1841220388zzzcccxxx-star/dsh-token-stats 预览 preview

1841220388zzzcccxxx-star/dsh-token-stats

DeepSeek Harness 的令牌使用与成本统计插件——按模型/日期/会话统计,成本估算(美元/人民币),CSV/JSON 导出 | DeepSeek Harness 令牌用量统计插件:按模型/日期/会话统计用量与费用,支持 CSV/JSON 导出

项目介绍Project Overview

dsh-token-stats 是 DeepSeek Harness 的外部插件,提供 Token 用量与费用统计。它在启动时回填历史会话日志,按模型、日期、会话聚合输入、输出、缓存读写及推理 Token,并依据内置定价表估算 USD / CNY 成本。原生页面位于「设置 → 📊 Token Stats」,支持日/周/月趋势 SVG 折线图、CSV/JSON 导出及模型/会话筛选。适用于需要追踪 API 消耗与成本核算的场景。需注意:缺失 usage 的记录会用 tokenMeter 估算并标记为 estimated。

dsh-token-stats is an external plugin for DeepSeek Harness that tracks token usage and estimated cost. On startup it backfills all persisted session logs and aggregates input, output, cache-read, cache-write, and reasoning tokens by model, date, and session, computing USD and CNY cost via a built-in pricing table for DeepSeek, GPT, Claude, Gemini, Qwen, and more. A native page under Settings → 📊 Token Stats provides daily/weekly/monthly SVG trend charts, filters, and CSV/JSON export. Use it to monitor API consumption and spending. Note: records lacking usage are estimated via tokenMeter and flagged as estimated.

或使用命令行安装(适合开发者)Or use CLI install (for developers)

命令行安装CLI Install

dsh plugin --profile web add github:1841220388zzzcccxxx-star/dsh-token-stats

1841220388zzzcccxxx-star/dsh-token-stats 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-token-stats

Token usage & cost statistics plugin for DeepSeek Harness (DSH).

Tracks token consumption per model, per date, and per session with cost estimation in USD / CNY, served as a native page under Settings → 📊 Token Stats. Installed as an external DSH plugin, it loads automatically at DSH startup — no manual activation needed.

中文说明

Features

  • 📊 Native settings page (dark/light aware, follows DSH theme tokens, i18n zh/en)
  • 📈 Daily / weekly / monthly trends with an SVG line chart (zero dependencies)
  • 💰 Cost estimation (USD & CNY) from a built-in pricing table for DeepSeek, GPT, Claude, Gemini, Qwen…
  • 🔁 History backfill: scans all persisted session logs at startup, so stats survive restarts
  • ⚡ Fast: batched session-title reads with an in-memory cache (TTL 5 min), single-pass summaries, memoized pricing
  • 📤 CSV / JSON export, filterable by model and session

Screenshot

Token Stats dashboard

Installation

The plugin is installed as an external DSH profile dependency.

  1. Clone / copy this repository to a local folder, e.g. D:\dev\dsh-token-stats

  2. In your DSH profile manifest (~/.dsh/profiles/web/package.json):

    {
      "dependencies": {
        "dsh-token-stats": "file:D:/dev/dsh-token-stats"
      },
      "dsh": {
        "profile": {
          "bundles": ["@deepseek-ai/dsh-base", "@deepseek-ai/dsh-web-app", "dsh-token-stats"]
        }
      }
    }
    
  3. cd ~/.dsh/profiles/web && pnpm install

  4. Restart DSH web. Open Settings → 📊 Token Stats.

cordis.patch.yml declares the bundle-layer mount point so the plugin auto-loads at startup.

How it works

  • Authoritative data = DSH persisted session logs: assistant/message events carry real usage (input / output / cache-read / cache-write / reasoning tokens), request/header events carry provider/model.
  • A one-shot backfill at startup (sessionQuery) rebuilds the in-memory aggregation index from all history (bounded concurrency).
  • llm/stream usage chunks are captured for live (display-only) in-flight totals.
  • When an adapter reports no usage, tokenMeter.estimateMessage is used and the record is flagged estimated.

HTTP API (/token-stats/api)

op description
summary today / week / month / total aggregates
query time series (day/week/month) + per-model / per-session aggregates; filters: model, sessionId, from, to
models built-in pricing table (USD per 1M tokens) + USD→CNY rate
sessions session list (id + title)
export CSV / JSON dump (format=csv|json, optional model / sessionId)

Development

node --check index.js      # server half
node --check client.js     # browser half
node test-plugin.js        # standalone mock tests: correctness + performance benchmarks
.\sync-deploy.ps1          # re-sync sources into the DSH profile (then restart DSH web)

Performance

Measured on the author's machine (14 sessions / ~10k records):

endpoint before after
sessions ~1700 ms (N serial readTitle calls) ~12 ms (one batched readTitleSnapshots + cache)
summary ~110 ms (4× full-array filters) <1 ms (single pass)
query ~10 ms ~18 ms at 10k records (memoized cost)

License

MIT © 2026 quansheng

上一个 Prev dsh-plugin-panel 下一个 Next dsh-delegate