。** 富媒体能够展示稳定的产品使用路径，但其内容会独立于命令和源码契约而逐渐陈旧。根 README 保持紧凑，并链接到可运行示例和各自维护的指南。 + +**将根 README 投影为文档网站首页。** 使用同一个首页可以避免两套叙事，但文档网站的用户指南与仓库面向产品和开发者的入口在导航和维护需求上并不相同。 + +## 结果 + +评审者可以区分事实更新与编辑性重写；今后的更新会保留既有措辞，除非其含义已经不再正确或完整。受影响的命令、入口、发布阶段声明或高层能力类别发生变化时，README 仍须同步更新；完整细节则继续以链接方式提供，而不是复制到正文。 diff --git a/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.i18n.yaml b/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.i18n.yaml new file mode 100644 index 0000000000..9d3ac28ed2 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.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/2026-07-31-coverage-exempt-heavy-suites.md +2026-07-31-coverage-exempt-heavy-suites.md: 7235a5193554947ecf71f62d522d09f4e21cb1da +2026-07-31-coverage-exempt-heavy-suites.zh.md: b739e4494ae8d240b0e35109920a49876ebd222d diff --git a/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.md b/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.md new file mode 100644 index 0000000000..7235a51935 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.md @@ -0,0 +1,61 @@ +# Agent Note: Coverage-exempt heavy suites + +Status: implemented + +English | [中文](2026-07-31-coverage-exempt-heavy-suites.zh.md) + +## Problem + +The CI coverage lane (`check:ci:coverage`) had its wall clock pinned by a handful of heavy test files: in a local 6-worker full-suite profile, 555 test files aggregated 1595 seconds, with `packages/typert/generator/tests/type-model.spec.ts` alone at 885 seconds and the top 10 files holding 84% of the aggregate. These suites share one shape — every case performs whole-workspace compiler analysis or drives real subprocess fixtures — and v8 instrumentation multiplies exactly that kind of runtime. + +The decisive waste: the instrumentation tax these suites paid contributed **nothing** to the per-file 100% thresholds — the measured code they execute in-process is either outside the threshold scope already or independently fully covered by other suites. Running them instrumented traded lane time for zero information. + +## Decision + +The `ci-coverage` aggregate splits into two parallel gates; every test still runs, and only the heavy suites stop paying the instrumentation tax: + +- **Instrumented gate** (`test:coverage`): sets `DSH_COVERAGE_EXEMPT_HEAVY=1`, which makes `vitest.config.ts` drop the exempt suites from both projects' excludes; every remaining file runs instrumented and carries the entire threshold proof. The variable is injected through the gate's own env (the existing `Gate.env` mechanism), not the workflow-global environment, so the uninstrumented gate beside it and any local `vitest run` never see it and behave unchanged. +- **Uninstrumented gate** (`test:coverage-exempt-heavy`): runs exactly the exempt suites through paired positional filters, keeping the correctness signal whole. + +`scripts/coverage-exempt.ts` is the single roster point, holding the membership contract and the filter/exclude pairs so the two sides cannot drift. + +### The roster, reconciled entry by entry + +A suite contributes to coverage exactly when it executes measured files in-process (`coverage.include` spans the package src trees). The current roster, audited: + +| Exempt suite | Measured code executed in-process | Who carries the coverage | +| --- | --- | --- | +| All 6 typert generator specs | The generator's own src | Generator src is threshold-excluded as a package (`vitest.config.ts`) — outside the threshold scope to begin with | +| tools-catalog.spec additionally imports | `typert-registry` and `tool-cordis` src | Each package's own tests cover them fully (verified with focused coverage runs, zero threshold errors) | +| `scripts/install-lefthook.spec.ts`, `scripts/oxlint-contract.spec.ts`, `scripts/change-scope.spec.ts` | None — they test `scripts/` sources (never in `coverage.include`) and work by spawning child processes | Nothing to carry | + +### Membership contract + +A new exemption must satisfy both: every measured file the suite executes in-process is already fully covered by other suites (or threshold-excluded), and the filter and exclude select exactly the same file set. The contract text lives beside the roster in the same file. + +### The gate polices the roster automatically + +The per-file 100% thresholds are themselves the roster's guard; a wrong roster cannot pass silently: + +- If a future exempt suite in fact solely covers some measured file, the instrumented gate goes red on the spot (that file drops below 100%). +- The converse holds too: new code covered only by an exempt suite turns the gate red immediately. + +Coverage-result invariance therefore does not rest on humans maintaining the roster, in line with the misconfiguration-fails-loud convention. The only thing given up is that the exempt suites' own execution no longer produces coverage data — the table above shows that data was entirely redundant, so the final report is file-for-file identical in threshold terms. + +## Alternatives considered + +- **CLI `--exclude` to drop the exempt suites from the instrumented gate.** Proven ineffective: vitest 4's `cliExclude` does not participate in per-project include resolution, so under a multi-project config the exempt suites stayed selected; the env + config route replaced it. +- **Lowering worker counts or raising gate concurrency.** Measured ineffective during the incident: the lane's wall clock was pinned by the longest tail files (aggregate/wall ≈ 4× effective parallelism), and the concurrency knobs moved nothing in either direction. +- **Cross-runner sharding (`--shard` + blob merge).** Would compress the wall clock further but adds matrix, artifact-pipeline, and merge-job complexity; with the split landed the lane sits near 2 minutes, which does not justify the cost. Revisit if the suite grows substantially. +- **Deleting or skipping the heavy suites.** Rejected: they are the sole correctness evidence for the typert generator and the scripts tooling; running them uninstrumented in parallel preserves the full signal. + +## Verification + +Measured on CI (16-core runner): the gate segment went from 424 seconds to the two gates in parallel — `test:coverage` 95.9 s + `test:coverage-exempt-heavy` 71.1 s — with the lane converging on the slower at about 96 seconds; the instrumented gate reported zero threshold errors both before and after the split. `vitest list` verifies the env toggle adds and removes exactly the exempt set; `run-gates.spec.ts` covers the aggregate graph construction. + +## Consequences + +- The coverage lane's gate segment drops from about 7 minutes to about 96 seconds with no change in threshold outcome or executed test set. +- `DSH_GATE_CONCURRENCY` has two schedulable gates in this lane again, so the aggregate scheduler is no longer a pass-through. +- Adding a heavy suite to the roster requires the membership audit above; a wrong entry fails the instrumented gate loudly rather than eroding coverage silently. +- The exempt suites no longer appear in the coverage report's file list of contributors; their correctness signal lives solely in the uninstrumented gate's pass/fail. diff --git a/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.zh.md b/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.zh.md new file mode 100644 index 0000000000..b739e4494a --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.zh.md @@ -0,0 +1,61 @@ +# Agent Note: 覆盖率豁免重型套件 + +Status: implemented + +[English](2026-07-31-coverage-exempt-heavy-suites.md) | 中文 + +## Problem + +CI 覆盖率 lane（`check:ci:coverage`）的墙钟被少数几个重型测试文件钉死：本地 6-worker 全量剖析中，555 个测试文件聚合 1595 秒，其中 `packages/typert/generator/tests/type-model.spec.ts` 一个文件占 885 秒，前 10 个文件占聚合时长的 84%。这类套件的共同点是每个用例都做全工作区编译器分析或真实子进程 fixture，v8 插桩把这类代码的运行时间放大数倍。 + +关键的浪费在于：这些套件缴纳的插桩税对 per-file 100% 阈值**没有任何贡献**——它们进程内执行的被度量代码，要么本来就不在阈值口径内，要么已由其他套件独立满覆盖。继续在插桩下运行它们，纯粹是用 lane 时长换零信息。 + +## Decision + +`ci-coverage` 聚合拆成两个并行 gate，全部测试仍然执行，只有重型套件不再交插桩税： + +- **插桩 gate**（`test:coverage`）：设 `DSH_COVERAGE_EXEMPT_HEAVY=1`，`vitest.config.ts` 据此从两个 project 的 exclude 中剔除豁免套件，其余全部文件照旧插桩并承担全部阈值证明。经 gate 自带 env 注入（既有 `Gate.env` 机制），不进 workflow 全局环境，因此并排的无插桩 gate 和本地直跑 `vitest run` 都看不到该变量、行为不变。 +- **无插桩 gate**（`test:coverage-exempt-heavy`）：用配对的 positional filter 恰好运行豁免套件，保证正确性信号不缩水。 + +`scripts/coverage-exempt.ts` 是唯一名单点，集中持有成员资格契约与 filter/exclude 配对，防止两侧漂移。 + +### 豁免名单与逐项对账 + +一个套件对覆盖率有贡献，当且仅当它在进程内执行了被度量的文件（`coverage.include` = 包 src 树）。现行名单逐项核对： + +| 豁免套件 | 进程内执行的被度量代码 | 覆盖由谁接住 | +| --- | --- | --- | +| typert generator 全部 6 个 spec | generator 自身 src | generator src 已整包 threshold-excluded（`vitest.config.ts`），本不在阈值口径内 | +| 其中 tools-catalog.spec 额外 import | `typert-registry`、`tool-cordis` 的 src | 两包各自的测试独立满覆盖（focused coverage 实测无阈值错误） | +| `scripts/install-lefthook.spec.ts`、`scripts/oxlint-contract.spec.ts`、`scripts/change-scope.spec.ts` | 无——被测对象是 `scripts/` 源码（从不在 coverage.include），执行方式是 spawn 子进程 | 无需接 | + +### 成员资格契约 + +新增豁免必须同时满足：套件进程内执行的每个被度量文件都已由其他套件满覆盖（或在阈值排除名单内）；filter 与 exclude 选中完全相同的文件集。契约文本随名单同文件维护。 + +### 门禁自动守卫名单正确性 + +per-file 100% 阈值本身就是豁免名单的守卫，名单错误无法静默通过： + +- 若未来某个豁免套件实际独家覆盖着某个被度量文件，插桩 gate 当场红（该文件跌破 100%）； +- 反向同理：出现"只有豁免套件才覆盖"的新代码，同样立刻红。 + +因此覆盖率结果的不变性不依赖人工维护名单，符合"misconfiguration fails loud"约定。唯一失去的是豁免套件自身的执行不再产出覆盖数据——由上表可知这些数据全部冗余，最终报告在阈值意义上逐文件相同。 + +## Alternatives considered + +- **CLI `--exclude` 从插桩 gate 剔除豁免套件。** 实证无效：vitest 4 的 `cliExclude` 不参与 per-project include 解析，多 project 配置下豁免套件仍被选中，故改走 env + config。 +- **降低 worker 数或提高 gate 并发。** 事故期间实测无效：lane 墙钟被尾部最长文件钉死（聚合/墙钟 ≈ 4× 有效并行），并发旋钮两个方向都动不了尾巴。 +- **跨 runner 分片（`--shard` + blob 合并）。** 能进一步压墙钟但引入 matrix、artifact 管道与合并 job 的复杂度；拆分落地后 lane 已到约 2 分钟，不值得付。若未来套件规模再涨可重新评估。 +- **直接删除或跳过重型套件。** 拒绝：它们是 typert generator 与 scripts 工具的唯一正确性证据，无插桩并排执行保住全部信号。 + +## Verification + +CI 实测（16 核 runner）：拆分前 gate 段 424 秒，拆分后两 gate 并行 `test:coverage` 95.9 秒 + `test:coverage-exempt-heavy` 71.1 秒，lane 收敛于较慢者约 96 秒；拆分前后插桩 gate 阈值错误均为零。`vitest list` 验证 env 开关两态恰好增删豁免集；`run-gates.spec.ts` 覆盖聚合图构造。 + +## Consequences + +- 覆盖率 lane 的 gate 段从约 7 分钟降到约 96 秒，阈值结果与执行测试集均无变化。 +- `DSH_GATE_CONCURRENCY` 在本 lane 重新拥有两个可调度对象，聚合调度器不再是直通。 +- 向名单新增重型套件必须完成上述成员资格对账；错误条目会让插桩 gate 大声失败，而不是静默侵蚀覆盖率。 +- 豁免套件不再出现在覆盖率报告的贡献文件列表中；其正确性信号完全由无插桩 gate 的红绿承载。 diff --git a/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.i18n.yaml b/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.i18n.yaml new file mode 100644 index 0000000000..e829874e9d --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.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/testing/2026-07-30-vitest-jsdom-webstorage-ownership.md +2026-07-30-vitest-jsdom-webstorage-ownership.md: 3956a7566fa1c79a767636bce9a19f16588126e2 +2026-07-30-vitest-jsdom-webstorage-ownership.zh.md: 9080ee2762b74bf2efdaccd7a5905672001bc0e8 diff --git a/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.md b/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.md new file mode 100644 index 0000000000..3956a7566f --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.md @@ -0,0 +1,26 @@ +# Agent Note: Keep browser storage owned by jsdom in Vitest + +Status: implemented + +English | [中文](2026-07-30-vitest-jsdom-webstorage-ownership.zh.md) + +## Problem + +The supported Node range includes releases that reserve a process-wide `globalThis.localStorage`. Node 26 exposes that property as `undefined` without `--localstorage-file`; Vitest sees the reserved key and does not project jsdom's isolated `Storage` object over it. Component suites then fail before exercising product behavior, while the primary Node 24 coverage lane remains green because that runtime does not reserve the key by default. + +## Decision + +Vitest workers disable Node's process-wide Web Storage when the runtime advertises the `--webstorage` flag. The configuration passes `--no-webstorage` through each test project's `execArgv`; runtimes without that flag receive no argument. Node-environment suites therefore stay browser-free, and files selecting jsdom through `@vitest-environment jsdom` receive jsdom's isolated `localStorage`. + +The Node compatibility aggregate runs a dedicated jsdom smoke on every advertised compatibility line. It asserts both the conditional worker argument and usable storage, so a future Node or Vitest change cannot leave the primary Node 24 suite as the only signal. + +## Alternatives considered + +- **Set `NODE_OPTIONS=--no-webstorage` in package scripts or CI.** Rejected because it leaks test-runner policy into subprocesses and misses direct `pnpm exec vitest` invocations. +- **Pass `--localstorage-file` to Node.** Rejected because one process-wide persistent store has different ownership and isolation semantics from browser storage created per jsdom environment. +- **Patch `globalThis.localStorage` in setup code or guard every component test.** Rejected because setup would depend on Vitest's private jsdom projection details, while per-test guards hide a broken browser environment and duplicate policy across suites. +- **Pin tests to Node 24.** Rejected because the package engine advertises newer even Node lines and the compatibility matrix exists to expose their runtime changes. + +## Consequences + +The same `pnpm test` command works on Node releases with and without built-in Web Storage. Test workers deliberately cannot exercise Node's process-wide Web Storage; a future product need for that API requires a separate explicit test configuration rather than weakening jsdom isolation. The compatibility lane adds one focused Vitest process instead of duplicating the complete unit inventory on every Node version. diff --git a/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.zh.md b/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.zh.md new file mode 100644 index 0000000000..9080ee2762 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-30-vitest-jsdom-webstorage-ownership.zh.md @@ -0,0 +1,26 @@ +# Agent Note: 在 Vitest 中将浏览器存储交由 jsdom 管理 + +Status: implemented + +[English](2026-07-30-vitest-jsdom-webstorage-ownership.md) | 中文 + +## 问题 + +受支持的 Node 版本范围包含会预留进程级 `globalThis.localStorage` 的版本。未设置 `--localstorage-file` 时，Node 26 将该属性暴露为 `undefined`；Vitest 检测到这个预留键后，不会用 jsdom 的隔离 `Storage` 对象覆盖该属性。因此，组件测试套件尚未验证产品行为便会失败，而主要的 Node 24 覆盖率分支仍能通过，因为该运行时默认不会预留此键。 + +## 决策 + +当运行时声明支持 `--webstorage` 标志时，Vitest worker 会禁用 Node 的进程级 Web Storage。配置通过每个测试项目的 `execArgv` 传入 `--no-webstorage`；未声明该标志的运行时则不传入此参数。因此，Node 环境测试套件不加载浏览器环境，而通过 `@vitest-environment jsdom` 选择 jsdom 的文件会获得 jsdom 隔离的 `localStorage`。 + +Node 兼容性汇总任务会在每条声明支持的兼容版本线上运行专用的 jsdom 冒烟测试。该测试同时断言 worker 参数按条件传入且存储可用，因此未来 Node 或 Vitest 的变化不会让主要的 Node 24 测试套件成为唯一检测信号。 + +## 曾考虑的替代方案 + +- **在包脚本或 CI 中设置 `NODE_OPTIONS=--no-webstorage`。** 否决：这会将测试运行器策略传播到子进程，也无法覆盖直接调用 `pnpm exec vitest` 的情况。 +- **向 Node 传入 `--localstorage-file`。** 否决：单个进程级持久化存储与每个 jsdom 环境分别创建的浏览器存储具有不同的归属和隔离语义。 +- **在初始化代码中修改 `globalThis.localStorage`，或为每个组件测试增加保护逻辑。** 否决：初始化逻辑会依赖 Vitest 私有的 jsdom 映射细节，而逐测试添加的保护逻辑会掩盖浏览器环境损坏，并在多个测试套件中重复该策略。 +- **将测试固定在 Node 24。** 否决：包的引擎范围声明支持更新的偶数 Node 版本线，而兼容性矩阵正是为了暴露这些版本的运行时变化。 + +## 后果 + +同一条 `pnpm test` 命令在有无内置 Web Storage 的 Node 版本上均可运行。测试 worker 被有意禁止使用 Node 的进程级 Web Storage；未来若产品需要该 API，必须使用独立且显式的测试配置，而不能削弱 jsdom 隔离。兼容性分支只增加一个专项 Vitest 进程，无需在每个 Node 版本上重复整套单元测试。 diff --git a/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.i18n.yaml index ad6c575d1e..96dc47f9f7 100644 --- a/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.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 -2026-07-25-client-settings-locale-theme.md: 87077b3fd3f0bd8a3375a71aebf947cbd9961799 -2026-07-25-client-settings-locale-theme.zh.md: a64a4afdf6565a527a25136694aa79305eeabb3c +# pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.md +2026-07-25-client-settings-locale-theme.md: c86d6ac053f7bb87ce758613a5f3a0a34951e428 +2026-07-25-client-settings-locale-theme.zh.md: 05edbb3c550828832a390e3cf4fad3262b5be196 diff --git a/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.md b/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.md index 87077b3fd3..c86d6ac053 100644 --- a/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.md +++ b/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.md @@ -55,7 +55,7 @@ root └─ models (order 10) ui-models 注册 ``` -Section and item contributions both use declaration-aware deferral (ui-slots' `deferRegistration()`: ledger-judged presence, `refresh()` for localized labels, one-call disposal) and do not depend on the client manifest's apply order. The SlotMap types split homes: trigger/header/close/section have their canonical home in the ui-settings contract (the consumers, general and models, both depend on the shell — no cycle); `settings.general.item`'s canonical home is the locale package — it is the lowest common dependency of all item registrants (a settings row always carries copy), while the declarer general's contract is unreachable from locale/ui-theme (it would form a cycle); ui-theme consumes it through a re-export seam. +Section and item contributions both use declaration-aware deferral (ui-slots' `deferRegistration()`: ledger-judged presence, one-call disposal; localized labels ride the label thunk from the [full-rollout note](../../implemented/architecture/2026-07-30-client-locale-full-rollout.md), not `refresh()`) and do not depend on the client manifest's apply order. The SlotMap types split homes: trigger/header/close/section have their canonical home in the ui-settings contract (the consumers, general and models, both depend on the shell — no cycle); `settings.general.item`'s canonical home is the locale package — it is the lowest common dependency of all item registrants (a settings row always carries copy), while the declarer general's contract is unreachable from locale/ui-theme (it would form a cycle); ui-theme consumes it through a re-export seam. ### Future work: promote slot declarations to first-class injectable waits diff --git a/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.zh.md b/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.zh.md index a64a4afdf6..05edbb3c55 100644 --- a/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.zh.md @@ -55,7 +55,7 @@ root └─ models (order 10) ui-models 注册 ``` -section/item contribution 均使用 declaration-aware deferral（ui-slots 的 `deferRegistration()`：ledger 判在位、`refresh()` 换本地化 label、一键 dispose），不依赖 client manifest 的 apply 顺序。SlotMap 类型分家：trigger/header/close/section 正家在 ui-settings contract（消费者 general/models 均依赖壳，无环）；`settings.general.item` 正家在 locale 包——它是全部 item 注册方的最低公共依赖（设置行必带文案），而声明方 general 的 contract 对 locale/ui-theme 不可达（会成环）；ui-theme 经 re-export seam 消费。 +section/item contribution 均使用 declaration-aware deferral（ui-slots 的 `deferRegistration()`：ledger 判在位、一键 dispose；本地化 label 走 [全量接入 Note](../../implemented/architecture/2026-07-30-client-locale-full-rollout.md) 的 label thunk，不再 `refresh()`），不依赖 client manifest 的 apply 顺序。SlotMap 类型分家：trigger/header/close/section 正家在 ui-settings contract（消费者 general/models 均依赖壳，无环）；`settings.general.item` 正家在 locale 包——它是全部 item 注册方的最低公共依赖（设置行必带文案），而声明方 general 的 contract 对 locale/ui-theme 不可达（会成环）；ui-theme 经 re-export seam 消费。 ### Future work：坑位声明升格为可 inject 的一等等待物 diff --git a/.github/workflows/build-exe-for-python-sdk.yml b/.github/workflows/build-exe-for-python-sdk.yml index 5965707630..017b77ee75 100644 --- a/.github/workflows/build-exe-for-python-sdk.yml +++ b/.github/workflows/build-exe-for-python-sdk.yml @@ -28,6 +28,11 @@ concurrency: permissions: contents: read +env: + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + jobs: # Job-level conditions cannot inspect `matrix`, so validate target names and # construct the matrix before the dependent jobs. diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 1f6ec52f0a..6b2a5dd9d5 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -24,6 +24,9 @@ permissions: env: PRIMARY_NODE_VERSION: '24' + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' jobs: diff --git a/.github/workflows/docs-pages.yml b/.github/workflows/docs-pages.yml index ab56636fed..6336089a41 100644 --- a/.github/workflows/docs-pages.yml +++ b/.github/workflows/docs-pages.yml @@ -23,6 +23,9 @@ permissions: env: PRIMARY_NODE_VERSION: '24' + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' jobs: build: diff --git a/.github/workflows/e2e.yml b/.github/workflows/e2e.yml index c445034a8c..d72e7bfee4 100644 --- a/.github/workflows/e2e.yml +++ b/.github/workflows/e2e.yml @@ -46,6 +46,11 @@ concurrency: permissions: contents: read +env: + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + jobs: e2e: runs-on: ubuntu-latest diff --git a/.github/workflows/expected-filenames.yml b/.github/workflows/expected-filenames.yml index 328da95529..59320b9261 100644 --- a/.github/workflows/expected-filenames.yml +++ b/.github/workflows/expected-filenames.yml @@ -10,6 +10,11 @@ on: permissions: contents: read +env: + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + jobs: expected-filenames: name: no golden filenames diff --git a/.github/workflows/landlock-run.yml b/.github/workflows/landlock-run.yml index 8916f59a56..dad9638761 100644 --- a/.github/workflows/landlock-run.yml +++ b/.github/workflows/landlock-run.yml @@ -19,6 +19,11 @@ concurrency: permissions: contents: read +env: + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + defaults: run: working-directory: native/landlock-run diff --git a/.github/workflows/pi-ai-provider-e2e.yml b/.github/workflows/pi-ai-provider-e2e.yml index 1306754d4c..255c7654e7 100644 --- a/.github/workflows/pi-ai-provider-e2e.yml +++ b/.github/workflows/pi-ai-provider-e2e.yml @@ -19,6 +19,11 @@ on: permissions: contents: read +env: + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + jobs: e2e: runs-on: ubuntu-latest diff --git a/.github/workflows/sandbox.yml b/.github/workflows/sandbox.yml index 36f58cc75b..939ca2f6ab 100644 --- a/.github/workflows/sandbox.yml +++ b/.github/workflows/sandbox.yml @@ -19,6 +19,11 @@ concurrency: permissions: contents: read +env: + # CI runs must never report to the production telemetry endpoint baked + # into apps/cli/cordis.yml (AppCLIEntry disables the row when set). + DSH_TELEMETRY_DISABLED: '1' + jobs: # Keyless real-kernel sandbox proofs (sandbox Agent Note § Testing): each ladder # rung is only provable on a host where it enforces, so this job fans out diff --git a/README.i18n.yaml b/README.i18n.yaml index 7584d4f293..66400262db 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: f9f7294b42e29132d5cd46c0ab6a5f5265a1d8f3 -README.zh.md: 88cbf8522d8f1a183a48dc7e80858d1a0ced8f0f +README.md: baf5d79b157ae845cc837261452853afd48dbe46 +README.zh.md: 57d7bcf44cda36b37ae233754dbfba4ead2204fd diff --git a/README.md b/README.md index f9f7294b42..baf5d79b15 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,16 @@ DeepSeek Harness (`dsh`) is an open-source coding agent built on the DeepSeek Ha It uses an architecture where **everything is a plugin**. +## Internal testing notice + +Thank you for making time to try DeepSeek Harness. + +This version is still in internal testing. Some features remain unfinished, and parts of the experience may feel rough. + +“As one cuts and files, as one carves and polishes.” Products grow through repeated encounters with real use and candid feedback. The problems you uncover in practice may lead us to re-examine, or even discard, existing designs. + +We especially want to hear about moments of failure, confusion, or friction. If DeepSeek Harness does not help—or instead makes your work harder—please leave a message in our WeCom group and tell us about your experience. Every report will help us refine it. + ## Install Install `dsh` with one command: @@ -22,20 +32,14 @@ The installer keeps every checkout under `~/.dsh/source`: the master clone at `~ ### Web UI -For the recommended local interface, build the frontend after installation and after each update, then start the Web UI. Resolve the running checkout from the `dsh` launcher so the command holds regardless of which staging worktree is current (the launcher resolves through the stable `current` symlink): +For the recommended local interface, build the active checkout after installation and after each update, then start the Web UI: ```sh -dsh_bin=$(cd "$(dirname "$(command -v dsh)")" && pwd -P)/$(basename "$(command -v dsh)") -while [ -L "$dsh_bin" ]; do - link=$(readlink "$dsh_bin") - case $link in /*) dsh_bin=$link ;; *) dsh_bin=$(cd "$(dirname "$dsh_bin")" && cd "$(dirname "$link")" && pwd -P)/$(basename "$link") ;; esac -done -dsh_dir=$(cd "$(dirname "$dsh_bin")/.." && pwd -P) -pnpm --dir "$dsh_dir" run build && pnpm --dir "$dsh_dir" run build:web +(cd ~/.dsh/source/current && pnpm run build) dsh web ``` -The Web UI is served at `http://127.0.0.1:3080` by default. +The full build produces the library and client bundles plus the frontend dist. The path above is the installer's default. If you set `DSH_SOURCE` or `DSH_CURRENT`, or reused an existing checkout, replace `~/.dsh/source/current` with that checkout path; see [`scripts/install.sh`](scripts/install.sh) for details. The Web UI is served at `http://127.0.0.1:3080` by default. ### TUI @@ -53,11 +57,22 @@ Run one task, print the final answer, and exit: dsh -p "summarize this workspace" ``` +### Automation and SDKs + +From a source checkout with `DEEPSEEK_API_KEY` in the environment or its root `.env`, start the ACP automation server: + +```sh +pnpm run demo:acp +``` + +The [Python SDK](python/README.md) drives a bundled JSON-RPC runtime. The [examples](examples/README.md) cover the runnable headless, ACP, JSON-RPC, Code Mode, and self-referential compositions. + ## Why DeepSeek Harness -Built-in capabilities cover file reading, editing, and search; shell execution; reusable skills; task tracking; subagents and workflows; persistent sessions; and context compaction. The TUI also includes Plan Mode. +Built-in capabilities cover file reading, editing, and search; shell and persistent PTY execution; reusable skills; task tracking, goals, plans, todos, and background tasks; subagents and workflows; sandboxing and approvals; settings and credentials; persistent, resumable, forkable, and queryable sessions; LSP and web access; context compaction; and telemetry. Each composition selects the subset appropriate to its surface. The TUI and Web UI both include Plan Mode. - **Everything is a plugin.** Models, tools, policies, storage, context management, and interfaces are composable [Cordis plugins](docs/user/develop/basic/index.md), so deployments can extend or replace behavior without forking the agent loop. See the [architecture](docs/architecture.md) for the underlying design. +- **Runs are reconstructable.** Anything visible to the model is logged in the authoritative session stream; persistence, resume/fork/query, replay, telemetry, and UIs derive from the same events. See the [session-log architecture](docs/architecture.md#session-log). - **Code Mode (opt-in).** It exposes a `run_code` tool and a generated TypeScript SDK; only program output re-enters model context. See [Code Mode](packages/core/tools/README.md#code-mode). - **Self-referential Cordis tools are opt-in.** They let the agent inspect its live runtime and mount or unmount plugins while it runs. See the [Cordis tools](packages/cordis/tool-cordis/README.md). @@ -76,7 +91,7 @@ Start with the [development guide](docs/development.md) and read the [architectu For agents, follow [AGENTS.md](AGENTS.md). -DeepSeek Harness is currently pre-release. +DeepSeek Harness is currently in internal testing. ## License diff --git a/README.zh.md b/README.zh.md index 88cbf8522d..57d7bcf44c 100644 --- a/README.zh.md +++ b/README.zh.md @@ -6,6 +6,16 @@ DeepSeek Harness（`dsh`）是一款基于 DeepSeek Harness SDK 构建的开源 它采用了**一切皆插件**的架构。 +## 内测声明 + +感谢您愿意拨冗试用 DeepSeek Harness。 + +目前的版本仍处于内部测试阶段，有些功能仍待完善，有些体验难免粗粝。 + +“如切如磋，如琢如磨。”产品的成长，离不开一次次真实的碰撞与坦诚的反馈。您在真实使用中暴露的问题，也可能促使我们重新审视，甚至推翻已有的设计。 + +我们尤其希望听见那些失败、困惑与不顺手的时刻——如果它未能帮到您，甚至反而为工作平添了麻烦，请在企业微信群中留言，将使用感受告诉我们。每一条反馈，都会帮助我们把它打磨得更好。 + ## 安装 使用一条命令安装 `dsh`： @@ -22,20 +32,14 @@ curl -fsSL https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/m ### Web UI -推荐在本地使用 Web UI。安装完成后以及每次更新后，请先构建前端，再启动 Web UI。通过 `dsh` 启动器解析当前运行的检出，这样无论当前是哪个 staging worktree，命令都成立（启动器会经由稳定的 `current` 符号链接解析）： +推荐在本地使用 Web UI。安装完成后以及每次更新后，请先构建当前生效的检出，再启动 Web UI： ```sh -dsh_bin=$(cd "$(dirname "$(command -v dsh)")" && pwd -P)/$(basename "$(command -v dsh)") -while [ -L "$dsh_bin" ]; do - link=$(readlink "$dsh_bin") - case $link in /*) dsh_bin=$link ;; *) dsh_bin=$(cd "$(dirname "$dsh_bin")" && cd "$(dirname "$link")" && pwd -P)/$(basename "$link") ;; esac -done -dsh_dir=$(cd "$(dirname "$dsh_bin")/.." && pwd -P) -pnpm --dir "$dsh_dir" run build && pnpm --dir "$dsh_dir" run build:web +(cd ~/.dsh/source/current && pnpm run build) dsh web ``` -Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。 +完整构建会生成库与客户端 bundle，以及前端 dist。上述路径是安装器的默认位置。如果你设置过 `DSH_SOURCE` 或 `DSH_CURRENT`，或者复用了已有检出，请把 `~/.dsh/source/current` 换成该检出路径；详情见 [`scripts/install.sh`](scripts/install.sh)。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。 ### TUI @@ -53,11 +57,22 @@ dsh dsh -p "summarize this workspace" ``` +### 自动化与 SDK + +在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`，然后启动 ACP（Agent Client Protocol）自动化服务器： + +```sh +pnpm run demo:acp +``` + +[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。 + ## 为什么选择 DeepSeek Harness -内置功能涵盖文件读取、编辑与搜索、shell 执行、可复用 skill（技能）、任务跟踪、subagent 与工作流、持久化会话，以及上下文压缩（context compaction）。TUI 还包含 Plan Mode。 +内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill（技能）、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩（context compaction），以及遥测。每个组合只选用适合其使用方式的能力子集。TUI 与 Web UI 均包含 Plan Mode。 - **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均可组合为 [Cordis 插件](docs/user/develop/basic/index.md)，部署方无需 fork agent loop（智能体循环）即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。 +- **运行可重建。** 凡是模型可见的内容，都会记录在权威会话流中；持久化、恢复／fork／查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。 - **Code Mode（需显式启用）。** 它会提供 `run_code` 工具和生成的 TypeScript SDK，只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。 - **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时，并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/cordis/tool-cordis/README.md)。 @@ -80,7 +95,7 @@ pnpm run test:coverage 面向 agent：遵循 [AGENTS.md](AGENTS.md)。 -DeepSeek Harness 目前处于预发布阶段。 +DeepSeek Harness 目前处于内测阶段。 ## 许可证 diff --git a/apps/cli/README.i18n.yaml b/apps/cli/README.i18n.yaml index 256587556f..b2fe93b91a 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: d783d75cc9747d13887386fcf7609a6778e5dfb5 -README.zh.md: 3f5ce7e7a3a302fd9e255c1042ccb7b03deb59d9 +README.md: c36a75fc61fd7118f48c9b68be3144177df19534 +README.zh.md: e926fa99c4e483351f52ca4e76b668e26b34d02f diff --git a/apps/cli/README.md b/apps/cli/README.md index d783d75cc9..c36a75fc61 100644 --- a/apps/cli/README.md +++ b/apps/cli/README.md @@ -17,13 +17,14 @@ The TUI surface: `dsh upgrade` is a guided fresh-session entry over the default TUI surface: it mints a fresh session in the invoking directory and seeds its first turn with the bundled `dsh-upgrade` skill, exactly as if the user typed `/skill:`. The launcher passes the skill name on the boot context ([`INITIAL_SKILL_KEY`](../../packages/ui/tui/README.md)), which the TUI auto-invokes once the chat is live. Both take no options — `--config`, `-p`, and `--resume` fail loud — and seed only on this first launch, so a later `dsh --resume ` of the session is an ordinary TUI session with no re-injection. - -The Web and headless surfaces boot `base.cordis.yml` plus `web.cordis.yml`, then apply `$DSH_HOME/config.yaml`; an explicit `--config ` replaces that personal overlay. Both surfaces otherwise share the same composition: both treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root ` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, and opt into first-message model titles. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`). +The Web and headless surfaces boot `base.cordis.yml` plus `web.cordis.yml`, then apply `$DSH_HOME/config.yaml`; an explicit `--config ` replaces that personal overlay. Both surfaces otherwise share the same composition: both treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root ` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, opt into first-message model titles, use the same bounded transient model-request retry policy as the TUI, and mount a disposable in-memory SQLite content-index service. That service is ACTIVE at boot, while its `node:sqlite` module and database handle open only on the first content search. This keeps Node 22 startup output free of SQLite's experimental warning before search is used; the first actual search may still emit the runtime warning. Each service instance owns its database, so parallel invocations neither share unsupported SQLite state nor leave derived index files behind, and the first search lazily reconciles live and persisted logs. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`). The shipped TUI and Web compositions register the native DeepSeek adapter plus pi-ai OpenAI and Anthropic profiles. Credentials and endpoint overrides come from the provider-standard `DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`, `OPENAI_API_KEY` / `OPENAI_BASE_URL`, and `ANTHROPIC_API_KEY` / `ANTHROPIC_BASE_URL` pairs in the boot's layered environment. `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). +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) Symlink the source-running launcher onto your PATH; it resolves the checkout through its own real path, so code changes apply on the next launch with no build step: diff --git a/apps/cli/README.zh.md b/apps/cli/README.zh.md index 3f5ce7e7a3..e926fa99c4 100644 --- a/apps/cli/README.zh.md +++ b/apps/cli/README.zh.md @@ -17,13 +17,14 @@ TUI 界面： `dsh upgrade` 是默认 TUI 界面之上的引导式全新会话入口：它在调用目录中创建一个全新会话，并以内置 `dsh-upgrade` skill 播种其首轮，效果等同于用户手动键入 `/skill:`。启动器将 skill 名称提供到启动上下文（[`INITIAL_SKILL_KEY`](../../packages/ui/tui/README.md)），TUI 在聊天就绪后自动调用它。两者都不接受任何选项——`--config`、`-p`、`--resume` 都会明确报错——且仅在首次启动时播种，因此之后 `dsh --resume ` 恢复该会话时是普通 TUI 会话，不会重复注入。 - -Web 和无头界面启动 `base.cordis.yml` 与 `web.cordis.yml`，随后应用 `$DSH_HOME/config.yaml`；显式的 `--config ` 会替代该个人覆盖。除此之外，两者共享同一套组合：两者都将调用目录视为默认项目和 Workspace 根目录，除非通过 `--workspace-root ` 覆盖，否则会在该根目录下创建具名 Workspace；它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中，渲染预算为 65,536 字节，并选用首条消息模型标题。无头界面唯一的差异是监听操作系统分配的端口（并行 `dsh -p` 运行绝不冲突；stderr 打印的 URL 会在浏览器中打开实时会话）。两者都需要先构建前端 dist 和客户端 bundle（`pnpm run build && pnpm run build:web`）。 +Web 和无头界面启动 `base.cordis.yml` 与 `web.cordis.yml`，随后应用 `$DSH_HOME/config.yaml`；显式的 `--config ` 会替代该个人覆盖。除此之外，两者共享同一套组合：两者都将调用目录视为默认项目和 Workspace 根目录，除非通过 `--workspace-root ` 覆盖，否则会在该根目录下创建具名 Workspace；它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中，渲染预算为 65,536 字节，选用首条消息模型标题，采用与 TUI 相同的有界暂时性模型请求重试策略，并挂载一个可丢弃的内存 SQLite 内容索引服务。该服务在启动时处于 ACTIVE 状态，但其 `node:sqlite` 模块与数据库句柄分别要到首次内容搜索才会导入和打开。这样可使 Node 22 在尚未使用搜索时的启动输出不出现 SQLite 实验性警告；首次实际搜索仍可能发出运行时警告。每个服务实例独占自己的数据库，因此并行调用既不会共享不受支持的 SQLite 状态，也不会留下派生索引文件，首次搜索还会惰性对账实时日志与持久化日志。无头界面唯一的差异是监听操作系统分配的端口（并行 `dsh -p` 运行绝不冲突；stderr 打印的 URL 会在浏览器中打开实时会话）。两者都需要先构建前端 dist 和客户端 bundle（`pnpm run build && pnpm run build:web`）。 已交付的 TUI 和 Web 组合会注册原生 DeepSeek 适配器，以及 pi-ai 的 OpenAI 和 Anthropic 提供方配置。凭据和端点覆盖来自启动分层环境中的提供方标准变量对：`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`、`OPENAI_API_KEY` / `OPENAI_BASE_URL` 和 `ANTHROPIC_API_KEY` / `ANTHROPIC_BASE_URL`。 `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）。 +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） 将从源码运行的启动器符号链接到 PATH 上；它通过自身真实路径解析 checkout，因此代码更改会在下次启动时生效，无需构建： diff --git a/apps/cli/composition.md b/apps/cli/composition.md index 2e71c6c07b..870b926054 100644 --- a/apps/cli/composition.md +++ b/apps/cli/composition.md @@ -38,6 +38,8 @@ flowchart LR cfg --> plugin_tui_session_persistence_jsonl plugin_tui_session_query_sqlite["session-query-sqlite
@deepseek-ai/dsh-session-query-sqlite"] cfg --> plugin_tui_session_query_sqlite + plugin_tui_telemetry_otel["telemetry-otel
@deepseek-ai/dsh-session-telemetry-otel"] + cfg --> plugin_tui_telemetry_otel plugin_tui_subprocess["subprocess
@deepseek-ai/dsh-subprocess-local"] cfg --> plugin_tui_subprocess plugin_tui_bash_local["bash-local
@deepseek-ai/dsh-bash-local"] @@ -123,6 +125,7 @@ flowchart LR | `llm-pi-ai` | `@deepseek-ai/dsh-llm-pi-ai` | | `session-persistence-jsonl` | `@deepseek-ai/dsh-session-persistence-jsonl` | | `session-query-sqlite` | `@deepseek-ai/dsh-session-query-sqlite` | +| `telemetry-otel` | `@deepseek-ai/dsh-session-telemetry-otel` | | `subprocess` | `@deepseek-ai/dsh-subprocess-local` | | `bash-local` | `@deepseek-ai/dsh-bash-local` | | `tool-bash` | `@deepseek-ai/dsh-tool-bash` | diff --git a/apps/cli/config/base.cordis.yml b/apps/cli/config/base.cordis.yml index 16d4e12471..5e0940d241 100644 --- a/apps/cli/config/base.cordis.yml +++ b/apps/cli/config/base.cordis.yml @@ -88,12 +88,45 @@ (() => { 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') })() # TUI consumes this shared session capability. Its launcher supplies a unique -# process-local path; non-TUI surfaces disable the row in their overlay. +# process-local path; other surfaces repoint or disable the row in their +# overlay (web patches it to an ephemeral in-memory index). - id: session-query-sqlite name: '@deepseek-ai/dsh-session-query-sqlite' config: path: !!js launcherSessionQueryPath ?? './.sessions/session-query.db' +# Session telemetry, on for every dsh surface: mirrors every session-log +# event (assistant/chunk projected to first-of-step) plus ops markers onto +# OTLP/HTTP log records, streaming on the batch processor's cadence +# (10s/batch here) — not at exit; a crash loses at most the last unexported +# interval. No telemetry/record redaction rule is mounted yet, so exports +# are the raw captured copy; the deployment stance, env seams, and +# follow-ups are pinned in the web-telemetry-default-mount Agent Note. +# DSH_TELEMETRY_OTLP_URL overrides the production endpoint, and a non-empty +# DSH_TELEMETRY_DISABLED — any value, including '0'/'false' — opts the +# process out (the launchers patch the row disabled; config cannot disable +# a row). The exporter/processor values bound the shutdown drain to ~1s +# against an unreachable collector: exporter.timeoutMillis is both the +# per-attempt socket timeout and the retry deadline (1s effectively +# disables the SDK's 5-try backoff), maxExportBatchSize == maxQueueSize +# (both explicit) makes the drain a single batch, and exportTimeoutMillis +# is the processor's own cap on that one export cycle — the second bound +# when the exporter's clock alone does not fire. Every surface's exit path +# drains it: web/headless dispose on SIGINT/SIGTERM, and the TUI's normal +# exit and /resume handoff both dispose the root. +- id: telemetry-otel + name: '@deepseek-ai/dsh-session-telemetry-otel' + config: + exporter: + url: !!js process.env.DSH_TELEMETRY_OTLP_URL ?? 'https://harness-telemetry.deepseeksvc.com/v1/logs' + compression: gzip + timeoutMillis: 1000 + processor: + scheduledDelayMillis: 10000 + maxQueueSize: 2048 + maxExportBatchSize: 2048 + exportTimeoutMillis: 1500 + - id: subprocess name: '@deepseek-ai/dsh-subprocess-local' diff --git a/apps/cli/config/tui.cordis.yml b/apps/cli/config/tui.cordis.yml index 556f9540a0..980f9d80ad 100644 --- a/apps/cli/config/tui.cordis.yml +++ b/apps/cli/config/tui.cordis.yml @@ -36,8 +36,8 @@ Verify your work by running the code or tests. Keep answers brief and factual. -# Shipped default: full thinking at max effort on every request (wire-only -# defaults; they never enter the request header). +# Shipped default: full thinking at max effort on every request. Exact-model +# resolution materializes request defaults before the request header is logged. - id: llm-deepseek config: apiKey: !!js process.env.DEEPSEEK_API_KEY diff --git a/apps/cli/config/web.cordis.yml b/apps/cli/config/web.cordis.yml index a2fc10804d..a67d95ff6b 100644 --- a/apps/cli/config/web.cordis.yml +++ b/apps/cli/config/web.cordis.yml @@ -14,9 +14,14 @@ - id: hmr disabled: true -# Session query is a TUI capability; Web owns its own session presentation. +# Web content search runs on an ephemeral in-memory index. The service +# activates at boot, while first-search defers the node:sqlite import and +# in-memory handle so Node 22 startup stays quiet until content search +# actually uses SQLite. That search then reconciles this boot's sources. - id: session-query-sqlite - disabled: true + config: + path: ':memory:' + openAt: first-search - id: tools config: diff --git a/apps/cli/package.json b/apps/cli/package.json index 94cf6da9c2..787682ce04 100644 --- a/apps/cli/package.json +++ b/apps/cli/package.json @@ -79,8 +79,10 @@ "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-session-projection": "workspace:^", "@deepseek-ai/dsh-session-projection-cache": "workspace:^", + "@deepseek-ai/dsh-session-query": "workspace:^", "@deepseek-ai/dsh-session-query-sqlite": "workspace:^", "@deepseek-ai/dsh-session-reference": "workspace:^", + "@deepseek-ai/dsh-session-telemetry-otel": "workspace:^", "@deepseek-ai/dsh-session-title": "workspace:^", "@deepseek-ai/dsh-session-title-first-message-llm": "workspace:^", "@deepseek-ai/dsh-settings-local": "workspace:^", @@ -123,7 +125,9 @@ "js-yaml": "^4.2.0" }, "devDependencies": { + "@deepseek-ai/dsh-llm-mock-server": "workspace:^", "@types/js-yaml": "^4.0.9", + "execa": "^10.0.0", "node-pty": "1.1.0" } } diff --git a/apps/cli/src/app-cli-entry.ts b/apps/cli/src/app-cli-entry.ts index f18399e27b..54ade122c7 100644 --- a/apps/cli/src/app-cli-entry.ts +++ b/apps/cli/src/app-cli-entry.ts @@ -3,7 +3,7 @@ * for the Web/headless surface. * Everything here is what must exist before the Loader runs: the patch * composition over the shipped base and surface overlay (profile json + CLI - * flags + the resolved frontend dist), and the fail-loud triple after the tree + * flags + the resolved frontend dist), and the fail-loud activation audit after the tree * settles. The environment is what the bin already loaded (ambient plus the * invoking directory's `.env`); `$DSH_HOME/.env` belongs to the credential * provider and is never hoisted here. @@ -24,6 +24,9 @@ import type {} from '@deepseek-ai/dsh-host-webserver' const PROFILE_DIR = '.dsh-tmp-profile' const PROFILE_FILE = 'config.json' +/** The session-telemetry row id the DSH_TELEMETRY_DISABLED switch targets (mounted in web.cordis.yml). */ +const TELEMETRY_ROW_ID = 'telemetry-otel' + /** The webserver schema's all-interfaces bind literal: gates LAN-authority derivation here and the printed LAN URL in web.ts. */ const ALL_INTERFACES_HOST = '0.0.0.0' @@ -59,6 +62,38 @@ export function resolveLanTrust( return { lanAddresses, trustedHosts: [...lanAddresses, ...extra] } } +/** + * Resolve the telemetry opt-out switch into its boot patch. ANY non-empty + * value (including `'0'`/`'false'`) disables: a privacy switch prefers + * off-by-mistake over on-by-mistake. Throws when the switch is set but the + * row is absent — a silently no-op "disabled" privacy switch would keep + * exporting while the user believes it is off. + * @param disabledEnv - the raw `DSH_TELEMETRY_DISABLED` value (`undefined` when unset). + * @param hasRow - whether the composition carries the {@link TELEMETRY_ROW_ID} row. + * @returns the disable patch, or `undefined` when telemetry stays enabled. + */ +export function resolveTelemetryPatch(disabledEnv: string | undefined, hasRow: boolean): PatchOptions | undefined { + if ((disabledEnv ?? '') === '') return undefined + if (!hasRow) { + throw new Error(`dsh: DSH_TELEMETRY_DISABLED is set but row "${TELEMETRY_ROW_ID}" is not in this composition`) + } + return { id: TELEMETRY_ROW_ID, disabled: true } +} + +/** + * Whether a config file carries the telemetry row, parsed under the same + * `!!js`-tolerant dialect the boot uses — the `hasRow` input for launchers + * that compose their patch lists outside {@link AppCLIEntry} (the TUI). + * @param file - absolute path of the config or overlay file. + * @returns true when a top-level (or inserted) row has the telemetry id. + */ +export function configHasTelemetryRow(file: string): boolean { + const doc = yaml.load(readFileSync(file, 'utf8'), { schema: includeYamlSchema }) + if (!Array.isArray(doc)) throw new Error(`dsh: ${file} is not a top-level entry list`) + return (doc as { id?: string; insert?: { id?: string }[] }[]).some(row => + row.id === TELEMETRY_ROW_ID || (row.insert ?? []).some(inserted => inserted.id === TELEMETRY_ROW_ID)) +} + /** One profile-json key mapped onto a yml row's config field. */ interface ProfileMapping { jsonPath: string @@ -203,9 +238,15 @@ export class AppCLIEntry { if (yml === undefined) throw new Error(`dsh: patch target row "${id}" not found in ${this.options.configPath}`) return { id, config: { ...(yml.config ?? {}) as Record, ...bag } } }) + + // Telemetry opt-out: a row can only be turned off at the patch layer + // (config cannot disable an entry), and the switch must hold BEFORE the + // plugin constructs — its exporter.url validation is load-time fail-loud. + const telemetryPatch = resolveTelemetryPatch(process.env.DSH_TELEMETRY_DISABLED, rows.has(TELEMETRY_ROW_ID)) + if (telemetryPatch !== undefined) this.patches.push(telemetryPatch) } - /** Shared Loader boot; the dev HMR row mounts before await so the fail-loud sweep covers it. */ + /** Shared Loader boot; the dev HMR row mounts before await so the activation audit covers it. */ private async bootTree(): Promise { // One include of the shared base with every overlay as a sibling patch // list: patches never cross an include boundary, so nesting them would diff --git a/apps/cli/src/headless.ts b/apps/cli/src/headless.ts index 5fef797cc5..3ec2792e8e 100644 --- a/apps/cli/src/headless.ts +++ b/apps/cli/src/headless.ts @@ -82,6 +82,17 @@ export async function runHeadless(task: string): Promise { }) const { ctx, port } = await entry.run() const dispose = async (): Promise => { await ctx.fiber.dispose() } + // Signal exits must still dispose the tree: the composition mounts + // exit-drained plugins (telemetry's queued tail and shutdown marker would + // otherwise be lost), and Node's default signal exit skips disposal. + let signalled = false + const disposeAndExit = (code: number): void => { + if (signalled) return + signalled = true + void dispose().finally(() => { process.exit(code) }) + } + process.on('SIGTERM', () => { disposeAndExit(143) }) + process.on('SIGINT', () => { disposeAndExit(130) }) // The headless session is web-observable while it runs (same composition). process.stderr.write(`dsh: observing at http://127.0.0.1:${String(port)}\n`) const api = new InProcessApiClient(toFetchHandler(ctx.apiProxy)) diff --git a/apps/cli/src/tui.ts b/apps/cli/src/tui.ts index 3469a737c1..dee865a0e1 100644 --- a/apps/cli/src/tui.ts +++ b/apps/cli/src/tui.ts @@ -31,6 +31,7 @@ import { resolveConfigPath, } from '@deepseek-ai/dsh-app-boot' import { SessionId } from '@deepseek-ai/dsh-session' +import { configHasTelemetryRow, resolveTelemetryPatch } from './app-cli-entry.ts' import { SESSION_QUERY_SQLITE_PATH_KEY } from '@deepseek-ai/dsh-session-query-sqlite' import { CONFIGURED_AGENT_IDENTITIES_KEY } from '@deepseek-ai/dsh-agent-loop' import type { Context } from 'cordis' @@ -196,16 +197,26 @@ export async function runTui( // demo or test config would silently run on the user's provider and model. // `--config-replace` additionally discards the base and the surface overlay. const replaceTree = configReplace !== undefined - const patches = replaceTree ? [] : [ - ...loadOverlayPatches(NAME, TUI_OVERLAY), - ...resolvedConfig === undefined - ? loadPersonalPatches(NAME) ?? [] - : loadOverlayPatches(NAME, resolveConfigPath(resolvedConfig, undefined)), + const bootConfig = resolvedConfigReplace === undefined ? BASE_CONFIG : resolveConfigPath(resolvedConfigReplace, undefined) + // Same opt-out semantics as the web surface (resolveTelemetryPatch: any + // non-empty value disables; setting the switch against a tree without the + // row fails loud rather than silently no-opping a privacy switch). The row + // presence is checked against the tree actually booting, so a + // --config-replace tree is judged on its own rows, not the shipped base's. + const telemetryPatch = resolveTelemetryPatch(process.env.DSH_TELEMETRY_DISABLED, configHasTelemetryRow(bootConfig)) + const patches = [ + ...replaceTree ? [] : [ + ...loadOverlayPatches(NAME, TUI_OVERLAY), + ...resolvedConfig === undefined + ? loadPersonalPatches(NAME) ?? [] + : loadOverlayPatches(NAME, resolveConfigPath(resolvedConfig, undefined)), + ], + ...telemetryPatch === undefined ? [] : [telemetryPatch], ] const queryIndexPath = join(tmpdir(), SESSION_QUERY_DB) const ctx = await boot( NAME, - resolvedConfigReplace === undefined ? BASE_CONFIG : resolveConfigPath(resolvedConfigReplace, undefined), + bootConfig, patches, (hostCtx) => { // The launcher owns session identity and the exit line: a config-mounted diff --git a/apps/cli/src/web.ts b/apps/cli/src/web.ts index 6c37598e11..9c6a2ec94c 100644 --- a/apps/cli/src/web.ts +++ b/apps/cli/src/web.ts @@ -57,12 +57,14 @@ export async function runWeb( void Promise.resolve(ctx.fiber.dispose()).finally(() => { process.exit(code) }) } + // Install shutdown handling before publishing readiness: supervisors may + // send a signal as soon as they observe the URL line. + process.on('SIGTERM', () => { shutdown(0) }) + process.on('SIGINT', () => { shutdown(130) }) + // The entry's boot-time snapshot, not a fresh sample: the printed LAN URL // must name an address the /api trust fence was configured with. const lanCandidate = entry.lanAddresses[0] const localUrl = `http://${LOOPBACK_HOST}:${boundPort}` console.log(`dsh web: ${localUrl}${lanCandidate === undefined ? '' : ` (LAN: http://${lanCandidate}:${boundPort})`}`) - - process.on('SIGTERM', () => { shutdown(0) }) - process.on('SIGINT', () => { shutdown(130) }) } diff --git a/apps/cli/tests/lazy-search-startup.compat.spec.ts b/apps/cli/tests/lazy-search-startup.compat.spec.ts new file mode 100644 index 0000000000..6e6d0b6e85 --- /dev/null +++ b/apps/cli/tests/lazy-search-startup.compat.spec.ts @@ -0,0 +1,112 @@ +/** + * Node 22 startup-output smoke for the shipped Web CLI composition. + * + * Only the dedicated Node compatibility gate opts this test in after building + * both artifacts; ordinary Vitest inventory deterministically skips it. + * The child runs built artifacts under plain Node with the real shipped + * config (base.cordis.yml + the web.cordis.yml overlay). + * Its URL line follows AppCLIEntry's settled boot; SIGTERM then exercises the + * shipped quiescent disposer. + */ + +import { spawn } from 'node:child_process' +import { existsSync } from 'node:fs' +import { mkdtemp, readFile, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join, resolve } from 'node:path' +import { fileURLToPath } from 'node:url' +import yaml from 'js-yaml' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../', import.meta.url)) +const builtBin = join(repoRoot, 'apps/cli/lib/bin.js') +const webDist = join(repoRoot, 'apps/web/dist/index.html') +// The web overlay owns the session-query-sqlite lazy-open patch row. +const configPath = join(repoRoot, 'apps/cli/config/web.cordis.yml') +const requireBuiltArtifacts = process.env.DSH_REQUIRE_BUILT_CLI_SMOKE === '1' + +interface ConfigRow { + id?: string + config?: { openAt?: unknown } +} + +const jsExprType = new yaml.Type('tag:yaml.org,2002:js', { + kind: 'scalar', + construct: value => String(value), +}) +const configSchema = yaml.JSON_SCHEMA.extend(jsExprType) + +/** Boot the built Web CLI, wait for its settled URL, then dispose through SIGTERM. */ +function runBuiltWeb(cwd: string): Promise<{ stdout: string; stderr: string; code: number }> { + return new Promise((resolveRun, rejectRun) => { + const env: NodeJS.ProcessEnv = { + ...process.env, + DEEPSEEK_API_KEY: 'dsh-cli-smoke-dummy-key', + DSH_HOME: join(cwd, '.dsh'), + } + delete env.DEEPSEEK_BASE_URL + delete env.NODE_OPTIONS + delete env.NODE_NO_WARNINGS + const child = spawn(process.execPath, [ + builtBin, + 'web', + '--host', + '127.0.0.1', + '--port', + '0', + ], { + cwd, + env, + stdio: ['ignore', 'pipe', 'pipe'], + }) + let stdout = '' + let stderr = '' + let settled = false + child.stdout.setEncoding('utf8') + child.stderr.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { + stdout += chunk + if (!settled && /dsh web: http:\/\/127\.0\.0\.1:\d+/u.test(stdout)) { + settled = true + child.kill('SIGTERM') + } + }) + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + const timer = setTimeout(() => { + child.kill('SIGKILL') + rejectRun(new Error(`built Web CLI did not settle and dispose within 60s\nstdout:\n${stdout}\nstderr:\n${stderr}`)) + }, 60_000) + child.on('error', (error) => { + clearTimeout(timer) + rejectRun(error) + }) + child.on('close', (code) => { + clearTimeout(timer) + if (!settled) { + rejectRun(new Error(`built Web CLI exited before settled startup (code ${String(code)})\nstdout:\n${stdout}\nstderr:\n${stderr}`)) + return + } + resolveRun({ stdout, stderr, code: code ?? -1 }) + }) + }) +} + +describe.skipIf(!requireBuiltArtifacts)('built CLI lazy-search startup', () => { + it('boots and disposes the shipped composition without a SQLite startup warning', async () => { + expect(existsSync(builtBin), `missing built CLI ${resolve(builtBin)}; run pnpm build`).toBe(true) + expect(existsSync(webDist), `missing Web dist ${resolve(webDist)}; run pnpm run build:web`).toBe(true) + const rows = yaml.load(await readFile(configPath, 'utf8'), { schema: configSchema }) as ConfigRow[] + const searchRow = rows.find(row => row.id === 'session-query-sqlite') + expect(searchRow?.config?.openAt).toBe('first-search') + + const cwd = await mkdtemp(join(tmpdir(), 'dsh-cli-lazy-search-')) + try { + const result = await runBuiltWeb(cwd) + expect(result.stdout).toMatch(/dsh web: http:\/\/127\.0\.0\.1:\d+/u) + expect(result.code).toBe(0) + expect(result.stderr).not.toMatch(/ExperimentalWarning: SQLite/u) + } finally { + await rm(cwd, { recursive: true, force: true }) + } + }, 70_000) +}) diff --git a/apps/cli/tests/telemetry-switch.spec.ts b/apps/cli/tests/telemetry-switch.spec.ts new file mode 100644 index 0000000000..0735aa93c7 --- /dev/null +++ b/apps/cli/tests/telemetry-switch.spec.ts @@ -0,0 +1,23 @@ +import { describe, expect, it } from 'vitest' +import { resolveTelemetryPatch } from '../src/app-cli-entry.ts' + +describe('resolveTelemetryPatch', () => { + it('keeps telemetry enabled when the switch is unset or empty', () => { + expect(resolveTelemetryPatch(undefined, true)).toBeUndefined() + expect(resolveTelemetryPatch('', true)).toBeUndefined() + }) + + it('disables on ANY non-empty value, including falsy-looking ones', () => { + for (const value of ['1', '0', 'false', 'no']) { + expect(resolveTelemetryPatch(value, true)).toEqual({ id: 'telemetry-otel', disabled: true }) + } + }) + + it('fails loud when the switch is set but the row is absent', () => { + expect(() => resolveTelemetryPatch('1', false)).toThrow('DSH_TELEMETRY_DISABLED is set but row "telemetry-otel" is not in this composition') + }) + + it('ignores a missing row while the switch is unset', () => { + expect(resolveTelemetryPatch(undefined, false)).toBeUndefined() + }) +}) diff --git a/apps/cli/tests/tui-keyless-smoke.e2e.ts b/apps/cli/tests/tui-keyless-smoke.e2e.ts index d8966ee081..359fe6338e 100644 --- a/apps/cli/tests/tui-keyless-smoke.e2e.ts +++ b/apps/cli/tests/tui-keyless-smoke.e2e.ts @@ -130,7 +130,9 @@ function smoke(overrides: Partial & { label: string }): Prom tempDirPrefix: 'dsh-tui-smoke-', binScript: dshBinScript, tsconfigPath, - env: { DEEPSEEK_API_KEY: 'keyless-tui-no-call' }, + // Telemetry now mounts in the shared base: keep fixture sessions from + // POSTing to the production endpoint when run outside CI's workflow env. + env: { DEEPSEEK_API_KEY: 'keyless-tui-no-call', DSH_TELEMETRY_DISABLED: '1' }, // Artifact CI builds and smokes concurrently on a contended runner. ...(process.env.DSH_EXAMPLE_MODE === 'lib' ? { timeoutMs: 60_000 } : {}), ...overrides, diff --git a/apps/web/index.html b/apps/web/index.html index fe5901f353..c9fc7d124c 100644 --- a/apps/web/index.html +++ b/apps/web/index.html @@ -3,6 +3,7 @@ + DeepSeek Harness diff --git a/apps/web/public/favicon.svg b/apps/web/public/favicon.svg new file mode 100644 index 0000000000..8a8fc56752 --- /dev/null +++ b/apps/web/public/favicon.svg @@ -0,0 +1,3 @@ + + + \ No newline at end of file diff --git a/apps/web/tests/approval-composer.e2e.ts b/apps/web/tests/approval-composer.e2e.ts index 2c6a78d2e5..b66277e0b2 100644 --- a/apps/web/tests/approval-composer.e2e.ts +++ b/apps/web/tests/approval-composer.e2e.ts @@ -151,7 +151,7 @@ describe('web e2e: approval takeover keeps its actions reachable', () => { await page.setViewportSize(original) } - await panel.getByRole('button', { name: '允许一次' }).click() + await panel.getByRole('button', { name: 'Allow once' }).click() const sessionId = await settled if (MODE === 'record') { diff --git a/apps/web/tests/built-boot.snapshot.ts b/apps/web/tests/built-boot.snapshot.ts index 69d5d5cfae..90b27e84cb 100644 --- a/apps/web/tests/built-boot.snapshot.ts +++ b/apps/web/tests/built-boot.snapshot.ts @@ -60,6 +60,9 @@ let unmount: (() => void) | undefined beforeEach(() => { localStorage.clear() + // English pinned before boot: role/text locators stay deterministic across + // localized component migrations (the newEnglishPage e2e convention). + localStorage.setItem('dsh.locale', 'en') document.title = 'DeepSeek Harness' vi.stubGlobal('ResizeObserver', ResizeObserverStub) vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) => @@ -108,6 +111,18 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn expect(document.querySelector('[data-sample="bash-global"]')).not.toBeNull() }, { timeout: 10_000 }) + // 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. + 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() + }, { timeout: 10_000 }) + // Every bundle injected its plugin-owned style tag (the loader's CSS path). const styleOwners = [...document.head.querySelectorAll('style[data-plugin]')] .map(style => style.getAttribute('data-plugin')) diff --git a/apps/web/tests/cordis-tool-round.e2e.ts b/apps/web/tests/cordis-tool-round.e2e.ts index e0ad2d26e1..66bc9c6900 100644 --- a/apps/web/tests/cordis-tool-round.e2e.ts +++ b/apps/web/tests/cordis-tool-round.e2e.ts @@ -107,7 +107,8 @@ describe('web e2e: Cordis tools use the generic row variants', () => { const mountRow = page.locator('[data-tool="cordis_mount"]').filter({ hasText: 'Mount temporary Plugin' }).first() await mountRow.waitFor({ timeout: 10_000 }) - await mountRow.locator('button[aria-expanded]').click() + // The whole summary row is the expand toggle (unified tool-row interaction). + await mountRow.locator('[aria-expanded]').first().click() await expect.poll(() => mountRow.locator('pre.shiki').textContent(), { timeout: 10_000 }) .toContain(MOUNT_CODE) diff --git a/apps/web/tests/details-session-lifecycle.e2e.ts b/apps/web/tests/details-session-lifecycle.e2e.ts index 8105519338..ce97cfb2a1 100644 --- a/apps/web/tests/details-session-lifecycle.e2e.ts +++ b/apps/web/tests/details-session-lifecycle.e2e.ts @@ -98,7 +98,7 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 }) await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0) - expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false) + expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false) await compareOrRefreshGolden(HANDLES_EXPECTED, await handleSnapshot(page), MODE) const sidebarBefore = await sidebarTrack(page) @@ -118,18 +118,18 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S await appFrame(page).waitFor({ timeout: 30_000 }) await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 }) await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0) - expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false) + expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false) await page.getByRole('button', { name: /^(?:New session|新.*会话)$/ }).last().click() await page.getByText("Let's start building", { exact: false }).waitFor({ timeout: 15_000 }) await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0) - expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false) + expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false) const original = page.locator('[role=treeitem]').filter({ hasText: 'Reply with the single word' }).first() await original.click() await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 }) await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0) - expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false) + expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false) const ungrouped = page.getByText('Ungrouped', { exact: true }) const ungroupedRow = ungrouped.locator('..').locator('..') diff --git a/apps/web/tests/lifecycle-chrome.e2e.ts b/apps/web/tests/lifecycle-chrome.e2e.ts index d4d684b1de..97ffefccf7 100644 --- a/apps/web/tests/lifecycle-chrome.e2e.ts +++ b/apps/web/tests/lifecycle-chrome.e2e.ts @@ -25,6 +25,8 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/lifecycle-chrome', import.meta.url)) const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl') const HERO_EXPECTED = join(SNAPSHOT_DIR, 'hero.expected.md') +const COMMAND_MENU_EXPECTED = join(SNAPSHOT_DIR, 'command-menu.expected.md') +const PLAN_ACTIVE_EXPECTED = join(SNAPSHOT_DIR, 'plan-active.expected.md') // Post-reload golden: the same settled conversation rebuilt purely from // persistence + history — byte-equal rendering is exactly the recovery claim. const RELOADED_EXPECTED = join(SNAPSHOT_DIR, 'reloaded.expected.md') @@ -56,6 +58,88 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', () await scaffold?.close() }) + it.skipIf(MODE === 'record')('opens the shared slash menu from plus with only Command candidates', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-command-menu-launcher')) + const launcher = page.getByRole('button', { name: 'Commands' }) + await launcher.click() + const menu = page.getByRole('listbox', { name: 'Trigger suggestions' }) + await menu.waitFor({ timeout: 10_000 }) + const snapshot = await captureStableAria(page, '[role="listbox"]', scaffold.workspaceCwd) + await compareOrRefreshGolden(COMMAND_MENU_EXPECTED, snapshot, MODE) + expect(snapshot).toContain('text: Commands') + expect(snapshot).not.toContain('text: Skills') + expect(snapshot).not.toContain('text: Subagents') + const launchedBox = await menu.boundingBox() + await page.locator('textarea').first().press('Escape') + await expect.poll(() => menu.count()).toBe(0) + const input = page.locator('textarea').first() + await input.fill('/') + await menu.waitFor({ timeout: 10_000 }) + const typedBox = await menu.boundingBox() + expect(launchedBox).not.toBeNull() + expect(typedBox).not.toBeNull() + expect(Math.abs(launchedBox!.x - typedBox!.x)).toBeLessThan(1) + expect(Math.abs( + launchedBox!.y + launchedBox!.height - typedBox!.y - typedBox!.height, + )).toBeLessThan(1) + await input.fill('') + await expect.poll(() => menu.count()).toBe(0) + }) + + it.skipIf(MODE === 'record')('shows active Plan as the warn-state status action', async () => { + const activeScaffold = await launchWebScaffold() + const activePage = await newEnglishPage(browser) + const activeTripwire = watchConsole(activePage) + try { + await activePage.goto(activeScaffold.baseUrl, { waitUntil: 'load' }) + await activePage.waitForSelector('[class*="frame"]', { timeout: 30_000 }) + await connectFreshWorkspace(activePage) + const input = activePage.locator('textarea').first() + await activePage.getByRole('button', { name: 'Commands' }).click() + const menu = activePage.getByRole('listbox', { name: 'Trigger suggestions' }) + await menu.waitFor({ timeout: 10_000 }) + await menu.getByRole('option', { name: 'plan Enter or leave plan mode' }).click() + await expect.poll(() => input.inputValue()).toBe('/plan ') + await input.press('Enter') + const planButton = activePage.getByRole('button', { name: 'Plan mode on, press to turn off' }) + await planButton.waitFor({ timeout: 10_000 }) + const planSnapshot = await captureStableAria(activePage, '[class*="frame"]', activeScaffold.workspaceCwd) + await compareOrRefreshGolden(PLAN_ACTIVE_EXPECTED, planSnapshot, MODE) + const planStyle = await planButton.evaluate((element) => { + const probe = document.createElement('span') + probe.style.color = 'var(--dsw-alias-state-warn-label)' + probe.style.backgroundColor = 'var(--dsw-alias-state-warn-tertiary)' + document.body.append(probe) + const actual = getComputedStyle(element) + const reference = getComputedStyle(probe) + const result = { + color: actual.color, + backgroundColor: actual.backgroundColor, + borderRadius: actual.borderRadius, + fontSize: actual.fontSize, + referenceColor: reference.color, + referenceBackgroundColor: reference.backgroundColor, + } + probe.remove() + return result + }) + expect(planStyle.color).toBe(planStyle.referenceColor) + expect(planStyle.backgroundColor).toBe(planStyle.referenceBackgroundColor) + expect(planStyle.borderRadius).toBe('999px') + expect(planStyle.fontSize).toBe('13px') + await planButton.click() + await expect.poll(() => planButton.count()).toBe(0) + expect(activeTripwire.pageErrors).toEqual([]) + expect(activeTripwire.warnings).toEqual([]) + } catch (error) { + await saveFailureShot(activePage, 'web-e2e-plan-active').catch(() => undefined) + throw error + } finally { + await activePage.close() + await activeScaffold.close() + } + }) + it('sends the first prompt from the empty-state hero (all modes)', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-lifecycle-send')) if (MODE !== 'record') { @@ -152,6 +236,8 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', () it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => { expect(tripwire.warnings).toEqual([]) - await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'hero.expected.md', 'reloaded.expected.md']) + await assertFixtureInventory(SNAPSHOT_DIR, [ + 'session.jsonl', 'command-menu.expected.md', 'hero.expected.md', 'plan-active.expected.md', 'reloaded.expected.md', + ]) }) }) diff --git a/apps/web/tests/live-interactions.e2e.ts b/apps/web/tests/live-interactions.e2e.ts index c563638e80..2a4107e128 100644 --- a/apps/web/tests/live-interactions.e2e.ts +++ b/apps/web/tests/live-interactions.e2e.ts @@ -221,8 +221,8 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => { // only on change, so attempt count is invisible there). expect(sessionEvents.filter(e => e.type === 'llm/retry').length).toBeGreaterThanOrEqual(1) await expect.poll(() => page.getByText('event sourcing', { exact: false }).count(), { timeout: 10_000 }).toBeGreaterThan(0) - // Golden of the recovered end-state: indistinguishable from a clean - // completion — retries are deliberately invisible in the transcript. + // Golden of the recovered end-state: the discarded partial stays absent, + // while the settled retry row remains as durable recovery context. const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd) await compareOrRefreshGolden(RETRY_EXPECTED, snapshot, MODE) expect(tripwire.pageErrors).toEqual([]) diff --git a/apps/web/tests/message-actions.e2e.ts b/apps/web/tests/message-actions.e2e.ts index 650c089d32..4d798e11ed 100644 --- a/apps/web/tests/message-actions.e2e.ts +++ b/apps/web/tests/message-actions.e2e.ts @@ -64,14 +64,14 @@ describe('web e2e: message IconActions and clocks on settled history', () => { await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBe(1) // Focus-reveal the footers (hover:hover keeps them opacity-hidden until - // hover/focus-within). User has three actions; each finalized assistant - // text node has copy + branch. - const copyButtons = page.getByRole('button', { name: '复制' }) + // hover/focus-within). User has three actions; each turn's last content + // assistant has copy + branch. + const copyButtons = page.getByRole('button', { name: 'Copy' }) await expect.poll(() => copyButtons.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2) await copyButtons.first().focus() - await expect.poll(() => page.getByRole('button', { name: '在新对话中分支' }).count(), { timeout: 5_000 }) + await expect.poll(() => page.getByRole('button', { name: 'Branch into a new conversation' }).count(), { timeout: 5_000 }) .toBeGreaterThanOrEqual(2) - await expect.poll(() => page.getByRole('button', { name: '编辑' }).count(), { timeout: 5_000 }).toBe(1) + await expect.poll(() => page.getByRole('button', { name: 'Edit' }).count(), { timeout: 5_000 }).toBe(1) }, 60_000) it.skipIf(MODE === 'record')('matches the conversation aria golden with IconActions and clocks', async () => { @@ -81,7 +81,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => { }).waitFor({ timeout: 10_000 }) // Keep a footer focused so opacity-hidden actions stay in the a11y tree // as an active/focused control during the capture. - await page.getByRole('button', { name: '复制' }).first().focus() + await page.getByRole('button', { name: 'Copy' }).first().focus() const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)) .split(SEED_ID).join('{{seededId}}') await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE) @@ -91,7 +91,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork')) // Exercise the assistant action specifically; package coverage pins the // user action separately at its own event seq. - await page.getByRole('button', { name: '在新对话中分支' }).last().click() + await page.getByRole('button', { name: 'Branch into a new conversation' }).last().click() await expect.poll( () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)), { timeout: 15_000 }, diff --git a/apps/web/tests/navigation-panes.e2e.ts b/apps/web/tests/navigation-panes.e2e.ts index e88cfa8857..8ffeb25ad1 100644 --- a/apps/web/tests/navigation-panes.e2e.ts +++ b/apps/web/tests/navigation-panes.e2e.ts @@ -23,6 +23,7 @@ import { newEnglishPage, saveFailureShot } from './support.ts' const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/navigation-panes', import.meta.url)) const SEED = join(SNAPSHOT_DIR, 'seed.jsonl') const TRAJECTORY_EXPECTED = join(SNAPSHOT_DIR, 'trajectory.expected.md') +const SEARCH_EXPECTED = join(SNAPSHOT_DIR, 'search-results.expected.md') const TERMINAL_EXPECTED = join(SNAPSHOT_DIR, 'terminal-card.expected.md') const MODE = webSnapshotMode() const SEED_ID = 'navigation-panes-web-e2e' @@ -95,39 +96,39 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { expect(calls.map(e => e.data.name).sort()).toEqual(['bash', 'read', 'read']) }, 400_000) - it.skipIf(MODE === 'record')('opens the seeded session and renders both turns from the log', async () => { - onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-open')) - // Expand the collapsed group row, then open the revealed session row. - const groupRow = page.locator('[role="treeitem"]').first() - await groupRow.waitFor({ timeout: 15_000 }) - await groupRow.click() - const sessionRow = page.locator('[role="treeitem"]').nth(1) - await sessionRow.waitFor({ timeout: 10_000 }) - await sessionRow.click() + it.skipIf(MODE === 'record')('finds an unopened seeded session by message content and opens it', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search')) + const search = page.getByPlaceholder('Search name, keywords', { exact: false }) + // The cold row has not been opened, so only the persisted log can satisfy + // this query. First search lazily reconciles the SQLite content index. + await search.fill('zzzqx-no-such-session') + await page.getByText('No matching sessions').waitFor({ timeout: 30_000 }) + await expect.poll( + () => page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem').count(), + { timeout: 10_000 }, + ).toBe(0) + + await search.fill('WATERFALL') + const resultTree = page.getByRole('tree', { name: 'Search results' }) + const result = resultTree.getByRole('treeitem') + await expect.poll(() => result.count(), { timeout: 30_000 }).toBe(1) + await expect.poll(() => result.getByText('WATERFALL', { exact: false }).count(), { + timeout: 10_000, + }).toBeGreaterThanOrEqual(1) + const snapshot = (await captureStableAria(page, '[class*="listArea"]', scaffold.workspaceCwd)) + .split(SEED_ID).join('{{seededId}}') + await compareOrRefreshGolden(SEARCH_EXPECTED, snapshot, MODE) + + await result.click() + // Search navigation addresses the session, not a specific event, and the + // query remains until the user explicitly clears it. + await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('WATERFALL') await expect.poll(() => page.getByText('FIRST_DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1) await expect.poll(() => page.getByRole('heading', { name: 'Navigation Summary' }).count(), { timeout: 15_000 }).toBe(1) - }, 90_000) - - it.skipIf(MODE === 'record')('filters the sidebar tree by title through the search box', async () => { - onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search')) - // Runs after the session is open: a cold summary carries no title (the - // sidebar shows the cwd basename), and the durable title lands with the - // attach subscription's baseline — which is itself worth pinning: search - // matches the title the user sees, not a hidden cold field. - const search = page.getByPlaceholder('Search name, keywords', { exact: false }) - await expect.poll(() => page.getByText('NavScenario', { exact: false }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1) - // Negative: a garbage query empties the tree (group rows hide too). - await search.fill('zzzqx-no-such-session') - await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBe(0) - // Positive: a title word narrows to the matched session + its group, - // force-expanded by search mode (case-insensitive client-side filter). - await search.fill('navscenario') - await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2) - // Clear restores the unfiltered tree. await page.getByRole('button', { name: 'Clear search' }).click() await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('') await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1) - }, 60_000) + }, 90_000) it.skipIf(MODE === 'record')('renders the trajectory ledger and opens its local record inspector', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-trajectory')) @@ -180,11 +181,13 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { await bashRow.waitFor({ timeout: 15_000 }) const frame = page.locator('[style*="grid-template-columns"]').first() expect(await frame.getAttribute('data-details-collapsed')).toBe('true') + // The row click is the card's expand toggle (unified tool-row + // interaction); it must not drive layout geometry either way. await bashRow.click() await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true') // The card's own controls are outside the summary row and must not open - // details either — the terminal card is read in place. - await page.locator('[data-sample="bash-global"] ~ [data-terminal] [class*="_copyButton_"]').first().click() + // details either — the expanded terminal card is read in place. + await page.locator('[data-sample="bash-global"] ~ div [data-terminal] [class*="_copyButton_"]').first().click() await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true') // Read summaries are host-open file links; they also must not open details. const fileLink = page.locator('[data-variant="read"] button').first() @@ -196,10 +199,14 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-terminal')) await page.getByRole('tab', { name: 'Chat' }).click() - // The card is resident in the keyed bash row (no expand gesture): the - // recorded command's own output sits in the message flow, derived from the - // logged call/result presentations alone. - const card = page.locator('[data-sample="bash-global"] ~ [data-terminal], [data-sample="bash-global"] [data-terminal]').first() + // The card is expand-gated behind the whole-row toggle (the unified + // tool-row interaction): open it if a previous case left it collapsed. + // Expanded, the recorded command's own output sits in the message flow, + // derived from the logged call/result presentations alone. + const bashRow = page.locator('[data-sample="bash-global"]').first() + await bashRow.waitFor({ timeout: 15_000 }) + if (await bashRow.getAttribute('aria-expanded') !== 'true') await bashRow.click() + const card = page.locator('[data-sample="bash-global"] ~ div [data-terminal]').first() await card.waitFor({ timeout: 15_000 }) // Real layout, not jsdom's stub (which computes no geometry at all): // squeeze the output pane below its content width and the line must keep @@ -253,7 +260,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { } }) expect(dot.state).toBe('done') - expect(dot.label).toBe('已完成') + expect(dot.label).toBe('Done') expect(dot.beforePrompt).toBe(true) expect(dot.insideCard).toBe(true) expect(dot.leftOfPrompt).toBe(true) @@ -270,7 +277,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { await page.context().grantPermissions(['clipboard-read', 'clipboard-write']) await card.locator('[class*="_copyButton_"]').first().click() await expect.poll(() => card.locator('[class*="_copyButton_"]').first().textContent(), { timeout: 5_000 }) - .toBe('复制成功') + .toBe('Copied') expect(await page.evaluate(() => navigator.clipboard.readText())).toContain('NAVIGATION_OK') }, 60_000) @@ -279,7 +286,8 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { expect(slotErrors).toEqual([]) expect(tripwire.warnings).toEqual([]) await assertFixtureInventory(SNAPSHOT_DIR, [ - 'seed.jsonl', 'trajectory.expected.md', 'terminal-card.expected.md', + 'seed.jsonl', 'search-results.expected.md', 'trajectory.expected.md', + 'terminal-card.expected.md', ]) }) }) diff --git a/apps/web/tests/queue-actions.e2e.ts b/apps/web/tests/queue-actions.e2e.ts index 1c2ca271aa..42e44c14ca 100644 --- a/apps/web/tests/queue-actions.e2e.ts +++ b/apps/web/tests/queue-actions.e2e.ts @@ -81,7 +81,7 @@ describe('web e2e: queue row actions', () => { await input.fill(text) await input.press('Enter') } - const queueHeader = page.getByRole('button', { name: '2 条排队消息' }) + const queueHeader = page.getByRole('button', { name: '2 queued messages' }) await expect.poll(() => queueHeader.getAttribute('aria-expanded'), { timeout: 10_000 }) .toBe('false') const collapsedSnapshot = await captureStableAria( @@ -92,21 +92,21 @@ describe('web e2e: queue row actions', () => { await compareOrRefreshGolden(COLLAPSED_EXPECTED, collapsedSnapshot, MODE) await queueHeader.click() await expect.poll( - () => page.getByRole('button', { name: '删除排队消息' }).count(), + () => page.getByRole('button', { name: 'Remove queued message' }).count(), { timeout: 10_000 }, ).toBe(2) const editRow = page.getByText(EDIT, { exact: true }).locator('..') - await editRow.getByRole('button', { name: '编辑排队消息' }).click() - const editor = page.getByRole('textbox', { name: '编辑排队消息' }) + await editRow.getByRole('button', { name: 'Edit queued message' }).click() + const editor = page.getByRole('textbox', { name: 'Edit queued message' }) await editor.fill(EDITED) const editingSnapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd) await compareOrRefreshGolden(EDITING_EXPECTED, editingSnapshot, MODE) - await page.getByRole('button', { name: '保存排队消息' }).click() + await page.getByRole('button', { name: 'Save queued message' }).click() await page.getByText(EDITED, { exact: true }).waitFor() const removeRow = page.getByText(REMOVE, { exact: true }).locator('..') - await removeRow.getByRole('button', { name: '删除排队消息' }).click() + await removeRow.getByRole('button', { name: 'Remove queued message' }).click() await expect.poll(() => page.getByText(REMOVE, { exact: true }).count()).toBe(0) const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd) @@ -116,7 +116,7 @@ describe('web e2e: queue row actions', () => { expect(tripwire.warnings).toEqual([]) const editedRow = page.getByText(EDITED, { exact: true }).locator('..') - await editedRow.getByRole('button', { name: '删除排队消息' }).click() + await editedRow.getByRole('button', { name: 'Remove queued message' }).click() await expect.poll(() => page.getByText(EDITED, { exact: true }).count()).toBe(0) await page.getByRole('button', { name: 'Stop generating' }).click() await settled diff --git a/apps/web/tests/scaffold.ts b/apps/web/tests/scaffold.ts index 45fb91e3b0..ff6824d6b1 100644 --- a/apps/web/tests/scaffold.ts +++ b/apps/web/tests/scaffold.ts @@ -218,6 +218,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise { }], }, })) - await page.getByRole('button', { name: '上下文注入' }).waitFor({ timeout: 10_000 }) + await page.getByRole('button', { name: 'Context injection' }).waitFor({ timeout: 10_000 }) }, 60_000) it.skipIf(MODE === 'record')('matches the historical conversation aria golden', async () => { @@ -165,7 +165,7 @@ describe('web e2e: seeded history renders through cold resume', () => { it.skipIf(MODE === 'record')('matches the Figma context disclosure geometry', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-context-injection')) - const disclosure = page.getByRole('button', { name: '上下文注入' }) + const disclosure = page.getByRole('button', { name: 'Context injection' }) expect(await disclosure.getAttribute('aria-expanded')).toBe('false') const collapsedIcon = disclosure.locator('svg').first() const collapsedIconBox = await collapsedIcon.boundingBox() diff --git a/apps/web/tests/smoke-real.e2e.ts b/apps/web/tests/smoke-real.e2e.ts index d2b2d32f21..8bcb8da23a 100644 --- a/apps/web/tests/smoke-real.e2e.ts +++ b/apps/web/tests/smoke-real.e2e.ts @@ -267,6 +267,98 @@ describe('dsh web keyless CLI smoke', () => { } }) + it('retries a partial transport failure through the shipped Web composition', async () => { + requireDist() + const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-retry-')) + const promptMarker = 'WEB_RETRY_REQUEST' + const recoveredMarker = 'WEB_RETRY_RECOVERED' + let mainAttempts = 0 + const provider = createServer((request, response) => { + let body = '' + request.setEncoding('utf8') + request.on('data', (chunk: string) => { body += chunk }) + request.on('end', () => { + const parsed = JSON.parse(body) as { max_tokens?: number; messages?: unknown[] } + const titleRequest = parsed.max_tokens === 64 + const mainRequest = !titleRequest && body.includes(promptMarker) + response.writeHead(200, { 'content-type': 'text/event-stream' }) + if (!mainRequest) { + response.end([ + 'data: {"choices":[{"delta":{"content":"Web retry title"}}]}', + 'data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1}}', + 'data: [DONE]', + '', + ].join('\n\n')) + return + } + mainAttempts++ + if (mainAttempts === 1) { + response.write('data: {"choices":[{"delta":{"content":"WEB_RETRY_DISCARDED"}}]}\n\n') + setTimeout(() => { response.destroy() }, 20) + return + } + response.end([ + `data: {"choices":[{"delta":{"content":"${recoveredMarker}"}}]}`, + 'data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}', + 'data: [DONE]', + '', + ].join('\n\n')) + }) + }) + await new Promise(resolve => provider.listen(0, '127.0.0.1', resolve)) + const address = provider.address() + if (address === null || typeof address === 'string') throw new Error('mock provider did not bind a TCP port') + const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href + const child = spawn( + process.execPath, + ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', '0'], + { + cwd: workspace, + env: { + ...process.env, + DEEPSEEK_API_KEY: 'keyless-web-retry', + DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`, + DSH_HOME: join(workspace, '.dsh'), + TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'), + }, + stdio: ['ignore', 'pipe', 'pipe'], + }, + ) + try { + const baseUrl = await waitForReadyLine(child) + const created = await rpc<{ sessionId: string }>(baseUrl, 'session.create', {}) + await rpc<{ accepted: true }>(baseUrl, 'session.prompt', { + sessionId: created.sessionId, + mode: 'queue', + content: [{ type: 'text', text: promptMarker }], + }) + let page: HistoryPage | undefined + await expect.poll(async () => { + page = await history(baseUrl, created.sessionId) + return hasAssistantMarker(page, recoveredMarker) + }, { timeout: 20_000 }).toBe(true) + if (page === undefined) throw new Error('retry history was not observed') + const retry = page.events.find(({ event }) => event.type === 'llm/retry')?.event + expect(mainAttempts).toBe(2) + expect(retry?.data).toMatchObject({ + turn: 1, + step: 1, + retry: 1, + maxRetries: 2, + failure: { code: 'TRANSPORT' }, + }) + expect(JSON.stringify(page.events)).toContain('WEB_RETRY_DISCARDED') + } finally { + const closed = child.exitCode === null + ? new Promise((resolveClose) => { child.once('close', () => { resolveClose() }) }) + : Promise.resolve() + if (child.exitCode === null) child.kill('SIGTERM') + await closed + await new Promise(resolveClose => provider.close(() => { resolveClose() })) + rmSync(workspace, { recursive: true, force: true }) + } + }, 30_000) + it('DSH_TOOLS_MODE=code collapses the provider wire tools to run_code with the SDK prompt section', async () => { requireDist() const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-code-mode-')) diff --git a/apps/web/tests/snapshots/approval-composer/ui.expected.md b/apps/web/tests/snapshots/approval-composer/ui.expected.md index 469ca78790..ef615091df 100644 --- a/apps/web/tests/snapshots/approval-composer/ui.expected.md +++ b/apps/web/tests/snapshots/approval-composer/ui.expected.md @@ -1,4 +1,4 @@ -- text: 等待审批 -- group "审批详情": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt" -- button "拒绝" -- button "允许一次" +- text: Waiting for approval +- group "Approval details": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt" +- button "Reject" +- button "Allow once" 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 0282a16f80..19845a6f77 100644 --- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md +++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md @@ -5,38 +5,39 @@ - tab "Chat" [selected] - tab "Trajectory" - text: "Using ONE run_code program: run bash `echo CODE_ROUND_OK`, then read the file missing.txt catching its error in the program. Return an object with both outcomes. Then reply DONE and stop. {{clock}}" -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - 'button "Think The user wants me to write a single `run_code` program that:"': - img - img - text: "Think The user wants me to write a single `run_code` program that:" -- button: +- button "Code Run bash echo and catch missing file read": - img - img -- text: Code Run bash echo and catch missing file read + - text: Code Run bash echo and catch missing file read - img -- text: Bash Echo CODE_ROUND_OK Read -- button "missing.txt" +- text: Bash Echo CODE_ROUND_OK +- '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 - text: Think The program ran successfully. Let me now reply DONE as instructed. - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md index 5b51e47cf4..0d0161867c 100644 --- a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md +++ b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md @@ -5,52 +5,54 @@ - tab "Chat" [selected] - tab "Trajectory" - text: "Use only Cordis tools. First call cordis_inspect with what \"temporary\". Then call cordis_mount with this exact code: \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\". Read its returned id and call cordis_unmount with that exact id. After all three calls succeed, reply exactly CORDIS_UI_DONE and stop. {{clock}}" -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to:": - img - img - text: "Think The user wants me to:" -- button: +- button "Inspect temporary": - img - img -- text: Inspect temporary + - text: Inspect temporary - 'button "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."': - img - img - text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code." -- button [expanded]: +- 'button "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }" [expanded]': - img -- text: Mount temporary Plugin typescript -- button "复制" + - text: "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }" +- text: typescript +- button "Copy" - code: "return { name: \"snapshot-noop\", apply(ctx) {} }" +- text: OUT Temporary Plugin dyn-1 is running (plugin "snapshot-noop"; available until unmounted or DSH restarts). +- button "Inspect" - 'button "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."': - img - img - text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id." -- button: +- button "Unmount temporary Plugin dyn-1": - img - img -- text: Unmount temporary Plugin dyn-1 + - text: Unmount temporary Plugin dyn-1 - button "Think All three calls succeeded. I should now reply exactly \"CORDIS_UI_DONE\" and stop.": - img - img - text: Think All three calls succeeded. I should now reply exactly "CORDIS_UI_DONE" and stop. - paragraph: CORDIS_UI_DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md index 49c7958292..7b181553b7 100644 --- a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md +++ b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md @@ -5,35 +5,34 @@ - tab "Chat" [selected] - tab "Trajectory" - text: "Use the bash tool to run exactly: echo WEB_E2E_OK. Then reply with the single word DONE and stop. {{clock}}" -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to run a simple bash command and reply with \"DONE\".": - img - img - text: Think The user wants me to run a simple bash command and reply with "DONE". -- img -- text: Bash Echo the test string 已完成 workspace echo WEB_E2E_OK -- button "复制" -- text: WEB_E2E_OK +- button "Bash Echo the test string": + - img + - img + - text: Bash Echo the test string - button "Think The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\".": - img - img - text: Think The command executed successfully and output "WEB_E2E_OK". I just need to reply with "DONE". - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - 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 new file mode 100644 index 0000000000..47ba98cf05 --- /dev/null +++ b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md @@ -0,0 +1,6 @@ +- listbox "Trigger suggestions": + - text: Commands + - option "goal set or view the goal for a long-running task" [selected] + - 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 65abda0dba..b45b0bfc0e 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md @@ -26,14 +26,13 @@ - text: workspace - img - textbox "Describe what you want to build" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img - button "Send message" [disabled] -- text: 详情 -- button "关闭详情" -- text: 点击消息流中的工具行查看详情 +- text: Details +- button "Close details" +- text: Click a tool row in the message flow to view its details diff --git a/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md new file mode 100644 index 0000000000..8be9ff8b86 --- /dev/null +++ b/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md @@ -0,0 +1,39 @@ +- button "New session" +- button "Collapse sidebar": + - img +- button "New session": + - img + - text: New Session +- text: Workspaces +- button "Group by": + - img +- button "Create workspace": + - img +- button "Search sessions": + - img +- textbox "Search name, keywords..." +- tree "Sessions": + - treeitem "workspace 1 session" [expanded]: + - img + - text: workspace 1 session + - treeitem "New Session now" [selected] +- button "Settings": + - img + - text: Settings +- text: Let's start building +- button "Choose workspace": + - img + - text: workspace + - img +- textbox "Describe what you want to build" +- button "Commands": + - img +- 'button "Access mode, current: Danger Full Access"': Danger Full Access +- button "Plan mode on, press to turn off": Plan +- button "Select model, current deepseek-v4-flash": + - text: deepseek-v4-flash + - img +- button "Send message" [disabled] +- text: Details +- button "Close details" +- text: Click a tool row in the message flow to view its details diff --git a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md index 45e3514fa4..9e2499c974 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md @@ -5,27 +5,26 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with the single word LIGHTHOUSE and stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to reply with a single word. Let me comply.": - img - img - text: Think The user wants me to reply with a single word. Let me comply. - paragraph: LIGHTHOUSE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/live-interactions/cancel.expected.md b/apps/web/tests/snapshots/live-interactions/cancel.expected.md index 4323c94285..c826bd6584 100644 --- a/apps/web/tests/snapshots/live-interactions/cancel.expected.md +++ b/apps/web/tests/snapshots/live-interactions/cancel.expected.md @@ -5,24 +5,23 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with a one-sentence description of event sourcing, then stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - paragraph: partial -- text: 已停止 -- button "复制": +- text: Stopped +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md index 1d78e91c73..3de32d7e7d 100644 --- a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md +++ b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md @@ -5,17 +5,16 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with a one-sentence description of event sourcing, then stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/live-interactions/retry.expected.md b/apps/web/tests/snapshots/live-interactions/retry.expected.md index 6a9c808342..605a75a0f7 100644 --- a/apps/web/tests/snapshots/live-interactions/retry.expected.md +++ b/apps/web/tests/snapshots/live-interactions/retry.expected.md @@ -5,27 +5,28 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with a one-sentence description of event sourcing, then stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img +- group: + - status: Retried model request (1/2) · {{duration}} - button "Think The user is asking for a one-sentence description of event sourcing. This is a straightforward knowledge question that doesn't require any skill loading or tool calls.": - img - img - text: Think The user is asking for a one-sentence description of event sourcing. This is a straightforward knowledge question that doesn't require any skill loading or tool calls. - paragraph: Event sourcing is a pattern where all changes to an application's state are stored as an immutable, append-only sequence of events, rather than persisting only the current state, enabling full auditability, temporal queries, and event-driven architectures. -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/message-actions/ui.expected.md b/apps/web/tests/snapshots/message-actions/ui.expected.md index 19ba02d99d..d423f6f53a 100644 --- a/apps/web/tests/snapshots/message-actions/ui.expected.md +++ b/apps/web/tests/snapshots/message-actions/ui.expected.md @@ -4,39 +4,42 @@ - tablist: - tab "Chat" [selected] - tab "Trajectory" -- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. {{clock}}" -- button "复制": +- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. 7/25 {{clock}}" +- button "Copy": - img -- tooltip "复制" -- button "在新对话中分支": +- tooltip "Copy" +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.": - 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 - text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed. - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- text: {{clock}} +- text: 7/25 {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current deepseek-v4-flash": - text: deepseek-v4-flash - img diff --git a/apps/web/tests/snapshots/navigation-panes/search-results.expected.md b/apps/web/tests/snapshots/navigation-panes/search-results.expected.md new file mode 100644 index 0000000000..49de115594 --- /dev/null +++ b/apps/web/tests/snapshots/navigation-panes/search-results.expected.md @@ -0,0 +1,2 @@ +- tree "Search results": + - 'treeitem "{{workspace}} {{workspace}} ## Navigation Summary - alpha nav - beta nav ``` echo WATERFALL ```"' diff --git a/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md b/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md index 298bf764b6..464e48628e 100644 --- a/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md +++ b/apps/web/tests/snapshots/navigation-panes/terminal-card.expected.md @@ -1,3 +1,3 @@ -- text: 已完成 {{workspace}} echo NAVIGATION_OK -- button "复制" +- text: Done {{workspace}} echo NAVIGATION_OK +- button "Copy" - text: NAVIGATION_OK diff --git a/apps/web/tests/snapshots/plan-review/approved.expected.md b/apps/web/tests/snapshots/plan-review/approved.expected.md index cb905c0b8b..915e1b3e40 100644 --- a/apps/web/tests/snapshots/plan-review/approved.expected.md +++ b/apps/web/tests/snapshots/plan-review/approved.expected.md @@ -6,11 +6,11 @@ - tab "Trajectory" - img - text: "plan Plan mode on. Use /plan off to leave. Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. {{clock}}" -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - 'button "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."': - img @@ -20,30 +20,24 @@ - text: Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with - code: exit_plan_mode - text: . -- button "复制": - - img -- button "在新对话中分支": - - img -- text: {{clock}} -- button: +- 'button "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"': - img - img -- text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI" + - text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI" - 'button "Think The plan was approved. The user''s last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."': - img - img - text: "Think The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop." - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/question-composer/answered.expected.md b/apps/web/tests/snapshots/question-composer/answered.expected.md index 36752c783a..49125fbcdd 100644 --- a/apps/web/tests/snapshots/question-composer/answered.expected.md +++ b/apps/web/tests/snapshots/question-composer/answered.expected.md @@ -5,35 +5,34 @@ - tab "Chat" [selected] - tab "Trajectory" - text: "Use the ask_user_question tool to ask me exactly one question with id \"color\", question \"Which color do you prefer?\", header \"Pick one\", and two options: label \"Blue\" with description \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\", and label \"Green\" with description \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\" After I answer, reply with the single word DONE and stop. {{clock}}" -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.": - img - img - text: Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that. -- button: +- button "Ask question 1/1 answered": - img - img -- text: Ask question 1/1 answered + - text: Ask question 1/1 answered - button "Think The user answered \"Blue\". I should now reply with the single word DONE and stop.": - img - img - text: Think The user answered "Blue". I should now reply with the single word DONE and stop. - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/queue-actions/collapsed.expected.md b/apps/web/tests/snapshots/queue-actions/collapsed.expected.md index cdbf6fc64b..c96454ed8f 100644 --- a/apps/web/tests/snapshots/queue-actions/collapsed.expected.md +++ b/apps/web/tests/snapshots/queue-actions/collapsed.expected.md @@ -5,19 +5,18 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with a one-sentence description of event sourcing, then stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - paragraph: partial -- button "2 条排队消息" +- button "2 queued messages" - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/queue-actions/editing.expected.md b/apps/web/tests/snapshots/queue-actions/editing.expected.md index cf287b5006..3e4864227d 100644 --- a/apps/web/tests/snapshots/queue-actions/editing.expected.md +++ b/apps/web/tests/snapshots/queue-actions/editing.expected.md @@ -5,32 +5,31 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with a one-sentence description of event sourcing, then stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - paragraph: partial -- button "2 条排队消息" [disabled] [expanded] +- button "2 queued messages" [disabled] [expanded] - list: - listitem: - text: Queue item to remove - - button "编辑排队消息": + - button "Edit queued message": - img - - button "删除排队消息": + - button "Remove queued message": - img - listitem: - - textbox "编辑排队消息": Edited queue item - - button "保存排队消息": + - textbox "Edit queued message": Edited queue item + - button "Save queued message": - img - - button "取消编辑": + - button "Cancel editing": - img - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/snapshots/queue-actions/ui.expected.md b/apps/web/tests/snapshots/queue-actions/ui.expected.md index 919617bdab..9daac19be5 100644 --- a/apps/web/tests/snapshots/queue-actions/ui.expected.md +++ b/apps/web/tests/snapshots/queue-actions/ui.expected.md @@ -5,25 +5,24 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Reply with a one-sentence description of event sourcing, then stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - paragraph: partial - list: - listitem: - text: Edited queue item - - button "编辑排队消息": + - button "Edit queued message": - img - - button "删除排队消息": + - button "Remove queued message": - img - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img 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 87ffd9fc55..f722bb36ae 100644 --- a/apps/web/tests/snapshots/seeded-history/command-row.expected.md +++ b/apps/web/tests/snapshots/seeded-history/command-row.expected.md @@ -4,44 +4,47 @@ - tablist: - tab "Chat" [selected] - tab "Trajectory" -- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. {{clock}}" -- button "复制": +- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. 7/25 {{clock}}" +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.": - 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 - text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed. - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- text: {{clock}} -- button "上下文注入": +- text: 7/25 {{clock}} +- button "Context injection": - img - img - - text: 上下文注入 + - text: Context injection - img - text: permission preset workspace-write - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Workspace Write"': Workspace Write -- button "Plan mode off, press to turn on": Plan off - button "Select model, current deepseek-v4-flash": - text: deepseek-v4-flash - img diff --git a/apps/web/tests/snapshots/seeded-history/ui.expected.md b/apps/web/tests/snapshots/seeded-history/ui.expected.md index efc43a272e..61d3996414 100644 --- a/apps/web/tests/snapshots/seeded-history/ui.expected.md +++ b/apps/web/tests/snapshots/seeded-history/ui.expected.md @@ -4,42 +4,45 @@ - tablist: - tab "Chat" [selected] - tab "Trajectory" -- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. {{clock}}" -- button "复制": +- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. 7/25 {{clock}}" +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.": - 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 - text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed. - paragraph: DONE -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- text: {{clock}} -- button "上下文注入": +- text: 7/25 {{clock}} +- button "Context injection": - img - img - - text: 上下文注入 + - text: Context injection - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current deepseek-v4-flash": - text: deepseek-v4-flash - img diff --git a/apps/web/tests/snapshots/steering/mid-steer.expected.md b/apps/web/tests/snapshots/steering/mid-steer.expected.md index 28127fd73b..31c5b2b1dc 100644 --- a/apps/web/tests/snapshots/steering/mid-steer.expected.md +++ b/apps/web/tests/snapshots/steering/mid-steer.expected.md @@ -5,20 +5,20 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "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.": - 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. -- button: +- button "Ask question waiting": - img - img -- text: Ask question waiting + - text: Ask question waiting - region "Ready to continue?": - text: Checkpoint - heading "Ready to continue?" [level=2] diff --git a/apps/web/tests/snapshots/steering/settled.expected.md b/apps/web/tests/snapshots/steering/settled.expected.md index 5efbcf385d..d84645270c 100644 --- a/apps/web/tests/snapshots/steering/settled.expected.md +++ b/apps/web/tests/snapshots/steering/settled.expected.md @@ -5,35 +5,35 @@ - tab "Chat" [selected] - tab "Trajectory" - text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. {{clock}} -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img -- button "编辑": +- button "Edit": - img - button "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.": - 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. -- button: +- button "Ask question 1/1 answered": - img - img -- text: "Ask question 1/1 answered 插话 Interjection: include the word BANANA in your final reply." + - text: Ask question 1/1 answered +- text: "Interjection Interjection: include the word BANANA in your final reply." - button "Think The user selected \"Yes\" and wants me to include the word \"BANANA\" in my final reply. Let me acknowledge their answer.": - img - img - text: Think The user selected "Yes" and wants me to include the word "BANANA" in my final reply. Let me acknowledge their answer. - paragraph: Great, let's move forward. BANANA! -- button "复制": +- button "Copy": - img -- button "在新对话中分支": +- button "Branch into a new conversation": - img - text: {{clock}} - textbox "Message the agent" -- button "Add attachment": +- button "Commands": - img - 'button "Access mode, current: Danger Full Access"': Danger Full Access -- button "Plan mode off, press to turn on": Plan off - button "Select model, current DeepSeek-V4-Flash": - text: DeepSeek-V4-Flash - img diff --git a/apps/web/tests/steering.e2e.ts b/apps/web/tests/steering.e2e.ts index b36e001dd1..3cbae0b9ee 100644 --- a/apps/web/tests/steering.e2e.ts +++ b/apps/web/tests/steering.e2e.ts @@ -121,9 +121,9 @@ describe('web e2e: mid-turn steering lands durably and visibly', () => { // exists yet and no interjection bubble renders — the composer still // blocks, alone. The DOM is stable here (no further SSE frames can // arrive until the question is answered), making this state capturable. - expect(await page.getByText('插话').count()).toBe(0) + expect(await page.getByText('Interjection', { exact: true }).count()).toBe(0) expect(await page.getByText(STEER, { exact: true }).count()).toBe(0) - expect(await page.getByRole('button', { name: '编辑排队消息' }).count()).toBe(0) + expect(await page.getByRole('button', { name: 'Edit queued message' }).count()).toBe(0) const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd) await compareOrRefreshGolden(MID_EXPECTED, snapshot, MODE) } @@ -157,7 +157,7 @@ describe('web e2e: mid-turn steering lands durably and visibly', () => { // Visible: the badged interjection bubble plus the reply that obeys it // (steer text + final reply each contain the marker word). - await expect.poll(() => page.getByText('插话').count(), { timeout: 15_000 }).toBe(1) + await expect.poll(() => page.getByText('Interjection', { exact: true }).count(), { timeout: 15_000 }).toBe(1) await expect.poll(() => page.getByText('Interjection:', { exact: false }).count(), { timeout: 10_000 }).toBe(1) await expect.poll(() => page.getByText('BANANA', { exact: false }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2) expect(await page.locator('[data-question-key]').count()).toBe(0) diff --git a/docs/architecture.i18n.yaml b/docs/architecture.i18n.yaml index d7054b8b3c..470ae7f7cf 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: bfea67b9f83958e16b58e63b99e326349f6eff15 -architecture.zh.md: c2fd6cdd84ad2f6435faebffa0c4c1a6da0ade96 +architecture.md: c6e14fac6436b2401509aaf8bb20ccaf29aeeafc +architecture.zh.md: 2e85f25eb3f40f58c8ffbfa7691bb793638c8b37 diff --git a/docs/architecture.md b/docs/architecture.md index bfea67b9f8..c6e14fac64 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -96,7 +96,7 @@ forever: assemble system prompt and tool schemas snapshot the derived messages (the reconstruction boundary) 'step/start' - agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound) + agent/request (config only) -> prepare adapter defaults/provenance under turn signal -> log request/header -> llm/stream (frozen, registration-bound) 'assistant/chunk' 'assistant/message' schedule tool calls by ctx.tools.executionMode: @@ -145,7 +145,7 @@ Each agent owns scoped `agent.ctx`; shared storage overlays its tool, prompt, an The session log is authoritative. `deriveMessages()` projects model history; raw `assistant/chunk` events preserve replay and UI fidelity. Fork, resume, transcript rendering, telemetry, and persistence derive from this stream. -**Model-visible ⟺ logged**: messages at `step/start` plus the folded `request/header` reconstruct every request; package-owned `dsh-agent-loop/invariant` can assert this through `ctx.invariants` ([reconstructability](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)). +**Model-visible ⟺ logged**: messages at `step/start` plus the folded `request/header` reconstruct every request; the header also marks adapter-materialized defaults so the next proposal can discard them and resolve the selected route without losing explicit conversation settings. Package-owned `dsh-agent-loop/invariant` can assert reconstructability through `ctx.invariants` ([reconstructability](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)). 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)). diff --git a/docs/architecture.zh.md b/docs/architecture.zh.md index c2fd6cdd84..2e85f25eb3 100644 --- a/docs/architecture.zh.md +++ b/docs/architecture.zh.md @@ -96,7 +96,7 @@ forever: assemble system prompt and tool schemas snapshot the derived messages (the reconstruction boundary) 'step/start' - agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound) + agent/request (config only) -> prepare adapter defaults/provenance under turn signal -> log request/header -> llm/stream (frozen, registration-bound) 'assistant/chunk' 'assistant/message' schedule tool calls by ctx.tools.executionMode: @@ -145,7 +145,7 @@ idle inject: 会话日志是权威依据。`deriveMessages()` 投影出模型历史；原始 `assistant/chunk` 事件保证回放和 UI 保真。fork、恢复、transcript（文本记录）渲染、遥测和持久化均派生自该事件流。 -**模型可见 ⟺ 已记录**：`step/start` 时的消息与折叠后的 `request/header` 可以重建每个请求；该包的 `dsh-agent-loop/invariant` 可通过 `ctx.invariants` 断言这一点（[可重建性](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)）。 +**模型可见 ⟺ 已记录**：`step/start` 时的消息与折叠后的 `request/header` 可以重建每个请求；该 header 还会标记适配器填入的默认值，使下一次提议可以丢弃这些值并解析所选路由，同时不丢失显式对话设置。该包的 `dsh-agent-loop/invariant` 可通过 `ctx.invariants` 断言可重建性（[可重建性](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)）。 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)）。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index e8600f8e55..3fb1e027ff 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -638,7 +638,9 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Default thinking effort (default `high`); `off` disables thinking per request. */ reasoningEffort?: 'off' | 'high' | 'max' - /** Positive context capacity used when the selected model has no exact value. */ + /** Default per-request output cap (default 256,000); explicit request values win. */ + maxTokens?: number + /** Positive context capacity used when the selected model has no exact value (default 1,000,000). */ defaultContextWindow?: number /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */ models?: DeepSeekCatalogModel[] @@ -663,7 +665,7 @@ export interface DeepSeekCatalogModel { Depends on: [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) -Source: [`packages/llm/llm-deepseek/src/index.ts:50`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:60`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` @@ -774,7 +776,7 @@ Requires: `agents` export type Config = Readonly> ``` -Source: [`packages/llm/llm-retry/src/index.ts:45`](../packages/llm/llm-retry/src/index.ts) +Source: [`packages/llm/llm-retry/src/index.ts:47`](../packages/llm/llm-retry/src/index.ts) ## `@deepseek-ai/dsh-lsp-local` @@ -1142,11 +1144,13 @@ Requires: `sessions` /** Combined session-query configuration backed by SQLite full-text search. */ export interface Config extends SessionQueryConfig { /** - * Dedicated derived-index path; `:memory:` is supported for tests. Missing - * directories and database files are created owner-only on POSIX filesystems; - * existing modes are preserved. + * Dedicated derived-index path; `:memory:` is supported for ephemeral + * indexes. Missing directories and database files are created owner-only on + * POSIX filesystems; existing modes are preserved. */ path: string + /** Open the SQLite module and handle at service activation or the first search. Defaults to `startup`. */ + openAt?: OpenAt /** SQLite journal mode. Defaults to `wal`. */ journalMode?: JournalMode /** Page size when a request omits `limit`. At most `Number.MAX_SAFE_INTEGER - 1`; defaults to 20. */ @@ -1159,13 +1163,16 @@ export interface Config extends SessionQueryConfig { persistedInspectConcurrency?: number } +/** SQLite module/handle opening phase. */ +export type OpenAt = 'startup' | 'first-search' + /** Supported SQLite journal modes. */ export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` Depends on: [`SessionQueryConfig`](../packages/session-query/session-query/src/index.ts) -Source: [`packages/session-query/session-query-sqlite/src/index.ts:86`](../packages/session-query/session-query-sqlite/src/index.ts) +Source: [`packages/session-query/session-query-sqlite/src/index.ts:89`](../packages/session-query/session-query-sqlite/src/index.ts) ## `@deepseek-ai/dsh-session-reference` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 541cbb6016..8eed1dab5d 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -328,7 +328,7 @@ Source: [`packages/bash/tool-bash/src/index.ts:104`](../../packages/bash/tool-ba ## `ctx.clientModuleHost` — `ClientModuleHostService` -The web plugin table service: incremental dshClient scan + wire composition + bundle route + index tap. Construction runs the activation scan synchronously — a malformed declaration or missing bundle among the already-loaded entries aggregates into one loud throw (FAILED fiber; the boot sweep reports it). +The web plugin table service: incremental dshClient scan + wire composition + bundle route + index tap. Construction runs the activation scan synchronously — a malformed declaration or missing bundle among the already-loaded entries aggregates into one loud throw (FAILED fiber; the boot activation audit reports it). ```ts cordis-catalog /** @@ -368,7 +368,7 @@ onRebuilt(listener: (id: string, rev: string) => void): () => void onGraphChanged(listener: () => void): () => void ``` -Source: [`packages/client/modules/src/index.ts:143`](../../packages/client/modules/src/index.ts) +Source: [`packages/client/modules/src/index.ts:184`](../../packages/client/modules/src/index.ts) ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam) @@ -844,7 +844,7 @@ async resolveModelInfo( provider: string, model: string, signal?: AbortSignal, ) /** * Validate a conversation call config against its exact model capability and - * materialize an adapter-configured default. Unsupported explicit efforts + * materialize adapter-configured defaults. Unsupported explicit efforts * reject before provider I/O; no clamping or aliasing is performed. This * standalone query does not bind a later dispatch; use {@link prepareCall} * when logging and streaming must share one adapter registration. @@ -882,7 +882,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [AdapterRegistrationHandle](../core-data-structures/core.md) · [GenerateOptions](../core-data-structures/core.md) · [LlmAdapter](../core-data-structures/llm-streaming.md) · [LlmCallConfig](../core-data-structures/core.md) · [LlmConfigurableProvider](../core-data-structures/core.md) · [LlmModelInfo](../core-data-structures/core.md) · [LlmProviderInfo](../core-data-structures/core.md) · [LlmResolvedModelInfo](../core-data-structures/core.md) · [PreparedLlmCall](../core-data-structures/llm-streaming.md) · [ResolvedRetryPolicy](../core-data-structures/llm-streaming.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:227`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:229`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` @@ -1652,7 +1652,7 @@ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Types: [CreateSessionOptions](../core-data-structures/persistence.md) · [Session](../core-data-structures/session.md) · [SessionId](../core-data-structures/core.md) -Source: [`packages/core/session/src/index.ts:714`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:739`](../../packages/core/session/src/index.ts) ## `ctx.sessionTitle` — `SessionTitleService` diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml index 9a5d7a3f3b..82ef063bec 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: 7176a6949211566c5f162bc3289189d047c6fc85 -core.zh.md: de06529d602fc0871688d0b8e038c8d1c3ac2ef7 +core.md: 5ed6a47c5488005d41fdac9349e4c9d1c550d13d +core.zh.md: 1b16b7ec994c6fccd6fedf1508dec6b1b057edf3 diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 7176a69492..5ed6a47c54 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -259,7 +259,7 @@ interface LlmModelInfo { } ``` -Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity and reasoning choices share one exact-model result so consumers do not repeat authoritative model resolution. +Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity, adapter call defaults, and reasoning choices share one exact-model result so consumers do not repeat authoritative model resolution. ```ts type-equiv /** Provider-owned context capacity for one exact provider/model route. */ @@ -306,6 +306,8 @@ interface LlmModelReasoningInfo { interface LlmResolvedModelInfo extends LlmModelInfo { /** Provider-owned context capacity when known. */ context?: LlmModelContext + /** Adapter-configured per-request output cap materialized when callers omit one. */ + defaultMaxTokens?: number /** Adapter-owned selectable reasoning levels when exposed. */ reasoning?: LlmModelReasoningInfo } @@ -392,9 +394,9 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition` ### The request envelope: `LlmCallConfig` and the logged header -The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, and authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset) through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md). +The loop builds each request from logged state. `EpochHeader` records call config, adapter-default provenance, rendered prompt, and authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset) through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md). -`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, reasoning effort, or sampling. After the waterfall, the loop prepares the exact model capability under the turn signal, rejects unsupported explicit effort ids without clamping, materializes an adapter-configured default, and logs the effective value. The prepared call keeps one adapter registration through dispatch. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests. +`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, reasoning effort, or sampling. Before the waterfall, the loop removes values marked as adapter defaults so exact-model preparation materializes the selected route's current values; unmarked explicit settings remain in the proposal. After the waterfall, preparation rejects unsupported explicit effort ids without clamping and logs the effective config plus provenance under the turn signal. The prepared call keeps one adapter registration through dispatch. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests. On the wire, a loop-built request reads the `system` slot (the rendered prompt assembly) followed by the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The dev invariant recomputes exactly this equation against every loop-built request. @@ -417,6 +419,17 @@ interface LlmCallConfig { } ``` +```ts type-equiv +/** + * Effective config fields supplied by exact-model adapter resolution rather + * than by the caller's request proposal. + */ +interface LlmCallConfigAdapterDefaults { + reasoningEffort?: true + maxTokens?: true +} +``` + ## Sessions A `Session` is an **append-only log** of typed `SessionEvent`s — the single source of truth. The LLM message history is *derived* from the log (`deriveMessages()`), not stored separately. The event vocabulary derives from `SessionEventMap`: @@ -658,7 +671,7 @@ 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 leaves the provider default in control. 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. `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 de06529d60..1b16b7ec99 100644 --- a/docs/core-data-structures/core.zh.md +++ b/docs/core-data-structures/core.zh.md @@ -265,7 +265,7 @@ interface LlmModelInfo { } ``` -对正确性敏感的元数据与参考目录分开解析，并归服务该确切路由的适配器所有。上下文容量和推理选项共用同一个确切模型结果，消费方因而无需重复执行权威模型解析。 +对正确性敏感的元数据与参考目录分开解析，并归服务该确切路由的适配器所有。上下文容量、适配器调用默认值和推理选项共用同一个确切模型结果，消费方因而无需重复执行权威模型解析。 ```ts type-equiv /** Provider-owned context capacity for one exact provider/model route. */ @@ -312,6 +312,8 @@ interface LlmModelReasoningInfo { interface LlmResolvedModelInfo extends LlmModelInfo { /** Provider-owned context capacity when known. */ context?: LlmModelContext + /** Adapter-configured per-request output cap materialized when callers omit one. */ + defaultMaxTokens?: number /** Adapter-owned selectable reasoning levels when exposed. */ reasoning?: LlmModelReasoningInfo } @@ -398,9 +400,9 @@ interface ToolSchema { ### 请求信封：`LlmCallConfig` 与记录的 header -循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词以及权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）。结合派生历史，请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。 +循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、适配器默认值来源、渲染后的提示词以及权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）。结合派生历史，请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。 -`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型、推理强度或采样参数。waterfall 结束后，循环会在轮次信号控制下完成确切模型的能力准备，拒绝显式指定但不受支持的推理强度 ID（不自动调整），填入适配器配置的默认值，并记录最终生效值。准备完成的调用直至分派完成始终持有同一项适配器注册。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。 +`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型、推理强度或采样参数。waterfall 开始前，循环会移除标记为适配器默认值的值，使确切模型准备过程填入所选路由的当前值；未带标记的显式设置仍保留在提议中。waterfall 结束后，准备过程会在轮次信号控制下拒绝显式指定但不受支持的推理强度 ID（不自动调整），并记录生效配置及其来源。准备完成的调用直至分派完成始终持有同一项适配器注册。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。 在协议格式上，循环构建的请求先读取 `system` 槽位（渲染后的提示词组装），再读取派生历史——边界快照，其尾部在轮次首步是最新的 `user/message`，在后续步骤是上一步的工具结果。开发不变式针对每个循环构建的请求精确重算此等式。 @@ -423,6 +425,17 @@ interface LlmCallConfig { } ``` +```ts type-equiv +/** + * Effective config fields supplied by exact-model adapter resolution rather + * than by the caller's request proposal. + */ +interface LlmCallConfigAdapterDefaults { + reasoningEffort?: true + maxTokens?: true +} +``` + ## 会话 `Session` 是一份类型化 `SessionEvent` 的**仅追加日志**——唯一的真源。LLM（大语言模型）消息历史从日志*派生*（`deriveMessages()`），而非单独存储。事件词汇从 `SessionEventMap` 派生： @@ -666,7 +679,7 @@ 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；省略时由提供方默认值控制。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。`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/core-data-structures/llm-streaming.i18n.yaml b/docs/core-data-structures/llm-streaming.i18n.yaml index c3924f184b..7e1ba8b7bb 100644 --- a/docs/core-data-structures/llm-streaming.i18n.yaml +++ b/docs/core-data-structures/llm-streaming.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/llm-streaming.md -llm-streaming.md: 6811611768a0ec577360a8ff82792899cf3b8fec -llm-streaming.zh.md: 35374af6a20086f15384840689dba5aa24351750 +llm-streaming.md: e7500a7985ea1916e206c41e05855701b48fcf00 +llm-streaming.zh.md: 2b61815f2730afdfb93bc06b8ee8925d2f4cac25 diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index 6811611768..e7500a7985 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -162,13 +162,15 @@ declare class BlockAssembler { ## The seam -`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerRetryPolicy()` is captured per route with normal defaults, while `providerInfo()` and asynchronous `listModels()` feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or capability, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmService.resolveModelInfo()` validates and detaches the aggregate. The service validates and materializes reasoning through `resolveCallConfig()` at the final adapter boundary, so direct calls cannot bypass unsupported-effort rejection; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). +`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerRetryPolicy()` is captured per route with normal defaults, while `providerInfo()` and asynchronous `listModels()` feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity, an adapter-configured `defaultMaxTokens`, and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or provider-owned behavior, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmService.resolveModelInfo()` validates and detaches the aggregate. At the final adapter boundary, `resolveCallConfig()` materializes the output default only when `maxTokens` is absent and validates and materializes reasoning, so direct calls cannot bypass either configured behavior; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). ```ts type-equiv /** One model call whose config and adapter registration were resolved together. */ interface PreparedLlmCall { /** Detached, deep-frozen config with any adapter-owned default materialized. */ readonly config: LlmCallConfig + /** Config fields materialized by the captured adapter rather than proposed by the caller. */ + readonly adapterDefaults: LlmCallConfigAdapterDefaults /** * Dispatch this call once through the registration captured during * preparation. The request's call-config fields must match {@link config}; @@ -215,7 +217,7 @@ declare abstract class LlmAdapter { * @param model - exact model id passed to {@link GenerateOptions.model}. * @param _signal - cancellation for this exact-model lookup; asynchronous * implementations must settle promptly after it aborts. - * @returns provider/model identity plus any context and reasoning metadata. + * @returns provider/model identity plus any context, call-default, and reasoning metadata. */ resolveModel( provider: string, diff --git a/docs/core-data-structures/llm-streaming.zh.md b/docs/core-data-structures/llm-streaming.zh.md index 35374af6a2..2b61815f27 100644 --- a/docs/core-data-structures/llm-streaming.zh.md +++ b/docs/core-data-structures/llm-streaming.zh.md @@ -162,13 +162,15 @@ declare class BlockAssembler { ## seam -`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerRetryPolicy()` 会按路由捕获并填入 normal 默认值，`providerInfo()` 与异步 `listModels()` 方法则为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、由模型持有的有序推理强度 ID 和部署默认值；字段缺失表示元数据或能力不可用，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmService.resolveModelInfo()` 会校验聚合结果并返回分离值。服务通过最终适配器边界的 `resolveCallConfig()` 校验推理强度并填入默认值，因此直接调用也无法绕过对不支持推理强度的拒绝；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。 +`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerRetryPolicy()` 会按路由捕获并填入 normal 默认值，`providerInfo()` 与异步 `listModels()` 方法则为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、适配器配置的 `defaultMaxTokens`、由模型持有的有序推理强度 ID 和部署默认值；字段缺失表示元数据不可用或保留提供方持有的行为，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmService.resolveModelInfo()` 会校验聚合结果并返回分离值。在最终适配器边界，`resolveCallConfig()` 仅在 `maxTokens` 缺失时填入输出默认值，并校验和填入推理强度，因此直接调用也无法绕过任何一项已配置行为；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。 ```ts type-equiv /** One model call whose config and adapter registration were resolved together. */ interface PreparedLlmCall { /** Detached, deep-frozen config with any adapter-owned default materialized. */ readonly config: LlmCallConfig + /** Config fields materialized by the captured adapter rather than proposed by the caller. */ + readonly adapterDefaults: LlmCallConfigAdapterDefaults /** * Dispatch this call once through the registration captured during * preparation. The request's call-config fields must match {@link config}; @@ -215,7 +217,7 @@ declare abstract class LlmAdapter { * @param model - exact model id passed to {@link GenerateOptions.model}. * @param _signal - cancellation for this exact-model lookup; asynchronous * implementations must settle promptly after it aborts. - * @returns provider/model identity plus any context and reasoning metadata. + * @returns provider/model identity plus any context, call-default, and reasoning metadata. */ resolveModel( provider: string, diff --git a/docs/core-data-structures/session.i18n.yaml b/docs/core-data-structures/session.i18n.yaml index 17c4ab68ba..04ad28d9b5 100644 --- a/docs/core-data-structures/session.i18n.yaml +++ b/docs/core-data-structures/session.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/session.md -session.md: 5389c2e2114094df5afdca25afd904b2cbbf8270 -session.zh.md: 29c4853213dfc886155e3f8d0991fa161e05c71a +session.md: e70add64198efd57538d1a014f24533d5197e531 +session.zh.md: d83cba6fbcb4ffcf137203d5e3e55045f1444a8b diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 5389c2e211..e70add6419 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -144,7 +144,7 @@ interface TodoItem { ### The request header event: `request/header` -The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas) — is logged session state, so every conversation request is a pure function of the log (the reconstructability Agent Note). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message. +The request envelope — the `EpochHeader` (call config + adapter-default provenance + rendered system prompt + assembled tool schemas) — is logged session state, so every conversation request is a pure function of the log (the reconstructability Agent Note). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message. ```ts type-equiv /** @@ -155,6 +155,8 @@ The request envelope — the `EpochHeader` (call config + rendered system prompt interface EpochHeader { /** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */ config: LlmCallConfig + /** Effective config fields materialized from the exact adapter rather than proposed by a caller. */ + adapterDefaults?: LlmCallConfigAdapterDefaults /** Rendered system prompt text; absent for a system-less request. */ system?: string /** Assembled tool schemas; absent for a tool-less request. */ diff --git a/docs/core-data-structures/session.zh.md b/docs/core-data-structures/session.zh.md index 29c4853213..d83cba6fbc 100644 --- a/docs/core-data-structures/session.zh.md +++ b/docs/core-data-structures/session.zh.md @@ -146,7 +146,7 @@ interface TodoItem { ### 请求头事件：`request/header` -请求信封（即 `EpochHeader`：调用配置 + 渲染后的系统提示词 + 已组装的工具 schema）会作为会话状态写入日志，因此每个对话请求都是日志的纯函数（见可重建性 Agent Note）。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界；之后请求发生变化时，系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`，不产生 LLM 消息。 +请求信封（即 `EpochHeader`：调用配置 + 适配器默认值来源 + 渲染后的系统提示词 + 已组装的工具 schema）会作为会话状态写入日志，因此每个对话请求都是日志的纯函数（见可重建性 Agent Note）。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界；之后请求发生变化时，系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`，不产生 LLM 消息。 ```ts type-equiv /** @@ -157,6 +157,8 @@ interface TodoItem { interface EpochHeader { /** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */ config: LlmCallConfig + /** Effective config fields materialized from the exact adapter rather than proposed by a caller. */ + adapterDefaults?: LlmCallConfigAdapterDefaults /** Rendered system prompt text; absent for a system-less request. */ system?: string /** Assembled tool schemas; absent for a tool-less request. */ diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index fd9dac0d37..ec1d10366c 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -71,7 +71,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `internal/dispatch` | - | [`commands`](../packages/ui/commands), [`compact`](../packages/compact/compact), [`fs`](../packages/fs/fs), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm-retry`](../packages/llm/llm-retry), [`permission`](../packages/ui/permission), [`plan-mode`](../packages/plan/plan-mode), [`pty-local`](../packages/pty/pty-local), `runtime`, [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-title`](../packages/session-title/session-title), [`subagent`](../packages/subagent/subagent), [`time-context`](../packages/context/time-context), [`tool-todo`](../packages/todo/tool-todo), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`workflow`](../packages/workflow/workflow) | | `internal/plugin` | - | `hmr`, `loader`, `modules`, `webserver` | | `internal/status` | - | [`agent`](../packages/core/agent) | -| `locale/change` | `locale` (`emit`) | `locale`, `ui-models`, `ui-settings-general` | +| `locale/change` | `locale` (`emit`) | `locale` | | `models/changed` | `runtime` (`emit`) | `ui-models` | | `settings/changed` | `runtime` (`emit`) | `ui-models`, `ui-settings-general` | | `slash/input-begin-command` | - | `ui-conversation` | diff --git a/docs/module-graph.md b/docs/module-graph.md index 44fb47ac8f..4d8190c4ed 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -309,6 +309,7 @@ flowchart TD pkg_client_test_runtime --> pkg_client_runtime pkg_client_test_runtime --> pkg_client_ui_slots pkg_client_test_runtime --> pkg_client_web_react + pkg_client_test_runtime --> pkg_host_apiproxy pkg_client_test_runtime --> pkg_invariants pkg_client_ui_settings --> pkg_client_runtime pkg_client_ui_settings --> pkg_client_ui_primitives @@ -316,10 +317,6 @@ flowchart TD pkg_client_ui_settings --> pkg_invariants pkg_client_ui_trajectory --> pkg_client_ui_primitives pkg_client_ui_trajectory --> pkg_invariants - pkg_client_ui_workspace --> pkg_client_runtime - pkg_client_ui_workspace --> pkg_client_ui_primitives - pkg_client_ui_workspace --> pkg_client_ui_slots - pkg_client_ui_workspace --> pkg_invariants pkg_credentials --> pkg_brand pkg_credentials --> pkg_invariants pkg_helper --> pkg_brand @@ -391,20 +388,15 @@ flowchart TD pkg_client_ui_theme --> pkg_client_ui_primitives pkg_client_ui_theme --> pkg_client_ui_slots pkg_client_ui_theme --> pkg_invariants + pkg_client_ui_workspace --> pkg_client_locale + pkg_client_ui_workspace --> pkg_client_runtime + pkg_client_ui_workspace --> pkg_client_ui_primitives + pkg_client_ui_workspace --> pkg_client_ui_slots + pkg_client_ui_workspace --> pkg_invariants pkg_credentials_local --> pkg_atomic_write pkg_credentials_local --> pkg_credentials pkg_credentials_local --> pkg_invariants pkg_credentials_local --> pkg_paths - pkg_host_directory_picker_browse --> pkg_client_locale - pkg_host_directory_picker_browse --> pkg_client_runtime - pkg_host_directory_picker_browse --> pkg_client_ui_primitives - pkg_host_directory_picker_browse --> pkg_client_ui_slots - pkg_host_directory_picker_browse --> pkg_client_ui_workspace - pkg_host_directory_picker_browse --> pkg_invariants - pkg_host_directory_picker_native --> pkg_client_runtime - pkg_host_directory_picker_native --> pkg_client_ui_slots - pkg_host_directory_picker_native --> pkg_client_ui_workspace - pkg_host_directory_picker_native --> pkg_invariants pkg_lsp --> pkg_brand pkg_lsp --> pkg_invariants pkg_lsp --> pkg_llm @@ -481,10 +473,16 @@ flowchart TD pkg_code_runtime_worker --> pkg_invariants pkg_code_runtime_worker --> pkg_session pkg_code_runtime_worker --> pkg_timeout - pkg_host_directory_picker_auto --> pkg_host_directory_picker_browse - pkg_host_directory_picker_auto --> pkg_host_directory_picker_native - pkg_host_directory_picker_auto --> pkg_host_webserver - pkg_host_directory_picker_auto --> pkg_invariants + pkg_host_directory_picker_browse --> pkg_client_locale + pkg_host_directory_picker_browse --> pkg_client_runtime + pkg_host_directory_picker_browse --> pkg_client_ui_primitives + pkg_host_directory_picker_browse --> pkg_client_ui_slots + pkg_host_directory_picker_browse --> pkg_client_ui_workspace + pkg_host_directory_picker_browse --> pkg_invariants + pkg_host_directory_picker_native --> pkg_client_runtime + pkg_host_directory_picker_native --> pkg_client_ui_slots + pkg_host_directory_picker_native --> pkg_client_ui_workspace + pkg_host_directory_picker_native --> pkg_invariants pkg_lsp_local --> pkg_brand pkg_lsp_local --> pkg_invariants pkg_lsp_local --> pkg_llm @@ -562,6 +560,7 @@ flowchart TD pkg_user_interaction --> pkg_invariants pkg_user_interaction --> pkg_llm pkg_client_ui_command --> pkg_client_connection + pkg_client_ui_command --> pkg_client_locale pkg_client_ui_command --> pkg_client_runtime pkg_client_ui_command --> pkg_client_ui_conversation pkg_client_ui_command --> pkg_client_ui_primitives @@ -575,6 +574,10 @@ flowchart TD pkg_tmux_context --> pkg_bash pkg_tmux_context --> pkg_invariants pkg_tmux_context --> pkg_session + pkg_host_directory_picker_auto --> pkg_host_directory_picker_browse + pkg_host_directory_picker_auto --> pkg_host_directory_picker_native + pkg_host_directory_picker_auto --> pkg_host_webserver + pkg_host_directory_picker_auto --> pkg_invariants pkg_pty --> pkg_agent pkg_pty --> pkg_brand pkg_pty --> pkg_invariants @@ -653,6 +656,7 @@ flowchart TD pkg_permission --> pkg_session_projection pkg_permission --> pkg_user_approval pkg_client_ui_goal --> pkg_client_connection + pkg_client_ui_goal --> pkg_client_locale pkg_client_ui_goal --> pkg_client_runtime pkg_client_ui_goal --> pkg_client_ui_conversation pkg_client_ui_goal --> pkg_client_ui_primitives @@ -927,8 +931,10 @@ flowchart TD pkg_tui --> pkg_tools pkg_tui --> pkg_user_interaction pkg_client_ui_plan --> pkg_client_connection + pkg_client_ui_plan --> pkg_client_locale pkg_client_ui_plan --> pkg_client_runtime pkg_client_ui_plan --> pkg_client_ui_conversation + pkg_client_ui_plan --> pkg_client_ui_primitives pkg_client_ui_plan --> pkg_client_ui_slots pkg_client_ui_plan --> pkg_invariants pkg_client_ui_plan --> pkg_plan_mode @@ -1055,10 +1061,9 @@ flowchart TD | [`client-connection`](../packages/client/connection) | `client` | [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/support/invariants) | | [`client-hmr`](../packages/client/hmr) | `client` | [`client-modules`](../packages/client/modules), [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/support/invariants) | | [`client-locale`](../packages/client/locale) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | -| [`client-test-runtime`](../packages/client/test-runtime) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-web-react`](../packages/client/web-react), [`invariants`](../packages/support/invariants) | +| [`client-test-runtime`](../packages/client/test-runtime) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-web-react`](../packages/client/web-react), [`host-apiproxy`](../packages/host/apiproxy), [`invariants`](../packages/support/invariants) | | [`client-ui-settings`](../packages/client/ui-settings) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-trajectory`](../packages/client/ui-trajectory) | `client` | [`client-ui-primitives`](../packages/client/ui-primitives), [`invariants`](../packages/support/invariants) | -| [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`credentials`](../packages/credentials/credentials) | `credentials` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants) | | [`helper`](../packages/sdk/helper) | `sdk` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`subprocess`](../packages/subprocess/subprocess) | | [`telemetry`](../packages/sdk/telemetry) | `sdk` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths) | @@ -1079,9 +1084,8 @@ flowchart TD | [`client-ui-sidebar`](../packages/client/ui-sidebar) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-slash`](../packages/client/ui-slash) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-theme`](../packages/client/ui-theme) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | +| [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`credentials-local`](../packages/credentials/credentials-local) | `credentials` | [`atomic-write`](../packages/util/atomic-write), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths) | -| [`host-directory-picker-browse`](../packages/host/directory-picker-browse) | `host` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) | -| [`host-directory-picker-native`](../packages/host/directory-picker-native) | `host` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) | | [`lsp`](../packages/lsp/lsp) | `lsp` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm) | | [`sandbox`](../packages/sandbox/sandbox) | `sandbox` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm) | | [`settings-local`](../packages/settings/settings-local) | `settings` | [`atomic-write`](../packages/util/atomic-write), [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths), [`settings`](../packages/settings/settings) | @@ -1104,7 +1108,8 @@ flowchart TD | [`client-ui-skill`](../packages/client/ui-skill) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-subagent`](../packages/client/ui-subagent) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | -| [`host-directory-picker-auto`](../packages/host/directory-picker-auto) | `host` | [`host-directory-picker-browse`](../packages/host/directory-picker-browse), [`host-directory-picker-native`](../packages/host/directory-picker-native), [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/support/invariants) | +| [`host-directory-picker-browse`](../packages/host/directory-picker-browse) | `host` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) | +| [`host-directory-picker-native`](../packages/host/directory-picker-native) | `host` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) | | [`lsp-local`](../packages/lsp/lsp-local) | `lsp` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | | [`sandbox-policy`](../packages/sandbox/sandbox-policy) | `sandbox` | [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) | @@ -1124,9 +1129,10 @@ flowchart TD | [`commands`](../packages/ui/commands) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`scope`](../packages/core/scope), [`session`](../packages/core/session) | | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm) | -| [`client-ui-command`](../packages/client/ui-command) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | +| [`client-ui-command`](../packages/client/ui-command) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session) | | [`tmux-context`](../packages/context/tmux-context) | `context` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session) | +| [`host-directory-picker-auto`](../packages/host/directory-picker-auto) | `host` | [`host-directory-picker-browse`](../packages/host/directory-picker-browse), [`host-directory-picker-native`](../packages/host/directory-picker-native), [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/support/invariants) | | [`pty`](../packages/pty/pty) | `pty` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants) | | [`scripts`](../packages/sdk/scripts) | `sdk` | [`app-boot`](../packages/ui/app-boot), [`invariants`](../packages/support/invariants) | | [`session-projection-cache`](../packages/session-projection/session-projection-cache) | `session-projection` | [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection`](../packages/session-projection/session-projection), [`storage-domain`](../packages/storage/storage-domain) | @@ -1143,7 +1149,7 @@ flowchart TD | [`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) | | [`acp`](../packages/acp/acp) | `acp` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`session-projection`](../packages/session-projection/session-projection), [`user-approval`](../packages/ui/user-approval) | -| [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | +| [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | | [`client-ui-model`](../packages/client/ui-model) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-command`](../packages/client/ui-command), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`pty-local`](../packages/pty/pty-local) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subprocess`](../packages/subprocess/subprocess) | | [`tasks-local`](../packages/tasks/tasks-local) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tasks`](../packages/tasks/tasks), [`timeout`](../packages/util/timeout) | @@ -1185,7 +1191,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`commands`](../packages/ui/commands), [`compact`](../packages/compact/compact), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`session-reference`](../packages/context/session-reference), [`session-title`](../packages/session-title/session-title), [`skill`](../packages/skill/skill), [`subprocess`](../packages/subprocess/subprocess), [`system-prompt`](../packages/core/system-prompt), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`plan-mode`](../packages/plan/plan-mode) | +| [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`plan-mode`](../packages/plan/plan-mode) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`paths`](../packages/util/paths), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-title`](../packages/session-title/session-title), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks-local`](../packages/tasks/tasks-local), [`tool-bash`](../packages/bash/tool-bash), [`tool-goal`](../packages/goal/tool-goal), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | | [`sdk-protocol`](../packages/sdk/sdk-protocol) | `sdk` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`tool-ralph`](../packages/workflow/tool-ralph) | `workflow` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 524ba6ffd7..4d4faa42e3 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -78,7 +78,7 @@ export type SessionEvent = { }[T] ``` -Sources: [`packages/core/session/src/types.ts:279`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:286`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:315`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:347`](../packages/core/session/src/types.ts) +Sources: [`packages/core/session/src/types.ts:282`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:289`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:318`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:350`](../packages/core/session/src/types.ts) ## Events @@ -154,7 +154,7 @@ Source: [`packages/ui/user-approval/src/index.ts:67`](../packages/ui/user-approv Types: [StreamChunk](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:212`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:215`](../packages/core/session/src/types.ts) #### `assistant/message` — surface @@ -170,7 +170,7 @@ Source: [`packages/core/session/src/types.ts:212`](../packages/core/session/src/ Types: [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:219`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:222`](../packages/core/session/src/types.ts) ### `command/*` @@ -379,7 +379,7 @@ Source: [`packages/plan/plan-mode/src/index.ts:51`](../packages/plan/plan-mode/s 'request/header': { header: EpochHeader; reason: RequestHeaderReason } ``` -Source: [`packages/core/session/src/types.ts:252`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:255`](../packages/core/session/src/types.ts) ### `sandbox/*` @@ -432,7 +432,7 @@ Source: [`packages/sandbox/sandbox-policy/src/session-mode.ts:33`](../packages/s 'session/end-seed': Record ``` -Source: [`packages/core/session/src/types.ts:275`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:278`](../packages/core/session/src/types.ts) #### `session/title` — log-only @@ -468,7 +468,7 @@ Source: [`packages/session-title/session-title-llm/src/index.ts:43`](../packages 'steering/message': { turn: number; message: UserMessage } ``` -Source: [`packages/core/session/src/types.ts:245`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:248`](../packages/core/session/src/types.ts) ### `step/*` @@ -479,7 +479,7 @@ Source: [`packages/core/session/src/types.ts:245`](../packages/core/session/src/ 'step/end': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:201`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:204`](../packages/core/session/src/types.ts) #### `step/start` — log-only @@ -488,7 +488,7 @@ Source: [`packages/core/session/src/types.ts:201`](../packages/core/session/src/ 'step/start': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:199`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:202`](../packages/core/session/src/types.ts) ### `todo/*` @@ -501,7 +501,7 @@ Source: [`packages/core/session/src/types.ts:199`](../packages/core/session/src/ Types: [TodoItem](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:247`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:250`](../packages/core/session/src/types.ts) ### `tool/*` @@ -518,7 +518,7 @@ Source: [`packages/core/session/src/types.ts:247`](../packages/core/session/src/ Types: [CallId](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:225`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:228`](../packages/core/session/src/types.ts) #### `tool/code-dispatch` — log-only @@ -591,7 +591,7 @@ Source: [`packages/core/tools/src/code-mode.ts:33`](../packages/core/tools/src/c } ``` -Source: [`packages/core/session/src/types.ts:237`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:240`](../packages/core/session/src/types.ts) ### `turn/*` @@ -609,7 +609,7 @@ Source: [`packages/core/session/src/types.ts:237`](../packages/core/session/src/ Types: [TurnEndReason](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:197`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:200`](../packages/core/session/src/types.ts) #### `turn/start` — log-only @@ -622,7 +622,7 @@ Source: [`packages/core/session/src/types.ts:197`](../packages/core/session/src/ Types: [TurnTrigger](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:190`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:193`](../packages/core/session/src/types.ts) ### `user/*` @@ -640,4 +640,4 @@ Source: [`packages/core/session/src/types.ts:190`](../packages/core/session/src/ 'user/message': UserMessage ``` -Source: [`packages/core/session/src/types.ts:210`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:213`](../packages/core/session/src/types.ts) diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index ed3c8dfc33..6f9f000182 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -5,7 +5,7 @@ # carries ACP JSON-RPC. # The DeepSeek adapter. Shipped default: full thinking at max effort on every -# request (wire-only defaults; they never enter the request header). +# request; exact-model resolution materializes request defaults before logging. - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' config: @@ -13,7 +13,6 @@ baseURL: !!js process.env.DEEPSEEK_BASE_URL thinking: enabled reasoningEffort: max - defaultContextWindow: 256000 models: - id: deepseek-v4-flash - id: deepseek-v4-pro diff --git a/examples/acp-agent/retry.cordis.yml b/examples/acp-agent/retry.cordis.yml index 310724bb82..589120c080 100644 --- a/examples/acp-agent/retry.cordis.yml +++ b/examples/acp-agent/retry.cordis.yml @@ -17,7 +17,6 @@ baseURL: !!js process.env.DEEPSEEK_BASE_URL thinking: enabled reasoningEffort: max - defaultContextWindow: 256000 retryPolicy: mode: normal maxRetries: 2 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 5a087badc4..bb4798fe34 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl @@ -11,7 +11,7 @@ {"type":"assistant/chunk","seq":9,"time":1783951000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":10,"time":1784449176722,"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":"1ac37046-d1c0-4ef6-9ea9-963e4b46d1cf"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"} {"type":"tool/call","seq":11,"time":1784449176722,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}} -{"type":"tool/result","seq":12,"time":1784449176732,"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 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 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 ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\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 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 '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 | 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":"1c43b8df-aae8-42e7-8253-5b275edc09bc"}},"sourceEventSeqs":[11],"surfaceOp":"append"} +{"type":"tool/result","seq":12,"time":1784449176732,"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 ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\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 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 '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 | 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":"1c43b8df-aae8-42e7-8253-5b275edc09bc"}},"sourceEventSeqs":[11],"surfaceOp":"append"} {"type":"step/end","seq":13,"time":1784449176732,"data":{"turn":1,"step":1}} {"type":"step/start","seq":14,"time":1784449176733,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":15,"time":1783951000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/examples/headless-agent/cordis.yml b/examples/headless-agent/cordis.yml index 29a743d443..3a74bd4976 100644 --- a/examples/headless-agent/cordis.yml +++ b/examples/headless-agent/cordis.yml @@ -18,7 +18,8 @@ # The DeepSeek adapter. Swap to '@deepseek-ai/dsh-llm-pi-ai' for the pi-ai-backed # twin (a `providers` dict keyed by route; `reasoning: high` replaces # thinking/reasoningEffort). Shipped default: full thinking at max effort on -# every request (wire-only defaults; they never enter the request header). +# every request. Exact-model resolution materializes request defaults before +# the request header is logged. - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' config: diff --git a/examples/headless-agent/tests/fixtures/deepseek-defaults.cordis.yml b/examples/headless-agent/tests/fixtures/deepseek-defaults.cordis.yml new file mode 100644 index 0000000000..cd472f737d --- /dev/null +++ b/examples/headless-agent/tests/fixtures/deepseek-defaults.cordis.yml @@ -0,0 +1,17 @@ +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../../cordis.yml + patches: + - id: llm-deepseek + config: + apiKey: snapshot-key + baseURL: !!js process.env.DSH_SNAPSHOT_BASE_URL + thinking: disabled + - id: cli-agent + config: + provider: deepseek-official + model: deepseek-v4-flash + persistenceRoot: './.sessions' + workspaceContext: false + persona: 'Keyless DeepSeek adapter defaults snapshot.' diff --git a/examples/headless-agent/tests/fixtures/startup-activation-error/activation-error.mjs b/examples/headless-agent/tests/fixtures/startup-activation-error/activation-error.mjs new file mode 100644 index 0000000000..16e5858045 --- /dev/null +++ b/examples/headless-agent/tests/fixtures/startup-activation-error/activation-error.mjs @@ -0,0 +1,6 @@ +/** Fail activation with a deterministic stack so the user-visible startup diagnostic is snapshot-stable. */ +export function apply() { + const failure = new Error('startup activation snapshot failure') + failure.stack = 'Error: startup activation snapshot failure\n at activation-error-fixture' + throw failure +} diff --git a/examples/headless-agent/tests/fixtures/startup-activation-error/cordis.yml b/examples/headless-agent/tests/fixtures/startup-activation-error/cordis.yml new file mode 100644 index 0000000000..2738e4a924 --- /dev/null +++ b/examples/headless-agent/tests/fixtures/startup-activation-error/cordis.yml @@ -0,0 +1,2 @@ +- id: activation-error + name: ./activation-error.mjs diff --git a/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml b/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml index d9cc454bfb..d1851ac7c9 100644 --- a/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml +++ b/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml @@ -8,6 +8,7 @@ - id: telemetry-redact-rule name: './telemetry-redact-rule.ts' +# Managed child-process groups required by the bash executor. - id: subprocess name: '@deepseek-ai/dsh-subprocess-local' diff --git a/examples/headless-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts index a9cde9532c..8b48165a83 100644 --- a/examples/headless-agent/tests/headless.snapshot.ts +++ b/examples/headless-agent/tests/headless.snapshot.ts @@ -1,4 +1,6 @@ import { readFile, readdir, writeFile } from 'node:fs/promises' +import { createServer } from 'node:http' +import type { IncomingMessage, ServerResponse } from 'node:http' import { delimiter, dirname, join } from 'node:path' import { fileURLToPath } from 'node:url' import { @@ -31,9 +33,12 @@ const credentialsScenarioDir = join(snapshotsDir, 'missing-credential') const credentialsConfigPath = fileURLToPath(new URL('../credentials.cordis.snapshot.yml', import.meta.url)) const ralphScenarioDir = join(snapshotsDir, 'ralph-loop') const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url)) +const startupFailureConfigPath = fileURLToPath(new URL('./fixtures/startup-activation-error/cordis.yml', import.meta.url)) +const startupFailureExpected = join(snapshotsDir, 'startup-activation-error', 'stderr.expected.txt') const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const reasoningConfigPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url)) +const deepseekDefaultsConfigPath = fileURLToPath(new URL('./fixtures/deepseek-defaults.cordis.yml', import.meta.url)) const refreshing = process.env.DSH_SNAPSHOT === 'refresh' interface JsonObject { @@ -45,6 +50,40 @@ interface PersistedLog { readonly header: JsonObject } +interface DeepSeekDefaultsServer { + readonly url: string + readonly requests: JsonObject[] + close(): Promise +} + +/** Serve one deterministic DeepSeek-compatible response while retaining its request body. */ +async function deepseekDefaultsServer(): Promise { + const requests: JsonObject[] = [] + const server = createServer((request: IncomingMessage, response: ServerResponse) => { + let body = '' + request.setEncoding('utf8') + request.on('data', (chunk: string) => { body += chunk }) + request.on('end', () => { + requests.push(JSON.parse(body) as JsonObject) + response.writeHead(200, { 'content-type': 'text/event-stream' }) + response.end([ + 'data: {"choices":[{"delta":{"content":"DEFAULTS_OK"}}]}', + 'data: {"choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}', + 'data: [DONE]', + '', + ].join('\n\n')) + }) + }) + await new Promise(resolve => server.listen(0, '127.0.0.1', resolve)) + const address = server.address() + if (address === null || typeof address === 'string') throw new Error('DeepSeek defaults snapshot server has no port') + return { + url: `http://127.0.0.1:${address.port}`, + requests, + close: () => new Promise(resolve => server.close(() => { resolve() })), + } +} + function parseJsonl(content: string): JsonObject[] { return content.split('\n') .filter(line => line.trim().length > 0) @@ -130,6 +169,20 @@ async function persistedLogs(cwd: string): Promise { } describe('headless stream-json snapshots', () => { + it('prints the original Loader activation error through the assembled one-shot app', async () => { + const result = await runLoaderSmoke({ + label: 'headless startup activation error snapshot', + tempDirPrefix: 'headless-snapshot-startup-error-', + binScript, + configPath: startupFailureConfigPath, + binArgs: ['--config', startupFailureConfigPath, '--output-format', 'stream-json', 'unreachable task'], + tsconfigPath, + expectedExitCode: 1, + }) + expect(result.stdout).toBe('') + await expect(result.stderr).toMatchFileSnapshot(startupFailureExpected) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('retries a transient provider failure through the one-shot app', async () => { const prompt = await scenarioPrompt(retryScenarioDir, 'provider-retry') const streamExpected = join(retryScenarioDir, 'stream-json.expected.jsonl') @@ -244,6 +297,57 @@ describe('headless stream-json snapshots', () => { `) }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('logs and sends the DeepSeek adapter maxTokens default through the one-shot app', async () => { + const server = await deepseekDefaultsServer() + try { + const result = await runLoaderSmoke({ + label: 'DeepSeek adapter defaults headless stream-json snapshot', + tempDirPrefix: 'headless-snapshot-deepseek-defaults-', + binScript, + configPath: deepseekDefaultsConfigPath, + binArgs: [ + '--config', + deepseekDefaultsConfigPath, + '--output-format', + 'stream-json', + 'return the deterministic response', + ], + tsconfigPath, + env: { + DSH_SNAPSHOT_BASE_URL: server.url, + NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '), + }, + }) + + expect(result.stderr).toBe('') + expect(server.requests).toHaveLength(1) + expect(server.requests[0]?.max_tokens).toBe(256_000) + const header = (parseJsonl(result.stdout) + .map(record => record.event) + .find((event): event is JsonObject => ( + event !== null + && typeof event === 'object' + && !Array.isArray(event) + && 'type' in event + && event.type === 'request/header' + ))?.data as JsonObject | undefined)?.header as JsonObject | undefined + expect(header?.config).toMatchInlineSnapshot(` + { + "maxTokens": 256000, + "model": "deepseek-v4-flash", + "provider": "deepseek-official", + "reasoningEffort": "off", + } + `) + expect(header?.adapterDefaults).toEqual({ + maxTokens: true, + reasoningEffort: true, + }) + } finally { + await server.close() + } + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('replays the advanced toolchain through the one-shot app', async () => { const prompt = await scenarioPrompt(advancedScenarioDir, 'advanced-toolchain') const fixtureFiles = [ diff --git a/examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl b/examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl index e0a6f076df..4098de697b 100644 --- a/examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl +++ b/examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl @@ -2,7 +2,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"say pong"}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"say pong","messageSeqs":[1],"source":{"kind":"fallback"}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":5,"time":0,"data":{"turn":1,"step":1}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":6,"time":0,"data":{"turn":1,"reason":{"kind":"error","step":1,"failure":{"message":"llm-deepseek: no API key for provider route \"deepseek-official\"; store DEEPSEEK_API_KEY through the credentials service (the web Models page writes it), export DEEPSEEK_API_KEY in the launching environment, or — as a last resort — set a literal \"apiKey\" in the llm-deepseek settings section","code":"MISSING_CREDENTIAL"}}}}} {"type":"result","success":false,"sessionId":"{{sessionId}}","turn":1,"result":"","reason":{"kind":"error","step":1,"failure":{"message":"llm-deepseek: no API key for provider route \"deepseek-official\"; store DEEPSEEK_API_KEY through the credentials service (the web Models page writes it), export DEEPSEEK_API_KEY in the launching environment, or — as a last resort — set a literal \"apiKey\" in the llm-deepseek settings section","code":"MISSING_CREDENTIAL"}}} diff --git a/examples/headless-agent/tests/snapshots/startup-activation-error/stderr.expected.txt b/examples/headless-agent/tests/snapshots/startup-activation-error/stderr.expected.txt new file mode 100644 index 0000000000..5896d03464 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/startup-activation-error/stderr.expected.txt @@ -0,0 +1,3 @@ +dsh-cli-demo: dsh-cli-demo: 1 entry did not activate +./activation-error.mjs: Error: startup activation snapshot failure + at activation-error-fixture diff --git a/examples/jsonrpc-agent/cordis.yml b/examples/jsonrpc-agent/cordis.yml index b23dd30b4a..9806413725 100644 --- a/examples/jsonrpc-agent/cordis.yml +++ b/examples/jsonrpc-agent/cordis.yml @@ -7,8 +7,8 @@ maxTokensAsSuccess: !!js "process.env.DSH_MAX_TOKENS_AS_SUCCESS === undefined ? true : JSON.parse(process.env.DSH_MAX_TOKENS_AS_SUCCESS)" # The DeepSeek adapter. Shipped default: full thinking at max effort on every -# request (wire-only defaults; they never enter the request header). The model -# arrives per session over JSON-RPC, so it is not pinned here. +# request; exact-model resolution materializes request defaults before logging. +# The model arrives per session over JSON-RPC, so it is not pinned here. - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' config: diff --git a/examples/web-cordis/cordis.yml b/examples/web-cordis/cordis.yml index 4cd96e396f..ff857643f4 100644 --- a/examples/web-cordis/cordis.yml +++ b/examples/web-cordis/cordis.yml @@ -12,7 +12,10 @@ config: host: 127.0.0.1 port: 3081 - distIndex: !!js "new URL('./apps/web/dist/index.html', 'file://' + process.cwd() + '/').pathname" + # Plain concatenation, not URL.pathname: a cwd with spaces + # percent-encodes through the URL round-trip and the encoded + # path never resolves. + distIndex: !!js "process.cwd() + '/apps/web/dist/index.html'" - insert: - id: tool-cordis diff --git a/packages/client/connection/README.i18n.yaml b/packages/client/connection/README.i18n.yaml index 70657d55d7..974e3014d6 100644 --- a/packages/client/connection/README.i18n.yaml +++ b/packages/client/connection/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/connection/README.md -README.md: d2fda9f15125915594259e01e5b153609ceb21bb -README.zh.md: 669ae760693b4d98ee873ee5fe323554f58e7ca5 +README.md: c8b7c4787cbcbf6a202fb944459a589fcadd7c8d +README.zh.md: 693420183ffa4fb20e1fecbff523a12261a45d45 diff --git a/packages/client/connection/README.md b/packages/client/connection/README.md index d2fda9f151..c8b7c4787c 100644 --- a/packages/client/connection/README.md +++ b/packages/client/connection/README.md @@ -10,7 +10,7 @@ The node half guards every request under `/api` before bridging (`src/api-reques ## Keyless fixture -Any `fixture` query parameter selects the in-memory carrier. `fixture=empty` starts with no Workspace or Session; `fixturePrompt=reject` rejects prompts before acceptance; `fixtureAttach=fail` publishes a Session but rejects its Workspace attachment; `fixtureSessionCreate=drop-response` publishes and frames a Session before dropping the create response; and `fixtureFrames=workspace-first` reverses the default session-first create-frame order. Workspace creation by name/path and caller-preallocated SessionIds remain deterministic enough for assembled Web tests to reconcile list and frame arrival. +Any `fixture` query parameter selects the in-memory carrier. `fixture=empty` starts with no Workspace or Session; `fixturePrompt=reject` rejects prompts before acceptance; `fixtureAttach=fail` publishes a Session but rejects its Workspace attachment; `fixtureSessionCreate=drop-response` publishes and frames a Session before dropping the create response; and `fixtureFrames=workspace-first` reverses the default session-first create-frame order. Workspace creation by name/path and caller-preallocated SessionIds remain deterministic enough for assembled Web tests to reconcile list and frame arrival. Fixture content search preserves the production-facing `unicode61`-style case, diacritic, and token-phrase behavior and returns a match-centered snippet of at most 120 Unicode code points. ## Model Experience diff --git a/packages/client/connection/README.zh.md b/packages/client/connection/README.zh.md index 669ae76069..693420183f 100644 --- a/packages/client/connection/README.zh.md +++ b/packages/client/connection/README.zh.md @@ -10,7 +10,7 @@ node 半侧在桥接前守卫 `/api` 下的每个请求（`src/api-request-trust ## 无密钥 fixture -任何 `fixture` 查询参数都会选择内存载体。`fixture=empty` 启动时不含 Workspace 或 Session；`fixturePrompt=reject` 在接受前拒绝提示词；`fixtureAttach=fail` 发布 Session 但拒绝将其附加到 Workspace；`fixtureSessionCreate=drop-response` 在丢弃创建响应前发布 Session 并为其发出帧；`fixtureFrames=workspace-first` 则反转默认的 Session 优先创建帧顺序。按名称／路径创建 Workspace 以及由调用方预先分配 SessionId，均具有足够的确定性，组装后的 Web 测试可以据此协调列表与帧的到达。 +任何 `fixture` 查询参数都会选择内存载体。`fixture=empty` 启动时不含 Workspace 或 Session；`fixturePrompt=reject` 在接受前拒绝提示词；`fixtureAttach=fail` 发布 Session 但拒绝将其附加到 Workspace；`fixtureSessionCreate=drop-response` 在丢弃创建响应前发布 Session 并为其发出帧；`fixtureFrames=workspace-first` 则反转默认的 Session 优先创建帧顺序。按名称／路径创建 Workspace 以及由调用方预先分配 SessionId，均具有足够的确定性，组装后的 Web 测试可以据此协调列表与帧的到达。fixture 内容搜索会保留面向生产环境的 `unicode61` 式大小写、变音符号和 token／短语行为，并返回以匹配位置为中心、最多包含 120 个 Unicode 码点的 snippet。 ## 模型体验 diff --git a/packages/client/connection/src/client/api.ts b/packages/client/connection/src/client/api.ts index cc9d2a1eb9..ae47eb9e89 100644 --- a/packages/client/connection/src/client/api.ts +++ b/packages/client/connection/src/client/api.ts @@ -1,12 +1,12 @@ // Central contract re-export point: every contract import inside // web-runtime goes through this single file. -// Types are type-only imports from the apiproxy api/ layer (zero Node deps, browser-safe); -// the only runtime values are the RpcId constructor and the AbstractApiClient seam. +// Types and runtime protocol helpers/bounds come from the apiproxy api/ layer +// (zero Node deps, browser-safe); AbstractApiClient is the client seam. // NEVER import the package root: it drags bootHost/cordis into the browser bundle. // The ./api and ./client subpath exports are the browser-safe channels added for this. export type { - ApiProxy, SessionsApi, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, + ApiProxy, SessionsApi, SessionSearchItem, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, ToolEventView, DirectoryEntry, DirectoryListing, WorkspaceApi, WorkspaceId, WorkspaceView, @@ -25,7 +25,11 @@ export type { // transportError moved down to the apiproxy api layer (it belongs beside // RpcResult, its subject); re-exported here so connection consumers keep one // contract entry point. -export { RpcId, transportError } from '@deepseek-ai/dsh-host-apiproxy/api' +export { + RpcId, + SESSION_SEARCH_RESULT_LIMIT, + transportError, +} from '@deepseek-ai/dsh-host-apiproxy/api' export { AbstractApiClient } from '@deepseek-ai/dsh-host-apiproxy/client' export type { IApiClient } from '@deepseek-ai/dsh-host-apiproxy/client' export type { SessionId, SessionEvent } from '@deepseek-ai/dsh-session/types' diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 068fdc8307..4b22213c15 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -26,13 +26,14 @@ import type { // Type-only: the brand constructor is host-side; the fixture casts at its // wire-fabrication boundary (the schema layer's one-cast-point posture). import type { CommandId } from '@deepseek-ai/dsh-commands/brand' +import { foldSurface } from '@deepseek-ai/dsh-session/surface' import type { ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HostFrame, MuxFrame, RpcReceipt, ModelProviderGroup, ModelTarget, RpcRequest, RpcResponse, RpcResult, ServerRequest, ServerResponse, SessionSummary, ToolCallView, ToolEventView, ToolResultView, WorkspaceId, WorkspaceView, } from './api.ts' import type { RequestPayload, ResponseValue, RpcMethodMap } from '@deepseek-ai/dsh-host-apiproxy/api' -import { AbstractApiClient, RpcId } from './api.ts' +import { AbstractApiClient, RpcId, SESSION_SEARCH_RESULT_LIMIT } from './api.ts' /** The fake carrier mints like a real one (business code never mints). */ function rpcRequest

(payload: P): RpcRequest

{ @@ -136,6 +137,44 @@ const TERMINAL_EXIT_STATUS: Record, 'card' | 'kind'> = { + answer: 'DeepSeek Harness is a plugin-based agent harness on vendored Cordis where **every capability is a plugin**.', + sources: [ + { + url: 'https://github.com/deepseek-ai/deepseek-harness', + title: 'DeepSeek Harness — plugin-based agent harness', + snippet: 'Everything is a plugin: session, tools, agent-loop, and LLM adapters all mount on the same Cordis context.', + publishedAt: '2026-07-01', + }, + { + url: 'https://www.deepseek.com/blog/harness-architecture', + snippet: 'The capability-seam pattern splits each capability into interface, implementation, and consumer packages.', + }, + { + url: 'https://docs.deepseek.com/harness/plugins', + title: 'Writing a harness plugin', + publishedAt: '2026-06-15', + }, + ], + truncated: true, +} + +/** The `web_fetch` result view for fixture turn 67, authored inline for the same reason. */ +const WEB_FETCH_RESULT: Omit, 'card' | 'kind'> = { + url: 'https://www.deepseek.com/blog/harness-architecture', + statusCode: 200, + truncated: false, +} + const DEEPSEEK_REASONING = { efforts: [ { id: 'off', name: 'Off' }, @@ -325,8 +364,20 @@ function buildAlphaLog(): SessionEvent[] { // strip empty and take the todo surfaces' own coverage with it. toolTurn(65, 'bash', '{"command":"pnpm run check","cwd":"/tmp/fixture/deep/nested"}', TERMINAL_OUTPUT_FIXTURE) + // Turns 66-67: the web render intent — a web_search whose result view carries + // structured sources plus an answer (the citation list, one source lacking a + // title so its hostname labels the link, the capped indicator on), and a + // web_fetch whose result view carries the fetched URL and its HTTP status. + // Both keep a generic pending call view and add the `web` card only at + // result time, which is the contract's result-only web shape. Named after + // the real tools so they hit the keyed WebRow registration. Ordered BEFORE + // the todo turn for the same reason turn 65 is: the standing plan retires at + // the next turn/start, so a turn after it would empty the dock's plan strip. + toolTurn(66, 'web_search', '{"query":"deepseek harness architecture"}', 'Search results for deepseek harness architecture.') + toolTurn(67, 'web_fetch', '{"url":"https://www.deepseek.com/blog/harness-architecture"}', '# Harness architecture\n\nEverything is a plugin.') + const todoArgs = JSON.stringify({ todos: fixtureTodos }) - toolTurn(66, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 1 in progress, 1 completed.') + toolTurn(68, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 1 in progress, 1 completed.') // The real tool appends the snapshot mid-execution — between tool/call and // tool/result — so the fixture reproduces that exact ordering (the last // toolTurn events run ... tool/call, tool/result, step/end, turn/end). @@ -365,6 +416,13 @@ function presentCall(name: string, argsRaw: string): ToolCallView | undefined { return { card: 'generic', title: `Edit ${str(args.file_path)}`, kind: 'edit', rawInput: args } case 'write': return { card: 'generic', title: `Write ${str(args.file_path)}`, kind: 'edit', rawInput: args } + // The web tools keep a GENERIC pending card and add the `web` result card + // only at result time (the contract's result-only web shape); their pending + // kind matches the result kind so a call and its result read as one category. + case 'web_search': + return { card: 'generic', title: `Search ${str(args.query)}`, kind: 'search', rawInput: args } + case 'web_fetch': + return { card: 'generic', title: `Fetch ${str(args.url)}`, kind: 'fetch', rawInput: args } default: return undefined // echo et al: the documented no-view fallback path } @@ -373,6 +431,17 @@ function presentCall(name: string, argsRaw: string): ToolCallView | undefined { function presentResult(name: string, argsRaw: string, resultText: string): ToolResultView | undefined { const call = presentCall(name, argsRaw) if (call === undefined) return undefined + // The web tools keep a generic pending card, so their result card is chosen + // by tool name rather than by the pending card tag: the structured `web` card + // the frontend consumes. The view carries no `content` copy (per the contract + // and the web-result-card note); a capability-less UI falls back to the raw + // `tool/result` content, which this fixture emits from `resultText`. + if (name === 'web_search') { + return { card: 'web', kind: 'search', ...WEB_SEARCH_RESULT } + } + if (name === 'web_fetch') { + return { card: 'web', kind: 'fetch', ...WEB_FETCH_RESULT } + } switch (call.card) { case 'terminal': // The sample's own exit status, authored beside it: re-parsing the @@ -575,6 +644,144 @@ function pageOf( return { events, hasMore: start > 0 } } +/** Fixture mirror of first-party message extraction used by session-query. */ +function searchBlockText(block: ContentBlock): string[] { + switch (block.type) { + case 'text': + return [block.text] + case 'reasoning': + return [] + case 'tool-call': + return [block.name, block.arguments] + case 'tool-result': + return block.content.flatMap(searchBlockText) + default: + return [] + } +} + +/** One current-surface user/assistant/steering document, if searchable. */ +function searchEventText(event: SessionEvent): string { + const content = event.type === 'user/message' + ? event.data.content + : event.type === 'assistant/message' || event.type === 'steering/message' + ? event.data.message.content + : undefined + if (content === undefined) return '' + return content.flatMap(searchBlockText).map(part => part.trim()).filter(Boolean).join('\n') +} + +interface FixtureSearchToken { + value: string + /** Inclusive code-point offset in the whitespace-normalized display text. */ + start: number + /** Exclusive code-point offset in the whitespace-normalized display text. */ + end: number +} + +/** + * Browser-safe approximation of SQLite FTS5 unicode61 token boundaries. + * Keeping phrase matching token-based prevents the development fixture from + * promising arbitrary within-token substring behavior that production lacks. + */ +function searchTokenSpans(value: string): { text: string; tokens: FixtureSearchToken[] } { + const text = value.replace(/\s+/gu, ' ').trim() + const characters = Array.from(text) + const tokens: FixtureSearchToken[] = [] + let start: number | undefined + let raw = '' + const flush = (end: number): void => { + if (start !== undefined) { + const folded = raw.normalize('NFD').replace(/\p{M}+/gu, '').toLowerCase() + if (folded !== '') tokens.push({ value: folded, start, end }) + } + start = undefined + raw = '' + } + for (let index = 0; index < characters.length; index++) { + const character = characters[index] as string + const tokenBase = character.normalize('NFD').replace(/\p{M}+/gu, '') + if (tokenBase === '') { + if (start !== undefined) raw += character + continue + } + if (/^[\p{L}\p{N}\p{Co}]+$/u.test(tokenBase)) { + start ??= index + raw += character + } else { + flush(index) + } + } + flush(characters.length) + return { text, tokens } +} + +interface FixturePhraseMatch { + count: number + start: number + end: number +} + +/** Count exact contiguous token-phrase occurrences and retain the first display span. */ +function phraseMatch(document: readonly FixtureSearchToken[], phrase: readonly string[]): FixturePhraseMatch { + if (phrase.length === 0 || phrase.length > document.length) return { count: 0, start: 0, end: 0 } + let count = 0 + let firstStart = 0 + let firstEnd = 0 + for (let start = 0; start <= document.length - phrase.length; start++) { + if (!phrase.every((token, offset) => document[start + offset]?.value === token)) continue + count++ + if (count === 1) { + firstStart = document[start]?.start ?? 0 + firstEnd = document[start + phrase.length - 1]?.end ?? firstStart + } + } + return { count, start: firstStart, end: firstEnd } +} + +/** Match-centered fixture excerpt, bounded by Unicode code points for the sidebar. */ +function searchSnippet(value: string, matchStart: number, matchEnd: number): string { + const characters = Array.from(value) + if (characters.length <= 120) return value + const boundedStart = Math.min(Math.max(0, matchStart), characters.length - 1) + const boundedEnd = Math.min( + characters.length, + Math.max(boundedStart + 1, matchEnd), + ) + const center = Math.floor((boundedStart + boundedEnd) / 2) + let start = Math.min( + characters.length - 118, + Math.max(0, center - Math.floor(118 / 2)), + ) + let end = start + 118 + if (start === 0) { + end = 119 + } else if (end === characters.length) { + start = characters.length - 119 + } + return `${start > 0 ? '…' : ''}${characters.slice(start, end).join('')}${end < characters.length ? '…' : ''}` +} + +interface FixtureSearchCandidate { + sessionId: SessionId + seq: number + time: number + text: string + matchCount: number + matchStart: number + matchEnd: number + documentLength: number +} + +/** Mirrors `packages/session-query/session-query-sqlite/src/index.ts`; update both together. */ +function compareSearchCandidates(a: FixtureSearchCandidate, b: FixtureSearchCandidate): number { + if (a.matchCount !== b.matchCount) return b.matchCount - a.matchCount + if (a.documentLength !== b.documentLength) return a.documentLength - b.documentLength + if (a.time !== b.time) return b.time - a.time + if (a.sessionId !== b.sessionId) return a.sessionId < b.sessionId ? -1 : 1 + return b.seq - a.seq +} + /** * Current plan projection over the full log (host parallel: latest todo/write * with no later turn/start; a new turn retires the previous plan). @@ -919,6 +1126,8 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { let failNextHistory = false /** Force-enders for currently open stream generators (timing hook: simulated connection loss). */ const streamBreakers = new Set<() => void>() + /** Retry scenarios opened by timing hooks and completed in a later browser assertion phase. */ + const retryScenarios = new Map() // Timing-acceptance hooks (browser test backdoor): the in-memory fixture is ideally timed, which // is exactly what masked the open-window and reconnect-gap bugs (audit S1/S3). These let @@ -942,6 +1151,89 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { const messageSeqs = log.filter(event => event.type === 'user/message').map(event => event.seq) append(sid(id), { type: 'session/title', data: { title, messageSeqs, source: { kind: 'provider', provider: 'fixture' } } }) }, + /** Open one failed model step whose partial remains visible until llm/retry arrives. */ + beginModelRetry(id: string): void { + const sessionId = sid(id) + const turn = nextTurn.get(sessionId) ?? 0 + nextTurn.set(sessionId, turn + 1) + retryScenarios.set(sessionId, { turn, stepStarted: true }) + setRunning(sessionId, true) + append(sessionId, { type: 'turn/start', data: { turn, trigger: { kind: 'message', source: { kind: 'user' } } } }) + append(sessionId, { type: 'user/message', surfaceOp: 'append', data: { content: text('请重试这个请求'), source: { kind: 'user' } } }) + append(sessionId, { type: 'step/start', data: { turn, step: 1 } }) + append(sessionId, { type: 'assistant/chunk', data: { turn, step: 1, chunk: { type: 'block-start', index: 0, blockType: 'text' } } }) + append(sessionId, { type: 'assistant/chunk', data: { turn, step: 1, chunk: { type: 'text-delta', index: 0, text: '应撤回的半截回复' } } }) + append(sessionId, { type: 'step/end', data: { turn, step: 1 } }) + }, + /** Record one retry decision, then open the next retry turn. */ + scheduleModelRetry(id: string, retry = 1, delayMs = 450): void { + const sessionId = sid(id) + const scenario = retryScenarios.get(sessionId) + if (scenario === undefined) throw new Error(`fixture: no model retry scenario for ${id}`) + if (!scenario.stepStarted) { + append(sessionId, { type: 'step/start', data: { turn: scenario.turn, step: 1 } }) + append(sessionId, { type: 'assistant/chunk', data: { turn: scenario.turn, step: 1, chunk: { type: 'block-start', index: 0, blockType: 'text' } } }) + append(sessionId, { type: 'assistant/chunk', data: { turn: scenario.turn, step: 1, chunk: { type: 'text-delta', index: 0, text: `第 ${String(retry)} 次应撤回的回复` } } }) + append(sessionId, { type: 'step/end', data: { turn: scenario.turn, step: 1 } }) + scenario.stepStarted = true + } + const failure = { code: 'TRANSPORT', message: '连接被重置' } + append(sessionId, { + type: 'llm/retry', + data: { + turn: scenario.turn, step: 1, + provider: 'fixture', mode: 'normal', policyKey: 'fixture-normal', + retry, maxRetries: 2, delayMs, failure, + }, + }) + append(sessionId, { + type: 'turn/end', + data: { turn: scenario.turn, reason: { kind: 'error', step: 1, failure } }, + }) + const next = nextTurn.get(sessionId) ?? scenario.turn + 1 + nextTurn.set(sessionId, next + 1) + append(sessionId, { type: 'turn/start', data: { turn: next, trigger: { kind: 'retry' } } }) + scenario.turn = next + scenario.stepStarted = false + }, + /** Record one retry decision, then cancel its source turn before the retry starts. */ + cancelModelRetryDuringBackoff(id: string, delayMs = 450): void { + const sessionId = sid(id) + const scenario = retryScenarios.get(sessionId) + if (scenario === undefined) throw new Error(`fixture: no model retry scenario for ${id}`) + const failure = { code: 'TRANSPORT', message: '连接被重置' } + append(sessionId, { + type: 'llm/retry', + data: { + turn: scenario.turn, step: 1, + provider: 'fixture', mode: 'normal', policyKey: 'fixture-normal', + retry: 1, maxRetries: 2, delayMs, failure, + }, + }) + append(sessionId, { type: 'turn/end', data: { turn: scenario.turn, reason: { kind: 'aborted' } } }) + retryScenarios.delete(sessionId) + setRunning(sessionId, false) + }, + /** Finish the timing-hook retry with a finalized response in the open retry turn. */ + completeModelRetry(id: string): void { + const sessionId = sid(id) + const scenario = retryScenarios.get(sessionId) + if (scenario === undefined) throw new Error(`fixture: no model retry scenario for ${id}`) + retryScenarios.delete(sessionId) + append(sessionId, { type: 'step/start', data: { turn: scenario.turn, step: 1 } }) + append(sessionId, { + type: 'assistant/message', + surfaceOp: 'append', + data: { + turn: scenario.turn, + step: 1, + message: assistantMessage(text('重试后的完整回复')), + }, + }) + append(sessionId, { type: 'step/end', data: { turn: scenario.turn, step: 1 } }) + append(sessionId, { type: 'turn/end', data: { turn: scenario.turn, reason: { kind: 'completed' } } }) + setRunning(sessionId, false) + }, /** Log append WITHOUT the mux emit: a frame lost in transit — history still serves it, the client must repull. */ appendSilent(id: string, msg: string): void { const log = logOf(sid(id)) @@ -987,6 +1279,45 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { return { sessions: { list: request => ok(request, { items: [...sessions].sort((a, b) => b.updatedAt - a.updatedAt) }), + search: (request, signal) => { + if (signal.aborted) { + return err(request, { + code: 'cancelled', + message: 'fixture session search was aborted', + details: {}, + }) + } + const query = searchTokenSpans(request.payload.query).tokens.map(token => token.value) + const matches = sessions.flatMap((summary) => { + const log = logs.get(summary.sessionId) ?? [] + const current = new Set(foldSurface(log).nodes) + const best = log.flatMap((event): FixtureSearchCandidate[] => { + if (!current.has(event.seq)) return [] + const eventText = searchEventText(event) + const document = searchTokenSpans(eventText) + const match = phraseMatch(document.tokens, query) + if (match.count === 0) return [] + return [{ + sessionId: summary.sessionId, + seq: event.seq, + time: event.time, + text: document.text, + matchCount: match.count, + matchStart: match.start, + matchEnd: match.end, + documentLength: Array.from(eventText).length, + }] + }).sort(compareSearchCandidates)[0] + return best === undefined ? [] : [best] + }).sort(compareSearchCandidates) + return ok(request, { + items: matches.slice(0, SESSION_SEARCH_RESULT_LIMIT).map(match => ({ + sessionId: match.sessionId, + snippet: searchSnippet(match.text, match.matchStart, match.matchEnd), + })), + hasMore: matches.length > SESSION_SEARCH_RESULT_LIMIT, + }) + }, create: async (request) => { const workspace = request.payload.workspaceId === undefined ? undefined @@ -1691,20 +2022,30 @@ export class FixtureApiClient extends AbstractApiClient { protected override async callUnary( method: K, payload: RequestPayload, + signal?: AbortSignal, ): Promise>> { const request = rpcRequest(payload) const full: ClientRequest = { type: 'client-request', rpcId: request.rpcId, method, payload } this.onEnvelope(full) - const response = await this.dispatch(method, request as RpcRequest) as RpcResponse> + const response = await this.dispatch( + method, + request as RpcRequest, + signal ?? new AbortController().signal, + ) as RpcResponse> const fullResponse: ServerResponse = { type: 'server-response', rpcId: response.rpcId, result: response.result } this.onEnvelope(fullResponse) return response } /** Method-key dispatch into the in-memory contract impl (a real carrier routes by URL path instead). */ - private dispatch(method: keyof RpcMethodMap, request: RpcRequest): Promise> { + private dispatch( + method: keyof RpcMethodMap, + request: RpcRequest, + signal: AbortSignal, + ): Promise> { switch (method) { case 'session.list': return this.api.sessions.list(request) + case 'session.search': return this.api.sessions.search(request, signal) case 'session.create': return this.api.sessions.create(request) case 'session.history': return this.api.sessions.history(request) case 'session.models': return this.api.sessions.models(request) @@ -1725,8 +2066,7 @@ export class FixtureApiClient extends AbstractApiClient { case 'workspace.delete': return this.api.workspace.delete(request) case 'workspace.insertSessionBefore': return this.api.workspace.insertSessionBefore(request) case 'command.list': return this.api.commands.list(request) - // The in-memory execute never blocks, so a never-aborting signal is faithful here. - case 'command.execute': return this.api.commands.execute(request, new AbortController().signal) + case 'command.execute': return this.api.commands.execute(request, signal) case 'skill.list': return this.api.skills.list(request) case 'goal.create': return this.api.goals.create(request) case 'goal.edit': return this.api.goals.edit(request) diff --git a/packages/client/connection/src/client/index.ts b/packages/client/connection/src/client/index.ts index 93f5153936..e286157e46 100644 --- a/packages/client/connection/src/client/index.ts +++ b/packages/client/connection/src/client/index.ts @@ -11,7 +11,7 @@ import { WebApiClient } from './web-api-client.ts' // ---- Contract re-exports (browser-safe apiproxy channels + core types) ---- export type { - ApiProxy, SessionsApi, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, + ApiProxy, SessionsApi, SessionSearchItem, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, ToolEventView, DirectoryEntry, DirectoryListing, ToolCallView, ToolResultView, WorkspaceApi, WorkspaceId, WorkspaceView, @@ -25,7 +25,11 @@ export type { SettingsApi, SettingsNamespaceView, SettingsPathOpView, SettingsSecretView, CredentialsApi, CredentialView, ConfigurableProviderView, LlmApi, } from './api.ts' -export { RpcId, AbstractApiClient, transportError } from './api.ts' +export { + RpcId, + AbstractApiClient, + transportError, +} from './api.ts' // Connection loop types are public through ConnectionHandle.start; the // controller remains package-internal. diff --git a/packages/client/connection/tests/fake-api.ts b/packages/client/connection/tests/fake-api.ts index 5524c3a20b..0d58800279 100644 --- a/packages/client/connection/tests/fake-api.ts +++ b/packages/client/connection/tests/fake-api.ts @@ -4,7 +4,7 @@ import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import type { CommandDescriptor, HostFrame, IApiClient, ModelTarget, MuxFrame, - RpcRequest, RpcResponse, SessionId, SessionModels, SkillEntry, + RpcRequest, RpcResponse, SessionId, SessionModels, SessionSearchItem, SkillEntry, } from '../src/client/api.ts' import { RpcId } from '../src/client/api.ts' @@ -44,6 +44,8 @@ export class FakeApiClient implements IApiClient { // Programmable slots (defaults answer OK-empty); reassign per case. onList: (payload: unknown) => Promise> = () => Promise.resolve(ok({ items: [] })) + onSearch: (payload: unknown) => Promise> = + () => Promise.resolve(ok({ items: [], hasMore: false })) onCreate: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId })) onRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 })) onFork: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId })) @@ -87,12 +89,17 @@ export class FakeApiClient implements IApiClient { private readonly muxConns: StreamConn[] = [] private readonly hostConns: StreamConn[] = [] + lastSearchSignal: AbortSignal | undefined // Parameter annotations below are local structural types on purpose: the CI // lint lane runs without built artifacts, where IApiClient's wire types // (apiproxy subpath) resolve to any and inferred params trip no-unsafe-argument. readonly sessions: IApiClient['sessions'] = { list: (payload: unknown) => this.record('session.list', payload, this.onList(payload)), + search: (payload: unknown, signal?: AbortSignal) => { + this.lastSearchSignal = signal + return this.record('session.search', payload, this.onSearch(payload)) + }, create: (payload: unknown) => this.record('session.create', payload, this.onCreate(payload)), history: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) => this.record('session.history', payload, this.onHistory(payload)), diff --git a/packages/client/connection/tests/fixture.spec.ts b/packages/client/connection/tests/fixture.spec.ts index 6dc8d7cb42..f70c4eb421 100644 --- a/packages/client/connection/tests/fixture.spec.ts +++ b/packages/client/connection/tests/fixture.spec.ts @@ -19,6 +19,10 @@ interface TimingHooks { failNextHistory(): void appendUser(id: string, msg: string): void appendTitle(id: string, title: string): void + beginModelRetry(id: string): void + scheduleModelRetry(id: string, retry?: number, delayMs?: number): void + cancelModelRetryDuringBackoff(id: string, delayMs?: number): void + completeModelRetry(id: string): void appendSilent(id: string, msg: string): void breakStreams(): void } @@ -48,6 +52,59 @@ describe('createFixtureApi', () => { expect(response.result.value.items[1]?.parentSessionId).toBe('fx-alpha') // lineage material }) + it('searches current message text with literal unicode61-style token phrases', async () => { + const api = createFixtureApi() + const signal = new AbortController().signal + const phrase = await api.sessions.search(req({ query: 'FIXTURE 历史消息' }), signal) + expect(phrase.result).toMatchObject({ + ok: true, + value: { + items: [{ sessionId: 'fx-alpha' }], + hasMore: false, + }, + }) + if (!phrase.result.ok) throw new Error('search failed') + expect(phrase.result.value.items[0]?.snippet).toContain('fixture 历史消息') + + timing().appendUser( + 'fx-alpha', + `${'leading context '.repeat(20)}late café token${' trailing context'.repeat(20)}`, + ) + const late = await api.sessions.search(req({ query: 'LATE CAFE TOKEN' }), signal) + if (!late.result.ok) throw new Error('late search failed') + const lateSnippet = late.result.value.items[0]?.snippet ?? '' + expect(lateSnippet).toContain('late café token') + expect(lateSnippet.startsWith('…')).toBe(true) + expect(lateSnippet.endsWith('…')).toBe(true) + expect(Array.from(lateSnippet).length).toBeLessThanOrEqual(120) + + timing().appendUser('fx-alpha', 'Greek final sigma: ος') + const finalSigma = await api.sessions.search(req({ query: 'ΟΣ' }), signal) + if (!finalSigma.result.ok) throw new Error('final sigma search failed') + expect(finalSigma.result.value.items[0]?.snippet).toContain('ος') + + const substring = await api.sessions.search(req({ query: 'ixtur' }), signal) + expect(substring.result).toEqual({ + ok: true, + value: { items: [], hasMore: false }, + }) + const punctuationOnly = await api.sessions.search(req({ query: '*' }), signal) + expect(punctuationOnly.result).toEqual({ + ok: true, + value: { items: [], hasMore: false }, + }) + const reasoningOnly = await api.sessions.search(req({ query: '思考过程' }), signal) + expect(reasoningOnly.result).toEqual({ + ok: true, + value: { items: [], hasMore: false }, + }) + + const aborted = new AbortController() + aborted.abort() + await expect(api.sessions.search(req({ query: 'fixture' }), aborted.signal)) + .resolves.toMatchObject({ result: { ok: false, error: { code: 'cancelled' } } }) + }) + it('pages history backwards on message-boundary cuts with seq-contiguous stitching', async () => { const api = createFixtureApi() const tail = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 10 })) @@ -761,8 +818,18 @@ describe('createFixtureApi', () => { hooks.appendSilent('fx-alpha', '静默丢帧') hooks.appendUser('fx-alpha', '正常直播') hooks.appendTitle('fx-alpha', 'Fixture 修订标题') + hooks.beginModelRetry('fx-alpha') + hooks.scheduleModelRetry('fx-alpha') + hooks.completeModelRetry('fx-alpha') + hooks.beginModelRetry('fx-alpha') + hooks.cancelModelRetryDuringBackoff('fx-alpha') await vi.waitFor(() => { expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('正常直播'))).toBe(true) + expect(seen.some(f => f.type === 'session/event' && (f.event as { type: string }).type === 'llm/retry')).toBe(true) + expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('重试后的完整回复'))).toBe(true) + expect(seen.some(f => f.type === 'session/event' + && f.event.type === 'turn/end' + && f.event.data.reason.kind === 'aborted')).toBe(true) expect(seen.some(f => f.type === 'session/projection' && f.key === 'title' && f.value === 'Fixture 修订标题')).toBe(true) }) expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('静默丢帧'))).toBe(false) @@ -819,6 +886,10 @@ describe('FixtureApiClient (protocol-level fake carrier)', () => { it('covers the whole unary dispatch table', async () => { const client = new FixtureApiClient() + expect((await client.sessions.search( + { query: 'fixture' }, + new AbortController().signal, + )).result.ok).toBe(true) const created = await client.sessions.create({}) if (!created.result.ok) throw new Error('create failed') const id = created.result.value.sessionId diff --git a/packages/client/modules/README.i18n.yaml b/packages/client/modules/README.i18n.yaml index 80bf46a996..c3dfc36e65 100644 --- a/packages/client/modules/README.i18n.yaml +++ b/packages/client/modules/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/modules/README.md -README.md: efba9e2eb0b148677fc7ac18bfad6333fb6f80da -README.zh.md: b057bfdd8c0a269252496d0c6a0fc4184932fd72 +README.md: 99565b349d782c58752ac3e73ce7c0be527f78a8 +README.zh.md: a8ed0a4949ccefce53933b4f2fb8f51f5291684f diff --git a/packages/client/modules/README.md b/packages/client/modules/README.md index efba9e2eb0..99565b349d 100644 --- a/packages/client/modules/README.md +++ b/packages/client/modules/README.md @@ -8,6 +8,8 @@ Lazy CJS model (web2): executing a plugin bundle only REGISTERS its factory (`wi Resolution branch order (`import(specifier)`): platform seed word → shell instance; memoized record → surface; shell-own static registry (`registerStatic`, app-shell) → module; registered factory → materialize; graph row (`window.__DSH_BOOT__`) → fetch + execute + materialize; anything else throws — the runtime mirror of the build-time bundle purity gate. The synchronous `require` handed to factories walks the same order minus the fetch branch and records observed edges into the module record. `prefetch` is the stage-one arrival hook (fetch + execute, registration only; concurrent calls share one in-flight task); `invalidate` drops the factory and the materialized record so the next prefetch/import refetches (the HMR hook). +The Node half scans enabled Loader entries for web `dshClient` packages, resolves each `exports["./client"]`, hashes the built bundle into the boot graph, and serves it under `/plugins`. Source launch maps host imports to TypeScript source but still consumes this built client export; missing files share one build instruction followed by a package/path list, while unrelated filesystem errors remain separate failures. + ## Model Experience None, as the module loader is browser-side kernel machinery; nothing here reaches a model request. diff --git a/packages/client/modules/README.zh.md b/packages/client/modules/README.zh.md index b057bfdd8c..a8ed0a4949 100644 --- a/packages/client/modules/README.zh.md +++ b/packages/client/modules/README.zh.md @@ -8,6 +8,8 @@ 解析分支顺序（`import(specifier)`）：平台种子词 → 外壳实例；记忆化记录 → 表层；外壳自身的静态注册表（`registerStatic`，app-shell）→ 模块；已注册 factory → 物化；模块图记录（`window.__DSH_BOOT__`）→ 抓取 + 执行 + 物化；其他情况一律抛出异常。这是构建时组合包纯度门禁的运行时镜像。交给 factory 的同步 `require` 采用相同顺序，但不含抓取分支，并把观察到的边记录到模块记录中。`prefetch` 是第一阶段加载钩子（抓取 + 执行，只注册；并发调用共享一个进行中的任务）；`invalidate` 会丢弃 factory 与物化记录，使下一次 prefetch/import 重新抓取；它是 HMR（热模块替换）钩子。 +Node 侧会扫描已启用的 Loader 配置项以发现 web `dshClient` 包，解析每个 `exports["./client"]`，把构建后的组合包哈希写入启动图，并通过 `/plugins` 提供该文件。源码启动会把宿主侧导入映射到 TypeScript 源码，但仍消费客户端导出的构建产物；缺失文件共享一条构建要求，随后以 package/path list 列出各项，而无关的文件系统错误仍是独立故障。 + ## 模型体验 无。模块 loader 属于浏览器侧内核机制；这里没有任何内容进入模型请求。 diff --git a/packages/client/modules/src/index.ts b/packages/client/modules/src/index.ts index ecfc31b77f..694295e7f2 100644 --- a/packages/client/modules/src/index.ts +++ b/packages/client/modules/src/index.ts @@ -58,6 +58,47 @@ interface PkgMeta { immediately: boolean } +/** Recovery instruction shared by grouped startup and steady-state bundle diagnostics. */ +const CLIENT_BUNDLE_BUILD_INSTRUCTION = 'run `pnpm run build` before launch' + +/** Missing built client export, retained as structured data for activation-error grouping. */ +class MissingClientBundleError extends Error { + constructor( + readonly packageName: string, + readonly clientPath: string, + cause: unknown, + ) { + super( + [ + `client-modules: client bundle not found; ${CLIENT_BUNDLE_BUILD_INSTRUCTION}:`, + ` package: ${packageName}`, + ` path: ${clientPath}`, + ].join('\n'), + { cause }, + ) + } +} + +/** Activation failures grouped by actionable package-build errors and unrelated failures. */ +class ClientPackageCompositionError extends AggregateError { + constructor(failures: Error[]) { + const missingBundles = failures.filter((error): error is MissingClientBundleError => error instanceof MissingClientBundleError) + const otherFailures = failures.filter(error => !(error instanceof MissingClientBundleError)) + const packageNoun = failures.length === 1 ? 'package' : 'packages' + const lines = [`client-modules: ${String(failures.length)} client ${packageNoun} failed to compose:`] + if (missingBundles.length > 0) { + lines.push(` client bundles not found; ${CLIENT_BUNDLE_BUILD_INSTRUCTION}:`) + for (const error of missingBundles) { + lines.push(` - package: ${error.packageName}`, ` path: ${error.clientPath}`) + } + } + if (otherFailures.length > 0) { + lines.push(' other failures:', ...otherFailures.map(error => ` - ${error.message}`)) + } + super(failures, lines.join('\n')) + } +} + /** One composed table row: the wire entry plus its bundle path. */ interface WebPluginRecord { entry: WebBootEntry @@ -138,7 +179,7 @@ export function injectBootManifest(html: string, graph: WebBootGraph): string { * + bundle route + index tap. Construction runs the activation scan * synchronously — a malformed declaration or missing bundle among the * already-loaded entries aggregates into one loud throw (FAILED fiber; the - * boot sweep reports it). + * boot activation audit reports it). */ export class ClientModuleHostService extends Service { static inject = ['httpServer', 'loader'] @@ -194,10 +235,7 @@ export class ClientModuleHostService extends Service { const failures: Error[] = [] this.flush(err => failures.push(err)) if (failures.length > 0) { - throw new AggregateError( - failures, - `client-modules: ${String(failures.length)} client package(s) failed to compose:\n${failures.map(e => ` - ${e.message}`).join('\n')}`, - ) + throw new ClientPackageCompositionError(failures) } ctx.effect( @@ -322,6 +360,22 @@ export class ClientModuleHostService extends Service { return meta } + /** + * Read the activation-time bundle revision. + * @param pkgName - package that declares the client bundle. + * @param clientPath - absolute path of the built client artifact. + * @returns the bundle content's short hash for use as its revision. + * @throws {MissingClientBundleError} when the read fails with `ENOENT`; other filesystem errors are rethrown unchanged. + */ + private initialBundleRevision(pkgName: string, clientPath: string): string { + try { + return shortHash(readFileSync(clientPath)) + } catch (error) { + if ((error as NodeJS.ErrnoException).code !== 'ENOENT') throw error + throw new MissingClientBundleError(pkgName, clientPath, error) + } + } + /** Reconcile one entry name against the live loader entries. @returns whether the table changed. */ private processOne(entryName: string): boolean { let qualifies = false @@ -337,7 +391,7 @@ export class ClientModuleHostService extends Service { if (meta === null) return false // The rev rides the row from here on: a fiber restart reuses the row (and // its rev) untouched; only rebuilt() re-reads the bundle. - const rev = shortHash(readFileSync(meta.clientPath)) + const rev = this.initialBundleRevision(entryName, meta.clientPath) this.table.set(entryName, { entry: graphRow(entryName, rev, meta.inject, meta.immediately), clientPath: meta.clientPath }) return true } diff --git a/packages/client/modules/tests/node-half.spec.ts b/packages/client/modules/tests/node-half.spec.ts new file mode 100644 index 0000000000..3eb99c0ead --- /dev/null +++ b/packages/client/modules/tests/node-half.spec.ts @@ -0,0 +1,87 @@ +/** Node-half composition diagnostics for package metadata and built client bundles. */ + +import { mkdirSync, mkdtempSync, realpathSync, rmSync, writeFileSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { pathToFileURL } from 'node:url' +import { Context } from 'cordis' +import { afterEach, describe, expect, it } from 'vitest' +import type { HttpServerService } from '@deepseek-ai/dsh-host-webserver' +import { ClientModuleHostService } from '../src/index.ts' + +let root: string | undefined + +afterEach(() => { + if (root !== undefined) rmSync(root, { recursive: true, force: true }) + root = undefined +}) + +/** Create a resolvable dshClient package whose client export points at the returned path. */ +function writePackage(packageName: string): string { + root ??= realpathSync(mkdtempSync(join(tmpdir(), 'dsh-client-modules-'))) + const pkgRoot = join(root, 'node_modules', ...packageName.split('/')) + const clientPath = join(pkgRoot, 'lib', 'client.js') + mkdirSync(pkgRoot, { recursive: true }) + writeFileSync(join(pkgRoot, 'package.json'), JSON.stringify({ + name: packageName, + exports: { + './client': './lib/client.js', + './package.json': './package.json', + }, + dshClient: { platform: 'web' }, + })) + return clientPath +} + +/** Construct the node-half service over the enabled fixture entries. */ +function construct(packageNames: string[]): ClientModuleHostService { + const ctx = new Context() + ctx.baseUrl = pathToFileURL(root!).href + '/' + ctx.provide('loader', { + *entries() { + for (const packageName of packageNames) { + yield { options: { name: packageName }, fiber: {}, disabled: false } + } + }, + }) + const httpServer: Pick = { + port: 0, + register: () => () => {}, + tapIndex: () => () => {}, + } + ctx.provide('httpServer', httpServer as HttpServerService) + return new ClientModuleHostService(ctx) +} + +describe('client bundle activation', () => { + it('groups missing bundles under one source-build instruction with a package/path list', () => { + const firstName = '@fixture/missing-first' + const secondName = '@fixture/missing-second' + const firstPath = writePackage(firstName) + const secondPath = writePackage(secondName) + expect(() => construct([firstName, secondName])).toThrow([ + 'client-modules: 2 client packages failed to compose:', + ' client bundles not found; run `pnpm run build` before launch:', + ` - package: ${firstName}`, + ` path: ${firstPath}`, + ` - package: ${secondName}`, + ` path: ${secondPath}`, + ].join('\n')) + }) + + it('does not report other bundle read failures as missing builds', () => { + const packageName = '@fixture/unreadable-client' + const clientPath = writePackage(packageName) + mkdirSync(clientPath, { recursive: true }) + let thrown: unknown + try { + construct([packageName]) + } catch (error) { + thrown = error + } + expect(String(thrown)).toContain('client-modules: 1 client package failed to compose:') + expect(String(thrown)).toContain(' other failures:') + expect(String(thrown)).toContain('EISDIR') + expect(String(thrown)).not.toContain('pnpm run build') + }) +}) diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 75fa6b2c6c..f42e4f09d0 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: a116a5e4ad3070f20e6d90490f2507c1e2369c37 -README.zh.md: f375811e6f1480d6636fe4eb77746b76d6414b1e +README.md: 9f2b165f1a98dcecfa3ab82386da9b094cfd2f54 +README.zh.md: 3ed047e65d3bddc14c3b6b84f327bbeebf805d4b diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index a116a5e4ad..9f2b165f1a 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -12,6 +12,8 @@ Workspace and Session lists have independent monotone `pending` → `ready` base SlotsService gives the renderer separate bare observables for `useSessions` and `useWorkspaces`; web-react creates the hooks. Workspace business state does not enter `SessionListState` or an entry store. +`SessionsService.search(query, signal)` is a stateless one-shot action over the `session.search` RPC. It returns ranked session/snippet pairs without putting query, loading, or error state into the shared Session list, so each UI owner controls debounce, cancellation, stale-response suppression, and fallback presentation. `searchResultLimit` re-exposes `SESSION_SEARCH_RESULT_LIMIT` — the bound the response schema itself enforces — as injected presentation data, so client plugins do not duplicate it. It is a protocol constant rather than per-connection state, so the connection handle does not carry it. + ## New Session and the blank mirror `WorkspacesService.connectWorkspace(workspaceId)` resolves the session a New Session flow lands in: it reuses the workspace's existing blank session from the list mirror (`blank && cwd == workspace.path`) or calls `session.create({workspaceId})`, returning the session id for the caller to open. `SessionSummary.blank` mirrors the host's derived empty-log bit and only ever lowers on the client: seeded by `session.list` / the `host/session-added` frame, flipped false by the first ACCEPTED local `prompt()` (on the RPC success response — acceptance proves the user message is in the host log; a rejected first prompt keeps the session blank and reusable) and by any `running: true` status frame, re-aligned by every list re-pull. List surfaces hide blank rows; the store carries every row. `SessionsService.create` accepts an optional caller-preallocated SessionId and throws `SessionCreateError` (carrying `requestedSessionId`) on failure. @@ -28,6 +30,10 @@ SlotsService gives the renderer separate bare observables for `useSessions` and `SessionManager` retains the latest validated `session/title` control snapshot independently of list and session-instance arrival. Newer event seqs replace older snapshots, title timestamps contribute to list recency, and a subscription baseline discards any retained title beyond its `lastSeq` before the optional folded title arrives. Explicit session removal also clears the retained title. The client-facing `SessionSummary.title` is therefore only the actual durable title; `displayTitle` is always present and falls back through the cwd basename and session id. A cold persisted session keeps that fallback until opening or resuming it causes the host to fold and project its log-backed title. `ISession.rename` settles the `title` projection cell directly from the unary response's `{title, seq}` under the same higher-seq-wins rule — the list row and every `useProjection('title')` reader update ahead of the push frame, whose later replay of the same seq is a no-op. +## Model retry projection + +The Session object validates plugin-owned, provider-routed `llm/retry` payloads at the event wire boundary against the producer's complete field contract, including timer, integer, status, provider-delay, and non-empty diagnostic bounds. A valid event removes the matching failed step's streaming partial and inserts a durable retry notice at the event's sequence position. The notice is `scheduled` until a following retry turn starts; an aborted or disposed source turn marks it `cancelled`, while the retry turn marks it `started`. Normal-mode notices carry their finite maximum; always-mode notices remain explicitly unbounded. Window rebuild and history replay apply the same projection, so logged chunks from the discarded attempt never reappear as an interrupted reply after refresh. A terminal turn without `llm/retry` retains the existing behavior: visible unfinalized output is frozen as an interrupted assistant node. + ## Session forking `ISessions.fork({sessionId, atSeq?, increaseTitle?})` resolves only after the child summary is locally addressable, carrying source lineage and cwd with `blank: false`; callers choose whether to open it. With `increaseTitle: true`, the client renames the child from the source session's persisted title: a trailing `(N)` or `（N）` is incremented without changing bracket style, while any other title gets ` (1)` appended; the rename is skipped when the source has no persisted title, and a rename failure rejects the promise but leaves the created child in place. This option is not sent in the Host fork request. A `workspace-attach-failed` response still identifies a child already published by the Host, so `SessionManager` reconciles that partial success before `SessionForkError` reaches the caller instead of making a retry create a duplicate child. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index f375811e6f..3ed047e65d 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -12,6 +12,8 @@ Workspace 和 Session 列表各自具有单调的 `pending` → `ready` 基线 SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 observable；web-react 创建钩子。Workspace 业务状态不会进入 `SessionListState` 或配置项 store。 +`SessionsService.search(query, signal)` 是基于 `session.search` RPC 的无状态单次操作。它返回经过排序的会话／snippet 对，但不会将查询条件、加载状态或错误状态写入共享 Session 列表，因此每个 UI 所有者都自行负责防抖、取消、抑制陈旧响应和回退呈现。`searchResultLimit` 将 `SESSION_SEARCH_RESULT_LIMIT`——即响应 schema 自身强制执行的上限——作为注入的呈现数据重新公开，使客户端插件无需复制该值。它是协议常量而非逐连接状态，因此连接 handle 不携带它。 + ## New Session 与 blank 镜像 `WorkspacesService.connectWorkspace(workspaceId)` 解析 New Session 流程最终落入的会话：先在列表镜像中复用该 workspace 的既有空会话（`blank && cwd == workspace.path`），未命中则调用 `session.create({workspaceId})`，返回会话 id 由调用方 open。`SessionSummary.blank` 镜像主机派生的空日志位，在客户端只降不升：由 `session.list`／`host/session-added` 帧播种，本地首次获 Host 接受的 `prompt()`（RPC 成功响应时——受理即证明用户消息已入主机日志；首讯被拒则会话保持 blank、保持可复用）与任何 `running: true` 状态帧翻为 false，每次列表重拉重新对齐。列表界面隐藏 blank 行；store 保留全部行。`SessionsService.create` 接受可选的、由调用方预先分配的 SessionId，失败时抛出 `SessionCreateError`（携带 `requestedSessionId`）。 @@ -28,6 +30,10 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 `SessionManager` 独立于列表和 Session 实例到达情况，保留最近一次通过验证的 `session/title` 控制快照。seq 更高的事件会替换旧快照，标题时间戳计入列表新近程度；订阅基线会先丢弃 seq 超过其 `lastSeq` 的任何已保留标题，再接收可选的折叠标题。显式移除 Session 也会清除已保留标题。因此，面向客户端的 `SessionSummary.title` 只包含实际的持久化标题；`displayTitle` 始终存在，并依次回退到 cwd basename 和 Session id。冷态持久化会话会保持该回退值，直到打开或恢复会话，促使主机折叠并投影由日志支撑的标题。`ISession.rename` 用 unary 响应中的 `{title, seq}` 直接结算 `title` 投影格，遵循同一 seq 高者胜规则——列表行和所有 `useProjection('title')` 读者在推送帧到达前即更新；推送帧随后重放同一 seq 时为无操作。 +## 模型重试投影 + +Session 对象会在事件 wire 边界依据生产方的完整字段契约，验证由插件负责、按提供方路由的 `llm/retry` 载荷，包括计时器、整数、状态、提供方延迟和非空诊断字段的边界。有效事件会移除对应失败步骤的流式输出片段，并在该事件的序列位置插入一条持久的重试提示。该提示在后续重试轮次开始前为 `scheduled`；源轮次中止或释放会将其标记为 `cancelled`，重试轮次则会将其标记为 `started`。normal mode 提示携带其有限上限；always mode 提示则保持显式无界。窗口重建与历史回放应用相同的投影，因此刷新后，来自已丢弃尝试的日志分片绝不会重新显示为中断回复。没有 `llm/retry` 的终止轮次保留现有行为：可见但尚未定稿的输出会冻结为中断的 assistant 节点。 + ## 会话 fork `ISessions.fork({sessionId, atSeq?, increaseTitle?})` 只在子会话摘要已能在本地寻址后才完成；该摘要携带源会话的谱系和 cwd，且 `blank: false`，由调用方决定是否打开。`increaseTitle: true` 会在 client 端把源会话的持久化标题改名到子会话：尾部 `(N)` 或 `（N）` 递增并保留括号样式，其余标题追加 ` (1)`；源会话没有持久化标题时跳过改名，改名失败时拒绝 promise 但保留已创建的子会话。该选项不会进入 Host fork 请求。即使响应为 `workspace-attach-failed`，其中仍会标识 Host 已发布的子会话，因此 `SessionManager` 会先将这一部分成功对账，再让 `SessionForkError` 到达调用方，避免重试创建重复的子会话。 diff --git a/packages/client/runtime/package.json b/packages/client/runtime/package.json index 60e2eddf09..a3897e9523 100644 --- a/packages/client/runtime/package.json +++ b/packages/client/runtime/package.json @@ -36,6 +36,7 @@ "@deepseek-ai/dsh-client-ui-slots": "workspace:^", "@deepseek-ai/dsh-host-apiproxy": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-llm-retry": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-projection": "workspace:^", "@deepseek-ai/dsh-session-title": "workspace:^", @@ -49,6 +50,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/dsh-timeout": "workspace:^", "@types/react": "~18.3.1", "cordis": "^4.0.0-rc.7" }, diff --git a/packages/client/runtime/src/client/contract/sessions.ts b/packages/client/runtime/src/client/contract/sessions.ts index 280bc602eb..79f20a234c 100644 --- a/packages/client/runtime/src/client/contract/sessions.ts +++ b/packages/client/runtime/src/client/contract/sessions.ts @@ -8,8 +8,9 @@ * explicit act of widening what features may do to the sessions domain. */ import type { Context } from 'cordis' -import type { SessionId } from '@deepseek-ai/dsh-client-connection/client' +import type { RpcResult, SessionId } from '@deepseek-ai/dsh-client-connection/client' import type { HostObservable, SessionMaybeProvideInfo } from '@deepseek-ai/dsh-client-ui-slots' +import type { SessionSearchResultItem } from '../sessions/manager.ts' import type { SessionBinding, SessionListState, SessionProvideDescriptor, } from '../sessions/service.ts' @@ -22,6 +23,12 @@ export interface ISessions { readonly list: ObservableSnapshot /** Atomic current-session provide projection (the renderer host's `sessions.provideInfo` feed). */ readonly currentProvideInfo: HostObservable + /** + * The `session.search` result bound the wire schema fixes, exposed to + * presentation as injected data. Not per-connection state: every transport + * (fixture included) reports the same number. + */ + readonly searchResultLimit: number /** * Select a session as current. * @param id - session id (must exist in the list; unknown ids fail loud). @@ -29,6 +36,17 @@ export interface ISessions { open(id: SessionId): void /** Clear the current selection into the no-session view state. */ clear(): void + /** + * Search the Host's visible message-content index. Results stay + * request-local; the list snapshot remains the metadata authority. + * @param query - non-blank literal phrase. + * @param signal - cancellation for a superseded search. + * @returns bounded results, or a business/transport error. + */ + search( + query: string, + signal: AbortSignal, + ): Promise> /** * Fork a session from a completed-turn prefix of the source; on resolution * the child is in the list store and `open()` can target it. diff --git a/packages/client/runtime/src/client/index.ts b/packages/client/runtime/src/client/index.ts index 9a5b3a535d..68d1a3931f 100644 --- a/packages/client/runtime/src/client/index.ts +++ b/packages/client/runtime/src/client/index.ts @@ -31,7 +31,7 @@ export type { IWorkspaces } from './contract/workspaces.ts' export type { SessionBinding, SessionListState, SessionProvideContribution, SessionProvideDescriptor, SessionSummary, } from './sessions/service.ts' -export type { SessionListPhase } from './sessions/manager.ts' +export type { SessionListPhase, SessionSearchResultItem } from './sessions/manager.ts' export type { WorkspaceListPhase } from './workspaces/manager.ts' export type { WorkspaceListState } from './workspaces/service.ts' export type { @@ -45,7 +45,7 @@ export type { export type { AssistantBlock, AssistantMessageNode, AssistantProvenanceView, AssistantRequestConfig, AssistantTiming, CodeSubCall, CommandNode, ComposerPhase, ContextMessageNode, ConversationNode, - ConversationSnapshot, QueuedMessage, RunningToolCall, + ConversationSnapshot, ModelRetryNode, QueuedMessage, RunningToolCall, SteeringMessageNode, TodoItem, ToolResultNode, UnknownSurfaceNode, UserMessageNode, } from './sessions/conversation.ts' export type { diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index f68a271c63..ff027d0b99 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -5,6 +5,7 @@ import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' +import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types' import type { TodoItem } from '@deepseek-ai/dsh-session/types' import type { InboxItemId, RpcError, SessionId, ToolCallView, ToolResultView, @@ -121,6 +122,19 @@ export interface ContextMessageNode { source: unknown } +/** Durable notice that a closed failed step is waiting for a model-request retry. */ +export type ModelRetryNode = LlmRetryEventData & { + kind: 'model-retry' + seq: number + /** Unix epoch ms from the llm/retry session event. */ + time: number + /** + * Client-derived lifecycle: scheduled until a retry turn starts, started + * once it does, or cancelled when the failed turn aborts first. + */ + retryState: 'scheduled' | 'started' | 'cancelled' +} + /** A tool result paired (when in-window) with its call head. */ export interface ToolResultNode { kind: 'tool-result' @@ -183,6 +197,7 @@ export type ConversationNode = | AssistantMessageNode | SteeringMessageNode | ContextMessageNode + | ModelRetryNode | ToolResultNode | CommandNode | UnknownSurfaceNode @@ -265,7 +280,7 @@ export interface PromptError { /** The immutable snapshot contract Session hands to uSES (see the web client architecture RFC). */ export interface ConversationSnapshot { sessionId: SessionId - /** Surface fold product (finalized conversation nodes in surface order). */ + /** Finalized surface events and durable operational notices in event order. */ nodes: readonly ConversationNode[] /** Fold degradation flag (cross-window replace defense): when true, nodes come from the lenient linear scan. */ foldDegraded: boolean diff --git a/packages/client/runtime/src/client/sessions/manager.ts b/packages/client/runtime/src/client/sessions/manager.ts index 4ba134b321..a89d8dbc31 100644 --- a/packages/client/runtime/src/client/sessions/manager.ts +++ b/packages/client/runtime/src/client/sessions/manager.ts @@ -2,7 +2,10 @@ // dispatch entry + list state, constructed and held by SessionsService (one per client runtime). // List data never enters zustand; React connects via subscribe/getListSnapshot. -import type { IApiClient, HostFrame, MuxFrame, RpcError, RpcRequest, RpcResult, SessionId, SessionSummary, WorkspaceId } from '@deepseek-ai/dsh-client-connection/client' +import type { + IApiClient, HostFrame, MuxFrame, RpcError, RpcRequest, RpcResult, SessionId, + SessionSummary, WorkspaceId, +} from '@deepseek-ai/dsh-client-connection/client' // Value import from the inline-safe wire layer (not the connection plugin): // plugin-to-plugin value imports are a bundle purity error. import { transportError } from '@deepseek-ai/dsh-host-apiproxy/api' @@ -27,6 +30,12 @@ import { Session } from './session.ts' */ export type SessionListPhase = 'pending' | 'ready' +/** Request-local content hit returned to sidebar search consumers. */ +export interface SessionSearchResultItem { + sessionId: SessionId + snippet: string +} + /** Immutable session-list snapshot for useSessionList. */ export interface SessionListSnapshot { items: readonly SessionListEntry[] @@ -248,6 +257,24 @@ export class SessionManager { return this.listInflight } + /** + * Search visible session message content without adding transient query + * state to the list snapshot. + * @param query - non-blank literal phrase. + * @param signal - cancellation for superseded UI queries. + * @returns the Host result or a folded transport error. + */ + async search( + query: string, + signal: AbortSignal, + ): Promise> { + try { + return (await this.api.sessions.search({ query }, signal)).result + } catch (error: unknown) { + return transportError(error) + } + } + /** * Contract session.create; on success merge into summaries immediately (no * wait for the next refresh). A created session is blank by definition diff --git a/packages/client/runtime/src/client/sessions/service.ts b/packages/client/runtime/src/client/sessions/service.ts index 342fc3b62e..93ecb3c791 100644 --- a/packages/client/runtime/src/client/sessions/service.ts +++ b/packages/client/runtime/src/client/sessions/service.ts @@ -16,7 +16,12 @@ * survives frozen (read-only view) until the stage moves on. */ import type { Context, Fiber } from 'cordis' -import type { IApiClient, RpcError, SessionId, WorkspaceId } from '@deepseek-ai/dsh-client-connection/client' +import type { + IApiClient, RpcError, RpcResult, SessionId, WorkspaceId, +} from '@deepseek-ai/dsh-client-connection/client' +// Value import from the inline-safe wire layer (not the connection plugin): +// plugin-to-plugin value imports are a bundle purity error. +import { SESSION_SEARCH_RESULT_LIMIT } from '@deepseek-ai/dsh-host-apiproxy/api' import type { HostObservable, SessionMaybeProvideInfo, SessionProvideInfo, } from '@deepseek-ai/dsh-client-ui-slots' @@ -26,7 +31,7 @@ import type { SessionFace } from '../contract/session.ts' import type { ISessions } from '../contract/sessions.ts' import { createScope, scopeOf as scopeTagOf } from '../agents/scope.ts' import { SessionManager } from './manager.ts' -import type { SessionListPhase } from './manager.ts' +import type { SessionListPhase, SessionSearchResultItem } from './manager.ts' import { SessionProvideChannel } from './provide.ts' import type { Session } from './session.ts' @@ -189,6 +194,13 @@ export interface SessionProvideDescriptor { /** Root sessions service: list store, current selection, object-layer manager, scope tree, bindings, ancestry. */ export class SessionsService implements ISessions { + /** + * The wire schema's own result bound, re-exposed for presentation plugins as + * injected data. Not per-connection state: the `session.search` response + * schema caps `items` at this constant, so every transport (fixture included) + * reports the same number. + */ + readonly searchResultLimit = SESSION_SEARCH_RESULT_LIMIT /** List snapshot store (list RPC + host stream increments; re-pulled on reconnect) — the useSessions standard feed, current included. */ readonly list: SnapshotStore /** The object-layer instance cluster and frame dispatch entry. */ @@ -228,7 +240,10 @@ export class SessionsService implements ISessions { * @param ctx - client root context (scope fibers mount under it). * @param api - wire client shared with every Session. */ - constructor(private readonly rootCtx: Context, api: IApiClient) { + constructor( + private readonly rootCtx: Context, + api: IApiClient, + ) { this.selection = createSnapshotStore<{ sessionId?: SessionId }>( {}, { persist: { name: 'dsh.sessions.current' } }) @@ -307,6 +322,20 @@ export class SessionsService implements ISessions { return this.manager.refreshList() } + /** + * Search the Host's visible message-content index. Results stay + * request-local; the list snapshot remains the metadata authority. + * @param query - non-blank literal phrase. + * @param signal - cancellation for a superseded search. + * @returns bounded results or a business/transport error. + */ + search( + query: string, + signal: AbortSignal, + ): Promise> { + return this.manager.search(query, signal) + } + /** * Route a mux stream envelope into the Session object layer. * @param envelope - validated mux stream envelope. diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index 6850e3e4c9..2b63600a59 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -2,6 +2,7 @@ import type { Context } from 'cordis' import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' +import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import type { HistoryEntry, IApiClient, InboxItemId, MuxFrame, QueueAction, RpcError, @@ -12,8 +13,8 @@ import type { import { transportError } from '@deepseek-ai/dsh-host-apiproxy/api' import type { SessionFace } from '../contract/session.ts' import type { - CodeSubCall, ComposerPhase, ConversationNode, ConversationSnapshot, OpenState, - PromptError, QueuedMessage, RunningToolCall, + CodeSubCall, ComposerPhase, ConversationNode, ConversationSnapshot, ModelRetryNode, + OpenState, PromptError, QueuedMessage, RunningToolCall, } from './conversation.ts' import type { PendingInteraction } from './pending.ts' import { PendingWait } from './pending.ts' @@ -26,6 +27,10 @@ import type { ProjectionsBaseline } from './projection-store.ts' /** Messages requested per history page. */ export const PAGE_MESSAGES = 50 +// Browser bundles cannot value-import the host timeout library. This protocol +// bound is pinned to @deepseek-ai/dsh-timeout's MAX_TIMER_DELAY_MS in tests. +const MAX_RETRY_DELAY_MS = 2_147_483_647 + /** Manager-owned observers of a Session object's local state edges. */ export interface SessionOptions { /** @@ -88,9 +93,9 @@ export class Session implements SessionFace { private readonly foldAdapter = new FoldAdapter() private partial: PartialAccumulator | null = null private openCalls = new Map() - /** Interrupted-turn terminal nodes (frozen partial text / aborted tool cards), merged into the flow by seq. - * Derived from window events (turn/end sweep) — rebuilt by rebuildDerivedFromWindow like partial/openCalls. */ - private frozenNodes: ConversationNode[] = [] + /** Operational notices and interrupted-turn terminal nodes merged into the flow by seq. + * Derived from window events — rebuilt by rebuildDerivedFromWindow like partial/openCalls. */ + private derivedNodes: ConversationNode[] = [] private pending = new Map() // Revision counters preserve array identity when derived content is unchanged, so // React.memo children survive unrelated snapshot swaps (chunk storms must not re-render every @@ -100,12 +105,12 @@ export class Session implements SessionFace { private callsCache: { rev: number; value: RunningToolCall[] } | null = null private pendingRev = 0 private pendingCache: { rev: number; value: PendingInteraction[] } | null = null + private derivedRev = 0 + private nodesCache: { folded: readonly ConversationNode[]; derivedRev: number; value: readonly ConversationNode[] } | null = null /** Authoritative stream-only inbox snapshot; pending work never hits history. */ private queued: QueuedMessage[] = [] private queueRev = 0 private queueCache: { rev: number; value: QueuedMessage[] } | null = null - private frozenRev = 0 - private nodesCache: { folded: readonly ConversationNode[]; frozenRev: number; value: readonly ConversationNode[] } | null = null /** `run_code` sub-dispatches by parent callId (window-derived, like openCalls). Appends * copy-on-write the per-parent array so published snapshot references never mutate. */ private codeDispatches = new Map() @@ -625,8 +630,28 @@ export class Session implements SessionFace { } /** Per-event side effects (right column of the §A.9 dispatch table): - * chunk accumulation / partial clear on finalize / openCalls add-remove. */ + * chunk/retry projection and openCalls add-remove. */ private applyEventSideEffects(event: SessionEvent, view?: ToolEventView): void { + const eventType = event.type as string + if (eventType === 'llm/retry') { + const data = parseRetryEventData(event.data) + if (data === null) { + console.error(`[web-runtime] ignored malformed llm/retry event at seq ${event.seq}`) + return + } + if (this.partial !== null && this.partial.turn === data.turn && this.partial.step === data.step) { + this.partial = null + } + this.derivedNodes.push({ + kind: 'model-retry', + seq: event.seq, + time: event.time, + retryState: 'scheduled', + ...data, + }) + this.derivedRev++ + return + } // The `tool/code-dispatch-start`/`tool/code-dispatch` pair is declared by // the host-side dsh-tools plugin whose types cannot enter the client // program (its host Context merges collide with the client's), so this @@ -687,6 +712,10 @@ export class Session implements SessionFace { return } switch (event.type) { + case 'turn/start': { + if (event.data.trigger.kind === 'retry') this.settleScheduledRetry('started') + return + } case 'assistant/chunk': { const { turn, step, chunk } = event.data if (this.partial === null || this.partial.turn !== turn || this.partial.step !== step) { @@ -715,6 +744,9 @@ export class Session implements SessionFace { return } case 'turn/end': { + if (event.data.reason.kind === 'aborted' || event.data.reason.kind === 'disposed') { + this.settleScheduledRetry('cancelled', event.data.turn) + } // Aborted turns never finalize. The accumulated partial is VALUE, not residue: freeze it // into an interrupted terminal node (pulse stops, text survives) instead of deleting it. // Shared by live and window-replay paths, so a refresh reconstructs the same frozen node @@ -724,12 +756,12 @@ export class Session implements SessionFace { const visible = blocks.some(b => (b.kind === 'text' || b.kind === 'reasoning' ? b.text !== '' : true)) if (visible) { // Fractional seq: strictly after every event of this turn (all < turn/end seq), before the next turn. - this.frozenNodes.push({ + this.derivedNodes.push({ kind: 'assistant', seq: event.seq - 0.9, time: event.time, turn: this.partial.turn, step: this.partial.step, blocks, interrupted: true, }) - this.frozenRev++ + this.derivedRev++ } this.partial = null } @@ -739,7 +771,7 @@ export class Session implements SessionFace { this.openCalls.delete(callId) this.callsRev++ // The spinner card becomes an interrupted terminal card (never vanishes mid-flow). - this.frozenNodes.push({ + this.derivedNodes.push({ kind: 'tool-result', seq: event.seq - 0.8 + callOffset++ * 0.01, time: event.time, callId, call: { name: call.name, argsRaw: call.argsRaw }, @@ -747,7 +779,7 @@ export class Session implements SessionFace { content: [], isError: true, error: { name: 'Interrupted', code: 'interrupted' }, callView: call.callView, resultView: null, }) - this.frozenRev++ + this.derivedRev++ } return } @@ -756,15 +788,36 @@ export class Session implements SessionFace { } } - /** Re-derive state (partial/openCalls/frozenNodes) from raw window events after a rebuild — keeps - * paging/stitching consistent, and makes the live freeze and the history replay converge on the - * same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text). */ + /** + * Settle the newest scheduled retry, optionally restricted to its failed turn. + * @param retryState - next client projection state to publish. + * @param turn - failed turn required for cancellation; omitted for the next retry turn start. + */ + private settleScheduledRetry( + retryState: Exclude, + turn?: number, + ): void { + const index = this.derivedNodes.findLastIndex(node => + node.kind === 'model-retry' + && node.retryState === 'scheduled' + && (turn === undefined || node.turn === turn)) + if (index < 0) return + const node = this.derivedNodes[index] + /* v8 ignore next -- findLastIndex's predicate narrows the indexed node only at runtime. */ + if (node?.kind !== 'model-retry') return + this.derivedNodes[index] = { ...node, retryState } + this.derivedRev++ + } + + /** Re-derive state (partial/openCalls/derivedNodes) from raw window events after a rebuild — keeps + * paging/stitching consistent, and makes live handling and history replay converge on the same + * retry notices and interrupted nodes. */ private rebuildDerivedFromWindow(): void { this.partial = null this.openCalls.clear() this.callsRev++ - this.frozenNodes = [] - this.frozenRev++ + this.derivedNodes = [] + this.derivedRev++ this.codeDispatches = new Map() this.dispatchesRev++ for (let i = 0; i < this.events.length; i++) { @@ -781,17 +834,17 @@ export class Session implements SessionFace { private buildSnapshot(): ConversationSnapshot { const { nodes: folded, degraded } = this.foldAdapter.nodes() - // Frozen interrupted nodes ride fractional seqs: a stable merge keeps them in flow order. - // The merged array is cached on (folded reference, frozenRev) so an unchanged flow keeps its + // Derived nodes use their event seq or a nearby fractional seq: a stable merge keeps flow order. + // The merged array is cached on (folded reference, derivedRev) so an unchanged flow keeps its // reference across snapshot swaps (§A.9.4). let nodes: readonly ConversationNode[] - if (this.nodesCache !== null && this.nodesCache.folded === folded && this.nodesCache.frozenRev === this.frozenRev) { + if (this.nodesCache !== null && this.nodesCache.folded === folded && this.nodesCache.derivedRev === this.derivedRev) { nodes = this.nodesCache.value } else { - nodes = this.frozenNodes.length === 0 + nodes = this.derivedNodes.length === 0 ? folded - : [...folded, ...this.frozenNodes].sort((a, b) => a.seq - b.seq) - this.nodesCache = { folded, frozenRev: this.frozenRev, value: nodes } + : [...folded, ...this.derivedNodes].sort((a, b) => a.seq - b.seq) + this.nodesCache = { folded, derivedRev: this.derivedRev, value: nodes } } if (this.callsCache === null || this.callsCache.rev !== this.callsRev) { this.callsCache = { rev: this.callsRev, value: [...this.openCalls.values()] } @@ -835,6 +888,58 @@ export class Session implements SessionFace { } } +/** Validate the plugin-owned payload at the session-event wire boundary. */ +function parseRetryEventData(value: unknown): LlmRetryEventData | null { + if (value === null || typeof value !== 'object') return null + const data = value as Record + const failure = data.failure + if (failure === null || typeof failure !== 'object') return null + const failureData = failure as Record + if (!nonNegativeSafeInteger(data.turn) + || !nonNegativeSafeInteger(data.step) + || typeof data.provider !== 'string' + || data.provider.length === 0 + || typeof data.policyKey !== 'string' + || data.policyKey.length === 0 + || !positiveSafeInteger(data.retry) + || typeof data.delayMs !== 'number' + || !Number.isFinite(data.delayMs) + || data.delayMs < 0 + || data.delayMs > MAX_RETRY_DELAY_MS + || typeof failureData.message !== 'string' + || failureData.message.length === 0 + || typeof failureData.code !== 'string' + || failureData.code.length === 0) return null + if (data.mode === 'normal') { + if (!positiveSafeInteger(data.maxRetries) || data.retry > data.maxRetries) return null + } else if (data.mode === 'always') { + if ('maxRetries' in data) return null + } else { + return null + } + if (failureData.status !== undefined + && (typeof failureData.status !== 'number' + || !Number.isInteger(failureData.status) + || failureData.status < 100 + || failureData.status > 599)) return null + if (failureData.providerRetryAfterMs !== undefined + && (typeof failureData.providerRetryAfterMs !== 'number' + || !Number.isFinite(failureData.providerRetryAfterMs) + || failureData.providerRetryAfterMs <= 0)) return null + if (failureData.requestId !== undefined + && (typeof failureData.requestId !== 'string' + || failureData.requestId.length === 0)) return null + return data as unknown as LlmRetryEventData +} + +function nonNegativeSafeInteger(value: unknown): value is number { + return typeof value === 'number' && Number.isSafeInteger(value) && value >= 0 +} + +function positiveSafeInteger(value: unknown): value is number { + return nonNegativeSafeInteger(value) && value > 0 +} + /** * The composerPhase judgment — the single site that knows the predicate * (consumers switch on the result, never re-derive). Monotone per session diff --git a/packages/client/runtime/tests/client-apply.spec.ts b/packages/client/runtime/tests/client-apply.spec.ts index d5b29f10a9..d389efe319 100644 --- a/packages/client/runtime/tests/client-apply.spec.ts +++ b/packages/client/runtime/tests/client-apply.spec.ts @@ -7,6 +7,7 @@ import { Context } from 'cordis' import { describe, expect, it } from 'vitest' import type { ConnectionHandle } from '@deepseek-ai/dsh-client-connection/client' import type { ConnectionSinks } from '@deepseek-ai/dsh-client-connection/client' +import { SESSION_SEARCH_RESULT_LIMIT } from '@deepseek-ai/dsh-host-apiproxy/api' import * as RuntimeClient from '../src/client/index.ts' import type { SessionsService } from '../src/client/sessions/service.ts' import type { WorkspacesService } from '../src/client/workspaces/service.ts' @@ -50,6 +51,8 @@ describe('runtime client apply', () => { const workspaces = bench.ctx.get('workspaces') expect(sessions !== undefined).toBe(true) expect(workspaces !== undefined).toBe(true) + // The bound the wire schema enforces, not a per-connection negotiation. + expect((sessions as SessionsService).searchResultLimit).toBe(SESSION_SEARCH_RESULT_LIMIT) if (workspaces === undefined) throw new Error('WorkspacesService missing after runtime apply') expect(bench.sinks).toBeDefined() diff --git a/packages/client/runtime/tests/event-script.ts b/packages/client/runtime/tests/event-script.ts index 53f80e0e69..b96fffaae9 100644 --- a/packages/client/runtime/tests/event-script.ts +++ b/packages/client/runtime/tests/event-script.ts @@ -63,7 +63,25 @@ export const ev = { }), stepEnd: (seq: number, turn: number, step = 0): SessionEvent => at(seq, { type: 'step/end', data: { turn, step } }), - turnEnd: (seq: number, turn: number, reason: 'completed' | 'cancelled' = 'completed'): SessionEvent => + retry: ( + seq: number, + turn: number, + step = 0, + retry = 1, + maxRetries = 2, + delayMs = 500, + message = 'temporary transport failure', + ): SessionEvent => + at(seq, { + type: 'llm/retry', + data: { + turn, step, + provider: 'fake', mode: 'normal', policyKey: 'fake-normal', + retry, maxRetries, delayMs, + failure: { code: 'TRANSPORT', message }, + }, + }), + turnEnd: (seq: number, turn: number, reason: 'completed' | 'aborted' | 'disposed' = 'completed'): SessionEvent => at(seq, { type: 'turn/end', data: { turn, reason: { kind: reason } } }), commandRun: (seq: number, commandId: string, name: string, args = ''): SessionEvent => at(seq, { type: 'command/run', data: { commandId, name, args, source: { kind: 'user' } } }), diff --git a/packages/client/runtime/tests/fake-api.ts b/packages/client/runtime/tests/fake-api.ts index 041ea02dee..06d948ae83 100644 --- a/packages/client/runtime/tests/fake-api.ts +++ b/packages/client/runtime/tests/fake-api.ts @@ -4,7 +4,7 @@ import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import type { ClientResponse, CommandDescriptor, HostFrame, IApiClient, ModelTarget, MuxFrame, - RpcError, RpcReceipt, RpcRequest, RpcResponse, SessionId, SessionModels, SkillEntry, + RpcError, RpcReceipt, RpcRequest, RpcResponse, SessionId, SessionModels, SessionSearchItem, SkillEntry, WorkspaceId, WorkspaceView, } from '@deepseek-ai/dsh-client-connection/client' import { RpcId } from '@deepseek-ai/dsh-client-connection/client' @@ -61,6 +61,8 @@ export class FakeApiClient implements IApiClient { // Programmable slots (defaults answer OK-empty); reassign per case. onList: (payload: unknown) => Promise> = () => Promise.resolve(ok({ items: [] })) + onSearch: (payload: unknown) => Promise> = + () => Promise.resolve(ok({ items: [], hasMore: false })) onCreate: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId })) readonly defaultModel: ModelTarget = { provider: 'deepseek-official', model: 'deepseek-v4-flash' } onRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 })) @@ -106,12 +108,17 @@ export class FakeApiClient implements IApiClient { private readonly muxConns: StreamConn[] = [] private readonly hostConns: StreamConn[] = [] + lastSearchSignal: AbortSignal | undefined // Parameters carry local structural annotations: the CI lint lane runs // without built lib/, so IApiClient's indexed-access types collapse to any // and inferred parameters would trip no-unsafe-argument. readonly sessions: IApiClient['sessions'] = { list: (payload: unknown) => this.record('session.list', payload, this.onList(payload)), + search: (payload: unknown, signal?: AbortSignal) => { + this.lastSearchSignal = signal + return this.record('session.search', payload, this.onSearch(payload)) + }, create: (payload: unknown) => this.record('session.create', payload, this.onCreate(payload)), history: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) => this.record('session.history', payload, this.onHistory(payload)), diff --git a/packages/client/runtime/tests/manager.spec.ts b/packages/client/runtime/tests/manager.spec.ts index 6a0f30f4c6..1330a49768 100644 --- a/packages/client/runtime/tests/manager.spec.ts +++ b/packages/client/runtime/tests/manager.spec.ts @@ -206,6 +206,49 @@ describe('list lifecycle', () => { }) }) +describe('search', () => { + it('returns bounded Host results and forwards the caller signal', async () => { + const api = new FakeApiClient() + api.onSearch = () => Promise.resolve(ok({ + items: [{ sessionId: S1, snippet: 'matching excerpt' }], + hasMore: true, + })) + const manager = new SessionManager(api) + const signal = new AbortController().signal + + await expect(manager.search('exact phrase', signal)).resolves.toEqual({ + ok: true, + value: { + items: [{ sessionId: S1, snippet: 'matching excerpt' }], + hasMore: true, + }, + }) + expect(api.callsOf('session.search')).toEqual([{ query: 'exact phrase' }]) + expect(api.lastSearchSignal).toBe(signal) + }) + + it('preserves business errors and folds transport failures', async () => { + const api = new FakeApiClient() + const manager = new SessionManager(api) + api.onSearch = () => Promise.resolve(err({ + code: 'internal', + message: 'index unavailable', + details: {}, + })) + const signal = new AbortController().signal + await expect(manager.search('first', signal)).resolves.toMatchObject({ + ok: false, + error: { code: 'internal', message: 'index unavailable' }, + }) + + api.onSearch = () => Promise.reject(new Error('wire down')) + await expect(manager.search('second', signal)).resolves.toMatchObject({ + ok: false, + error: { code: 'internal', message: 'wire down' }, + }) + }) +}) + describe('host frame routing', () => { it('adds/removes/flips sessions from host frames and keeps removed instances resident', async () => { const api = new FakeApiClient() diff --git a/packages/client/runtime/tests/session.spec.ts b/packages/client/runtime/tests/session.spec.ts index e62e14bd48..a8b1fbd5dc 100644 --- a/packages/client/runtime/tests/session.spec.ts +++ b/packages/client/runtime/tests/session.spec.ts @@ -8,6 +8,7 @@ import { describe, expect, it, vi } from 'vitest' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' +import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout' import type { SessionId } from '@deepseek-ai/dsh-client-connection/client' import { Session } from '../src/client/sessions/session.ts' import { FakeApiClient, deferred, err, ok } from './fake-api.ts' @@ -161,6 +162,214 @@ describe('live event path', () => { expect((last as { interrupted?: true }).interrupted).toBeUndefined() }) + it('retracts the failed step partial on retry and keeps a replayable notice before the recovered response', async () => { + const { session } = await opened() + const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } + const retryTurn = [ + ev.turnStart(6, 1), + ev.user(7, '请重试'), + ev.stepStart(8, 1), + ev.chunkStart(9, 1), + ev.chunkText(10, 1, '不完整回复'), + ev.stepEnd(11, 1), + ev.retry(12, 1, 0, 1, 2, 450, '连接被重置'), + at(13, { + type: 'turn/end', + data: { + turn: 1, + reason: { + kind: 'error', step: 0, + failure: { code: 'TRANSPORT', message: '连接被重置' }, + }, + }, + }), + at(14, { type: 'turn/start', data: { turn: 2, trigger: { kind: 'retry' } } }), + ev.stepStart(15, 2), + ev.assistant(16, 2, '完整回复'), + ev.stepEnd(17, 2), + ev.turnEnd(18, 2), + ] + for (const event of retryTurn.slice(0, 7)) feed(event) + + let snapshot = session.getSnapshot() + expect(snapshot.partial).toBeNull() + expect(snapshot.nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'scheduled', + turn: 1, + step: 0, + provider: 'fake', + mode: 'normal', + policyKey: 'fake-normal', + retry: 1, + maxRetries: 2, + delayMs: 450, + failure: { code: 'TRANSPORT', message: '连接被重置' }, + }) + expect(JSON.stringify(snapshot.nodes)).not.toContain('不完整回复') + + for (const event of retryTurn.slice(7)) feed(event) + snapshot = session.getSnapshot() + expect(snapshot.nodes.slice(-2).map(node => node.kind)).toEqual(['model-retry', 'assistant']) + expect(snapshot.nodes.at(-2)).toMatchObject({ kind: 'model-retry', retryState: 'started' }) + expect(snapshot.nodes.at(-1)).toMatchObject({ kind: 'assistant', blocks: [{ kind: 'text', text: '完整回复' }] }) + + const replay = makeSession() + replay.api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ...retryTurn]) + await replay.session.open() + expect(replay.session.getSnapshot().nodes).toEqual(snapshot.nodes) + expect(replay.session.getSnapshot().partial).toBeNull() + }) + + it('rejects retry payloads outside the producer contract without retracting the current partial', async () => { + const { session } = await opened() + const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } + feed(ev.turnStart(6, 1)) + feed(ev.chunkStart(7, 1)) + feed(ev.chunkText(8, 1, '仍在生成')) + const valid = { + turn: 1, step: 0, + provider: 'fake', mode: 'normal', policyKey: 'fake-normal', + retry: 1, maxRetries: 2, delayMs: 500, + failure: { code: 'TRANSPORT', message: 'temporary failure' }, + } + const invalid = [ + { ...valid, turn: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, step: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, provider: '' }, + { ...valid, policyKey: '' }, + { ...valid, retry: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, maxRetries: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, delayMs: -1 }, + { ...valid, delayMs: Number.POSITIVE_INFINITY }, + { ...valid, delayMs: MAX_TIMER_DELAY_MS + 1 }, + { ...valid, failure: { ...valid.failure, message: '' } }, + { ...valid, failure: { ...valid.failure, code: '' } }, + { ...valid, failure: { ...valid.failure, status: '429' } }, + { ...valid, failure: { ...valid.failure, status: 99 } }, + { ...valid, failure: { ...valid.failure, status: 429.5 } }, + { ...valid, failure: { ...valid.failure, status: 600 } }, + { ...valid, failure: { ...valid.failure, providerRetryAfterMs: 0 } }, + { ...valid, failure: { ...valid.failure, providerRetryAfterMs: Number.POSITIVE_INFINITY } }, + { ...valid, failure: { ...valid.failure, requestId: 1 } }, + { ...valid, failure: { ...valid.failure, requestId: '' } }, + ] + const errorSpy = vi.spyOn(console, 'error').mockImplementation(() => undefined) + try { + for (const [index, data] of invalid.entries()) { + feed(at(9 + index, { type: 'llm/retry', data })) + } + expect(session.getSnapshot().partial?.blocks).toEqual([{ kind: 'text', text: '仍在生成' }]) + expect(session.getSnapshot().nodes.filter(node => node.kind === 'model-retry')).toEqual([]) + expect(errorSpy).toHaveBeenCalledTimes(invalid.length) + expect(errorSpy).toHaveBeenCalledWith('[web-runtime] ignored malformed llm/retry event at seq 9') + } finally { + errorSpy.mockRestore() + } + }) + + it('accepts complete retry payloads at the producer field boundaries', async () => { + const { session } = await opened() + session.handleMuxEnvelope('r' as never, { + type: 'session/event', + sessionId: SID, + event: at(6, { + type: 'llm/retry', + data: { + turn: Number.MAX_SAFE_INTEGER, + step: Number.MAX_SAFE_INTEGER, + provider: 'fake', + mode: 'normal', + policyKey: 'fake-normal', + retry: Number.MAX_SAFE_INTEGER, + maxRetries: Number.MAX_SAFE_INTEGER, + delayMs: MAX_TIMER_DELAY_MS, + failure: { + code: 'RATE_LIMIT', + message: 'provider busy', + status: 599, + providerRetryAfterMs: Number.MIN_VALUE, + requestId: 'req-1', + }, + }, + }), + }) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'scheduled', + retry: Number.MAX_SAFE_INTEGER, + delayMs: MAX_TIMER_DELAY_MS, + failure: { status: 599, providerRetryAfterMs: Number.MIN_VALUE, requestId: 'req-1' }, + }) + }) + + it('projects always-mode retries and rejects mode-specific maximums or unknown modes', async () => { + const { session } = await opened() + const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } + const errorSpy = vi.spyOn(console, 'error').mockImplementation(() => undefined) + try { + feed(at(6, { + type: 'llm/retry', + data: { + turn: 1, step: 0, + provider: 'fake', mode: 'always', policyKey: 'fake-always', + retry: 3, delayMs: 500, + failure: { code: 'TRANSPORT', message: 'retry forever' }, + }, + })) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'scheduled', + mode: 'always', + retry: 3, + }) + + feed(at(7, { + type: 'llm/retry', + data: { + turn: 2, step: 0, + provider: 'fake', mode: 'always', policyKey: 'fake-always', + retry: 4, maxRetries: 4, delayMs: 500, + failure: { code: 'TRANSPORT', message: 'unexpected maximum' }, + }, + })) + feed(at(8, { + type: 'llm/retry', + data: { + turn: 2, step: 0, + provider: 'fake', mode: 'sometimes', policyKey: 'fake-unknown', + retry: 4, delayMs: 500, + failure: { code: 'TRANSPORT', message: 'unknown mode' }, + }, + })) + expect(session.getSnapshot().nodes.filter(node => node.kind === 'model-retry')).toHaveLength(1) + expect(errorSpy).toHaveBeenCalledTimes(2) + } finally { + errorSpy.mockRestore() + } + }) + + it.each(['aborted', 'disposed'] as const)( + 'marks a scheduled retry as cancelled when its failed turn ends %s', + async (reason) => { + const { session } = await opened() + const feed = (event: SessionEvent) => { + session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) + } + feed(ev.turnStart(6, 1)) + feed(ev.retry(7, 1)) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'scheduled', + }) + feed(ev.turnEnd(8, 1, reason)) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'cancelled', + }) + }, + ) + it('freezes an unfinalized partial into an interrupted node on turn/end (cancel path)', async () => { const { session } = await opened() const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } @@ -168,7 +377,7 @@ describe('live event path', () => { feed(ev.user(7, '要被打断的')) feed(ev.chunkStart(8, 1)) feed(ev.chunkText(9, 1, '说到一半')) - feed(ev.turnEnd(10, 1, 'cancelled')) // no assistant/message ever arrives + feed(ev.turnEnd(10, 1, 'aborted')) // no assistant/message ever arrives const snapshot = session.getSnapshot() expect(snapshot.partial).toBeNull() const frozen = snapshot.nodes.at(-1) @@ -187,7 +396,7 @@ describe('live event path', () => { expect(session.getSnapshot().runningCalls).toEqual([]) // Second call never resolves: turn/end freezes it as an error card. feed(ev.toolCall(9, 1, 'c2', 'slow_tool', '{}')) - feed(ev.turnEnd(10, 1, 'cancelled')) + feed(ev.turnEnd(10, 1, 'aborted')) const snapshot = session.getSnapshot() expect(snapshot.runningCalls).toEqual([]) expect(snapshot.nodes.at(-1)).toMatchObject({ @@ -529,7 +738,7 @@ describe('remaining branches', () => { const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } feed(ev.turnStart(6, 1)) feed(ev.chunkStart(7, 1)) // empty text block only, no delta - feed(ev.turnEnd(8, 1, 'cancelled')) + feed(ev.turnEnd(8, 1, 'aborted')) const snapshot = session.getSnapshot() expect(snapshot.partial).toBeNull() expect(snapshot.nodes.filter(n => n.kind === 'assistant' && (n as { interrupted?: true }).interrupted)).toEqual([]) @@ -543,7 +752,7 @@ describe('remaining branches', () => { feed(ev.turnStart(6, 1)) feed(ev.toolCall(7, 1, 'turn1-call', 'echo', '{}')) feed(ev.toolCall(8, 2, 'turn2-call', 'echo', '{}')) // stray call attributed to a later turn - feed(ev.turnEnd(9, 1, 'cancelled')) + feed(ev.turnEnd(9, 1, 'aborted')) const snapshot = session.getSnapshot() expect(snapshot.runningCalls.map(c => c.callId)).toEqual(['turn2-call']) expect(snapshot.nodes.at(-1)).toMatchObject({ kind: 'tool-result', callId: 'turn1-call', isError: true }) @@ -637,7 +846,7 @@ describe('remaining branches', () => { const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } feed(ev.turnStart(6, 1)) feed(at(7, { type: 'assistant/chunk', data: { turn: 1, step: 0, chunk: { type: 'tool-call-delta', index: 0, id: 'c1', name: 'echo', argumentsDelta: '{' } } })) - feed(ev.turnEnd(8, 1, 'cancelled')) + feed(ev.turnEnd(8, 1, 'aborted')) const frozen = session.getSnapshot().nodes.at(-1) expect(frozen).toMatchObject({ kind: 'assistant', interrupted: true, blocks: [{ kind: 'tool-call', callId: 'c1' }] }) }) diff --git a/packages/client/runtime/tests/sessions-service.spec.ts b/packages/client/runtime/tests/sessions-service.spec.ts index 8687f208f0..9fabb0d8de 100644 --- a/packages/client/runtime/tests/sessions-service.spec.ts +++ b/packages/client/runtime/tests/sessions-service.spec.ts @@ -69,6 +69,29 @@ describe('list store projection', () => { }) }) +describe('search', () => { + it('delegates transient content search without changing the list snapshot', async () => { + const b = bench() + await feedList(b, [{ id: 's1' }]) + const before = b.svc.list.getSnapshot() + b.api.onSearch = () => Promise.resolve(ok({ + items: [{ sessionId: sid('s1'), snippet: 'matching excerpt' }], + hasMore: false, + })) + const signal = new AbortController().signal + + await expect(b.svc.search('needle', signal)).resolves.toEqual({ + ok: true, + value: { + items: [{ sessionId: 's1', snippet: 'matching excerpt' }], + hasMore: false, + }, + }) + expect(b.api.lastSearchSignal).toBe(signal) + expect(b.svc.list.getSnapshot()).toBe(before) + }) +}) + describe('scope tree', () => { it('mints lazily on first resolution, tags the ctx, and keeps binding identity stable', async () => { const b = bench() diff --git a/packages/client/runtime/tsconfig.json b/packages/client/runtime/tsconfig.json index 7d3f05e6c7..1abbb0414e 100644 --- a/packages/client/runtime/tsconfig.json +++ b/packages/client/runtime/tsconfig.json @@ -35,6 +35,9 @@ { "path": "../../llm/llm" }, + { + "path": "../../llm/llm-retry" + }, { "path": "../../support/invariants" } diff --git a/packages/client/test-runtime/package.json b/packages/client/test-runtime/package.json index 10b80bdd68..e892d9cd52 100644 --- a/packages/client/test-runtime/package.json +++ b/packages/client/test-runtime/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-client-runtime": "^0.0.1", "@deepseek-ai/dsh-client-ui-slots": "^0.0.1", "@deepseek-ai/dsh-client-web-react": "^0.0.1", + "@deepseek-ai/dsh-host-apiproxy": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "cordis": "^4.0.0-rc.7", "react": "^18.2.0", @@ -37,6 +38,7 @@ "@deepseek-ai/dsh-client-runtime": "workspace:^", "@deepseek-ai/dsh-client-ui-slots": "workspace:^", "@deepseek-ai/dsh-client-web-react": "workspace:^", + "@deepseek-ai/dsh-host-apiproxy": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@types/react": "~18.3.1", "@types/react-dom": "~18.3.0", diff --git a/packages/client/test-runtime/src/index.ts b/packages/client/test-runtime/src/index.ts index 987039b385..7100e1595e 100644 --- a/packages/client/test-runtime/src/index.ts +++ b/packages/client/test-runtime/src/index.ts @@ -37,6 +37,7 @@ export { FixtureSession, TestSessions } from './sessions.ts' export { TestWorkspaces } from './workspaces.ts' export { conversationSnapshot, workspaceListState } from './fixtures.ts' export type { SessionBehaviorOverrides, SessionFixture, Stabilizer } from './fixtures.ts' +export { makeTranslate } from './translate.ts' /** Erased register face for the internal root call (the public declare seam holds the typing). */ type ErasedRegister = (options: object, component: unknown) => () => void diff --git a/packages/client/test-runtime/src/sessions.ts b/packages/client/test-runtime/src/sessions.ts index f40f9a14a5..b26c033bb7 100644 --- a/packages/client/test-runtime/src/sessions.ts +++ b/packages/client/test-runtime/src/sessions.ts @@ -4,8 +4,11 @@ import { createScope, scopeOf, SessionProvideChannel } from '@deepseek-ai/dsh-cl import { createSnapshotStore } from '@deepseek-ai/dsh-client-runtime/client' import type { ConversationSnapshot, ISessions, ObservableSnapshot, ProjectionsFace, SessionFace, SessionId, - SessionListState, SessionProvideDescriptor, SessionSummary, SnapshotStore, + SessionListState, SessionProvideDescriptor, SessionSearchResultItem, SessionSummary, SnapshotStore, } from '@deepseek-ai/dsh-client-runtime/client' +// The double reports the wire schema's own search bound, like the production +// service — a transport-varying limit would be a fiction no client can see. +import { SESSION_SEARCH_RESULT_LIMIT } from '@deepseek-ai/dsh-host-apiproxy/api' import type { HostObservable, SessionMaybeProvideInfo, SessionProvideInfo } from '@deepseek-ai/dsh-client-ui-slots' import { conversationSnapshot } from './fixtures.ts' import type { SessionFixture, Stabilizer } from './fixtures.ts' @@ -151,8 +154,8 @@ export interface TestSessionBinding { * * Implements the same ISessions face features receive as `ctx.sessions`, so * a production face change breaks this double at compile time; the extra - * members (add/updateSnapshot/setCurrent/remove/behavior/calls and the - * legacy provideInfo/maybeProvideInfo lookups) are bench-only surface. + * members (add/updateSnapshot/setCurrent/remove/behavior/calls/stubSearch and + * the legacy provideInfo/maybeProvideInfo lookups) are bench-only surface. */ export class TestSessions implements ISessions { /** The useSessions standard feed (list rows + current selection). */ @@ -168,8 +171,14 @@ export class TestSessions implements ISessions { /** The production provide channel (roster, materialization rules, current projection) — no test-side mirror. */ private readonly channel: SessionProvideChannel - /** Calls observed on the service-level face (open/clear), newest last. */ - readonly calls: { method: 'open' | 'clear' | 'fork'; args: unknown[] }[] = [] + /** Calls observed on the service-level face (open/clear/search/fork), newest last. */ + readonly calls: { method: 'open' | 'clear' | 'search' | 'fork'; args: unknown[] }[] = [] + + /** The wire schema's `session.search` result bound (production parity). */ + readonly searchResultLimit = SESSION_SEARCH_RESULT_LIMIT + + /** Replaceable search behavior (see {@link TestSessions.stubSearch}). */ + private searchStub: ((query: string, signal: AbortSignal) => { items: SessionSearchResultItem[]; hasMore: boolean }) | undefined /** * @param stabilize - the owning runtime's act wrapper. @@ -392,6 +401,27 @@ export class TestSessions implements ISessions { this.list.update((draft) => { draft.current = undefined }) } + /** + * Replace the sidebar-search result page (the call is still recorded). + * @param impl - hits for a query, as the Host would rank them. + */ + stubSearch(impl: (query: string, signal: AbortSignal) => { items: SessionSearchResultItem[]; hasMore: boolean }): void { + this.searchStub = impl + } + + /** + * Content search over the fixture corpus (recorded). The default answers an + * empty page: content ranking is Host behavior, so a scenario that asserts + * hits declares them through {@link TestSessions.stubSearch}. + * @param query - non-blank literal phrase. + * @param signal - cancellation for a superseded search (recorded and forwarded). + * @returns the stubbed or empty result page. + */ + search(query: string, signal: AbortSignal): ReturnType { + this.calls.push({ method: 'search', args: [query, signal] }) + return Promise.resolve({ ok: true, value: this.searchStub?.(query, signal) ?? { items: [], hasMore: false } }) + } + /** * Recorded fork stub: no child materializes (benches asserting the full * fork flow drive the production service; this face only proves the call). diff --git a/packages/client/test-runtime/src/translate.ts b/packages/client/test-runtime/src/translate.ts new file mode 100644 index 0000000000..65c06d5cee --- /dev/null +++ b/packages/client/test-runtime/src/translate.ts @@ -0,0 +1,32 @@ +/** + * Test double of the locale lookup chain: a translate stub over plain + * dictionaries, mirroring LocaleService's resolution order (first dictionary + * that owns the key wins, then the key itself stays visible) and its + * `{name}` template interpolation. Specs stub the framework-injected `t` + * seat with `makeTranslate(zh, commonZh)` instead of re-implementing the + * chain per suite. + */ + +/** + * Build a translate stub resolving through `dicts` in order (namespace + * first, then the shared common vocabulary), falling back to the key. + * @param dicts - dictionaries consulted in order. + * @returns the translate function (assignable to any `XxxProps['t']` seat). + */ +export function makeTranslate( + ...dicts: readonly Record[] +): (key: string, params?: Record) => string { + return (key, params) => { + let template = key + for (const dict of dicts) { + const hit = dict[key] + if (hit !== undefined) { + template = hit + break + } + } + if (!params) return template + return template.replace(/\{(\w+)\}/g, (match, name: string) => + name in params ? String(params[name]) : match) + } +} diff --git a/packages/client/test-runtime/tests/runtime.spec.tsx b/packages/client/test-runtime/tests/runtime.spec.tsx index 62bab2845a..8909f88162 100644 --- a/packages/client/test-runtime/tests/runtime.spec.tsx +++ b/packages/client/test-runtime/tests/runtime.spec.tsx @@ -221,6 +221,28 @@ describe('sessions', () => { ]) await runtime.dispose() }) + + it('answers search with an empty page until a scenario declares hits, recording every call', async () => { + const runtime = await runtimeWithFrame() + await runtime.sessions.add({ id: 's1' }) + const signal = new AbortController().signal + expect(runtime.sessions.searchResultLimit).toBeGreaterThan(0) + await expect(runtime.sessions.search('marker', signal)) + .resolves.toEqual({ ok: true, value: { items: [], hasMore: false } }) + runtime.sessions.stubSearch(query => ({ + items: [{ sessionId: 's1' as SessionId, snippet: `hit: ${query}` }], + hasMore: true, + })) + await expect(runtime.sessions.search('marker', signal)).resolves.toEqual({ + ok: true, + value: { items: [{ sessionId: 's1', snippet: 'hit: marker' }], hasMore: true }, + }) + expect(runtime.sessions.calls).toEqual([ + { method: 'search', args: ['marker', signal] }, + { method: 'search', args: ['marker', signal] }, + ]) + await runtime.dispose() + }) }) describe('stores', () => { diff --git a/packages/client/test-runtime/tsconfig.json b/packages/client/test-runtime/tsconfig.json index 3e8a8561f8..6a758c66f9 100644 --- a/packages/client/test-runtime/tsconfig.json +++ b/packages/client/test-runtime/tsconfig.json @@ -22,6 +22,9 @@ }, { "path": "../../support/invariants" + }, + { + "path": "../../host/apiproxy" } ] } diff --git a/packages/client/ui-command/package.json b/packages/client/ui-command/package.json index c34f34dc18..8144aea6c8 100644 --- a/packages/client/ui-command/package.json +++ b/packages/client/ui-command/package.json @@ -25,6 +25,7 @@ "dshClient": { "inject": [ "@deepseek-ai/dsh-client-runtime", + "@deepseek-ai/dsh-client-locale", "@deepseek-ai/dsh-client-ui-slash", "@deepseek-ai/dsh-client-ui-conversation" ], @@ -40,6 +41,7 @@ }, "peerDependencies": { "@deepseek-ai/dsh-client-connection": "^0.0.1", + "@deepseek-ai/dsh-client-locale": "^0.0.1", "@deepseek-ai/dsh-client-runtime": "^0.0.1", "@deepseek-ai/dsh-client-ui-conversation": "^0.0.1", "@deepseek-ai/dsh-client-ui-primitives": "^0.0.1", @@ -51,7 +53,9 @@ }, "devDependencies": { "@deepseek-ai/dsh-client-connection": "workspace:^", + "@deepseek-ai/dsh-client-locale": "workspace:^", "@deepseek-ai/dsh-client-runtime": "workspace:^", + "@deepseek-ai/dsh-client-test-runtime": "workspace:^", "@deepseek-ai/dsh-client-ui-conversation": "workspace:^", "@deepseek-ai/dsh-client-ui-primitives": "workspace:^", "@deepseek-ai/dsh-client-ui-slash": "workspace:^", diff --git a/packages/client/ui-command/src/client/PopupSelectView.tsx b/packages/client/ui-command/src/client/PopupSelectView.tsx index ec0bbdd2bb..7fe5edcb86 100644 --- a/packages/client/ui-command/src/client/PopupSelectView.tsx +++ b/packages/client/ui-command/src/client/PopupSelectView.tsx @@ -13,6 +13,7 @@ import { useEffect, useRef } from 'react' import { useSyncExternalStore } from 'react' import clsx from 'clsx' import { IconCheckOutline16, useAnchoredMaxHeight } from '@deepseek-ai/dsh-client-ui-primitives' +import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' import { filterOptions } from './popup.ts' import type { PopupSelectController } from './popup.ts' import css from './PopupSelectView.module.css' @@ -26,12 +27,15 @@ export interface PopupSelectInjected { popup: PopupSelectController } +/** Full shell props: injected face + the locale seat. */ +export type PopupSelectViewProps = PopupSelectInjected & PropsLocale<'command'> + /** * Render the popupSelect shell overlay entry. - * @param props - injected face: the session's shell controller. + * @param props - injected face: the session's shell controller; `t` rides the standard locale seat. * @returns the select card while open; null while closed. */ -export function PopupSelectView({ popup }: PopupSelectInjected) { +export function PopupSelectView({ popup, t }: PopupSelectViewProps) { const state = useSyncExternalStore( fn => popup.state.subscribe(fn), () => popup.state.getSnapshot(), @@ -103,15 +107,15 @@ export function PopupSelectView({ popup }: PopupSelectInjected) { ref={cardRef} className={css.card} style={{ maxHeight }} - aria-label={`/${String(state.command)} options`} + aria-label={t('overlay.aria', { command: String(state.command) })} onKeyDown={onKeyDown} > { popup.setSearch(ev.currentTarget.value) }} @@ -120,15 +124,15 @@ export function PopupSelectView({ popup }: PopupSelectInjected) {

{state.error} {state.status === 'failed' && ( - + )}
)} - {state.status === 'pending' &&
Loading options…
} - {state.submitting &&
Applying…
} - {state.status === 'ready' && rows.length === 0 &&
No options
} + {state.status === 'pending' &&
{t('status.loading')}
} + {state.submitting &&
{t('status.applying')}
} + {state.status === 'ready' && rows.length === 0 &&
{t('status.empty')}
} {state.status === 'ready' && ( -
+
{rows.map((option, index) => (
ctx.locale.register(NS, { zh, en }), 'ui-command: dictionaries') ctx.plugin(CommandService) // Conditional mount, same seam as ui-slash's MenuView registration: // 'conversation.input.overlay' is declared by the conversation composer @@ -51,6 +66,7 @@ export function apply(ctx: ClientContext): void { name: 'conversation.input.overlay', id: 'command-popup', order: 1, + locale: NS, inject: (sessionId): PopupSelectInjected => { const actx = sessions.scope(sessionId) if (actx === undefined) throw new Error(`ui-command: session "${String(sessionId)}" resolved no scope`) diff --git a/packages/client/ui-command/src/client/locales.ts b/packages/client/ui-command/src/client/locales.ts new file mode 100644 index 0000000000..63c5862cf2 --- /dev/null +++ b/packages/client/ui-command/src/client/locales.ts @@ -0,0 +1,26 @@ +/** `command` namespace dictionaries (the popupSelect shell's copy). */ + +/** Simplified Chinese dictionary (the key-set source of truth). */ +export const zh = { + 'search.placeholder': '搜索…', + 'search.aria': '筛选选项', + 'status.loading': '正在加载选项…', + 'status.applying': '正在应用…', + 'status.empty': '无选项', + 'overlay.aria': '/{command} 选项', + 'listbox.aria': '/{command} 匹配项', +} satisfies Record + +/** The command namespace key union. */ +export type CommandKey = keyof typeof zh + +/** English dictionary, checked complete against the zh key set. */ +export const en = { + 'search.placeholder': 'Search…', + 'search.aria': 'Filter options', + 'status.loading': 'Loading options…', + 'status.applying': 'Applying…', + 'status.empty': 'No options', + 'overlay.aria': '/{command} options', + 'listbox.aria': '/{command} matches', +} satisfies Record diff --git a/packages/client/ui-command/tests/browser-plugin.spec.ts b/packages/client/ui-command/tests/browser-plugin.spec.ts index 03c0df2d50..bb49cdf4d1 100644 --- a/packages/client/ui-command/tests/browser-plugin.spec.ts +++ b/packages/client/ui-command/tests/browser-plugin.spec.ts @@ -13,6 +13,7 @@ import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client' import type { SlashSource } from '@deepseek-ai/dsh-client-ui-slash/client' import type { CommandServiceContract } from '../src/client/contract.ts' import type { PopupSelectInjected } from '../src/client/PopupSelectView.tsx' +import { LocaleService } from '@deepseek-ai/dsh-client-locale/client' import { apply, CommandService, inject } from '../src/client/index.ts' const sid = (k: string): SessionId => k as SessionId @@ -41,6 +42,7 @@ async function bench() { }, }) ctx.provide('conversation', {}) + ctx.provide('locale', new LocaleService(ctx)) const fiber = ctx.plugin({ inject: [...inject], apply }) await fiber.await() const mint = (key: string) => { @@ -53,7 +55,7 @@ async function bench() { describe('apply', () => { it('declares the services it binds', () => { - expect(inject).toEqual(['slash', 'sessions', 'connection']) + expect(inject).toEqual(['slash', 'sessions', 'connection', 'locale']) }) it('mounts ctx.command, registers the source and the overlay entry, and folds up on disposal', async () => { diff --git a/packages/client/ui-command/tests/popup-view.spec.tsx b/packages/client/ui-command/tests/popup-view.spec.tsx index 2cd9891478..d8fadaae7a 100644 --- a/packages/client/ui-command/tests/popup-view.spec.tsx +++ b/packages/client/ui-command/tests/popup-view.spec.tsx @@ -14,6 +14,12 @@ import type { SelectOption } from '../src/client/contract.ts' import type { PopupSpec, TokenSegment } from '../src/client/popup.ts' import { PopupSelectController } from '../src/client/popup.ts' import { PopupSelectView } from '../src/client/PopupSelectView.tsx' +import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime' +import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts' +import { zh } from '../src/client/locales.ts' + +// The framework-injected t seat, stubbed over the zh dictionaries (the default locale). +const t: Parameters[0]['t'] = makeTranslate(zh, commonZh) // jsdom has no scrollIntoView; the view calls it on the highlighted row. const scrollIntoView = vi.fn() @@ -47,12 +53,12 @@ async function mountOpen(overrides: Partial> = {}, consumeResu const consume = vi.fn((_segment: TokenSegment) => consumeResult) const focusComposer = vi.fn() const popup = new PopupSelectController({ consume, focusComposer }) - const view = render() + const view = render() await act(async () => { popup.open('theme', spec(overrides), 'ctx-A', SEGMENT) await Promise.resolve() }) - return { popup, view, consume, focusComposer, search: screen.getByRole('textbox', { name: 'Filter options' }) } + return { popup, view, consume, focusComposer, search: screen.getByRole('textbox', { name: '筛选选项' }) } } function rowLabels(): string[] { @@ -62,13 +68,13 @@ function rowLabels(): string[] { describe('PopupSelectView', () => { it('renders null while closed, opens with focus in the search input', async () => { const popup = new PopupSelectController({ consume: () => true, focusComposer: () => {} }) - const view = render() + const view = render() expect(view.container.childElementCount).toBe(0) await act(async () => { popup.open('theme', spec(), 'ctx-A', SEGMENT) await Promise.resolve() }) - const search = screen.getByRole('textbox', { name: 'Filter options' }) + const search = screen.getByRole('textbox', { name: '筛选选项' }) expect(document.activeElement).toBe(search) expect(rowLabels()).toEqual(['Dark', 'Light', 'Sepia']) }) @@ -82,7 +88,7 @@ describe('PopupSelectView', () => { expect(options).toHaveBeenCalledTimes(1) act(() => { fireEvent.change(search, { target: { value: 'zzz' } }) }) expect(screen.queryByRole('option')).toBeNull() - expect(screen.queryByText('No options')).not.toBeNull() + expect(screen.queryByText('无选项')).not.toBeNull() }) it('ArrowUp/Down move the filtered highlight; ArrowLeft/Right are left to the native caret', async () => { @@ -110,13 +116,13 @@ describe('PopupSelectView', () => { it('caps the card height at the design maximum when the composer sits low enough', async () => { vi.spyOn(Element.prototype, 'getBoundingClientRect').mockReturnValue({ bottom: 800 } as DOMRect) await mountOpen() - expect(screen.getByLabelText('/theme options').style.maxHeight).toBe('320px') + expect(screen.getByLabelText('/theme 选项').style.maxHeight).toBe('320px') }) it('clamps the card height to the space above the composer minus the safe margin', async () => { vi.spyOn(Element.prototype, 'getBoundingClientRect').mockReturnValue({ bottom: 200 } as DOMRect) await mountOpen() - expect(screen.getByLabelText('/theme options').style.maxHeight).toBe('188px') + expect(screen.getByLabelText('/theme 选项').style.maxHeight).toBe('188px') }) it('Enter selects the highlighted row: onSelect, consume, close, focusComposer', async () => { @@ -148,7 +154,7 @@ describe('PopupSelectView', () => { const onSelect = vi.fn(() => new Promise((resolve) => { release = resolve })) const { search, consume } = await mountOpen({ onSelect }) await act(async () => { fireEvent.keyDown(search, { key: 'Enter' }) }) - expect(screen.queryByText('Applying…')).not.toBeNull() + expect(screen.queryByText('正在应用…')).not.toBeNull() expect((search as HTMLInputElement).readOnly).toBe(true) await act(async () => { fireEvent.keyDown(search, { key: 'Enter' }) @@ -162,7 +168,7 @@ describe('PopupSelectView', () => { expect(consume).toHaveBeenCalledTimes(1) }) - it('a failed options load shows the error with a Retry button that reloads', async () => { + it('a failed options load shows the error with a retry button that reloads', async () => { let attempts = 0 await mountOpen({ options: () => { @@ -172,7 +178,7 @@ describe('PopupSelectView', () => { }) expect(screen.getByRole('alert').textContent).toContain('directory down') await act(async () => { - fireEvent.click(screen.getByRole('button', { name: 'Retry' })) + fireEvent.click(screen.getByRole('button', { name: '重试' })) await Promise.resolve() }) expect(attempts).toBe(2) @@ -183,7 +189,7 @@ describe('PopupSelectView', () => { const { search, consume } = await mountOpen({ onSelect: () => Promise.reject(new Error('host rejected')) }) await act(async () => { fireEvent.keyDown(search, { key: 'Enter' }) }) expect(screen.getByRole('alert').textContent).toContain('host rejected') - expect(screen.queryByRole('button', { name: 'Retry' })).toBeNull() + expect(screen.queryByRole('button', { name: '重试' })).toBeNull() expect(consume).not.toHaveBeenCalled() expect(screen.getAllByRole('option').length).toBe(3) }) diff --git a/packages/client/ui-command/tsconfig.json b/packages/client/ui-command/tsconfig.json index b95692eda1..f83486aa36 100644 --- a/packages/client/ui-command/tsconfig.json +++ b/packages/client/ui-command/tsconfig.json @@ -14,6 +14,9 @@ { "path": "../connection" }, + { + "path": "../locale" + }, { "path": "../runtime" }, diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index ddb93caa18..7847c477fa 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: 60000c35c3e30883c4b29cc8410d30e58021318c -README.zh.md: 8f9fe7278d2d4bf5251582867de44290d0727710 +README.md: 2f3e545bfd7d29dbdbb0e23d833c2c19ee685a9d +README.zh.md: 12c043f78a242730a6f1e622df997ec5cbacc8fd diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index 60000c35c3..2f3e545bfd 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -14,17 +14,21 @@ Logged non-user messages render as a default-collapsed `上下文注入` disclos Generic tool rows classify the built-in bash, read, search, write, edit, and run_code names into dedicated visual variants. The filesystem variants render the edit icon and a path summary; that path is a hover-underline link that opens the file with the host OS default application (`host.openPath`, relative paths resolve against the session cwd). Tool rows are not whole-row click targets and do not open the details panel. The code variant summarizes with the model-authored `description` and expands to the program itself; its logged sub-dispatches render as always-visible nested rows through the SAME keyed toolview hole (custom registrations and the GenericToolCard fallback apply to sub-rows unchanged). Cordis lifecycle tools reuse those generic variants while presenting `Inspect`, `Mount temporary Plugin`, and `Unmount temporary Plugin` with a shared Cordis accent; mount keeps the code variant's expandable source rendering. -A tool call declaring the `terminal` render intent renders its command output inline, at both conversation render sites, through ui-primitives' `TerminalBlock`. `contract/terminal-card-model.ts` is the single derivation from the snapshot's `callView`/`resultView` pair, so the sites cannot disagree about a command, its cwd, or its exit status; it yields null — the generic path — for any other card tag, including one this client version does not know. 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 for this intent alone; a generic tool's content remains panel-only ([decision](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)). +A tool call declaring the `terminal` render intent renders its command output inline, at both conversation render sites, through ui-primitives' `TerminalBlock`. `contract/terminal-card-model.ts` is the single derivation from the snapshot's `callView`/`resultView` pair, so the sites cannot disagree about a command, its cwd, or its exit status; it yields null — the generic path — for any other card tag, including one this client version does not know. Both sites therefore also show the card's run-state dot, which is the same `StateDot` semantic a tool row's leading icon carries, so a row and its own card always agree about one command's state. 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)). + +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. 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). -The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`/ 已完成 · ` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: 10` — between Goal and Queue — and is the plan strip: it reads the host-computed `todos` projection via `useProjection` (standing plan: latest `todo/write` with no later `turn/start`) and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and starts collapsed as a header of title plus `"/ tasks · in progress"` (status glyphs are the figma check / progress / dashed-pending set). The dock adapter owns the selection so the panel stays a pure function of its props; the standing list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included. +The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`/ 已完成 · ` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: -1` — above the queue rows — and is the plan strip: it reads the host-computed `todos` projection via `useProjection` (standing plan: latest `todo/write` with no later `turn/start`) and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and starts collapsed as a header of title plus `"/ tasks · in progress"` (status glyphs are the figma check / progress / dashed-pending set). The dock adapter owns the selection so the panel stays a pure function of its props; the standing list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included. `QueueDock` is the terminal input-dock entry at `order: 20`. It hides while empty, renders one pending row directly, and defaults two or more rows to a collapsed `" 条排队消息"` header whose button expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Each visible row remains a single-line preview with its exact-occurrence edit and delete actions. Per-session UI state for selection and the active view lives in the declared chat store (`stores.ts` `createChatStore`); the InputHub owns the composer state machine and mirrors its draft into that store for persistence. Apply passes one store handle to the strict session subtree, chat view, and details registrations, so each session shares one instance and the framework owns its lifecycle. Components are pure: the framework standard kit supplies `useSession`/`sessionId`, global `useSessions`/`useWorkspaces`, and the input machine's `useInput`/`inputActions`; store faces and inject factories supply the remaining state and callbacks. -The composer bar declares session-scoped single seats for `'conversation.input.plan'` (right of the local access-mode control) and `'conversation.input.model'` (immediately before the pending indicator and send/stop button), plus list slots for overlay, dock, left, and right input extensions. Feature packages own each control and its state; ui-conversation supplies placement, the `locked` owner prop, and the standard slot shares. While the `plan` projection's effective target is plan mode, InputBar swaps its textarea placeholder to the plan-task wording, localized through the `command.hint` locale namespace this package registers and shared verbatim with the claimed `/plan` command hint (a host-folded value read through the standard-kit `useProjection`; owner-supplied placeholders win). A pending composer takeover remains mounted when another conversation view is active so the blocked agent can still receive its answer; without a pending interaction, the active-session composer belongs to Chat. The composer-bar slot itself is `session-maybe`: with no current session the same bar renders inert (machine faces absent, `disabled` owner prop) instead of swapping in a parallel disabled tree, so the textarea DOM survives the workspace pick; the strict-session control seats simply stay empty until a session exists. +The composer bar declares session-scoped single seats for `'conversation.input.plan'` (right of the local access-mode control) and `'conversation.input.model'` (immediately before the pending indicator and send/stop button), plus list slots for overlay, dock, left, and right input extensions. Feature packages own each control and its state; ui-conversation supplies placement, the `locked` owner prop, and the standard slot shares. The leading plus button is a Command launcher, not an attachment surface: it asks the session's `SlashController` to open only the `/` trigger's `command` source over the current textarea selection, while ui-slash's existing `MenuView` remains the sole floating menu and pick path. No file row, file input, upload protocol, or second menu component is introduced. While the `plan` projection's effective target is plan mode, InputBar swaps its textarea placeholder to the plan-task wording, localized through the `conversation` locale namespace this package registers (the `placeholder.plan` / `hint.plan` keys) and shared verbatim with the claimed `/plan` command hint (a host-folded value read through the standard-kit `useProjection`; owner-supplied placeholders win). A pending composer takeover remains mounted when another conversation view is active so the blocked agent can still receive its answer; without a pending interaction, the active-session composer belongs to Chat. The composer-bar slot itself is `session-maybe`: with no current session the same bar renders inert (machine faces absent, `disabled` owner prop) instead of swapping in a parallel disabled tree, so the textarea DOM survives the workspace pick; the strict-session control seats simply stay empty until a session exists. `src/client/` is organized for the future package split: `contract/` is the sole inter-domain shared face (`slots.ts` slot declarations + composed slot props including the tool-row contract, `views.ts` shared primitives, `tool-call-model.ts`); the `skeleton/`, `chat/`, and `toolviews/` (sample registrants) domain directories import contract files and never each other; `apply.ts` is the only assembly point allowed to import all three domains. The `/client` export surface is the contract only — `apply`/`inject`, the two service classes, and the `contract/` type families; implementation components (skeleton, chat rows) and the store factory stay internal and reach the page exclusively through apply's slot registrations (tests take them via the `./src/*` subpath). @@ -40,7 +44,7 @@ None; this package neither assembles nor sends a provider request. - **Stats-line durations cover the in-window flow only** — LLM and tool wall times fold the snapshot's assistant `timing` and tool call/result pairs, so nodes outside the loaded event window (older history) are not counted. - **Details panel is the minimal form and currently has no entry point** — selected call args/result raw display; the Input/Output/Metadata switch, Prev/Next stepping, and See-in-trajectory deep link are deferred. Tool rows stopped being details-panel click targets and nothing replaced that gesture, so `ChatViewInjected.openDetails` is implemented but uncalled and the panel (including its terminal card) is unreachable in the assembled application; its rendering stays covered by mounting it with a selection directly. -- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch forks through the turn containing that message, increments the inherited title on the client, and then opens the child, while a fork or rename failure leaves the source selected. +- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under the last content-text assistant of each turn only; mid-turn narration and Think-only nodes stay chrome-free. Branch forks through the turn containing that message, increments the inherited title on the client, and then opens the child, while a fork or rename failure leaves the source selected. - **The sparkle icon for the others tool row is a hand-drawn approximation** — the design glyph's vector geometry is not exportable locally; promotion into ui-primitives waits on an exact export. - **The approval panel's "Always allow this type" is deferred** — durable grants need a grant-storage design; only allow-once/reject answer today. - **TodoPanel truncates long item text to one ellipsized line** — the figma strip has no wrap or expand affordance; full text is not readable inline. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index 8f9fe7278d..12c043f78a 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -12,19 +12,23 @@ 通用工具行把内置的 bash、read、search、write、edit 和 run_code 名称归入专用视觉变体。文件系统变体会渲染 edit 图标和路径摘要；该路径是悬停下划线链接，点击后通过宿主操作系统的默认应用打开文件（`host.openPath`，相对路径相对会话 cwd 解析）。工具行不再是整行点击目标，也不会打开 details 面板。code 变体以模型撰写的 `description` 作摘要，展开后显示程序本身；其已记录的子调用经由同一个键控 toolview 空位渲染为始终可见的嵌套行（自定义注册和 GenericToolCard fallback 原样适用于子行）。Cordis 生命周期工具复用这些通用变体，同时以统一的 Cordis 强调色呈现 `Inspect`、`Mount temporary Plugin` 和 `Unmount temporary Plugin`；mount 行保留 code 变体的可展开源码渲染。 -声明 `terminal` 渲染意图的工具调用，会在两个对话渲染点上都通过 ui-primitives 的 `TerminalBlock` 内联渲染其命令输出。`contract/terminal-card-model.ts` 是从快照的 `callView`／`resultView` 对推导的唯一位置，因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧；对任何其他 card 标签——包括当前客户端版本不认识的标签——它返回 null，落回通用路径。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。内联输出只对该意图开放；通用工具的内容仍然只在面板中呈现（[决策](../../../.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md)）。 +声明 `terminal` 渲染意图的工具调用，会在两个对话渲染点上都通过 ui-primitives 的 `TerminalBlock` 内联渲染其命令输出。`contract/terminal-card-model.ts` 是从快照的 `callView`／`resultView` 对推导的唯一位置，因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧；对任何其他 card 标签——包括当前客户端版本不认识的标签——它返回 null，落回通用路径。因此两个渲染点也都显示卡片的运行状态点，它与工具行行首图标承载同一套 `StateDot` 语义，所以一行与其自身的卡片对同一条命令的状态总是一致。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)）。 + +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。 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 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）。 审批经由本包声明的链接管编辑器：`ApprovalPanel` 注册为按选择器路由的 `'conversation.composer'` 配置项（ui-question 模式），在审批等待未决期间取代 InputBar 占据编辑器（琥珀色条、理由标题、来自运行中调用参数的配对命令行、一次性的拒绝／允许）。`contract/slots.ts` 中的 `PendingApproval` 领域面在运行时 `PendingWait` 载体之上拥有 wire 编码——带审计关联的 `ApprovalResponsePayload` 值；广播的 `approval/resolved` 帧使等待落定并恢复编辑器。侧边栏通过 manager 跟踪的 `waitingApproval` 列表位（未实例化会话同样点亮）镜像该阻塞状态，其优先级高于运行中圆环，直至问题解决。未决等待完全离开消息流：问题（ui-question）与审批（ApprovalPanel）都经编辑器接管作答，不再保留只读占位卡。编辑器底行的 Access 席位挂载 `PermissionSelect`，由 host 计算的 `permissions` 投影经标准工具包 `useProjection` 供数（key 缺席即隐藏 chip）；chip 打开 Menu 原语下拉，kebab-case 预设名渲染为 Title Case 标签（与 `/permission` popup 的显示变换孪生），选中会经由输入栏注入的 `command` 回调提交 `/permission ` 命令行。 -todo 两个面就是在该形状上的两个注册项，都是普通注册方插件，`inject: ['slots', 'conversation']`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。`TodoDock` 以 `order: 10` 占用 `'conversation.input.dock'` 列表 slot（位于 Goal 和 Queue 之间），是计划条：它经 `useProjection` 读取 host 计算的 `todos` 投影（站立计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏；列表非空时面板初始折叠，表头显示标题加 `"<已完成>/<总数> tasks · in progress"`（状态图标为 figma 的勾选／进行中／虚线未开始一组）。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；站立列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。 +todo 两个面就是在该形状上的两个注册项，都是普通注册方插件，`inject: ['slots', 'conversation']`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。`TodoDock` 以 `order: -1` 占用 `'conversation.input.dock'` 列表 slot（位于队列行之上），是计划条：它经 `useProjection` 读取 host 计算的 `todos` 投影（站立计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏；列表非空时面板初始折叠，表头显示标题加 `"<已完成>/<总数> tasks · in progress"`（状态图标为 figma 的勾选／进行中／虚线未开始一组）。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；站立列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。 `QueueDock` 是 `order: 20` 的末端 input-dock 条目。队列为空时隐藏；只有一个待处理项时直接渲染该行；存在两个或更多待处理项时，默认收起为 `" 条排队消息"` 表头，其按钮可展开或收起完整列表。表头暴露 `aria-expanded` 和 `aria-controls`；展开后的列表以 180px 为高度上限，并可滚动。存在进行中的编辑或变更时，列表行会保持可见；队列清空后，下一次出现队列时会恢复默认收起状态。每条可见行仍是单行预览，并提供针对精确单次入队项的编辑和删除操作。 逐 Session UI 状态中的选择与活跃视图位于已声明的聊天 store（`stores.ts` `createChatStore`）中；InputHub 拥有输入区状态机，并将草稿镜像到该 store 以便持久化。apply 将同一个 store handle 传给严格限定于会话的子树、聊天视图和详情注册，因此每个会话内共享一个实例，框架拥有其生命周期。组件保持纯粹：框架标准工具包提供 `useSession`／`sessionId`、全局 `useSessions`／`useWorkspaces`，以及输入状态机的 `useInput`／`inputActions`；store 表层与 inject factory 提供其余状态和回调。 -输入栏为 `'conversation.input.plan'`（位于本地 access 模式控件右侧）和 `'conversation.input.model'`（渲染在 pending 指示器与发送／停止按钮之前）声明会话作用域的单实例 seat，并为 overlay、dock、left 和 right 输入扩展声明列表 slot。各功能包拥有相应控件及其状态；ui-conversation 提供放置位置、`locked` owner prop 和标准 slot share。当 `plan` 投影的有效目标为 plan mode 时，InputBar 将文本框 placeholder 切换为 plan 任务措辞，经本包注册的 `command.hint` locale 命名空间本地化，并与已认领 `/plan` 命令的提示逐字共用同一份文案（经标准套件 `useProjection` 读取的 host 折叠值；owner 提供的 placeholder 优先）。另一个会话视图活跃时，待处理的 composer 接管仍保持挂载，使被阻塞的 agent（智能体）仍能收到回答；没有待处理交互时，活跃会话的 composer 归 Chat 所有。composer bar slot 本身为 `session-maybe`：没有当前会话时，同一个 bar 以不可交互状态渲染（machine face 均缺席、`disabled` owner prop），而不是换入一棵平行的 disabled 树，因此选择 workspace 时 textarea DOM 不会被销毁；严格会话作用域的控件 seat 在会话存在之前保持为空。 +输入栏为 `'conversation.input.plan'`（位于本地 access 模式控件右侧）和 `'conversation.input.model'`（渲染在 pending 指示器与发送／停止按钮之前）声明会话作用域的单实例 seat，并为 overlay、dock、left 和 right 输入扩展声明列表 slot。各功能包拥有相应控件及其状态；ui-conversation 提供放置位置、`locked` owner prop 和标准 slot share。前置加号按钮是 Command launcher，而非附件入口：它要求当前会话的 `SlashController` 基于 textarea 当前 selection，只打开 `/` trigger 的 `command` source，同时 ui-slash 既有的 `MenuView` 仍是唯一的浮层菜单与 pick 路径。不引入 File 行、file input、上传协议或第二套菜单组件。当 `plan` 投影的有效目标为 plan mode 时，InputBar 将文本框 placeholder 切换为 plan 任务措辞，经本包注册的 `conversation` locale 命名空间（`placeholder.plan` / `hint.plan` 键）本地化，并与已认领 `/plan` 命令的提示逐字共用同一份文案（经标准套件 `useProjection` 读取的 host 折叠值；owner 提供的 placeholder 优先）。另一个会话视图活跃时，待处理的 composer 接管仍保持挂载，使被阻塞的 agent（智能体）仍能收到回答；没有待处理交互时，活跃会话的 composer 归 Chat 所有。composer bar slot 本身为 `session-maybe`：没有当前会话时，同一个 bar 以不可交互状态渲染（machine face 均缺席、`disabled` owner prop），而不是换入一棵平行的 disabled 树，因此选择 workspace 时 textarea DOM 不会被销毁；严格会话作用域的控件 seat 在会话存在之前保持为空。 `src/client/` 按未来的包拆分组织：`contract/` 是唯一的跨领域共享表层（`slots.ts` slot 声明 + 组合后的 slot props，包括工具行契约、`views.ts` 共享原语、`tool-call-model.ts`）；`skeleton/`、`chat/` 和 `toolviews/`（示例注册方）领域目录只导入 contract 文件，彼此绝不导入；`apply.ts` 是唯一允许导入全部三个领域的组装点。`/client` 导出表层只包含契约：`apply`／`inject`、两个服务类和 `contract/` 类型家族；实现组件（骨架、聊天行）与 store factory 保持内部状态，只能通过 apply 的 slot 注册到达页面（测试通过 `./src/*` 子路径获取它们）。 @@ -40,7 +44,7 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插 - **统计行的耗时只覆盖窗口内消息流**：LLM（大语言模型）与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。 - **详情面板是最小形态，且当前没有入口**：以原始形式显示已选择调用的参数／结果；Input/Output/Metadata 切换、Prev/Next 步进与 See-in-trajectory 深链接暂缓实现。工具行已不再是详情面板的点击目标，且没有任何手势接替它，因此 `ChatViewInjected.openDetails` 虽已实现却无人调用，该面板（含其终端卡片）在组装后的应用中不可达；其渲染仍由直接以选中态挂载它来覆盖。 -- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支会 fork 到包含该消息的轮次末尾，在 client 端递增继承标题后打开子会话，而 fork 或改名失败时源会话保持选中。 +- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在每个轮次中最后一条带 text 内容的 assistant 下；轮次中间的叙述与纯 Think 节点不带 chrome。分支会 fork 到包含该消息的轮次末尾，在 client 端递增继承标题后打开子会话，而 fork 或改名失败时源会话保持选中。 - **others 工具行的闪光图标是手绘近似版本**：无法在本地导出设计字形的矢量几何；等到存在精确导出后再将其提升到 ui-primitives。 - **审批面板的「始终允许此类」暂缓**：持久授权需要授权存储设计；今天只能回答允许一次／拒绝。 - **TodoPanel 将过长条目截成单行省略号**：figma 条没有换行或展开入口，完整文本无法在行内读完。 diff --git a/packages/client/ui-conversation/src/client/apply.ts b/packages/client/ui-conversation/src/client/apply.ts index 9c2008f092..24c26ab432 100644 --- a/packages/client/ui-conversation/src/client/apply.ts +++ b/packages/client/ui-conversation/src/client/apply.ts @@ -1,6 +1,6 @@ /** Registers the conversation components, shared store, and service callbacks. */ import type { Context } from 'cordis' -import type { BoundActions } from '@deepseek-ai/dsh-client-ui-slots' +import { resolveSlotLabel, type BoundActions } from '@deepseek-ai/dsh-client-ui-slots' import type { ISessions, SessionId } from '@deepseek-ai/dsh-client-runtime/client' import type {} from '@deepseek-ai/dsh-client-ui-layout/client' // Type-only: pulls the locale plugin's Context merge (ctx.locale). @@ -20,6 +20,7 @@ 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 { webToolview } from './toolviews/web-row.tsx' import { ApprovalPanel } from './skeleton/ApprovalPanel.tsx' import { todoToolview } from './toolviews/todo-row.tsx' import { askQuestionToolview } from './toolviews/ask-question-row.tsx' @@ -28,6 +29,14 @@ import { queueDockEntry } from './queue/QueueDock.tsx' import { ConversationRoot } from './skeleton/ConversationRoot.tsx' import { ConversationSession } from './skeleton/ConversationSession.tsx' import { DetailsPanel } from './skeleton/DetailsPanel.tsx' +import { en, NS, zh, type ConversationKey } from './locales.ts' + +declare module '@deepseek-ai/dsh-client-ui-slots' { + interface LocaleNamespaceMap { + /** The conversation surfaces' copy (skeleton, chat view, toolviews, docks). */ + conversation: ConversationKey + } +} /** Services required by the conversation plugin. */ export const inject = ['slots', 'layout', 'sessions', 'workspaces', 'locale'] @@ -44,6 +53,10 @@ const ABSENT_LEXICON = { getSnapshot: () => EMPTY_LEXICON, subscribe: () => () => {}, } +const ABSENT_MENU_LAUNCHER = { + getSnapshot: (): string | null => null, + subscribe: () => () => {}, +} /** Resolve the session-scoped conversation face (scope-addressed send/cancel), failing loud. */ function scopedConversation(sessions: ISessions, id: SessionId): IConversation { @@ -68,42 +81,27 @@ export function apply(ctx: Context): void { const layout = ctx.layout const slots = ctx.slots - // Command hint locale: friendly placeholder text for claimed commands. The - // claimed /plan hint and the plan-mode textarea placeholder share one - // string: both describe the same next action. - const HINT_NS = 'command.hint' - const PLAN_HINT_ZH = '描述你的任务以生成计划' - const PLAN_HINT_EN = 'describe your task to generate plan' - ctx.effect(() => { - const disposers = [ - ctx.locale.register(HINT_NS, 'zh', { - plan: PLAN_HINT_ZH, - goal: '输入目标，智能体将持续执行', - 'goal.active': '当前目标进行中。可输入 edit 修改 / pause 暂停 / resume 继续 / clear 清除', - 'placeholder.plan': PLAN_HINT_ZH, - 'placeholder.default': '给智能体发消息', - }), - ctx.locale.register(HINT_NS, 'en', { - plan: PLAN_HINT_EN, - goal: 'describe the objective for a long-running task', - 'goal.active': 'goal active — edit / pause / resume / clear', - 'placeholder.plan': PLAN_HINT_EN, - 'placeholder.default': 'Message the agent', - }), - ] - return () => { for (const dispose of disposers) dispose() } - }, 'ui-conversation: command hint dictionaries') - const translateHint = ctx.locale.bind(HINT_NS) + ctx.effect(() => ctx.locale.register(NS, { zh, en }), 'ui-conversation: dictionaries') + + // Registration-time text (the view tab label) reads through the bound + // translate as a thunk, so it follows the active locale without + // re-registration; components read the standard `t` seat instead. + const t = ctx.locale.bind(NS) // Apply-time construction keeps store identity bound to this fiber. const chatStore = createChatStore() + // Chat scroll offsets by session, surviving view switches (the chat view + // unmounts under the tab ring). Deliberately not persisted: a fresh page + // load should keep the open-jump-to-bottom default. + const chatScrollTops = new Map() + const viewTabs = (): ViewTab[] => { const tabs: ViewTab[] = [] for (const entry of slots.entries('conversation.view')) { /* v8 ignore next -- unreachable: list registration validates id at load. */ if (entry.options.id === undefined) continue - tabs.push({ id: entry.options.id, label: entry.options.label ?? entry.options.id }) + tabs.push({ id: entry.options.id, label: resolveSlotLabel(entry.options.label) ?? entry.options.id }) } return tabs } @@ -132,6 +130,7 @@ export function apply(ctx: Context): void { // frame while strict session slots fill only their session-bound regions. slots.register({ name: 'conversation', + locale: NS, children: { 'conversation.session': { kind: 'single', scope: 'session' }, 'conversation.composer': { kind: 'chain', scope: 'session' }, @@ -163,6 +162,7 @@ export function apply(ctx: Context): void { // the resident parent keeps Hero and composer layout identity stable. slots.register({ name: 'conversation.session', + locale: NS, children: { 'conversation.view': { kind: 'list', scope: 'session' } }, store: chatStore, inject: (sessionId: SessionId, _actions: BoundActions): ConversationSessionInjected => ({ @@ -185,6 +185,7 @@ export function apply(ctx: Context): void { // observableHook caching and hook order stay stable across transitions). slots.register({ name: 'conversation.composer.bar', + locale: NS, // The two named control seats in the bar's tool row (plan beside the // access control, model right); empty until their owning plugins // register (B ruling). @@ -196,15 +197,28 @@ export function apply(ctx: Context): void { if (sessionId === undefined) { return { keyboard: undefined, + toggleCommandMenu: undefined, stop: undefined, command: undefined, - translateHint, - hooks: { notices: ABSENT_NOTICES, lexicon: ABSENT_LEXICON }, + hooks: { notices: ABSENT_NOTICES, lexicon: ABSENT_LEXICON, menuLauncher: ABSENT_MENU_LAUNCHER }, } } const shell = inputHub.shell(sessionId) + const slash = inputHub.slash(sessionId) return { keyboard: shell, + toggleCommandMenu: slash === undefined + ? undefined + : (selection) => { + shell.dismissPopup() + const snapshot = shell.snapshot + slash.toggleSource('command', { + trigger: '/', + query: '', + position: snapshot.draft.slice(0, selection.start).trim() === '' ? 'leading' : 'inline', + span: { ...selection, draftRev: snapshot.draftRev }, + }) + }, stop: () => { scopedConversation(sessions, sessionId).cancel().catch(() => { // Stop failure surfaces via snapshot.promptError; nothing to restore. @@ -216,8 +230,11 @@ export function apply(ctx: Context): void { const result = await session.command(line) return result.ok && result.value.matched }, - translateHint, - hooks: { notices: shell.notices, lexicon: shell.lexicon }, + hooks: { + notices: shell.notices, + lexicon: shell.lexicon, + menuLauncher: slash?.launcher ?? ABSENT_MENU_LAUNCHER, + }, } }, }, InputBar) @@ -230,7 +247,7 @@ export function apply(ctx: Context): void { // pending — a question is a conversation the model is waiting on, while an // approval only blocks one tool call; answering the question first cannot // strand the approval (it re-elects the moment the question resolves). - slots.register({ name: 'conversation.composer', select: selectApproval, priority: 1 }, ApprovalPanel) + slots.register({ name: 'conversation.composer', select: selectApproval, priority: 1, locale: NS }, ApprovalPanel) // The chat view: first entry of the ring this package just declared. // Declaring the keyed toolview hole here is claiming it: ChatView is the @@ -241,7 +258,8 @@ export function apply(ctx: Context): void { name: 'conversation.view', id: 'chat', order: 0, - label: 'Chat', + label: () => t('view.chat'), + locale: NS, children: { 'conversation.chat.toolview': { kind: 'keyed', scope: 'session' }, 'conversation.chat.commandview': { kind: 'keyed', scope: 'session' }, @@ -262,6 +280,19 @@ export function apply(ctx: Context): void { }) }, loadOlder: () => { void scoped.loadOlder() }, + // Unregistered 'trajectory' id is safe: the tab ring falls back to + // the first view, and the untouched inspect target stays inert. + inspectCall: (callId) => { + actions.setInspect({ callId }) + actions.setView('trajectory') + }, + chatScroll: { + save: (top) => { + if (top === null) chatScrollTops.delete(sessionId) + else chatScrollTops.set(sessionId, top) + }, + read: () => chatScrollTops.get(sessionId) ?? null, + }, forkAt: (seq) => { sessions.fork({ sessionId, atSeq: seq, increaseTitle: true }) .then((childId) => { sessions.open(childId) }) @@ -288,6 +319,11 @@ export function apply(ctx: Context): void { // (ToolRow-matching Bash · {description} chrome; scoped badge in child sessions). ctx.plugin(bashToolviewSample) + // 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). + ctx.plugin(webToolview) + // The todo_write row rides the same seam (a product registration, not a sample). ctx.plugin(todoToolview) @@ -303,6 +339,7 @@ export function apply(ctx: Context): void { slots.register({ name: 'details', + locale: NS, store: chatStore, inject: (): DetailsInjected => ({ closeDetails: () => { layout.closeDetails() }, diff --git a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx index 7de69083ac..387a7fd82a 100644 --- a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx +++ b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx @@ -4,14 +4,16 @@ // view groups them into tool rows through its keyed toolview slot (figma // step-summary flow). Shared by finalized nodes and the streaming partial; // the turn-level loading dots live in the chat view's tail, not here. -// Finalized content (text) nodes append IconActions once streaming ends; -// Think / tool-head-only nodes stay chrome-free. +// Finalized turn-tail content (text) nodes append IconActions once streaming +// ends (`time` is omitted for mid-turn narration); Think / tool-head-only +// nodes stay chrome-free. -import { memo } from 'react' +import { memo, useMemo } from 'react' import type { AssistantBlock } from '@deepseek-ai/dsh-client-runtime/client' import { IconThinkOutline14, JsonBlock, MarkdownText, } from '@deepseek-ai/dsh-client-ui-primitives' +import type { ChatViewSlotProps } from '../contract/slots.ts' import { MessageIconActions } from './MessageIconActions.tsx' import { ToolRow } from './ToolRow.tsx' import css from './AssistantMarkdown.module.css' @@ -19,14 +21,17 @@ import css from './AssistantMarkdown.module.css' export interface AssistantMarkdownProps { blocks: readonly AssistantBlock[] streaming: boolean - /** Frozen partial of an aborted turn: rendered with a 已停止 marker. */ + /** Frozen partial of an aborted turn: rendered with a stopped marker. */ interrupted?: boolean | undefined - /** Unix epoch ms for the finalized IconActions clock; omitted while streaming. */ + /** Unix epoch ms for the IconActions clock; omitted while streaming or when + * the parent withholds chrome (mid-turn content assistants). */ time?: number | undefined /** Event sequence used as the fork boundary; omitted while streaming. */ seq?: number | undefined /** Fork the session through the turn containing this finalized message. */ onFork?: ((seq: number) => void) | undefined + /** The owning view's locale seat, passed down as a plain prop. */ + t: ChatViewSlotProps['t'] } function firstLine(text: string): string { @@ -49,23 +54,26 @@ function hasContentText(blocks: readonly AssistantBlock[]): boolean { } /** Reasoning block as the Think variant summary row (figma 39:28304). */ -function ThinkRow({ text, running }: { text: string; running: boolean }) { +function ThinkRow({ text, running, t }: { text: string; running: boolean; t: AssistantMarkdownProps['t'] }) { return ( } title="Think" summary={firstLine(text)} body={text} state={running ? 'running' : 'ok'} - expandOnRowClick /> ) } export const AssistantMarkdown = memo(function AssistantMarkdown({ - blocks, streaming, interrupted, time, seq, onFork, + blocks, streaming, interrupted, time, seq, onFork, t, }: AssistantMarkdownProps) { + // Stable per locale revision (t identity changes on switch): a fresh object + // per render would rebuild MarkdownText's component table every chunk. + const codeLabels = useMemo(() => ({ copyLabel: t('copy'), copiedLabel: t('copied') }), [t]) const last = blocks.length - 1 // Tool-call heads render as tool rows in the chat view's grouping pass, so // a node that is only those heads (or empty) would paint an empty root @@ -81,14 +89,23 @@ export const AssistantMarkdown = memo(function AssistantMarkdown({
{blocks.map((block, i) => { switch (block.kind) { - case 'text': return - case 'reasoning': return + case 'text': return ( + + ) + case 'reasoning': return // Grouped into tool rows by ChatView; hasVisible above skips an empty shell. case 'tool-call': return null - default: return + default: return ( + t('json.truncated', { total })} + /> + ) } })} - {interrupted && 已停止} + {interrupted && {t('message.stopped')}}
{showActions && ( { onFork(seq) }} className={css.actions} + t={t} /> )}
diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.tsx b/packages/client/ui-conversation/src/client/chat/ChatView.tsx index 2941348eb1..d509a2e521 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.tsx +++ b/packages/client/ui-conversation/src/client/chat/ChatView.tsx @@ -30,7 +30,7 @@ import type { import type { SnapshotSelectorHook } from '@deepseek-ai/dsh-client-ui-slots' import { IconChevronDownOutline14 } from '@deepseek-ai/dsh-client-ui-primitives' import type { ChatViewSlotProps } from '../contract/slots.ts' -import { deriveChatFlow, type ChatFlowItem } from './chat-flow.ts' +import { assistantActionsSeqs, deriveChatFlow, type ChatFlowItem } from './chat-flow.ts' import { AssistantMarkdown } from './AssistantMarkdown.tsx' import { GenericCommandCard } from './GenericCommandCard.tsx' import { GenericToolCard } from './GenericToolCard.tsx' @@ -46,6 +46,8 @@ function scrollerOf(from: HTMLElement): HTMLElement { type OpenFile = (path: string) => void +type InspectCall = (callId: string) => void + /** The declared toolview hole's render share (stable framework binding, passed through memoized rows). */ type RenderToolRow = ChatViewSlotProps['renderSlot'] @@ -53,27 +55,41 @@ type RenderToolRow = ChatViewSlotProps['renderSlot'] * chat view narrows once to the runtime snapshot the binding actually feeds. */ type UseConversation = SnapshotSelectorHook +function activeRetrySeq(nodes: readonly ConversationNode[], running: boolean): number | null { + if (!running) return null + for (let index = nodes.length - 1; index >= 0; index -= 1) { + const node = nodes[index] + if (node === undefined) continue + if (node.kind === 'model-retry') return node.retryState === 'cancelled' ? null : node.seq + if (node.kind === 'assistant' || node.kind === 'user') return null + } + return null +} + /** One `run_code` sub-dispatch row: the identical keyed-slot dispatch as a * top-level call (same registrations, same fallback), nested by the parent. * A started-but-unsettled sub-call arrives as the RunningToolCall shape and * renders the running state exactly as a native in-flight row. */ -const SubCallRow = memo(function SubCallRow({ renderSlot, node, openFile, selected, cwd }: { +const SubCallRow = memo(function SubCallRow({ renderSlot, node, openFile, selected, cwd, inspectCall, t }: { renderSlot: RenderToolRow node: CodeSubCall openFile: OpenFile selected: boolean cwd: string | undefined + inspectCall: InspectCall + t: ChatViewSlotProps['t'] }) { const settled = 'kind' in node const toolName = settled ? node.call?.name ?? '' : node.name const owner = useMemo(() => ({ callId: node.callId, toolName, block: node, openFile, cwd, - }), [node, toolName, openFile, cwd]) + inspect: () => { inspectCall(node.callId) }, + }), [node, toolName, openFile, cwd, inspectCall]) return (
{renderSlot('conversation.chat.toolview', owner, { entryKey: toolName, - fallback: , + fallback: , })}
) @@ -85,7 +101,7 @@ const SubCallRow = memo(function SubCallRow({ renderSlot, node, openFile, select * renders its logged sub-dispatches as always-visible indented rows — * each one the same keyed-slot dispatch as a native top-level call. */ const CallRow = memo(function CallRow({ - renderSlot, callId, toolName, block, openFile, selected, subCalls, selectedCallId, cwd, + renderSlot, callId, toolName, block, openFile, selected, subCalls, selectedCallId, cwd, inspectCall, t, }: { renderSlot: RenderToolRow callId: string @@ -100,15 +116,18 @@ const CallRow = memo(function CallRow({ selectedCallId?: string | undefined /** Session workspace root for path-relative summaries. */ cwd: string | undefined + inspectCall: InspectCall + t: ChatViewSlotProps['t'] }) { const owner = useMemo(() => ({ callId, toolName, block, openFile, cwd, - }), [callId, toolName, block, openFile, cwd]) + inspect: () => { inspectCall(callId) }, + }), [callId, toolName, block, openFile, cwd, inspectCall]) return (
{renderSlot('conversation.chat.toolview', owner, { entryKey: toolName, - fallback: , + fallback: , })} {subCalls !== undefined && subCalls.length > 0 && (
@@ -120,6 +139,8 @@ const CallRow = memo(function CallRow({ openFile={openFile} selected={node.callId === selectedCallId} cwd={cwd} + inspectCall={inspectCall} + t={t} /> ))}
@@ -129,7 +150,7 @@ const CallRow = memo(function CallRow({ }) /** Consecutive tool results as one step-run group (uniform 16px rhythm). */ -const ToolGroup = memo(function ToolGroup({ renderSlot, results, openFile, selectedCallId, codeDispatches, cwd }: { +const ToolGroup = memo(function ToolGroup({ renderSlot, results, openFile, selectedCallId, codeDispatches, cwd, inspectCall, t }: { renderSlot: RenderToolRow results: readonly ToolResultNode[] openFile: OpenFile @@ -139,6 +160,8 @@ const ToolGroup = memo(function ToolGroup({ renderSlot, results, openFile, selec codeDispatches: ReadonlyMap /** Session workspace root for path-relative summaries. */ cwd: string | undefined + inspectCall: InspectCall + t: ChatViewSlotProps['t'] }) { return (
@@ -154,6 +177,8 @@ const ToolGroup = memo(function ToolGroup({ renderSlot, results, openFile, selec subCalls={codeDispatches.get(node.callId)} selectedCallId={selectedCallId} cwd={cwd} + inspectCall={inspectCall} + t={t} /> ))}
@@ -163,16 +188,17 @@ const ToolGroup = memo(function ToolGroup({ renderSlot, results, openFile, selec /** One command lifecycle row: keyed dispatch on the command name with the * generic card as the render-site fallback (zero registration required). A * run-less cross-window node has no name and always lands on the fallback. */ -const CommandRow = memo(function CommandRow({ renderSlot, node }: { +const CommandRow = memo(function CommandRow({ renderSlot, node, t }: { renderSlot: RenderToolRow node: CommandNode + t: ChatViewSlotProps['t'] }) { const owner = useMemo(() => ({ node }), [node]) return (
{renderSlot('conversation.chat.commandview', owner, { entryKey: node.name ?? '', - fallback: , + fallback: , })}
) @@ -214,23 +240,26 @@ function TurnDots() { /** The streaming partial, isolated so chunk batches re-render only this tail. * onGrow lets the scroll owner follow content the parent never re-renders for. */ -function StreamingTail({ useSession, onGrow }: { +function StreamingTail({ useSession, onGrow, t }: { useSession: UseConversation onGrow: () => void + t: ChatViewSlotProps['t'] }) { const partial = useSession(s => s.partial) useLayoutEffect(() => { onGrow() }) if (partial === null) return null - return + return } /** * The chat view slot entry: pure component over the composed props (tool rows * render through the declared keyed hole's renderSlot share). */ -export function ChatView({ useSession, useSessions, useStore, renderSlot, sessionId, openFile, loadOlder, forkAt }: ChatViewSlotProps) { +export function ChatView({ + useSession, useSessions, useStore, renderSlot, sessionId, openFile, loadOlder, inspectCall, chatScroll, forkAt, t, +}: ChatViewSlotProps) { const nodes = useSession(s => s.nodes) // Workspace root off the session list row: path summaries display relative to it. const cwd = useSessions(s => s.byId[sessionId]?.cwd) @@ -238,12 +267,16 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio const runningCalls = useSession(s => s.runningCalls) const codeDispatches = useSession(s => s.codeDispatches) const openState = useSession(s => s.openState) - const openErrorMessage = useSession(s => s.openError === null ? null : `${s.openError.message}（${s.openError.code}）`) + const openError = useSession(s => s.openError) const hasMore = useSession(s => s.hasMore) const loadingOlder = useSession(s => s.loadingOlder) const selectedCallId = useStore(s => s.selection?.callId) const items = useMemo(() => deriveChatFlow(nodes), [nodes]) + const activeRetry = useMemo(() => activeRetrySeq(nodes, running), [nodes, running]) + // Only the last content assistant of each turn owns IconActions; mid-turn + // text (before tools) omits `time` so AssistantMarkdown stays chrome-free. + const actionSeqs = useMemo(() => assistantActionsSeqs(nodes), [nodes]) const listRef = useRef(null) const atBottomRef = useRef(true) @@ -274,10 +307,20 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio /* v8 ignore next -- ref-null guard: React attaches the ref before layout effects run. */ if (local === null) return const el = scrollerOf(local) - // Open completed: jump to the bottom once. + // Open completed: jump to the bottom once — unless a scroll position + // survives from a previous mount (view-tab switch away and back), which + // is restored instead of snapping the reader back to the floor. if (openState === 'open' && !openedRef.current) { openedRef.current = true - toBottom(el) + const saved = chatScroll.read() + if (saved === null) { + toBottom(el) + } else { + el.scrollTop = saved + const isAtBottom = el.scrollHeight - el.scrollTop - el.clientHeight <= FOLLOW_THRESHOLD + 1 + atBottomRef.current = isAtBottom + setAtBottom(isAtBottom) + } firstSeqRef.current = firstSeq lastKeyRef.current = lastKey followSigRef.current = followSig @@ -315,6 +358,9 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio const isAtBottom = el.scrollHeight - el.scrollTop - el.clientHeight <= FOLLOW_THRESHOLD + 1 atBottomRef.current = isAtBottom setAtBottom(isAtBottom) + // Continuous save (unmount happens after ref detach, so saving there is + // too late); pinned-to-bottom clears so a remount keeps following. + chatScroll.save(isAtBottom ? null : el.scrollTop) } // Bind scroll to the resolved scrollport (host or local) once per mount. @@ -365,6 +411,8 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio selectedCallId={inGroup ? selectedCallId : undefined} codeDispatches={codeDispatches} cwd={cwd} + inspectCall={inspectCall} + t={t} /> ) } @@ -376,35 +424,48 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio blocks={node.blocks} streaming={false} interrupted={node.interrupted} - time={node.time} + time={actionSeqs.has(node.seq) ? node.time : undefined} seq={node.seq} onFork={forkAt} + t={t} /> ) } if (node.kind === 'command') { - return + return } /* v8 ignore next -- tool-result never reaches here: deriveChatFlow folds them into groups. */ if (node.kind === 'tool-result') return null - return + return ( + + ) } return (
- {openState === 'loading' &&
载入历史…
} - {openState === 'error' &&
历史加载失败：{openErrorMessage}
} + {openState === 'loading' &&
{t('chat.loadingHistory')}
} + {openState === 'error' && openError !== null && ( +
+ {t('chat.loadError', { message: openError.message, code: openError.code })} +
+ )} {hasMore && (
)} {items.map(renderItem)} - + {runningCalls.length > 0 && (
{runningCalls.map(call => ( @@ -419,6 +480,8 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio subCalls={codeDispatches.get(call.callId)} selectedCallId={selectedCallId} cwd={cwd} + inspectCall={inspectCall} + t={t} /> ))}
@@ -435,7 +498,7 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio
{open && children}
diff --git a/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx b/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx index 4b42a94c72..aa236c87ca 100644 --- a/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx +++ b/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx @@ -6,7 +6,7 @@ import { ToolRow } from './ToolRow.tsx' import type { ToolRowState } from '../contract/tool-call-model.ts' -import type { CommandRowOwnerProps } from '../contract/slots.ts' +import type { ChatViewSlotProps, CommandRowOwnerProps } from '../contract/slots.ts' import { IconApiOutline14 } from '@deepseek-ai/dsh-client-ui-primitives' /** Node state → row state semantic (running while unsettled; outcome kind after). */ @@ -15,20 +15,26 @@ function stateOf(outcome: CommandRowOwnerProps['node']['outcome']): ToolRowState return outcome.kind === 'error' ? 'error' : 'ok' } -export function GenericCommandCard({ node }: CommandRowOwnerProps) { +/** Card props: the owner payload plus the render site's locale seat (plain prop). */ +export interface GenericCommandCardProps extends CommandRowOwnerProps { + t: ChatViewSlotProps['t'] +} + +export function GenericCommandCard({ node, t }: GenericCommandCardProps) { const text = node.outcome?.text const summary = node.outcome === null - ? '执行中…' - : text ?? (node.outcome.kind === 'error' ? '命令失败' : '已完成') + ? t('command.running') + : text ?? (node.outcome.kind === 'error' ? t('command.failed') : t('command.done')) // Title is the bare command name: the row already reads `name · outcome`, // and the dispatched line's own `/` and arguments only restate what the // settlement text says (`permission · preset workspace-write`). A // cross-window node whose run page fell out of the window has no name. - const title = node.name ?? '命令' + const title = node.name ?? t('command.title') return ( } + icon={} title={title} summary={summary} // Expandable only when the outcome text overflows a one-line summary. diff --git a/packages/client/ui-conversation/src/client/chat/GenericToolCard.module.css b/packages/client/ui-conversation/src/client/chat/GenericToolCard.module.css new file mode 100644 index 0000000000..13a4ef9d62 --- /dev/null +++ b/packages/client/ui-conversation/src/client/chat/GenericToolCard.module.css @@ -0,0 +1,15 @@ +/* The generic card grows a resident web card under its summary row when the + tool declares the `web` render intent but has no keyed row of its own (the + web_search/web_fetch rows register their own WebRow). A column around the + ToolRow keeps the row's own 24px height. */ + +.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; +} diff --git a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx index ce55d84f57..d35e7c0721 100644 --- a/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx +++ b/packages/client/ui-conversation/src/client/chat/GenericToolCard.tsx @@ -7,12 +7,14 @@ import type { ReactNode } from 'react' import { IconApiOutline14, IconBrowseOutline16, IconCodeOutline16, IconEditOutline16, IconSearchOutline16, IconSparkle16, - IconThinkOutline14, + IconThinkOutline14, WebBlock, } from '@deepseek-ai/dsh-client-ui-primitives' -import type { ToolRowOwnerProps } from '../contract/slots.ts' -import { terminalCardModel } from '../contract/terminal-card-model.ts' +import type { ChatViewSlotProps, ToolRowOwnerProps } from '../contract/slots.ts' +import { terminalCardModel, terminalFailed } from '../contract/terminal-card-model.ts' +import { CHAT_WEB_MAX_SOURCES, 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 = { @@ -26,12 +28,24 @@ const VARIANT_ICONS: Record = { others: , } -export function GenericToolCard({ toolName, block, cwd, openFile }: ToolRowOwnerProps) { +/** Card props: the owner payload plus the render site's locale seat (plain prop). */ +export interface GenericToolCardProps extends ToolRowOwnerProps { + t: ChatViewSlotProps['t'] +} + +export function GenericToolCard({ toolName, block, cwd, openFile, inspect, t }: GenericToolCardProps) { const model = toolRowModel(toolName, block, cwd) const terminal = terminalCardModel(block, cwd) + 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. + const state = model.state === 'ok' && terminal !== null && terminalFailed(terminal) + ? 'error' + : model.state const singleFile = model.filePath !== undefined - return ( + const 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/MessageIconActions.tsx b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx index 3075c258a6..dbb8a8628e 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx @@ -6,6 +6,7 @@ import { useCallback } from 'react' import { IconBranchOutline16, IconCopyOutline16, IconEditOutline16, Tooltip, } from '@deepseek-ai/dsh-client-ui-primitives' +import type { ChatViewSlotProps } from '../contract/slots.ts' import { formatMessageClock, writeClipboard } from './message-chrome.ts' import { useCalendarDay } from './use-calendar-day.ts' import css from './MessageIconActions.module.css' @@ -23,6 +24,8 @@ export interface MessageIconActionsProps { onBranch?: (() => void) | undefined /** Parent layout class composed onto the actions row. */ className?: string | undefined + /** The owning view's locale seat, passed down as a plain prop. */ + t: ChatViewSlotProps['t'] } /** @@ -31,7 +34,7 @@ export interface MessageIconActionsProps { * @returns The actions row element. */ export function MessageIconActions({ - text, time, clock, edit, onBranch, className, + text, time, clock, edit, onBranch, className, t, }: MessageIconActionsProps) { const day = useCalendarDay() const onCopy = useCallback(() => { @@ -39,25 +42,25 @@ export function MessageIconActions({ }, [text]) const clockEl = ( - {formatMessageClock(time, day)} + {formatMessageClock(time, t, day)} ) return (
{clock === 'start' ? clockEl : null} - - - - {edit === true && ( - - diff --git a/packages/client/ui-conversation/src/client/chat/MessageItem.module.css b/packages/client/ui-conversation/src/client/chat/MessageItem.module.css index 2667024bcd..3ecc77a23d 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageItem.module.css +++ b/packages/client/ui-conversation/src/client/chat/MessageItem.module.css @@ -34,6 +34,106 @@ padding: 2px 0; } +.retryRow { + color: var(--dsw-alias-label-tertiary); + font-size: 13px; + line-height: 20px; +} + +.retrySummary { + display: inline-flex; + align-items: center; + width: fit-content; + padding: 2px 0; + gap: 7px; + border-radius: 3px; + color: inherit; + cursor: pointer; + list-style: none; + user-select: none; +} + +.retrySummary::-webkit-details-marker { + display: none; +} + +.retrySummary::after { + width: 6px; + height: 6px; + border-right: 1.5px solid currentcolor; + border-bottom: 1.5px solid currentcolor; + content: ''; + opacity: 0.8; + transform: rotate(-45deg); + transition: transform 120ms ease; +} + +.retrySummary:hover { + color: var(--dsw-alias-label-secondary); +} + +.retrySummary:focus-visible { + outline: 1.5px solid var(--dsw-alias-button-info-fill); + outline-offset: 2px; +} + +.retryText { + color: inherit; +} + +.retryRow[data-active] .retryText { + background: + linear-gradient( + 90deg, + var(--dsw-alias-label-tertiary) 0%, + var(--dsw-alias-label-tertiary) 40%, + var(--dsw-alias-label-secondary) 50%, + var(--dsw-alias-label-tertiary) 60%, + var(--dsw-alias-label-tertiary) 100% + ); + background-position: 100% 50%; + background-size: 200% 100%; + background-clip: text; + color: transparent; + animation: retry-shimmer 1.6s ease-in-out infinite; +} + +.retryRow[open] .retrySummary::after { + transform: rotate(45deg); +} + +.retryDetails { + display: grid; + gap: 2px; + margin-top: 3px; + padding-left: 14px; + overflow-wrap: anywhere; + font-size: 12px; + line-height: 18px; +} + +.retryDetailLabel { + color: var(--dsw-alias-label-secondary); +} + +@keyframes retry-shimmer { + from { + background-position: 100% 50%; + } + + to { + background-position: 0 50%; + } +} + +@media (prefers-reduced-motion: reduce) { + .retryRow[data-active] .retryText { + background: none; + color: inherit; + animation: none; + } +} + /* Reference chip projection inside a user bubble (`name` model spans render as chips; free geometry — no textarea pairing here). */ .refChip { diff --git a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx index 2eb8e313ae..d271db9989 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx @@ -1,23 +1,25 @@ -// MessageItem: the four simple node kinds — user bubble (right-aligned, with +// MessageItem: simple chat nodes — user bubble (right-aligned, with // clock + copy / branch / edit IconActions), steering (badged bubble), context -// injection and unknown-surface JSON rows. Props are frozen node slices off -// the snapshot cache; memo holds across streaming because unchanged nodes -// keep their references. +// injection, retry disclosure, and unknown-surface JSON rows. -import { memo } from 'react' +import { memo, useEffect, useMemo, useState } from 'react' import type { ReactNode } from 'react' import type { - ContextMessageNode, SteeringMessageNode, UnknownSurfaceNode, UserMessageNode, + ContextMessageNode, ModelRetryNode, SteeringMessageNode, UnknownSurfaceNode, UserMessageNode, } from '@deepseek-ai/dsh-client-runtime/client' import { JsonBlock, MessageText } from '@deepseek-ai/dsh-client-ui-primitives' +import type { ChatViewSlotProps } from '../contract/slots.ts' import { ContextInjectionRow } from './ContextInjectionRow.tsx' import { MessageIconActions } from './MessageIconActions.tsx' import css from './MessageItem.module.css' export interface MessageItemProps { - node: UserMessageNode | SteeringMessageNode | ContextMessageNode | UnknownSurfaceNode + node: UserMessageNode | SteeringMessageNode | ContextMessageNode | ModelRetryNode | UnknownSurfaceNode + retryActive?: boolean /** Fork the session through the turn containing this message (user-bubble branch action). */ onFork?: (seq: number) => void + /** The owning view's locale seat, passed down as a plain prop. */ + t: ChatViewSlotProps['t'] } function contentText(content: readonly unknown[]): { text: string; rest: unknown[] } { @@ -31,6 +33,80 @@ function contentText(content: readonly unknown[]): { text: string; rest: unknown return { text: texts.join(''), rest } } +function retrySeconds(milliseconds: number): number { + return Math.max(1, Math.ceil(milliseconds / 1_000)) +} + +interface RetryCountdown { + deadline: number + seconds: number +} + +function ModelRetryItem({ node, active, t }: { + node: ModelRetryNode + active: boolean + t: ChatViewSlotProps['t'] +}) { + // Anchor the host-scheduled delay to this browser's first render of the + // retry node. Host event time and Date.now() may belong to different clocks. + const deadline = useMemo(() => Date.now() + node.delayMs, [node.delayMs, node.seq]) + const scheduledSeconds = retrySeconds(node.delayMs) + const maximum = node.mode === 'normal' ? node.maxRetries : '∞' + const [countdown, setCountdown] = useState(() => ({ + deadline, + seconds: retrySeconds(deadline - Date.now()), + })) + const remainingSeconds = countdown.deadline === deadline + ? countdown.seconds + : retrySeconds(deadline - Date.now()) + + useEffect(() => { + if (!active) return + const updateCountdown = (): number => { + const next = retrySeconds(deadline - Date.now()) + setCountdown(current => ( + current.deadline === deadline && current.seconds === next + ? current + : { deadline, seconds: next } + )) + return next + } + if (updateCountdown() === 1) return + const timer = window.setInterval(() => { + if (updateCountdown() === 1) window.clearInterval(timer) + }, 250) + return () => { window.clearInterval(timer) } + }, [active, deadline]) + + const label = active + ? t('message.retry.active') + : node.retryState === 'cancelled' + ? t('message.retry.cancelled') + : node.retryState === 'started' + ? t('message.retry.started') + : t('message.retry.scheduled') + const seconds = active ? remainingSeconds : scheduledSeconds + + return ( +
+ + + {t('message.retry.status', { label, retry: node.retry, maximum, seconds })} + + +
+
+ {t('message.retry.delay')} + {Math.round(node.delayMs)}ms +
+
+ {t('message.retry.failure')} + {node.failure.message} +
+
+
+ ) +} /** * Display projection of reference forms in a user bubble (free geometry — no * textarea alignment constraint here); everything else stays plain text. The @@ -63,7 +139,10 @@ function projectUserText(text: string): ReactNode { return <>{parts} } -export const MessageItem = memo(function MessageItem({ node, onFork }: MessageItemProps) { +export const MessageItem = memo(function MessageItem({ + node, retryActive = false, onFork, t, +}: MessageItemProps) { + const truncated = (total: number): string => t('json.truncated', { total }) switch (node.kind) { case 'user': { const { text, rest } = contentText(node.content) @@ -71,7 +150,7 @@ export const MessageItem = memo(function MessageItem({ node, onFork }: MessageIt
{projectUserText(text)} - {rest.map((block, i) => )} + {rest.map((block, i) => )}
{ onFork(node.seq) }} className={css.actions} + t={t} />
) @@ -89,21 +169,23 @@ export const MessageItem = memo(function MessageItem({ node, onFork }: MessageIt return (
- 插话 + {t('message.steering')} {projectUserText(text)} - {rest.map((block, i) => )} + {rest.map((block, i) => )}
) } case 'context': return ( - + ) + case 'model-retry': + return default: return (
- +
) } 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 e53b472c50..43cb37462a 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.module.css +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.module.css @@ -56,6 +56,10 @@ background: var(--dsw-alias-state-business-primary); } +.chevron { + color: var(--dsw-alias-label-secondary); +} + .title { font-weight: 400; } @@ -103,8 +107,65 @@ text-decoration: underline; } -/* Expanded body: pad-left 22 indented gray text, no border, no fill. */ -.body { +/* Error row's collapsed summary: the failure's first line in the error color. */ +.errorSummary { + color: var(--dsw-alias-state-error-primary); +} + +/* Expanded body + Inspect pill wrapper (sibling of .row: clicks never toggle). */ +.bodyWrap { + display: flex; + flex-direction: column; +} + +/* Hover-revealed jump to the trajectory record: a small pill in real flow + under the expanded body's bottom-left corner (it reserves its line, so + revealing never shifts layout); revealed by hovering anywhere on the tool + call — title row included — or by keyboard focus. */ +.inspectButton { + display: inline-flex; + align-self: flex-start; + align-items: center; + gap: 4px; + margin: 4px 0 2px 4px; + padding: 2px 8px; + border: 1px solid var(--dsw-alias-border-l2); + border-radius: 999px; + /* Base background, not bg-overlay: the overlay token is a raised dark + surface and reads too heavy for a quiet in-flow affordance. */ + background: var(--dsw-alias-bg-base); + color: var(--dsw-alias-label-secondary); + font-size: 11px; + line-height: 16px; + cursor: pointer; + opacity: 0; + transition: opacity 100ms ease; +} + +.root:hover .inspectButton, +.inspectButton:focus-visible { + opacity: 1; +} + +/* Solid hover fill (a translucent token would let content bleed through). */ +.inspectButton:hover { + background: var(--dsw-alias-interactive-bg-hover-solid); + color: var(--dsw-alias-label-primary); +} + +/* Expanded-body scroll wrapper for the run_code CodeBlock; the IN/OUT card + and the terminal card scroll INSIDE their own surface instead, so the + scrollbar sits within the rounded card. */ +.bodyScroll { + max-height: 260px; + overflow-y: auto; +} + +/* Think expanded body: plain indented gray reasoning prose — no IN/OUT card + (the reasoning is not an input payload), pre-wrapped at the row's indent. + Uncapped: reasoning reads as message prose, so it flows with the page + instead of scrolling in a box. */ +.thinkBody { padding: 4px 0 4px 22px; font-size: 14px; line-height: 24px; @@ -113,6 +174,78 @@ color: var(--dsw-alias-label-tertiary); } +/* Expanded input/output card (figma 1249:35657): the code-block surface and + radius from the TerminalBlock/CodeBlock family. The card itself is a plain + column — the padding and the IN/OUT gutter-label grid live on each section + so the divider spans the full card width and each section scrolls alone. */ +.ioCard { + display: flex; + flex-direction: column; + margin: 4px 0 4px 4px; + border: 1px solid var(--dsw-alias-border-l1); + border-radius: 12px; + background: var(--dsw-alias-markdown-code-block); + font: var(--dsw-font-markdown-code-block-small); +} + +/* One card section (IN or OUT): the gutter-label grid, capped and scrolling + independently so a long input never buries a short output (and vice versa). */ +.ioSection { + display: grid; + grid-template-columns: max-content 1fr; + column-gap: 14px; + align-items: baseline; + padding: 12px 16px; + max-height: 150px; + overflow-y: auto; +} + +/* Card-internal scrollbar: a 2px transparent border clips the thumb inward so + it floats off the rounded card edge instead of hugging it (the terminal + card's own output scroller carries the same treatment in TerminalBlock). */ +.ioSection::-webkit-scrollbar-thumb { + border: 2px solid transparent; + background-clip: padding-box; + border-radius: 6px; +} + +/* Track end-margins keep the thumb's travel out of the rounded corners. */ +.ioSection::-webkit-scrollbar-track { + margin: 6px 0; +} + +/* Caption (not tertiary): one step dimmer than the payload text so the + gutter labels read as labels, not as part of the content. Sticky against + the section's own scroll so the label stays readable while its payload + scrolls underneath (top 0 = the section's padding edge inside the + scrollport; start-aligned because sticky needs a block-start anchor). */ +.ioLabel { + position: sticky; + top: 0; + align-self: start; + color: var(--dsw-alias-label-caption); +} + +/* l2 hairline between the IN and OUT sections, spanning the full card width + (it sits between the padded sections, not inside their grid). */ +.ioDivider { + flex: none; + height: 1px; + background: var(--dsw-alias-border-l2); +} + +.ioText { + min-width: 0; + white-space: pre-wrap; + word-break: break-word; + color: var(--dsw-alias-label-secondary); +} + +/* A failed call's OUT text shares the collapsed summary's error color. */ +.ioText[data-error] { + color: var(--dsw-alias-state-error-primary); +} + /* The two block-shaped expanded bodies: the code variant's run_code program through CodeBlock (shiki-highlighted TypeScript) and a terminal card's command output through TerminalBlock. Both are drawn by the shared @@ -121,15 +254,21 @@ flow's row rhythm. */ .codeBody, .terminalBody { - margin: 4px 0 4px 22px; + margin: 4px 0 4px 4px; } -/* Indented to the body's own column so the description reads as the card's - heading rather than as another summary row, and sits tight against the card - below it. Its own rule: grouping it with a body would put description - typography on a `CodeBlock` wrapper and change that body's spacing. */ -.terminalDescription { - margin: 4px 0 0 22px; - color: var(--dsw-alias-label-secondary); - font: var(--dsw-font-xs-13); +/* 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 { + --dsl-code-block-content-font: var(--dsw-font-markdown-code-block-small); +} + +/* The terminal card scrolls its OUTPUT inside its own surface (same l1 + hairline as the IN/OUT card): the banner stays pinned and the scrollbar + never rides over it. 224px = the 260px card cap minus the ~36px banner. */ +.terminalBody { + --dsl-terminal-font: var(--dsw-font-markdown-code-block-small); + --dsl-terminal-line-height: 18px; + --dsl-terminal-output-max-height: 224px; + border: 1px solid var(--dsw-alias-border-l1); } diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx index 365000ebb9..9413e1809c 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx @@ -1,21 +1,33 @@ // ToolRow: the single-line tool summary row (figma component set 122:9479) — // 16px leading slot (state dot / tool icon, chevron on hover or expanded) + title + -// separator dot + FILL-truncated summary. The collapsed row is always one -// line; the expanded body is indented gray text, the run_code program through -// CodeBlock, or — for a call whose render intent is a terminal card — the -// command's own output through TerminalBlock, capped at -// CHAT_TERMINAL_MAX_LINES so the message flow stays scannable. Expand state is -// component-local view state. File-tool summaries are path links that open -// through the host; the row itself is not a details-panel control. +// 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, or terminal material 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, or a terminal +// card's command output through TerminalBlock — 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. import { useState, type MouseEvent, type ReactNode } from 'react' +import clsx from 'clsx' import { CodeBlock, StateDot, TerminalBlock } from '@deepseek-ai/dsh-client-ui-primitives' -import { CHAT_TERMINAL_MAX_LINES, type TerminalCardModel } from '../contract/terminal-card-model.ts' +import type { TranslateNS } from '@deepseek-ai/dsh-client-ui-slots' +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' import css from './ToolRow.module.css' export interface ToolRowProps { + /** The render site's conversation locale seat (terminal/code body copy). */ + t: TranslateNS<'conversation'> variant: ToolRowVariant /** Wire tool name for tool-owned styling layered over the generic variant. */ toolName?: string | undefined @@ -23,18 +35,20 @@ export interface ToolRowProps { icon: ReactNode title: string summary: string - /** Expanded-body text; null = no text body (`terminal` is the other body source). */ + /** Expanded-body input text; null = no input section. */ body: string | null + /** Flattened result text for the expanded Output section; null/absent = no output section. */ + output?: string | null | undefined + /** Error first line shown as the collapsed summary on an error row; null/absent = keep `summary`. */ + errorSummary?: string | null | undefined /** * Terminal-card material for a call whose render intent is a terminal card - * (derived by `terminalCardModel`); it replaces the text body when present. - * Null or absent leaves the text body, and a row with neither is not - * expandable (its leading slot never toggles). + * (derived by `terminalCardModel`); it replaces the text sections when + * present. A row with no body, no output, and no terminal material is not + * expandable. */ terminal?: TerminalCardModel | null | undefined state: ToolRowState - /** Makes the row itself the expand control instead of only its leading icon. */ - expandOnRowClick?: boolean | undefined /** * Filesystem path from tool args; when set with onOpenFile, the summary * renders as a hover-underline link that opens the host default app. @@ -42,6 +56,21 @@ export interface ToolRowProps { filePath?: string | undefined /** Open the path with the host OS default application (already cwd-resolved). */ onOpenFile?: ((path: string) => void) | undefined + /** + * Jump to this call in the trajectory view: a hover-revealed Inspect pill + * over the expanded body. Absent = no affordance (rows without a call + * identity, like Think). + */ + inspect?: (() => void) | undefined +} + +/** The Inspect pill's code glyph (user-supplied 16×16), fill follows text color. */ +function IconInspect() { + return ( + + + + ) } /** Leading-slot state substitution: the tool icon yields to the terminal state @@ -56,32 +85,32 @@ function leadingFor(state: ToolRowState, icon: ReactNode): ReactNode { } export function ToolRow({ + t, variant, toolName, icon, title, summary, body, + output, + errorSummary, terminal, state, - expandOnRowClick = false, filePath, onOpenFile, + inspect, }: ToolRowProps) { const [expanded, setExpanded] = useState(false) const terminalBody = terminal ?? null - // A row that names a single file keeps one interaction (open that path); - // args expand is off whether or not the open callback is wired yet. Terminal - // material still expands: only the file variants carry a path, so a terminal - // card and a file link never land on the same row. - const singleFile = filePath !== undefined - const fileLink = singleFile && onOpenFile !== undefined - const expandable = (body !== null && !singleFile) || terminalBody !== null - // The text arms take the empty string for a null body: a row expandable - // only through its terminal material renders the terminal body instead, so - // this substitution never shows. - const text = body ?? '' + const outputText = output ?? null + const expandable = body !== null || outputText !== null || terminalBody !== null const open = expanded && expandable + // 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 + const summaryText = failureLine ?? summary + // The failure line is error prose, not the path: no open-file affordance. + const fileLink = filePath !== undefined && onOpenFile !== undefined && failureLine === null const toggleExpand = () => { setExpanded(v => !v) } @@ -89,20 +118,33 @@ export function ToolRow({ event.stopPropagation() if (filePath !== undefined) onOpenFile?.(filePath) } + // 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. + const isThink = variant === 'think' + // The code variant's program renders through CodeBlock (shiki), so only its + // output joins the IN/OUT card; every other variant's input does too. + const cardBody = variant === 'code' ? null : body + // The state substitution rides the idle icon slot, so an expandable error + // row keeps DisclosureRow's icon→chevron hover preview (its default) instead + // of losing it with the icon. return (
{fileLink ? ( @@ -111,24 +153,71 @@ export function ToolRow({ className={css.fileLink} onClick={openFile} > - {summary} + {summaryText} ) : ( - {summary} + + {summaryText} + )} )} > - {/* The terminal presenter's description belongs above the card per - the render-intent contract. */} - {terminalBody?.description !== undefined && ( -
{terminalBody.description}
- )} - {terminalBody !== null - ? - : variant === 'code' - ? - :
{text}
} + {/* The wrapper (sibling of the header row, so clicks inside never + toggle it) carries the expanded body and the Inspect pill below. */} +
+ {terminalBody !== 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 && ( + + )} +
) diff --git a/packages/client/ui-conversation/src/client/chat/chat-flow.ts b/packages/client/ui-conversation/src/client/chat/chat-flow.ts index f1ce061af8..f925ffbebb 100644 --- a/packages/client/ui-conversation/src/client/chat/chat-flow.ts +++ b/packages/client/ui-conversation/src/client/chat/chat-flow.ts @@ -1,17 +1,27 @@ /** * Chat flow derivation: ConversationSnapshot nodes -> render items. Tool * results group into consecutive-run tool groups (figma step-summary flow, - * VERTICAL gap10) alternating with narration; everything else passes through. + * VERTICAL gap10) alternating with narration. Consecutive retry notices + * reuse the first notice's row while projecting the latest retry turn. * Item identity keys are stable across snapshots so the list parent can - * subscribe to keys only while rows subscribe to content. + * subscribe to keys only while rows subscribe to content. IconActions ownership + * (last content assistant per turn) is derived here too so ChatView and the + * flow share one gate. */ -import type { ConversationNode, ToolResultNode } from '@deepseek-ai/dsh-client-runtime/client' +import type { + AssistantBlock, ConversationNode, ToolResultNode, +} from '@deepseek-ai/dsh-client-runtime/client' /** One renderable flow item; key is the React key and the parent's identity unit. */ export type ChatFlowItem = | { kind: 'node'; key: string; node: ConversationNode } | { kind: 'tool-group'; key: string; results: readonly ToolResultNode[] } +/** True when the node has model-visible text content worth IconActions chrome. */ +function hasContentText(blocks: readonly AssistantBlock[]): boolean { + return blocks.some(block => block.kind === 'text' && block.text.trim() !== '') +} + /** An assistant node that renders nothing: only tool-call heads (rows render * via the grouping pass) and blank text/reasoning. Skipped by the flow so it * neither costs column gaps nor splits a tool-row run. Interrupted nodes @@ -22,10 +32,25 @@ function rendersNothing(node: ConversationNode): boolean { || ((b.kind === 'text' || b.kind === 'reasoning') && b.text.trim() === '')) } +/** + * Seq set of assistants that own IconActions: the last content-text assistant + * in each turn. Mid-turn narration (text before tools) stays chrome-free. + * @param nodes - snapshot nodes (surface order). + * @returns Seq values ChatView may pass as `time` into AssistantMarkdown. + */ +export function assistantActionsSeqs(nodes: readonly ConversationNode[]): ReadonlySet { + const lastByTurn = new Map() + for (const node of nodes) { + if (node.kind !== 'assistant' || !hasContentText(node.blocks)) continue + lastByTurn.set(node.turn, node.seq) + } + return new Set(lastByTurn.values()) +} + /** * Group finalized nodes into the step-summary flow. * @param nodes - snapshot nodes (surface order). - * @returns flow items; consecutive tool-results merged into one group keyed by the first seq. + * @returns flow items; consecutive tool results and retry notices reuse their first key. */ export function deriveChatFlow(nodes: readonly ConversationNode[]): ChatFlowItem[] { const items: ChatFlowItem[] = [] @@ -39,6 +64,17 @@ export function deriveChatFlow(nodes: readonly ConversationNode[]): ChatFlowItem } else { group.push(node) } + } else if (node.kind === 'model-retry') { + group = null + const previous = items[items.length - 1] + if ( + previous?.kind === 'node' + && previous.node.kind === 'model-retry' + ) { + items[items.length - 1] = { ...previous, node } + } else { + items.push({ kind: 'node', key: `n${node.seq}`, node }) + } } else { group = null items.push({ kind: 'node', key: `n${node.seq}`, node }) diff --git a/packages/client/ui-conversation/src/client/chat/message-chrome.ts b/packages/client/ui-conversation/src/client/chat/message-chrome.ts index b005b8404b..67b625e71d 100644 --- a/packages/client/ui-conversation/src/client/chat/message-chrome.ts +++ b/packages/client/ui-conversation/src/client/chat/message-chrome.ts @@ -1,6 +1,11 @@ // Shared chrome helpers for user/assistant IconActions rows: clipboard write // and the compact date+clock label from a session-event epoch. +import type { Translate } from '@deepseek-ai/dsh-client-ui-slots' + +/** The date-template share of the conversation dictionary the clock consumes. */ +export type ClockTranslate = Translate<'clock.md' | 'clock.ymd'> + /** * Best-effort clipboard write; rejections stay swallowed (no success chrome). * @param text - Plain text to place on the clipboard. @@ -67,14 +72,16 @@ export function msUntilNextLocalMidnight(ms: number): number { } /** - * Compact local timestamp for message IconActions. - * Same calendar day → `HH:mm`; earlier this year → `M月D日 HH:mm`; - * other years → `YYYY年M月D日 HH:mm`. + * Compact local timestamp for message IconActions. Same calendar day → + * `HH:mm`; earlier this year → the `clock.md` date template + clock; other + * years → the `clock.ymd` template + clock. Pure: the date templates arrive + * through the caller's locale seat. * @param time - Unix epoch ms from the source session event. + * @param t - translate seat supplying the `clock.md` / `clock.ymd` templates. * @param now - Reference instant for the day/year cut (defaults to wall clock). * @returns Date-aware clock string (24-hour, zero-padded time). */ -export function formatMessageClock(time: number, now: number = Date.now()): string { +export function formatMessageClock(time: number, t: ClockTranslate, now: number = Date.now()): string { const d = new Date(time) const n = new Date(now) const clock = `${pad2(d.getHours())}:${pad2(d.getMinutes())}` @@ -85,7 +92,7 @@ export function formatMessageClock(time: number, now: number = Date.now()): stri ) { return clock } - const md = `${d.getMonth() + 1}月${d.getDate()}日` - if (d.getFullYear() === n.getFullYear()) return `${md} ${clock}` - return `${d.getFullYear()}年${md} ${clock}` + const params = { y: d.getFullYear(), m: d.getMonth() + 1, d: d.getDate() } + const md = d.getFullYear() === n.getFullYear() ? t('clock.md', params) : t('clock.ymd', params) + return `${md} ${clock}` } diff --git a/packages/client/ui-conversation/src/client/contract/slots.ts b/packages/client/ui-conversation/src/client/contract/slots.ts index dca8cbc567..b909b6e979 100644 --- a/packages/client/ui-conversation/src/client/contract/slots.ts +++ b/packages/client/ui-conversation/src/client/contract/slots.ts @@ -1,11 +1,11 @@ /** Conversation slot declarations and their composed component props. */ import type { ReactNode, RefObject } from 'react' import type { - InjectFace, MaybeSnapshotSelectorHook, PropsRenderSlots, PropsRuntime, PropsStore, SnapshotSelectorHook, + InjectFace, MaybeSnapshotSelectorHook, PropsLocale, PropsRenderSlots, PropsRuntime, PropsStore, SnapshotSelectorHook, } from '@deepseek-ai/dsh-client-ui-slots' import type { CommandNode, ConversationSnapshot, ObservableSnapshot, PendingInteraction, PendingWait, SessionId, ToolCallBlock, WorkspaceId } from '@deepseek-ai/dsh-client-runtime/client' import type {} from '@deepseek-ai/dsh-client-ui-layout/client' -import type { ComposerKeyboard, InputActions, InputNotice, InputState } from '../input/contract.ts' +import type { ComposerKeyboard, EditSelection, InputActions, InputNotice, InputState } from '../input/contract.ts' import type { createChatStore } from '../stores.ts' import type { CallId, SelectionTarget, ViewTab } from './views.ts' @@ -147,13 +147,17 @@ export interface InputZone { } /** - * View-slot owner share: deliberately empty — ConversationRoot supplies - * nothing at its renderSlot site (sessionId and the snapshot hook arrive as + * View-slot owner share: the cross-view inspect handoff (otherwise views need + * nothing from the render site — sessionId and the snapshot hook arrive as * framework-standard props; tool rows go through each view's own declared - * toolview hole). Kept as the named owner seat so a future cross-view - * payload has a home. + * toolview hole). */ -export interface ConvViewOwnerProps {} +export interface ConvViewOwnerProps { + /** One-shot inspect request from another view (chat's Inspect button); null when idle. */ + inspect?: { callId: CallId } | null + /** Acknowledge the inspect request once applied (clears the store field). */ + onInspectDone?: () => void +} /** * Owner share of a per-view toolview slot: the call material the rendering @@ -176,6 +180,11 @@ export interface ToolRowOwnerProps { * The chat view resolves relative paths against the session cwd. */ openFile: (path: string) => void + /** + * Jump to this call's record in the trajectory view (the expanded row's + * hover Inspect affordance). Undefined when no trajectory jump is wired. + */ + inspect?: (() => void) | undefined } /** @@ -265,14 +274,14 @@ export interface ComposerBarOwnerProps { rightItems?: ReactNode /** composer.dock entries (stats line), rendered under the card inside the bar's width column. */ footer?: ReactNode - onAdd?: () => void - addLabel?: string } /** Injected share of the composer-bar entry (package-internal faces). */ export interface ComposerBarInjected { /** The InputBar-exclusive keyboard/DOM command face (decision 20 private plane); absent with the session. */ keyboard: ComposerKeyboard | undefined + /** Toggle the shared slash menu with only its command source; absent without ui-slash or a session. */ + toggleCommandMenu: ((selection: EditSelection) => void) | undefined /** Cancel the in-flight turn; absent with the session. */ stop: (() => void) | undefined /** @@ -282,8 +291,6 @@ export interface ComposerBarInjected { * Resolves admission: false = rejected/unmatched/transport failure. */ command: ((line: string) => Promise) | undefined - /** Locale-aware hint translator for claimed command placeholders (session-independent — always present). */ - translateHint: (key: string) => string /** * Registrant hooks compartment: the renderer binds these to * useNotices/useLexicon (static absent sources without a session — hook @@ -294,6 +301,8 @@ export interface ComposerBarInjected { notices: ObservableSnapshot /** Hot plain-text reference lexicon for the decoration scan (decision 21). */ lexicon: ObservableSnapshot> + /** Source name opened by the programmatic menu launcher, or null. */ + menuLauncher: ObservableSnapshot } } @@ -306,11 +315,12 @@ export interface InputControlOwnerProps { locked: boolean } -/** Full composer-bar component props: standard kit & owner share & control-seat render share & injected share (hooks compartment bound). */ +/** Full composer-bar props: standard kit & owner share & control-seat render share & injected share (hooks bound) & locale seat. */ export type ComposerBarProps = PropsRuntime<'conversation.composer.bar'> & PropsRenderSlots<'conversation.input.plan' | 'conversation.input.model'> & InjectFace + & PropsLocale<'conversation'> /** * Composer chain currency: what ConversationRoot dispatches at its @@ -325,7 +335,8 @@ export interface ComposerChainProps { /** * Full conversation-slot component props: runtime & child-render (view ring - * + composer chain/bar + input-region + hero picker slots) & store & injected shares. + * + composer chain/bar + input-region + hero picker slots) & store & injected + * shares & the locale seat. */ export type ConversationSlotProps = PropsRuntime<'conversation'> & PropsRenderSlots< @@ -336,13 +347,15 @@ export type ConversationSlotProps = | 'conversation.hero.workspace' > & ConversationInjected + & PropsLocale<'conversation'> -/** Full strict-session content props: per-session store, view ring, and callbacks. */ +/** Full strict-session content props: per-session store, view ring, callbacks, and the locale seat. */ export type ConversationSessionSlotProps = PropsRuntime<'conversation.session'> & PropsRenderSlots<'conversation.view'> & PropsStore & ConversationSessionInjected + & PropsLocale<'conversation'> /** The pending approval carrier the owner dispatches into the composer chain. */ export type ApprovalWait = PendingWait<'approval'> @@ -400,11 +413,13 @@ export class PendingApproval { /** * Full approval-composer props: the framework runtime share (chain currency + * session/global standard kit) plus the chain `matched` share — the entry's - * selector result, already narrowed to the approval carrier. No injected - * share: the carrier plus the domain face above carry the whole behavior - * surface; the paired command line derives from useSession in-component. + * selector result, already narrowed to the approval carrier — plus the + * standard locale seat. No injected share: the carrier plus the domain face + * above carry the whole behavior surface; the paired command line derives + * from useSession in-component. */ -export type ApprovalComposerProps = PropsRuntime<'conversation.composer'> & { matched: ApprovalWait } +export type ApprovalComposerProps = + PropsRuntime<'conversation.composer'> & { matched: ApprovalWait } & PropsLocale<'conversation'> /** * Injected share of the chat view entry: the two callbacks whose targets live @@ -419,14 +434,27 @@ export interface ChatViewInjected { */ openFile: (path: string) => void loadOlder: () => void + /** Hand a call off to the trajectory view: write the one-shot inspect target and switch tabs. */ + inspectCall: (callId: CallId) => void + /** + * Per-session scroll memory surviving view switches (in-memory, never + * persisted): the view saves on every scroll and restores on remount; a + * fresh page load starts empty and keeps the open-jump-to-bottom default. + */ + chatScroll: { + /** Record the scroll offset; null clears it (pinned to bottom). */ + save: (top: number | null) => void + /** Last recorded offset, or null when pinned or never recorded. */ + read: () => number | null + } /** Fork the session through the turn containing the message at `seq`, then open the child. */ forkAt: (seq: number) => void } -/** Full chat-view component props: runtime share & the declared toolview/commandview holes' render share & store share & injected share. */ +/** Full chat-view component props: runtime & the declared toolview/commandview holes' render share & store & injected & locale seat. */ export type ChatViewSlotProps = PropsRuntime<'conversation.view'> & PropsRenderSlots<'conversation.chat.toolview' | 'conversation.chat.commandview'> - & PropsStore & ChatViewInjected + & PropsStore & ChatViewInjected & PropsLocale<'conversation'> /** * Injected share of the details slot: the panel is otherwise a pure reader of @@ -437,8 +465,8 @@ export interface DetailsInjected { closeDetails: () => void } -/** Full details-slot component props: selection arrives through the shared store, call material through useSession. */ -export type DetailsSlotProps = PropsRuntime<'details'> & PropsStore & DetailsInjected +/** Full details-slot component props: selection rides the shared store, call material useSession; copy the locale seat. */ +export type DetailsSlotProps = PropsRuntime<'details'> & PropsStore & DetailsInjected & PropsLocale<'conversation'> /** Owner share common to the hero / New-Session Workspace pickers. */ export interface EmptyWorkspaceOwnerProps { diff --git a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts index e25d68cbbb..f6c7f5a911 100644 --- a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts +++ b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts @@ -8,19 +8,34 @@ * are derived once. * @module */ -import type { TerminalBlockProps } from '@deepseek-ai/dsh-client-ui-primitives' +import type { TerminalBlockLabels, TerminalBlockProps } from '@deepseek-ai/dsh-client-ui-primitives' +import type { TranslateNS } from '@deepseek-ai/dsh-client-ui-slots' import { resolveToolPath, type ToolCallBlock } from './tool-call-model.ts' /** - * Output lines the chat row's expanded terminal body shows before collapsing - * the middle — half the primitive's own default, which the details panel - * keeps. A chat row is a summary surface inside the message flow: the flow - * must stay scannable across many calls, while the details panel is the - * single-call reading surface. A design constant of this UI's row geometry, - * not a deployment choice, so it is fixed here rather than a plugin Config - * field. + * Build the TerminalBlock display copy from the conversation locale seat — + * the one place the primitive's label surface pairs with this package's + * dictionary, shared by every terminal render site (chat row, bash row, + * details panel). + * @param t - the render site's conversation locale seat. + * @returns the full label set for {@link TerminalBlockProps}'s `labels`. */ -export const CHAT_TERMINAL_MAX_LINES = 8 +export function terminalBlockLabels(t: TranslateNS<'conversation'>): TerminalBlockLabels { + return { + signal: signal => t('terminal.signal', { signal }), + exitCode: code => t('terminal.exitCode', { code }), + running: t('terminal.running'), + failed: t('terminal.failed'), + done: t('terminal.done'), + copy: t('copy'), + copied: t('copied'), + noOutput: t('terminal.noOutput'), + collapseAria: t('terminal.collapseAria'), + collapse: t('collapse'), + expandAria: hidden => t('terminal.expandAria', { n: hidden }), + expand: hidden => t('terminal.expandRest', { n: hidden }), + } +} /** * The {@link TerminalBlock} props this derivation owns. Picked off the @@ -44,6 +59,20 @@ export interface TerminalCardModel { description: string | undefined } +/** + * True when a settled terminal card reports a failing exit — a non-zero code + * or a terminating signal. The bash tool settles a failing command as a + * completed call (`isError` stays false: the exit status is result data), so + * this is the collapsed row's only failure signal; without it the red exit + * pill would be visible only after expanding the card. + * @param model - a derived terminal card. + * @returns whether the card's exit status is a failure. + */ +export function terminalFailed(model: TerminalCardModel): boolean { + const { exitCode, signal, running } = model.card + return running !== true && ((exitCode !== undefined && exitCode !== 0) || signal !== undefined) +} + /** * Resolve a terminal view's working directory the way the render-intent * contract assigns to the UI bridge: an absolute path is used as-is, a relative diff --git a/packages/client/ui-conversation/src/client/contract/tool-call-model.ts b/packages/client/ui-conversation/src/client/contract/tool-call-model.ts index b53ef95c01..d7735fdab2 100644 --- a/packages/client/ui-conversation/src/client/contract/tool-call-model.ts +++ b/packages/client/ui-conversation/src/client/contract/tool-call-model.ts @@ -1,14 +1,15 @@ /** * Pure row-model derivation for tool summary rows: variant classification, - * one-line summary and expanded-body text from the frozen call slice. This - * derivation reads the call ARGUMENTS only; a call whose render intent is a - * terminal card gets its expanded body from the views instead, through + * one-line summary, expanded-body text, and flattened result output from the + * frozen call slice. Input material comes from the call ARGUMENTS; output and + * error material from the settled result node. A call whose render intent is + * a terminal card gets its expanded body from the views instead, through * `terminalCardModel` in terminal-card-model.ts. */ // The block union's defining home is runtime (fold-product types); this // contract only forwards it (type-definition authority stays with the layer // that produces the values). -import type { ToolCallBlock } from '@deepseek-ai/dsh-client-runtime/client' +import type { ToolCallBlock, ToolResultNode } from '@deepseek-ai/dsh-client-runtime/client' export type { ToolCallBlock } from '@deepseek-ai/dsh-client-runtime/client' @@ -70,11 +71,34 @@ export interface ToolRowModel { * relative values against the session cwd before opening. */ filePath: string | undefined - /** Expanded-body text (pretty args); null = row not expandable. */ + /** Expanded-body input text (pretty args); null = no input section. */ body: string | null + /** Flattened result text ({@link resultText}); null while running or when the result carries no text. */ + output: string | null + /** First line of the result text on an error row; null for every other state. */ + errorSummary: string | null state: ToolRowState } +/** + * Flatten a settled result's content blocks to display text: text blocks + * verbatim, other block shapes as pretty JSON. Empty content on a failed call + * falls back to the structured error's `name: code` line. + * @param node - the settled result node. + * @returns the flattened result text (may be empty). + */ +export function resultText(node: ToolResultNode): string { + const parts: string[] = [] + for (const block of node.content) { + if (block.type === 'text') parts.push(block.text) + else parts.push(JSON.stringify(block, null, 2)) + } + if (parts.length === 0 && node.error !== undefined) { + parts.push(`${node.error.name}: ${node.error.code}`) + } + return parts.join('\n') +} + function parseArgs(argsRaw: string): unknown { try { return JSON.parse(argsRaw) @@ -192,12 +216,19 @@ export function toolRowModel(toolName: string, block: ToolCallBlock, cwd?: strin const summary = variant === 'others' && toolName !== '' && toolTitle === undefined ? `${toolName} · ${base}` : base + // The empty string is "no text" for both derived result fields: a settled + // call with blank content has nothing to expand, and a blank first line + // would erase the collapsed error row's summary slot. + const output = done ? (resultText(block) || null) : null + const errorSummary = state === 'error' && output !== null ? firstLine(output) : null return { variant, title: toolTitle ?? VARIANT_TITLES[variant], summary, filePath: deriveFilePath(variant, argsRaw), body: deriveBody(variant, argsRaw), + output, + errorSummary, state, } } diff --git a/packages/client/ui-conversation/src/client/contract/views.ts b/packages/client/ui-conversation/src/client/contract/views.ts index 9ef9515f19..a8da4121b9 100644 --- a/packages/client/ui-conversation/src/client/contract/views.ts +++ b/packages/client/ui-conversation/src/client/contract/views.ts @@ -23,4 +23,10 @@ export interface ChatStoreState { draft: string /** Active conversation view id ('conversation.view' entry id); null falls back to the first view. */ view: string | null + /** + * One-shot inspect handoff: chat writes the call to reveal, the trajectory + * view consumes it and acknowledges by clearing. Read with `?? null` — + * persisted snapshots from before this field rehydrate without it. + */ + inspect: { callId: CallId } | null } diff --git a/packages/client/ui-conversation/src/client/contract/web-card-model.ts b/packages/client/ui-conversation/src/client/contract/web-card-model.ts new file mode 100644 index 0000000000..f2b15e023a --- /dev/null +++ b/packages/client/ui-conversation/src/client/contract/web-card-model.ts @@ -0,0 +1,84 @@ +/** + * Pure derivation of the web-card props from a frozen call slice: the + * `card:'web'` render intent the `web_search`/`web_fetch` tools declare at + * result time arrives on the snapshot as `resultView`, and this is the one + * place that turns it into what {@link WebBlock} draws. Both conversation + * render sites (the chat tool row's resident/expanded body and the details + * panel's Output section) call this, so the sources and fetch summary they + * show are derived once. + * + * The web card is result-only by contract: those tools keep a generic pending + * call view, so there is nothing to derive while the call is still running and + * a running call always takes the generic path. + * @module + */ +import type { WebBlockProps } from '@deepseek-ai/dsh-client-ui-primitives' +import type { ToolCallBlock } from './tool-call-model.ts' + +/** + * Sources the chat row's web body shows before collapsing the middle — half + * the primitive's own default, which the details panel keeps. A chat row is a + * summary surface inside the message flow: the flow must stay scannable across + * many calls, while the details panel is the single-call reading surface. A + * design constant of this UI's row geometry, not a deployment choice, so it is + * fixed here rather than a plugin Config field. + */ +export const CHAT_WEB_MAX_SOURCES = 8 + +/** + * Derive the web-card props for a tool call, or null when this call is not a + * web card and belongs on the generic path. + * + * The result side supplies the whole card: the sources and answer for a + * `search`, the URL and status for a `fetch`. Cases producing null, all of + * them the documented generic-card default: + * + * - A running call (no `resultView` yet): the web tools keep a generic pending + * card, so nothing web-shaped exists until the call settles. + * - A settled call whose result view is not a web card — including a `card` + * value this UI version does not know, which arrives over the wire and so + * cannot be trusted to be one of the compiled variants, and a generic result + * view (a web tool's error path returns the generic card, whose text the + * generic path preserves). + * - A web card whose `kind` this UI version does not know (a newer host's + * value): the wire cannot be trusted to be `search` or `fetch`, so it takes + * the generic path rather than rendering as a malformed fetch. + * @param block - RunningToolCall or ToolResultNode off the snapshot caches. + * @returns the web-card props, or null for the generic path. + */ +export function webCardModel(block: ToolCallBlock): WebBlockProps | null { + // Running calls have no result view; the web card is result-only. + if (!('kind' in block)) return null + const result = block.resultView + if (result?.card !== 'web') return null + if (result.kind === 'search') { + return { + kind: 'search', + answer: result.answer, + sources: result.sources.map(source => ({ + url: source.url, + title: source.title, + snippet: source.snippet, + publishedAt: source.publishedAt, + })), + truncated: result.truncated, + } + } + // Discriminate `fetch` explicitly rather than treating it as the else of + // `search`: a `kind` this UI version does not know arrives over the wire from + // a newer host, and reading it as a fetch would draw an empty URL and + // `HTTP undefined`. It takes the generic path, the same wire-boundary default + // an unknown `card` tag takes above. The static union narrows `kind` to + // `'fetch'` here, but the runtime value is off the wire, so the guard and its + // null fallthrough are load-bearing despite the type. + // oxlint-disable-next-line typescript/no-unnecessary-condition + if (result.kind === 'fetch') { + return { + kind: 'fetch', + url: result.url, + statusCode: result.statusCode, + truncated: result.truncated, + } + } + return null +} diff --git a/packages/client/ui-conversation/src/client/index.ts b/packages/client/ui-conversation/src/client/index.ts index 56d398def3..d04f2473e1 100644 --- a/packages/client/ui-conversation/src/client/index.ts +++ b/packages/client/ui-conversation/src/client/index.ts @@ -11,6 +11,7 @@ export type { CallId, ChatStoreState, SelectionTarget, ViewTab, } from './contract/views.ts' export type { ToolCallBlock } from './contract/tool-call-model.ts' +export type { ConversationKey } from './locales.ts' export type { ChatStore, ChatViewInjected, ChatViewSlotProps, CommandRowOwnerProps, CommandRowProps, ComposerBarInjected, ComposerChainProps, ConversationInjected, diff --git a/packages/client/ui-conversation/src/client/input/hub.ts b/packages/client/ui-conversation/src/client/input/hub.ts index 2641e0dcc4..7b8fa344d6 100644 --- a/packages/client/ui-conversation/src/client/input/hub.ts +++ b/packages/client/ui-conversation/src/client/input/hub.ts @@ -106,6 +106,17 @@ export class InputHub implements InputService { return this.shell(id) } + /** + * Resolve the optional slash controller for composer chrome that launches + * the shared candidate menu without typing a trigger. + * @param id - session id. + * @returns the resident controller, or undefined when ui-slash is absent. + */ + slash(id: SessionId): SlashController | undefined { + const actx = this.sessions().scope(id) + return actx === undefined ? undefined : this.controller(actx) + } + /** * Default sink: optimistic clear + prompt. The session is always a real * host entity (materialized when its workspace was picked), so there is diff --git a/packages/client/ui-conversation/src/client/locales.ts b/packages/client/ui-conversation/src/client/locales.ts new file mode 100644 index 0000000000..2ac6f25a20 --- /dev/null +++ b/packages/client/ui-conversation/src/client/locales.ts @@ -0,0 +1,184 @@ +/** `conversation` namespace dictionaries. */ + +/** Dictionary namespace owned by this plugin. */ +export const NS = 'conversation' + +// The claimed /plan hint and the plan-mode textarea placeholder share one +// string: both describe the same next action. +const PLAN_NEXT_ACTION_ZH = '描述你的任务以生成计划' +const PLAN_NEXT_ACTION_EN = 'describe your task to generate plan' + +/** Simplified Chinese dictionary (the key-set source of truth). */ +export const zh = { + 'view.chat': '对话', + 'hint.plan': PLAN_NEXT_ACTION_ZH, + 'hint.goal': '输入目标，智能体将持续执行', + 'hint.goal.active': '当前目标进行中。可输入 edit 修改 / pause 暂停 / resume 继续 / clear 清除', + 'placeholder.plan': PLAN_NEXT_ACTION_ZH, + 'placeholder.default': '给智能体发消息', + 'placeholder.unavailable': '会话不可用', + 'placeholder.hero': '描述你想要构建的内容', + 'placeholder.workspace': '选择一个工作区开始', + 'input.commands': '命令', + 'input.stop': '停止生成', + 'input.send': '发送消息', + 'input.accessMode': '访问模式，当前：{name}', + 'hero.headline': '开始构建吧', + 'hero.chooseWorkspace': '选择工作区', + 'session.hierarchy': '会话层级', + 'details.title': '详情', + 'details.close': '关闭详情', + 'details.empty': '点击消息流中的工具行查看详情', + 'details.notInWindow': '该调用不在当前窗口内', + 'details.input': '输入', + 'details.output': '输出', + 'details.running': '运行中…', + 'todo.title': '任务清单', + 'todo.progress': '{done}/{total} 项任务 · {active} 项进行中', + 'todo.rowTitle': '更新任务清单', + 'todo.completed': '{done}/{total} 已完成', + 'chat.loadingHistory': '载入历史…', + 'chat.loadError': '历史加载失败：{message}（{code}）', + 'chat.loadOlder': '加载更早', + 'chat.toBottom': '回到底部', + 'message.extraBlock': '附加内容块', + 'message.steering': '插话', + 'message.contextInjection': '上下文注入', + 'message.unknownSurface': '未知 surface 事件：{type}', + 'message.unknownBlock': '未知内容块', + 'message.stopped': '已停止', + 'message.branch': '在新对话中分支', + 'message.retry.active': '正在重试模型请求', + 'message.retry.cancelled': '模型请求重试已取消', + 'message.retry.started': '已重试模型请求', + 'message.retry.scheduled': '等待重试模型请求', + 'message.retry.status': '{label}（{retry}/{maximum}） · {seconds}s', + 'message.retry.delay': '重试延迟：', + 'message.retry.failure': '失败原因：', + 'command.running': '执行中…', + 'command.failed': '命令失败', + 'command.done': '已完成', + 'command.title': '命令', + 'approval.waiting': '等待审批', + 'approval.detail.aria': '审批详情', + 'approval.escalation': '工具 {toolName} 请求越权执行', + 'approval.reject': '拒绝', + 'approval.allowOnce': '允许一次', + 'ask.rowTitle': '提问', + 'ask.waiting': '等待回答', + 'ask.cancelled': '已取消', + 'ask.interrupted': '已中断', + 'ask.answered': '{answered}/{total} 已回答', + 'bash.running': '运行中', + 'bash.failed': '失败', + 'bash.stopped': '已停止', + 'queue.count': '{n} 条排队消息', + 'queue.edit': '编辑排队消息', + 'queue.edit.unsupported': '包含非文本内容，暂不支持编辑', + 'queue.save': '保存排队消息', + 'queue.cancelEdit': '取消编辑', + 'queue.remove': '删除排队消息', + 'queue.editFailed': '编辑失败：这条消息可能已经开始发送。', + 'queue.removeFailed': '删除失败：这条消息可能已经开始发送。', + 'terminal.signal': '信号 {signal}', + 'terminal.exitCode': '退出码 {code}', + 'terminal.running': '运行中', + 'terminal.failed': '失败', + 'terminal.done': '已完成', + 'terminal.noOutput': '无输出', + 'terminal.collapseAria': '收起输出', + 'terminal.expandAria': '展开其余 {n} 行输出', + 'terminal.expandRest': '… 其余 {n} 行', + 'json.truncated': '… 已截断，共 {total} 字符', + 'clock.md': '{m}月{d}日', + 'clock.ymd': '{y}年{m}月{d}日', +} satisfies Record + +/** The conversation namespace key union. */ +export type ConversationKey = keyof typeof zh + +/** English dictionary, checked complete against the zh key set. */ +export const en = { + 'view.chat': 'Chat', + 'hint.plan': PLAN_NEXT_ACTION_EN, + 'hint.goal': 'describe the objective for a long-running task', + 'hint.goal.active': 'goal active — edit / pause / resume / clear', + 'placeholder.plan': PLAN_NEXT_ACTION_EN, + 'placeholder.default': 'Message the agent', + 'placeholder.unavailable': 'Session unavailable', + 'placeholder.hero': 'Describe what you want to build', + 'placeholder.workspace': 'Choose a workspace to start', + 'input.commands': 'Commands', + 'input.stop': 'Stop generating', + 'input.send': 'Send message', + 'input.accessMode': 'Access mode, current: {name}', + 'hero.headline': 'Let\'s start building', + 'hero.chooseWorkspace': 'Choose workspace', + 'session.hierarchy': 'Session hierarchy', + 'details.title': 'Details', + 'details.close': 'Close details', + 'details.empty': 'Click a tool row in the message flow to view its details', + 'details.notInWindow': 'This call is outside the current window', + 'details.input': 'Input', + 'details.output': 'Output', + 'details.running': 'Running…', + 'todo.title': 'To-dos', + 'todo.progress': '{done}/{total} tasks · {active} in progress', + 'todo.rowTitle': 'Update to-do list', + 'todo.completed': '{done}/{total} completed', + 'chat.loadingHistory': 'Loading history…', + 'chat.loadError': 'Failed to load history: {message} ({code})', + 'chat.loadOlder': 'Load earlier', + 'chat.toBottom': 'Back to bottom', + 'message.extraBlock': 'Extra content block', + 'message.steering': 'Interjection', + 'message.contextInjection': 'Context injection', + 'message.unknownSurface': 'Unknown surface event: {type}', + 'message.unknownBlock': 'Unknown content block', + 'message.stopped': 'Stopped', + 'message.branch': 'Branch into a new conversation', + 'message.retry.active': 'Retrying model request', + 'message.retry.cancelled': 'Model request retry cancelled', + 'message.retry.started': 'Retried model request', + 'message.retry.scheduled': 'Waiting to retry model request', + 'message.retry.status': '{label} ({retry}/{maximum}) · {seconds}s', + 'message.retry.delay': 'Retry delay: ', + 'message.retry.failure': 'Failure reason: ', + 'command.running': 'Running…', + 'command.failed': 'Command failed', + 'command.done': 'Completed', + 'command.title': 'Command', + 'approval.waiting': 'Waiting for approval', + 'approval.detail.aria': 'Approval details', + 'approval.escalation': 'Tool {toolName} requests privileged execution', + 'approval.reject': 'Reject', + 'approval.allowOnce': 'Allow once', + 'ask.rowTitle': 'Ask question', + 'ask.waiting': 'waiting', + 'ask.cancelled': 'cancelled', + 'ask.interrupted': 'interrupted', + 'ask.answered': '{answered}/{total} answered', + 'bash.running': 'Running', + 'bash.failed': 'Failed', + 'bash.stopped': 'Stopped', + 'queue.count': '{n} queued messages', + 'queue.edit': 'Edit queued message', + 'queue.edit.unsupported': 'Contains non-text content; editing is not supported yet', + 'queue.save': 'Save queued message', + 'queue.cancelEdit': 'Cancel editing', + 'queue.remove': 'Remove queued message', + 'queue.editFailed': 'Edit failed: this message may have already started sending.', + 'queue.removeFailed': 'Removal failed: this message may have already started sending.', + 'terminal.signal': 'signal {signal}', + 'terminal.exitCode': 'exit code {code}', + 'terminal.running': 'Running', + 'terminal.failed': 'Failed', + 'terminal.done': 'Done', + 'terminal.noOutput': 'No output', + 'terminal.collapseAria': 'Collapse output', + 'terminal.expandAria': 'Expand the remaining {n} output lines', + 'terminal.expandRest': '… {n} more lines', + 'json.truncated': '… truncated, {total} characters total', + 'clock.md': '{m}/{d}', + 'clock.ymd': '{y}-{m}-{d}', +} satisfies Record diff --git a/packages/client/ui-conversation/src/client/queue/QueueDock.tsx b/packages/client/ui-conversation/src/client/queue/QueueDock.tsx index 67de5d0796..1bc6f75e85 100644 --- a/packages/client/ui-conversation/src/client/queue/QueueDock.tsx +++ b/packages/client/ui-conversation/src/client/queue/QueueDock.tsx @@ -5,13 +5,14 @@ // ../contract/slots.ts beside the other input-region slots. import type { Context } from 'cordis' import { useEffect, useId, useState } from 'react' -import type { PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots' +import type { PropsLocale, PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots' import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client' import { IconCheckOutline16, IconChevronDownOutline14, IconChevronUpOutline14, IconCloseOutline16, IconEditOutline16, IconTrashOutline16, } from '@deepseek-ai/dsh-client-ui-primitives' import type { QueueAction, QueueItemId } from '../contract/queue.ts' +import { NS } from '../locales.ts' import css from './QueueDock.module.css' /** Queue operations injected by the session-scoped registration. */ @@ -20,14 +21,14 @@ export interface QueueDockInjected { notify: (level: 'info' | 'error', text: string) => void } -/** Full props of a dock entry: InputZone owner share + session standard kit + global seat. */ -export type QueueDockProps = PropsRuntime<'conversation.input.dock'> & QueueDockInjected +/** Full props of a dock entry: InputZone owner share + session standard kit + global seat + the locale seat. */ +export type QueueDockProps = PropsRuntime<'conversation.input.dock'> & QueueDockInjected & PropsLocale<'conversation'> /** * Queue strip: one item renders directly; multiple items default to a * collapsible count header; an empty queue renders nothing. */ -export function QueueDock({ useSession, updateQueue, notify }: QueueDockProps) { +export function QueueDock({ useSession, updateQueue, notify, t }: QueueDockProps) { const queue = useSession(s => s.queue) const [editing, setEditing] = useState<{ id: QueueItemId; text: string } | null>(null) const [busy, setBusy] = useState(null) @@ -67,7 +68,7 @@ export function QueueDock({ useSession, updateQueue, notify }: QueueDockProps) { if (await applyAction( editing.id, { kind: 'edit', content: [{ type: 'text', text: editing.text }] }, - '编辑失败：这条消息可能已经开始发送。', + t('queue.editFailed'), )) setEditing(null) } @@ -83,7 +84,7 @@ export function QueueDock({ useSession, updateQueue, notify }: QueueDockProps) { disabled={interactionActive} onClick={() => { setCollapsed(value => !value) }} > - {queue.length} 条排队消息 + {t('queue.count', { n: queue.length })} {expanded ? : } @@ -97,7 +98,7 @@ export function QueueDock({ useSession, updateQueue, notify }: QueueDockProps) { { setEditing({ id: row.id, text: event.currentTarget.value }) }} onKeyDown={(event) => { @@ -120,8 +121,8 @@ export function QueueDock({ useSession, updateQueue, notify }: QueueDockProps) {
diff --git a/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx b/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx index 3f9635bb48..c52ba0b6b3 100644 --- a/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx @@ -14,7 +14,7 @@ export type ConversationRootProps = ConversationSlotProps export function ConversationRoot({ sessionId, useSession, useSessions, useWorkspaces, useInput, - renderSlot, renderSlotChain, selectWorkspace, + renderSlot, renderSlotChain, selectWorkspace, t, }: ConversationRootProps) { const openState = useSession(s => s.openState) const composerPhase = useSession(s => s.composerPhase) @@ -94,6 +94,7 @@ export function ConversationRoot({ label={chipTitle} menuOpen={pickerOpen} onClick={() => { setPickerOpen(open => !open) }} + t={t} /> {renderSlot('conversation.hero.workspace', { open: pickerOpen, @@ -120,8 +121,8 @@ export function ConversationRoot({ const inputBar = renderSlot('conversation.composer.bar', { variant: hero ? 'hero' : 'composer', ...(inert - ? { disabled: true, placeholder: 'Choose a workspace to start' } - : hero ? { placeholder: 'Describe what you want to build' } : {}), + ? { disabled: true, placeholder: t('placeholder.workspace') } + : hero ? { placeholder: t('placeholder.hero') } : {}), overlay: renderSlot('conversation.input.overlay', {}), leftItems: zone === undefined ? null : renderSlot('conversation.input.left', zone), rightItems: zone === undefined ? null : renderSlot('conversation.input.right', zone), @@ -133,7 +134,7 @@ export function ConversationRoot({ const composerBar = (
{hero && } - {hero && } + {hero && } {hero && heroWorkspaceRow} {!hero && zone !== undefined && renderSlot('conversation.input.dock', zone)} {inputBar} diff --git a/packages/client/ui-conversation/src/client/skeleton/ConversationSession.tsx b/packages/client/ui-conversation/src/client/skeleton/ConversationSession.tsx index 33b24f5245..677f33f46a 100644 --- a/packages/client/ui-conversation/src/client/skeleton/ConversationSession.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/ConversationSession.tsx @@ -24,7 +24,7 @@ function deriveAncestry(list: SessionListState, id: SessionId): readonly Session export function ConversationSession({ sessionId, useSession, useSessions, useInput, inputActions, useStore, actions, - renderSlot, views, bindDraftMirror, open, wrapActiveBody, + renderSlot, views, bindDraftMirror, open, wrapActiveBody, t, }: ConversationSessionProps) { useSyncExternalStore(views.subscribe, views.version) const tabs = views.list() @@ -35,6 +35,8 @@ export function ConversationSession({ const blank = useSession(s => s.blank) const inputState = useInput(s => s) const storedDraft = useStore(s => s.draft) + // `?? null`: persisted snapshots from before the inspect field rehydrate without it. + const inspect = useStore(s => s.inspect ?? null) useEffect(() => { if (inputState.draft === '' && storedDraft !== '') inputActions.setDraft(storedDraft) @@ -52,7 +54,10 @@ export function ConversationSession({ const view: ReactNode = hideChrome ? null : (
- {active !== undefined && renderSlot('conversation.view', {}, { only: active.id })} + {active !== undefined && renderSlot('conversation.view', { + inspect, + onInspectDone: () => { actions.setInspect(null) }, + }, { only: active.id })}
) @@ -65,7 +70,7 @@ export function ConversationSession({ {!hideChrome && ( <>
-