DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
F

dsh-frame

Frame

See the costs on this machine laid bare: how many tokens each model request consumes, how much goes to the system prompt and tool table, and how far it is from context compression. Reads session logs, does not call the model, and does not write a single word to the system prompt. Frame: what a sessi

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:7gzgn/dsh-frame#2cd31e2e6203048dbcf9d4ff374d75e1a09c942d
READMECompatibilityVersions

Description

See the costs on this machine laid bare: how many tokens each model request consumes, how much goes to the system prompt and tool table, and how far it is from context compression. Reads session logs, does not call the model, and does not write a single word to the system prompt. Frame: what a session actually costs.

Compatibility and provenance

Frame is published as dsh-frame and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
10/24/2026

Versions

0.1.0stable
10/24/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/24/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in models-usage.

Experimental Cot Translation Bundle@deepseek-ai/dsh-experimental-cot-translation-bundleExperimental machine translation of expanded reasoningWhale Widgetdsh-whale-widgetDeepSeek balance whale widget in the bottom-right corner of the DSH Web interface: balance/today’s usage/peak-off-peak pricing, customizable bubble click sequence (text/balance/today/peak-off-peak/image/random phrases and parallel weighted selection), per-line styles and fonts, floating quick editinOur Free Model@ebony-vinyl/dsh-our-free-modelOur Free Model — Install this plugin in dsh to use cutting-edge models including DeepSeek V4.1 Flash and Kimi K3, with no login, registration, or API Key required. The desktop version also offers an EAC co-payment channel; starting with 2.0, it supports ten account channels: LobsterAI, Qoder, TRAE, Usage@linxin666/dsh-usageUsage statistics plugin for the dsh web GUI: per-provider balance and coding-plan quota detection plus a live token usage ledger, with a compact price glance card above the sidebar's Settings row

README

dsh-frame

看清一场对话到底吃了多少。给 DSH(DeepSeek Harness) 加一个工具 frame, 一次调用就报出这一场的请求次数、上下文体积、累计 token、估算花费,以及离自动压缩还有多远。

它不调模型、不联网、不往 system prompt 写一个字。 全部数字来自本地会话日志。

它回答什么

问题怎么来的
这一场模型请求了多少次?数会话日志里的 step/start(不是 request/header——那个只在表头变化时写)
system prompt 与工具表各占多少?取最新一条 system/message 的字符数;工具表按 request/header 里的 schema 序列化长度
最后一步吃进去多少?system + 工具表 + 累积历史,逐 step 累加
累计多少 token、多少钱?每次请求的输入字符 ÷ 2 估算 token;乘一个可配的单价(默认 0.054 元/百万)
离压缩还有多远?上下文压力 = 当前 token / contextWindow,压缩在 80% 触发、压完保留 16%

用法

装好之后直接调:

frame                          # 最近改动的那个会话
frame session=<日志路径>        # 指定会话
frame pricePerMillion=0.5      # 换一个单价口径

输出长这样:

📐 这一场的开销
  · 模型请求 330 次 / 45 轮
  · system prompt 9,096 字符
  · 工具表 98,950 字符 / 121 个工具
  · 最后一次请求输入 755,428 字符(约 377,714 token)
  · 累计输入约 76,413,754 token → 估算 4.126 元(按 0.054 元/百万)
  · 上下文压力 36.0%(窗口 1,048,576 token,压缩在 80% 触发、压后留 16%)
  · 离压缩还差 2.2 倍

安装

# 1. 链接进 profile
New-Item -ItemType Junction -Path "$env:USERPROFILE\.dsh\profiles\desktop\node_modules\dsh-frame" -Target <本仓库路径>
# 2. profile 的 package.json 里 dependencies 加 "dsh-frame": "link:<本仓库路径>"
# 3. 同文件 dsh.profile.bundles 数组里加 "dsh-frame"
# 4. 重启宿主

数字口径与已知局限

  • 默认挑哪个会话:取「最近改动、且 delegationDepth 为 0 的主会话」。subagent / fork 出来的子会话会被跳过——否则刚跑完一个子 agent,"最近"就会指到它身上。要指定会话就传 session=<路径>。
  • token 是估的:字符数 ÷ 2,中英混排的粗估,不是分词器的真值。要看真值得等 provider 回 usage。
  • 单价是默认值:0.054 元/百万 input token 是 2026-10 在 DeepSeek flash 上反推出来的量级(含缓存命中折扣),换模型/换价自己传 pricePerMillion。
  • 会话日志是多帧 zstd:zstdDecompressSync 只解第一帧(只有 187 字节),本插件按 magic 28 B5 2F FD 切帧逐段解压。
  • 工具表那栏取的是最后一条 request/header:这个事件只在配置或工具集变化时写,所以它能反映"装/卸插件之后"的真实数量;但如果本次会话从头到尾没变过工具集,那条记录会是很早的。

开发

node test/smoke.mjs     # 拿最近一个真实会话跑一遍,验证数字与结构
DSH_FRAME_DEBUG=1       # 打开探针日志(apply 进入 / register 结果)

MIT