dsh-token-usage
Global token totals across every local DSH conversation, de-duplicated by message id, with custom date ranges and per-provider monthly quota tracking.
统计本机全部 DSH 会话的历史 token 消耗，按 message.id 去重，支持自定义日期区间与按接入方的月度额度剩余。
How to install
dsh plugin add @liuguangzhe/dsh-token-usage About
dsh-token-usage 统计**本机全部 DSH 会话**的历史 token 总消耗。与 dsh-context（只看单个会话）互补，只回答一个问题：**我一共花了多少 token？** 🎯 **全局总量**：跨会话、跨工作区、跨 DSH home 汇总 🧹 **正确去重**：按 message.id 消除 v0/v3 与 resume/fork 副本（否则虚高约 3 倍） 🖥️ **桌面壳优先**：Host 只依赖 Node 内置模块，不导入 @deepseek-ai/* 🪶 **极简**：不捆绑费用、余额、热力图、宠物 🔒 **只读会话日志**：绝不修改会话；只在 $DSH_HOME/dsh-token-usage/ 写自己的缓存与额度配置，不联网 📊 **多维拆分**：按天 / 模型 / Provider / 项目 / 会话 📅 **自定义日期**：只填起始 = 起始日至今；只填截止 = 截止日之前全部；都填 = 该区间 🎫 **按接入方额度**：只列出已配置的接入方，其余从「添加接入方」挑选；各自额度/刷新日/启用开关，分开统计剩余 ⚡ **快**：61.6MB / 99 个会话文件全量扫描约 **1.4s**，结果落盘缓存 --- 它统计什么 数据来自会话日志中每条最终 assistant 消息的 usage 字段： | 字段 | 含义 | |--…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 1
- mo. downloads
- 289
- Last push
- 2026-09-16
- Created
- 2026-09-11
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh, dsh-plugin, token-usage
Related plugins
dsh-damage-pulse
wssfk12138/dsh-damage-pulse
Tracks DeepSeek token usage, per-call and session costs, and account balance with cache-aware charge animations in the DSH Web UI.
TokenLedger
zh667/TokenLedger
Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.
dsh-usage-stats
Ychris12138/dsh-usage-stats
Multi-provider usage dashboard with provider/model token breakdowns, calendar drill-downs, account balances, and OpenCode Go / Z.ai subscription quota tracking.
dsh-personal-center
PolinniZhong/dsh-personal-center
Personal center for DeepSeek Harness: cross-session usage statistics, per-model cost estimation, global custom instructions, a global font-size adjuster, a data-driven desktop pet with bitmap & vector skins, and a conversation status overview, all local and offline.