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 340f07b15c..ef95863be1 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: f397ca6a25cffa0ba709d0a8e84717a1c228b951 -2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: e1cde78bad16d618913e52894eff1271dac74be1 +2026-07-24-web-config-tree-boot-and-transport-layering.md: eb30ba84ef293a169931ef6519a9d6d2ea98af7f +2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 7a175b44fa8806b4b73eca538f32f16aa778fdee 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 f397ca6a25..eb30ba84ef 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 @@ -18,7 +18,7 @@ English | [中文](2026-07-24-web-config-tree-boot-and-transport-layering.zh.md) **Config sources have one declaration place each.** Bundle yml values are engineering defaults, Settings sections are writable user preferences, CLI flags address their owning launcher rows, and env values enter through yml `!!js` expressions. Patches replace a row's config wholesale. The resolved frontend `distIndex` uses that patch channel as an assembly fact. The transport-independent provider/model default belongs to `ctx.agentDefaultModel`; the [direct headless entry point](2026-08-09-headless-direct-core-entry-point.md) and the Web gateway consume the same state. -**The transport splits five ways.** `dsh-host-apiproxy` is the gateway plugin (`api-gateway` row): it default-exports `ApiProxyService`, configures only `{nativeOpen?}`, consumes the base layer's entry-point-neutral `ctx.agentDefaultModel`, provides `ctx.apiProxy`, remains transport-agnostic, and registers no routes. `dsh-host-webserver` is a plain route-registration plugin: `WebServer` provides `ctx.webServer` (`register(route) → disposer` with duplicate-pattern throw, `tapIndex` transforms applied in registration order, `port`), listens on activation, answers per-request failures with 400 and logging, and knows no harness concepts. The connection node half owns the `/api` binding from `ctx.apiProxy` through `toFetchHandler`. The modules node half (`ClientModuleRegistry`, providing `ctx.clientModules`) owns incremental package scanning, the bundle route, the index tap, and `onRebuilt`/`onGraphChanged` notification. The hmr node half owns dev reload through `fs.watchFile` membership and the `/plugins/events` SSE route. +**The transport splits five ways.** `dsh-host-apiproxy` is the gateway plugin (`api-gateway` row): it default-exports `ApiProxyService`, configures only `{nativeOpen?}`, consumes the base layer's entry-point-neutral `ctx.agentDefaultModel`, provides `ctx.apiProxy`, remains transport-agnostic, and registers no routes. `dsh-host-webserver` is a plain route-registration plugin: `WebServer` provides `ctx.webServer` (`register(route) → disposer` with duplicate-pattern throw, `renderIndex` rendering — structured `webserver/index-inject` rows, then raw `tapIndex` transforms in registration order — and `port`), listens on activation, answers per-request failures with 400 and logging, and knows no harness concepts. The connection node half owns the `/api` binding from `ctx.apiProxy` through `toFetchHandler`. The modules node half (`ClientModuleRegistry`, providing `ctx.clientModules`) owns incremental package scanning, the bundle route, the boot injection rows, and `onRebuilt`/`onGraphChanged` notification. The hmr node half owns dev reload through `fs.watchFile` membership and the `/plugins/events` SSE route. **Package export discipline.** The modules package exposes exactly `.` (node half) and `./client` (the complete browser half: `ClientModuleSystem`, `parseBootManifest`, the adoption plugin face) — no bespoke subpaths; wire types re-export through the root for host-side consumers. The adoption handshake: the kernel writes the constructed instance to `window.__DSH_MODULES__` before cordis exists; the `./client` apply reads the slot (missing = loud throw) and provides `ctx.modules`. 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 e1cde78bad..7a175b44fa 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 @@ -18,7 +18,7 @@ Status: implemented **每个配置源有唯一声明位置。** 组合包 yml 值是工程默认,Settings 分节是可写的用户偏好,CLI(命令行界面)flags 面向其归属的启动器配置行,env 值则通过 yml `!!js` 表达式进入。patch 会整体替换一行的 config。解析后的前端 `distIndex` 通过同一条 patch 通道作为组装事实传递。与传输无关的提供方/模型默认值归 `ctx.agentDefaultModel` 所有;[直接 headless 入口](2026-08-09-headless-direct-core-entry-point.md)与 Web 网关消费同一份状态。 -**传输五分。** `dsh-host-apiproxy` 是网关插件(`api-gateway` 行):默认导出 `ApiProxyService`,只配置 `{nativeOpen?}`,消费 base 层不偏向特定入口的 `ctx.agentDefaultModel`,provide `ctx.apiProxy`,保持传输无关且不注册路由。`dsh-host-webserver` 是朴素的路由注册插件:`WebServer` provide `ctx.webServer`(`register(route) → disposer`、重复 pattern 即抛、`tapIndex` 按注册序应用、`port`),激活即 listen,单请求失败时答 400 并记日志,且不认识任何 harness 概念。connection node 半拥有从 `ctx.apiProxy` 经 `toFetchHandler` 绑定到 `/api` 的逻辑。modules node 半(`ClientModuleRegistry`,provide `ctx.clientModules`)拥有单包增量扫描、bundle 路由、index tap 与 `onRebuilt`/`onGraphChanged` 通知。HMR(热模块替换) node 半通过 `fs.watchFile` membership 与 `/plugins/events` SSE 路由拥有开发期重载。 +**传输五分。** `dsh-host-apiproxy` 是网关插件(`api-gateway` 行):默认导出 `ApiProxyService`,只配置 `{nativeOpen?}`,消费 base 层不偏向特定入口的 `ctx.agentDefaultModel`,provide `ctx.apiProxy`,保持传输无关且不注册路由。`dsh-host-webserver` 是朴素的路由注册插件:`WebServer` provide `ctx.webServer`(`register(route) → disposer`、重复 pattern 即抛、`renderIndex` 渲染——先结构化 `webserver/index-inject` 行、后原始 `tapIndex` 按注册序应用——与 `port`),激活即 listen,单请求失败时答 400 并记日志,且不认识任何 harness 概念。connection node 半拥有从 `ctx.apiProxy` 经 `toFetchHandler` 绑定到 `/api` 的逻辑。modules node 半(`ClientModuleRegistry`,provide `ctx.clientModules`)拥有单包增量扫描、bundle 路由、启动注入行与 `onRebuilt`/`onGraphChanged` 通知。HMR(热模块替换) node 半通过 `fs.watchFile` membership 与 `/plugins/events` SSE 路由拥有开发期重载。 **包出口纪律。** modules 包只暴露 `.`(node 半)与 `./client`(完整浏览器半:`ClientModuleSystem`、`parseBootManifest`、收编插件面)——不设专用子路径;wire 类型经根出口 re-export 给 host 侧消费方。收编握手:内核在 cordis 之前把建好的实例写入 `window.__DSH_MODULES__`;`./client` 的 apply 读取该槽位(缺少时显式抛错)并 provide `ctx.modules`。 diff --git a/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.i18n.yaml new file mode 100644 index 0000000000..90d1f96dff --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.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/2026-08-19-web-index-injection-table.md +2026-08-19-web-index-injection-table.md: 9ed02aa94cd318d107a32802d8723652e6b10ea2 +2026-08-19-web-index-injection-table.zh.md: 8ad036766faa14071b20da12ef907ab012cae23f diff --git a/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.md b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.md new file mode 100644 index 0000000000..9ed02aa94c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-19-web-index-injection-table.md @@ -0,0 +1,30 @@ +# Agent Note: structured index injection table (webserver/index-inject) + +Status: implemented + +English | [中文](2026-08-19-web-index-injection-table.zh.md) + +## Problem + +The web shell's boot HTML needs three kinds of injection: client-modules' boot protocol (the `__ModuleLoader__` registration queue inline script, the parser-blocking preload `` +})()` const preload = PARSER_PRELOAD_IDS.map(id => graph.entries.find(entry => entry.id === id)) .filter((entry): entry is WebBootEntry => entry !== undefined) - .map(entry => ``) - .join('') - const script = `${queue}${preload}` - const head = html.indexOf('
') - if (head !== -1) return `${html.slice(0, head + 6)}${script}${html.slice(head + 6)}` - // Headless fixture pages may lack ; prepending keeps the read-before-shell ordering. - return `${script}${html}` + .map((entry): IndexInjection => ({ kind: 'script-src', placement: 'head', src: entry.url })) + return [ + { kind: 'script', placement: 'head', text: queue }, + ...preload, + { kind: 'global', name: '__DSH_BOOT__', value: graph }, + ] } /** * The web plugin table service: incremental `dsh.client` scan + wire composition - * + bundle route + index tap. Construction runs the activation scan + * + bundle route + index injection rows. 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). @@ -353,10 +340,9 @@ export class ClientModuleRegistry extends Service { () => ctx.webServer.register({ kind: 'prefix', path: '/plugins', handler: this.serveBundle }), 'client-modules: bundle route', ) - ctx.effect( - () => ctx.webServer.tapIndex(html => injectBootManifest(html, this.composed)), - 'client-modules: boot manifest injection', - ) + ctx.on('webserver/index-inject', (table) => { + table.push(...bootInjections(this.composed)) + }) } /** diff --git a/packages/client/modules/tests/node-half.client.spec.ts b/packages/client/modules/tests/node-half.client.spec.ts index 0dc6ea0e3c..8577d2a57d 100644 --- a/packages/client/modules/tests/node-half.client.spec.ts +++ b/packages/client/modules/tests/node-half.client.spec.ts @@ -8,9 +8,9 @@ import { pathToFileURL } from 'node:url' import { runInNewContext } from 'node:vm' import { Context } from '@deepseek-ai/cordis' import { afterEach, describe, expect, it } from 'vitest' -import type { WebServer, WebRoute } from '@deepseek-ai/dsh-host-webserver' +import { renderIndexInjections, type WebServer, type WebRoute } from '@deepseek-ai/dsh-host-webserver' import * as modulesClient from '../src/client/index.ts' -import { ClientModuleRegistry, injectBootManifest, orderByModuleGraph } from '../src/index.ts' +import { ClientModuleRegistry, bootInjections, orderByModuleGraph } from '../src/index.ts' import type { ClientModuleLoaderTarget, WebBootEntry, WebBootGraph } from '../src/client/index.ts' const MODULES_ID = '@deepseek-ai/dsh-client-modules' @@ -81,9 +81,12 @@ function construct(packageNames: string[]): ClientModuleRegistry { return constructWithRoute(packageNames).service } -/** Execute the exact first inline script emitted by the Host HTML transform. */ +/** Execute the exact first inline script emitted by the Host boot rows. */ function injectedFacade(graph: WebBootGraph): { html: string; target: ClientModuleLoaderTarget } { - const html = injectBootManifest('', graph) + const html = renderIndexInjections( + '', + bootInjections(graph), + ) const source = /') const runtimeAt = html.indexOf('') - const graphAt = html.indexOf('window.__DSH_BOOT__ = ') + const graphAt = html.indexOf('globalThis["__DSH_BOOT__"] = ') const entryAt = html.indexOf('') expect([facadeAt, modulesAt, runtimeAt, graphAt, entryAt]).toEqual([...new Set([ facadeAt, modulesAt, runtimeAt, graphAt, entryAt, diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 74a73ffb4a..44c63ba33c 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: 71dafd1c4d683f2d6da8fefd88aec81d56149481 -README.zh.md: e4d4ab990c74229bd2e077b575e7c87bb648ade9 +README.md: a90d1d9dd8156fc1063dc7358374f8b1715deb1a +README.zh.md: acab41ad8c95c9e24b39fc875f3047f429f3add2 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index 71dafd1c4d..a90d1d9dd8 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -40,7 +40,7 @@ Image intake accepts paste and whole-page drop: the bar binds document-level dra 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 controls), 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 `InputTriggerController` to open only the `/` trigger's `command` source over the current textarea selection, while ui-input-trigger'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 keeps message actions inert (machine faces absent, `disabled` owner prop), while the whole dashed card opens the existing Workspace picker by pointer and the read-only textarea opens it through Enter or Space. Disabled controls release pointer events to the card, and the card contains `pointerdown` so the open picker's outside-close cannot race a reopen. The bar never swaps in a parallel tree, so the textarea DOM survives Workspace selection; strict-session control seats stay empty until a session exists. -The chat stats line takes its token accounting from the generic token-meter `tokenUsage` projection read through the standard-kit `useProjection`: billed input is uncached input plus cache reads and writes; cache hit divides cache reads by that total. The turn and step counts, the LLM and tool wall times, and the latency/throughput group all ride the whole-log `sessionStats` projection (host-folded from step boundaries, first-token chunks, tool pairs, and assembled messages), so paging and compaction cannot change any strip figure; an assembly without that unit falls back to the window fold over visible nodes, whose fields mirror the projection's. The strip averages each recorded step's TTFT and divides sampled output tokens by their summed decode spans into a latency/throughput group localized through the `conversation` locale namespace (`TTFT avg … · … tok/s` in English); a step missing a timing boundary or a usage sample drops out of those figures instead of skewing them, and durable count, token, and context groups remain visible when compaction leaves no assistant node in the loaded window. The turn-count, step-count, duration, cache, and token labels use the same namespace. Each settled turn additionally appends hover-revealed `TTFT {s}s · {tps} tok/s` labels to its assistant footer after the `Ran for` duration — the turn's first-step TTFT and its turn-aggregate decode throughput — gated on the turn's timing being in the loaded window (a contiguous log suffix, so an in-window turn carries every one of its steps) and omitting whichever figure is unrecorded. A deployment without token-meter drops the token groups; when the line overflows, it elides with an ellipsis and a delayed hover tooltip carries the full text only while actually clipped. Context occupancy renders as the composer's trailing ContextMeter: a 14px occupancy ring after the model seat, fed by `contextPressure` and rendered only once both a numerator and a route capacity are known, that click-opens a panel pairing the `percent used` header and `~used / capacity` figures with a color-segmented bar and `~`-prefixed heuristic composition rows (system prompt, tools, messages) from the `contextBreakdown` projection. The ring and header read `projectedTokens` — the provider sample carried forward over the surface's movement since — so a compaction registers immediately instead of after a further turn; the composition rows stay wholly heuristic and therefore still do not sum to the header ([rationale](../../llm/token-meter/README.md)). Occupancy is deliberately an approximation: numerator and capacity are independent last-wins projection fields, not one atomic request observation. +The chat stats line takes its token accounting from the generic token-meter `tokenUsage` projection read through the standard-kit `useProjection`: billed input is uncached input plus cache reads and writes; cache hit divides cache reads by that total. Every non-empty ratio starts with integer rounding. A non-full ratio adds decimal places only while the current precision would round to 100%, stopping at the minimum precision that remains below 100%; only a full cache hit displays 100%, and the precision has no fixed limit. The turn and step counts, the LLM and tool wall times, and the latency/throughput group all ride the whole-log `sessionStats` projection (host-folded from step boundaries, first-token chunks, tool pairs, and assembled messages), so paging and compaction cannot change any strip figure; an assembly without that unit falls back to the window fold over visible nodes, whose fields mirror the projection's. The strip averages each recorded step's TTFT and divides sampled output tokens by their summed decode spans into a latency/throughput group localized through the `conversation` locale namespace (`TTFT avg … · … tok/s` in English); a step missing a timing boundary or a usage sample drops out of those figures instead of skewing them, and durable count, token, and context groups remain visible when compaction leaves no assistant node in the loaded window. The turn-count, step-count, duration, cache, and token labels use the same namespace. Each settled turn additionally appends hover-revealed `TTFT {s}s · {tps} tok/s` labels to its assistant footer after the `Ran for` duration — the turn's first-step TTFT and its turn-aggregate decode throughput — gated on the turn's timing being in the loaded window (a contiguous log suffix, so an in-window turn carries every one of its steps) and omitting whichever figure is unrecorded. A deployment without token-meter drops the token groups; when the line overflows, it elides with an ellipsis and a delayed hover tooltip carries the full text only while actually clipped. Context occupancy renders as the composer's trailing ContextMeter: a 14px occupancy ring after the model seat, fed by `contextPressure` and rendered only once both a numerator and a route capacity are known, that click-opens a panel pairing the `percent used` header and `~used / capacity` figures with a color-segmented bar and `~`-prefixed heuristic composition rows (system prompt, tools, messages) from the `contextBreakdown` projection. The ring and header read `projectedTokens` — the provider sample carried forward over the surface's movement since — so a compaction registers immediately instead of after a further turn; the composition rows stay wholly heuristic and therefore still do not sum to the header ([rationale](../../llm/token-meter/README.md)). Occupancy is deliberately an approximation: numerator and capacity are independent last-wins projection fields, not one atomic request observation. `src/client/` is organized by domain. `contract/` is the shared face for slot declarations, composed props, and cross-domain types; `skeleton/`, `chat/`, `input/`, `queue/`, and `settings/` keep their implementations internal, while `apply.ts` is their assembly point. The `/client` exports contain only loader entries, service classes, and contract types; components and store factories reach the page through slot registrations. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index e4d4ab990c..acab41ad8c 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -40,7 +40,7 @@ Host 带 placement 的 `session/queue` 快照也会携带待处理 steering。Qu 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/停止控件之前)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 `InputTriggerController` 基于 textarea 当前 selection,只打开 `/` trigger 的 `command` source,同时 ui-input-trigger 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 会让消息操作保持不可交互(machine face 均缺席、`disabled` owner prop),整张虚线卡片可经指针打开现有 Workspace picker,只读 textarea 也可通过 Enter 或 Space 打开。禁用控件会把指针事件交给卡片,卡片也会拦下 `pointerdown`,避免已打开 picker 的外点关闭与重新打开发生竞态。它不会换入一棵平行树,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。 -聊天统计行的 token 账目来自经标准套件 `useProjection` 读取的通用 token-meter 投影 `tokenUsage`:计费输入为未缓存输入、缓存读取与缓存写入之和;缓存命中率以缓存读取除以该总量。轮次与步骤计数、LLM(大语言模型)与工具墙钟时间、以及延迟/吞吐分组都来自全日志的 `sessionStats` 投影(Host 端从步边界、首 token chunk、工具配对与已组装消息折算),因此分页与压缩都无法改变统计条的任何数字;未组合该单元的装配回退为对可见节点做窗口折算,其字段与投影一一对应。统计条把每个有完整记录的步骤的 TTFT(首 token 延迟)取平均,并用采样到的输出 token 数除以其解码时长之和,得到经 `conversation` locale 命名空间本地化的延迟/吞吐分组(中文为 `首 token 平均 … · … tok/s`);缺少某个 timing 边界或 usage 采样的步骤会直接退出这些数字,而不是让它们失真;压缩(compaction)使已加载窗口不再包含 assistant 节点时,持久计数、token 与上下文分组仍保持可见。轮次计数、步骤计数、耗时、缓存与 token 各项的标签也使用同一命名空间。每个已结算轮次还会在其 assistant footer 的 `用时` 之后追加 hover 才显示的 `首 token {s}秒 · {tps} tok/s` 标签——即该轮次首个步骤的 TTFT 与轮次聚合的解码吞吐——仅当该轮次的 timing 位于已加载窗口内才显示(窗口是日志的连续后缀,因此窗口内的轮次必然带着它的全部步骤),未记录的数字会各自省略。未组合 token-meter 的部署会整组省略 token 分组;统计行过长时以省略号截断,仅在内容真的被裁切时由延迟 hover tooltip 承载完整文本。上下文占用率渲染为 composer 尾部的 ContextMeter:模型座位之后的一枚 14px 占用圆环,由 `contextPressure` 供数,仅当分子与路由容量都已知时才渲染;点击弹出的面板把「已用百分比」标题与 `~已用 / 容量` 数字,与来自 `contextBreakdown` 投影、带 `~` 前缀的启发式组成明细行(系统提示词、工具、对话消息)及分色分段进度条并列。圆环与标题读取 `projectedTokens`——把提供方样本沿此后表层的增减推进到当下——因此压缩会立刻反映出来,而不必再等一整轮;组成明细行仍是纯启发式,因此加起来依然不等于标题数字([原理](../../llm/token-meter/README.md))。占用率是刻意为之的近似值:分子与容量是两个相互独立的「后写覆盖」投影字段,并非同一次请求的原子观测。 +聊天统计行的 token 账目来自经标准套件 `useProjection` 读取的通用 token-meter 投影 `tokenUsage`:计费输入为未缓存输入、缓存读取与缓存写入之和;缓存命中率以缓存读取除以该总量。所有非空比率都先按整数舍入。非满命中只有在当前精度会舍入成 100% 时才增加小数位,并在首次得到低于 100% 的结果时停止;只有完整缓存命中才显示 100%,且精度没有固定上限。轮次与步骤计数、LLM(大语言模型)与工具墙钟时间、以及延迟/吞吐分组都来自全日志的 `sessionStats` 投影(Host 端从步边界、首 token chunk、工具配对与已组装消息折算),因此分页与压缩都无法改变统计条的任何数字;未组合该单元的装配回退为对可见节点做窗口折算,其字段与投影一一对应。统计条把每个有完整记录的步骤的 TTFT(首 token 延迟)取平均,并用采样到的输出 token 数除以其解码时长之和,得到经 `conversation` locale 命名空间本地化的延迟/吞吐分组(中文为 `首 token 平均 … · … tok/s`);缺少某个 timing 边界或 usage 采样的步骤会直接退出这些数字,而不是让它们失真;压缩(compaction)使已加载窗口不再包含 assistant 节点时,持久计数、token 与上下文分组仍保持可见。轮次计数、步骤计数、耗时、缓存与 token 各项的标签也使用同一命名空间。每个已结算轮次还会在其 assistant footer 的 `用时` 之后追加 hover 才显示的 `首 token {s}秒 · {tps} tok/s` 标签——即该轮次首个步骤的 TTFT 与轮次聚合的解码吞吐——仅当该轮次的 timing 位于已加载窗口内才显示(窗口是日志的连续后缀,因此窗口内的轮次必然带着它的全部步骤),未记录的数字会各自省略。未组合 token-meter 的部署会整组省略 token 分组;统计行过长时以省略号截断,仅在内容真的被裁切时由延迟 hover tooltip 承载完整文本。上下文占用率渲染为 composer 尾部的 ContextMeter:模型座位之后的一枚 14px 占用圆环,由 `contextPressure` 供数,仅当分子与路由容量都已知时才渲染;点击弹出的面板把「已用百分比」标题与 `~已用 / 容量` 数字,与来自 `contextBreakdown` 投影、带 `~` 前缀的启发式组成明细行(系统提示词、工具、对话消息)及分色分段进度条并列。圆环与标题读取 `projectedTokens`——把提供方样本沿此后表层的增减推进到当下——因此压缩会立刻反映出来,而不必再等一整轮;组成明细行仍是纯启发式,因此加起来依然不等于标题数字([原理](../../llm/token-meter/README.md))。占用率是刻意为之的近似值:分子与容量是两个相互独立的「后写覆盖」投影字段,并非同一次请求的原子观测。 `src/client/` 按领域组织。`contract/` 是 slot 声明、组合 props 与跨领域类型的共享表层;`skeleton/`、`chat/`、`input/`、`queue/` 和 `settings/` 保持内部实现,`apply.ts` 是它们的组装点。`/client` 导出表层只包含 loader entry、service class 和 contract 类型;组件与 store factory 经 slot 注册抵达页面。 diff --git a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css index 8fdba2baa0..c9e8d19d77 100644 --- a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css +++ b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.module.css @@ -17,6 +17,28 @@ gap: 16px; } +/* Wide markdown tables (the renderer's ≥4-column md-table-wide hook) span + the whole transcript width instead of clipping at the 748px message + column, while the table content keeps starting at its normal x (the lead + padding compensates the negative margin) — deepsuite chat TableWrapper + parity, with 100cqw (the ChatView scroll container) standing in for its + JS-measured --dsl-virtual-list-width. `--dsh-table-spare` clamps to zero + when the transcript is narrower than the message column, so narrow + viewports keep the plain in-column scroll with no sideways shift. + Percentages resolve against the wrapper's containing block, so a table + indented inside a list still reaches the same transcript edges. */ +.body :global(.md-table-wide) { + --dsh-table-spare: max(0px, calc((100cqw - var(--dsh-chat-content-width)) / 2)); + --dsh-table-lead: calc(var(--dsh-table-spare) + min(var(--dsh-chat-content-width), 100cqw) - 100%); + box-sizing: border-box; + width: calc(100% + var(--dsh-table-lead) + var(--dsh-table-spare)); + /* The base .tableScroll caps at the column (max-width: 100%); the breakout + is exactly the case that must exceed it. */ + max-width: none; + margin-left: calc(-1 * var(--dsh-table-lead)); + padding-left: var(--dsh-table-lead); +} + /* Interrupted-turn terminal marker: quiet inline tag, no animation. */ .stopped { align-self: flex-start; diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.module.css b/packages/client/ui-conversation/src/client/chat/ChatView.module.css index ffee12984f..73fa688f95 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.module.css +++ b/packages/client/ui-conversation/src/client/chat/ChatView.module.css @@ -18,6 +18,11 @@ /* Sides = composer clearance + 16px: on narrow viewports the transcript stays exactly 32px narrower than the input card (the shared width rule). */ padding: 16px calc(var(--dsh-composer-side-clearance) + 16px); + /* Inline-size query container: wide markdown tables size their breakout + against this box's content width (100cqw in AssistantMarkdown's + md-table-wide rule) — the CSS stand-in for deepsuite chat's JS-measured + --dsl-virtual-list-width. */ + container-type: inline-size; } :global([data-conversation-scroll]) .root { diff --git a/packages/client/ui-conversation/src/client/chat/StatsLine.tsx b/packages/client/ui-conversation/src/client/chat/StatsLine.tsx index 147d2b7c6c..2d9d14483b 100644 --- a/packages/client/ui-conversation/src/client/chat/StatsLine.tsx +++ b/packages/client/ui-conversation/src/client/chat/StatsLine.tsx @@ -101,16 +101,64 @@ export function formatDuration(ms: number): string { return `${Math.floor(whole / 60)}m${whole % 60}s` } +/** Round a cache-read ratio to an integer percentage, with positive ties rounded up. */ +function roundedIntegerPercent(cacheReadTokens: number, denominator: number): number { + const denominatorQuotient = Math.floor(denominator / 200) + const denominatorRemainder = denominator % 200 + let lower = 0 + let upper = 100 + while (lower < upper) { + const candidate = Math.floor((lower + upper + 1) / 2) + const factor = candidate * 2 - 1 + const threshold = factor * denominatorQuotient + + Math.ceil(factor * denominatorRemainder / 200) + if (cacheReadTokens >= threshold) { + lower = candidate + } else { + upper = candidate - 1 + } + } + return lower +} + /** - * Cache-hit share of prompt-side input over the whole durable log. + * Display-ready cache-hit share of prompt-side input over the whole durable log. * @param usage - the session's token-usage projection value. - * @returns rounded integer percent, or null when no input was billed. + * @returns integer text when integer rounding stays below 100, otherwise the + * minimum decimal precision that still rounds below 100; a full hit returns + * 100, and no billed input returns null. */ -export function cacheHitPercent(usage: TokenUsageProjection): number | null { +export function cacheHitPercent(usage: TokenUsageProjection): string | null { const denominator = billedInputTokens(usage) - return denominator === 0 - ? null - : Math.round(usage.cacheReadTokens / denominator * 100) + if (denominator === 0) return null + const missedInputTokens = usage.uncachedInputTokens + usage.cacheWriteTokens + if (missedInputTokens === 0) return '100' + + const integerPercent = roundedIntegerPercent(usage.cacheReadTokens, denominator) + if (integerPercent < 100) return String(integerPercent) + + // At the first distinguishing precision, the rounded result is 100 minus + // one to five units in the final decimal place. Scale only while the next + // multiplication remains at or below the denominator, then derive that + // final digit through exact small-factor comparisons. + let decimalPlaces = 1 + let scaledDoubleGap = missedInputTokens * 200 + const denominatorTens = Math.floor(denominator / 10) + while (scaledDoubleGap <= denominatorTens) { + scaledDoubleGap *= 10 + decimalPlaces += 1 + } + const denominatorOnes = denominator % 10 + let roundedLoss = 5 + for (let loss = 1; loss < 5; loss += 1) { + const factor = loss * 2 + 1 + const threshold = factor * denominatorTens + Math.floor(factor * denominatorOnes / 10) + if (scaledDoubleGap <= threshold) { + roundedLoss = loss + break + } + } + return `99.${'9'.repeat(decimalPlaces - 1)}${10 - roundedLoss}` } /** diff --git a/packages/client/ui-conversation/tests/chat-stats.client.spec.tsx b/packages/client/ui-conversation/tests/chat-stats.client.spec.tsx index 01be6e0850..be55ee0579 100644 --- a/packages/client/ui-conversation/tests/chat-stats.client.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-stats.client.spec.tsx @@ -191,6 +191,10 @@ describe('StatsLine', () => { return { useSession: bindSnapshotSelector(source), useProjection: projections(values), t: tEn } } + function tokenUsage(cacheReadTokens: number, uncachedInputTokens: number) { + return { uncachedInputTokens, outputTokens: 1, cacheReadTokens, cacheWriteTokens: 0 } + } + it('renders the grouped stats row and hides a brand-new empty session', () => { const { source } = makeSource({ nodes: [assistant(1, 1)] }) const view = render(- {wrapBlockChildren(renderChildren(node.children, context).filter(child => child !== null), true)} + {wrapBlockChildren( + renderChildren(node.children, { ...context, inBlockquote: true }).filter(child => child !== null), + true, + )}) case 'thematicBreak': @@ -393,8 +399,23 @@ function renderListItem( function renderTable(node: Md.Table, key: Key, context: MarkdownRenderContext): ReactNode { const align = node.align ?? null const [headRow, ...bodyRows] = node.children + const columns = align === null ? headRow?.children.length ?? 0 : align.length + // Four or more columns read as a comparison matrix: the block keeps the + // table at natural width and exposes the stable `md-table-wide` hook so a + // hosting layout (the chat transcript) can widen it past the message + // column. Narrower tables — and any table inside a blockquote — fill the + // column and wrap instead (deepsuite chat TableWrapper parity). + const wide = columns >= 4 && context.inBlockquote !== true return ( -
| + #text "C1" + | + #text "C2" + | + #text "C3" + | + #text "C4" + | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| + #text "a" + | + #text "b" + | + #text "c" + |
+ #text "d"
+ + |