QP内容库 Logo
首页
文章
文档
默认分类
关于
登录 →
QP内容库 Logo
首页 文章
文档
默认分类 关于
登录
  1. 首页
  2. 文档
  3. DeepSeek Harness
  4. 子系统
  5. Token 计量

Token 计量

  • 子系统
  • 发布于 2026-09-30
  • 0 次阅读
目录
当前文章没有目录

English | 中文

@deepseek-ai/dsh-token-meter 公开一个独立的回放快照,用于表示请求压力与按位置计算的表层定价。logRevision 表示生成该计量中每个字段时所消费的持久事件数量。

来源:packages/llm/token-meter/src/types.ts

TokenMeasurement

/** Detached immutable request-pressure and surface snapshot at one consumed log revision. */
interface TokenMeasurement {
  /** Number of durable events consumed; equal to the next unread event seq. */
  readonly logRevision: SessionLogOffset
  /** Provider or heuristic anchor used for this measurement. */
  readonly baseline: TokenMeasurementBaseline
  /** Signed repricing of current surface content relative to the baseline anchor. */
  readonly surfaceDeltaTokens: number
  /** Non-negative current request-and-response pressure. */
  readonly totalTokens: number
  /** Total route-priced request tokens across the current surface; equals the sum of the node prices. */
  readonly surfaceTokens: number
  /** Current surface nodes in positional head-to-tail order. */
  readonly nodes: readonly TokenSurfaceNode[]
}

每次计量都会通过 ctx.llm 把生效信封的路由 provider/model 解析为该路由声明的请求图片定价,因此图片出现处按请求实际发送的视觉 token 加模型可见文本计价;未声明定价的路由与组合保持固定启发式规则。baseline.kind === 'usage' 表示最近一次成功的提供方调用具有相同的规范请求 envelope,且该调用的总量不低于其完整路由定价锚点。estimated 表示不存在可复用的保守 usage 锚点,因此服务自行对完整信封和表层定价。后续成功请求会替换早先的锚点;有符号的 surfaceDeltaTokens 会保留相对于匹配锚点的增长与缩减,且两侧按同一路由重新定价。totalTokens 仍表示请求与响应压力,surfaceTokens 则是表层的路由定价总量,等于所有节点价格之和。

TokenSurfaceNode

/** One token-priced node in the current ordered session surface. */
interface TokenSurfaceNode {
  /** Durable sequence number of the surface event. */
  readonly seq: SessionSeq
  /**
   * Request-pressure tokens for the exact message projected by this node under
   * the measured route: image occurrences carry the route's declared visual
   * price when the routed adapter declares one, and the fixed heuristic
   * otherwise. Trigger, retention, and range selection all read this price.
   */
  readonly tokens: number
  /**
   * Fixed-heuristic tokens for the same message, independent of any route.
   * The shadow-price protocol prices replacements with this value so the O(1)
   * projection fold stays in agreement with its own appends.
   */
  readonly heuristicTokens: number
}

表层顺序具有权威性;替换节点的持久 seq 可能高于位置排在其后的节点。该快照不可变,不会随底层回放折叠推进而增长。

Cordis API

Generated from source by scripts/gen-cordis-catalog.ts (verified fresh by pnpm run verify-cordis-catalog in doc-sync; regenerate with pnpm run gen-cordis-catalog) — the language sides differ only in locale-specific paired document paths. Signature blocks use a ts cordis-catalog fence and keep the original source JSDoc; dispatch modes are defined in the primer, and the framework-inherited ctx API lives in cordis-api/inherited.md.

ctx.tokenMeter — TokenMeter

Replay owner for one service-wide estimator and isolated per-session folds.

/**
 * Measure current request pressure and surface through the durable tail.
 *
 * The effective envelope's routed provider/model selects the request-image
 * pricing every node is priced under: a route whose adapter declares image
 * pricing charges each retained image its visual tokens plus its
 * model-visible text, while other routes keep the fixed heuristic. Provider
 * usage is reused only when the latest successful call's canonical request
 * envelope matches `requestHeader` and its total is no lower than that
 * call's full route-priced anchor; otherwise the complete envelope and
 * surface are repriced. The anchor includes all surface nodes immediately
 * before the assistant message, including inputs admitted after step/start.
 *
 * `requestHeader` replaces the latest logged envelope for pressure and node
 * pricing; the node set always describes the current session surface. Every
 * call clones those positional nodes, so measurement is O(surface).
 *
 * @param session - session to replay through its current durable tail.
 * @param requestHeader - optional effective request envelope replacing the latest logged header.
 * @returns a detached deeply immutable pressure and surface measurement.
 */
measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement

/**
 * Heuristically price one model-visible message (instance face of the pure
 * `estimateMessage` export from `estimate.ts`).
 * @param message - message to price without mutation.
 * @returns content and role-framing tokens under the fixed service heuristic.
 */
estimateMessage(message: Message): number

Types: EpochHeader · Message · Session

Source: packages/llm/token-meter/src/index.ts

相关文章

工作区

English | 中文 工作区(workspace)是用户工作目录的持久记录:一个建立在规范路径之上的稳定 id、一个显示标题,以及归属于它的会话的有序账本。该子系统是单个包(package)(dsh-workspace,ctx.workspaceRegistry)——一项宿主侧可选能力,不属于

工作流

English | 中文 工作流 seam 允许 agent(智能体)运行由模型编写、会启动 subagent 的编排脚本。与 subagent 一样,它是一项可选能力,不属于 agent loop,因此其类型和操作记录在此处,而非 core.md。与 bash 一样,每个上下文只允许一个引擎实现提

Webhook runtime

English | 中文 Webhook 子系统会把已通过身份验证的外部交付转换为可选的普通根 Session。提供方适配器拥有身份验证与通用 JSON 接收;受信任的程序化规则拥有条件与外部调用;ctx.webhookRuntime 拥有回调生命周期以及基于 Workspace 的 Session

Web 访问

English | 中文 Web 访问 seam 是一个能力 seam,在同一个 ctx.web 服务上横跨两项操作(search 与 fetch),并拆分到多个包:Service Definition(dsh-web,ctx.web + 提供方注册表)、Service Provider(dsh-w

HTTP 服务器

English | 中文 dsh-host-webserver 是 GUI Host 的浏览器 HTTP 载体:它是一个提供 ctx.webServer 的 node:http 插件,包含具名路由注册表、可选的 gzip 响应压缩、index.html 转换回调,以及一个可由插件认领的回退处理器。它

Web Client 架构

English | 中文 Web Client 是由独立加载插件组装而成的浏览器侧 Cordis 应用。它有四个可复用底座:Client Modules 加载插件图,API Gateway 提供类型化 Host 通信,Slots 组合 React UI,Conversation 把 Session

目录
当前文章没有目录

星沉月落夜闻香,素手出锋芒。

Copyright © 2026 quping.com All Rights Reserved. Powered by Halo.
鲁ICP备09092435号