creatixchu
42164508c8
Closes #2848. - dsh-llm 新增 LlmAdapter.imageRequestPricing 同步钩子与 LlmImageRequestPricing/LlmImageRequestPrice 词汇，ctx.llm 按路由解析 - llm-deepseek 用官方公布的 v4 视觉计算器逐句移植（14px patch、3:1 降采样、384 上限、最坏对齐 pad）实现该钩子，复现请求投影的最旧优先 offload 与像素预算缩放；纯几何 requestImageDimensions 上移到 dsh-attachment - token-meter 表层 fold 存储与路由无关的节点事实，measure() 按生效 envelope 的路由为图片出现处定价；锚点存快照并按同一路由重定价；TokenSurfaceNode 同时携带路由价 tokens 与固定启发式 heuristicTokens - compaction 触发、保留与选段读取同一套路由价，记录的 shadowedTokenCount 保持启发式以维持 O(1) 投影 fold 一致 - llm-replay 支持按模型的 imageRequestTokens 声明；新增 keyless 的 image-compaction ACP 快照场景端到端验证装配应用
100 lines
3.7 KiB
TypeScript
100 lines
3.7 KiB
TypeScript
/**
|
|
* Fixed-density heuristic token pricing shared by the meter service and the
|
|
* pure context-breakdown projection, so both surfaces price identical content
|
|
* to identical numbers.
|
|
*
|
|
* @module @deepseek-ai/dsh-token-meter/estimate
|
|
*/
|
|
|
|
import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm'
|
|
import type { EpochHeader } from '@deepseek-ai/dsh-session'
|
|
|
|
/** Fixed text-density estimate used until exact tokenization is needed. */
|
|
const CHARS_PER_TOKEN = 4
|
|
|
|
/** Per-block structural overhead for JSON framing and type tags. */
|
|
const BLOCK_OVERHEAD = 4
|
|
|
|
/** Role-field framing overhead added to every priced message. */
|
|
export const ROLE_OVERHEAD = 4
|
|
|
|
/**
|
|
* Structural JSON price of one block outside the typed pricing arms: the
|
|
* fixed heuristic for merge-extended blocks and for image references, whose
|
|
* request price is route-owned rather than fixed.
|
|
* @param block - block to price without mutation.
|
|
* @returns heuristic tokens for the block's JSON structure.
|
|
*/
|
|
export function estimateStructuralBlock(block: ContentBlock): number {
|
|
return BLOCK_OVERHEAD + Math.ceil(JSON.stringify(block).length / CHARS_PER_TOKEN)
|
|
}
|
|
|
|
/**
|
|
* Price content blocks recursively under the fixed density heuristic.
|
|
* @param blocks - content blocks to price without mutation.
|
|
* @returns heuristic tokens including per-block structural overhead.
|
|
*/
|
|
export function estimateContent(blocks: readonly ContentBlock[]): number {
|
|
let tokens = 0
|
|
for (const block of blocks) {
|
|
switch (block.type) {
|
|
case 'text':
|
|
case 'reasoning':
|
|
tokens += Math.ceil(block.text.length / CHARS_PER_TOKEN) + BLOCK_OVERHEAD
|
|
break
|
|
case 'tool-call':
|
|
tokens += Math.ceil(block.name.length / CHARS_PER_TOKEN)
|
|
+ Math.ceil(block.arguments.length / CHARS_PER_TOKEN)
|
|
+ BLOCK_OVERHEAD
|
|
break
|
|
case 'tool-result':
|
|
tokens += estimateContent(block.content) + BLOCK_OVERHEAD
|
|
break
|
|
default:
|
|
// ContentBlockMap is merge-extensible; unknown blocks (and image
|
|
// references, whose request price is route-owned) retain a
|
|
// conservative structural JSON price under the fixed heuristic.
|
|
tokens += estimateStructuralBlock(block)
|
|
}
|
|
}
|
|
return tokens
|
|
}
|
|
|
|
/**
|
|
* Heuristically price one model-visible message.
|
|
* @param message - message to price without mutation.
|
|
* @returns content and role-framing tokens under the fixed heuristic.
|
|
*/
|
|
export function estimateMessage(message: Message): number {
|
|
return estimateContent(message.content) + ROLE_OVERHEAD
|
|
}
|
|
|
|
/**
|
|
* Price the system-prompt part of a canonical request envelope.
|
|
* @param header - canonical envelope, or undefined before any request.
|
|
* @returns heuristic system-prompt tokens; 0 when absent.
|
|
*/
|
|
export function estimateSystemTokens(header: EpochHeader | undefined): number {
|
|
if (header?.system === undefined) return 0
|
|
return Math.ceil(header.system.length / CHARS_PER_TOKEN) + ROLE_OVERHEAD
|
|
}
|
|
|
|
/**
|
|
* Price the tool-schema part of a canonical request envelope.
|
|
* @param header - canonical envelope, or undefined before any request.
|
|
* @returns heuristic tool-schema tokens; 0 when absent or empty.
|
|
*/
|
|
export function estimateToolsTokens(header: EpochHeader | undefined): number {
|
|
if (header?.tools === undefined || header.tools.length === 0) return 0
|
|
return Math.ceil(JSON.stringify(header.tools).length / CHARS_PER_TOKEN) + BLOCK_OVERHEAD
|
|
}
|
|
|
|
/**
|
|
* Price the complete non-surface request envelope.
|
|
* @param header - canonical envelope, or undefined before any request.
|
|
* @returns heuristic system plus tool tokens.
|
|
*/
|
|
export function estimateHeader(header: EpochHeader | undefined): number {
|
|
return estimateSystemTokens(header) + estimateToolsTokens(header)
|
|
}
|