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

dsh-plugin-usage-panel

Plugin Usage Panel

A usage panel for provider plans: shows how much of each quota window is left (GLM Coding Plan and OpenCode Zen) as a compact chip next to the model selector, with a detail popover.

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

npx -y @deepseek-ai/dsh plugin --profile web add dsh-plugin-usage-panel@0.2.2
READMECompatibilityVersions

Compatibility and provenance

Plugin Usage Panel is published as dsh-plugin-usage-panel and currently resolves to version 0.2.2. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
10/26/2026

Versions

0.2.2stable
10/26/2026
0.2.0stable
10/25/2026
0.1.2stable
10/23/2026

Related plugins

Loading related plugins…

Latest
0.2.2
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
43.6 kB
Files
8
Surface
web
License
MIT
Source
npm
Weekly downloads
0
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.

Whale 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 rowConnect Workbuddydsh-connect-workbuddyConnects locally signed-in WorkBuddy models (domestic and international versions) to DeepSeek Harness, automatically reading each model’s points multiplier from the upstream catalog on every refresh, with per-model image input toggles, multi-account switching, automatic account rotation from an acco

README

dsh-plugin-usage-panel

给 DeepSeek Harness 加一个供应商套餐用量面板:在模型选择器右侧显示一枚小图标,悬停(或点击)展开当前套餐的窗口明细。

已接入两家:

套餐面板列
GLM Coding Plan(智谱 / Z.ai)5 小时 · 每周 · 工具调用
OpenCode Zen(Go)滚动窗口 · 每周 · 每月
  • 按会话实际使用的供应商显示:面板问 Host「这个会话在跑哪家」,Host 从会话自己的 model/selection 事件读 provider id,所以 newapi 之类的网关不会误显示
  • 平时不发任何请求:只有悬停/点击时才查一次(?refresh=1 绕过缓存),移开即关闭
  • API key 只在 Host 进程内使用,不下发到浏览器;上游结果按 refreshSeconds 缓存

安装

dsh plugin install dsh-plugin-usage-panel

或在 Plugins 页安装后重启。

配置

键默认说明
sourceautoauto / glm / opencode;auto 按当前 provider 判断
apiKeyEnvZAI_CODING_CN_API_KEY智谱 key 的凭据名
baseUrlhttps://api.z.ai智谱接口域名;BigModel 用 https://open.bigmodel.cn
opencodeApiKeyEnvOPENCODE_GO_API_KEYOpenCode key 的凭据名
opencodeBaseUrlhttps://opencode.ai/zen/go/v1OpenCode 接口域名
refreshSeconds20缓存时间(下限 10 秒)

两个 key 都只在 Host 进程内使用,不会下发到浏览器。只配一家也能用,另一家会显示「未配置 API Key」。

数据来源

与各家客户端自己用的接口一致:

# GLM Coding Plan
GET <base>/api/monitor/usage/quota/limit
authorization: <api key>

# OpenCode Zen (Go)
GET <opencodeBaseUrl>/usage
authorization: Bearer <api key>

OpenCode 返回的是三个窗口的使用百分比:

{"usage":{"rolling":{"percent":1,"resetsAt":"..."},"weekly":{"percent":0,...},"monthly":{"percent":0,...}}}

位置与可见性

  • 挂在 conversation.input.activity:输入框工具行里、模型选择器右侧紧邻。 (布局没有"模型左侧"的插槽:conversation.input.left 是最左边那一簇,而模型选择器本身是 single 槽,不能被扩展。)

  • 渲染前先问 Host 一次 ?probe=1(纯本地、不打上游),Host 用会话的 model/selection 事件得出 provider: 判断顺序:

    1. 模型控件上的 data-provider-id(选择器自己渲染的属性,就是用户眼前那个)→ 最优先
    2. 会话的 model/selection 事件(会话记录过选择时)
    3. 都没有 → 隐藏图标

    为什么不能只看模型名:deepseek-v4.1-flash 这类模型同时挂在多个供应商下,名字分不出归属。 为什么不能退到「profile 默认模型」:新会话在第一次选择被记录前没有事件,而默认模型未必是用户刚切换的那个——之前就因此把 GLM 会话显示成了 OpenCode。

显示内容

  • 触发图标:一个柱状小图标,不显示数字
  • 弹层:套餐徽标(GLM Coding Plan / OpenCode Go)+ 各窗口一列(名称、剩余百分比、重置日期、进度条)
  • 底部:本次读数时间

接口字段对照

面板GLMOpenCode
5 小时 / 滚动TOKENS_LIMIT + unit: 3usage.rolling.percent
每周TOKENS_LIMIT + unit: 6usage.weekly.percent
每月—usage.monthly.percent
工具调用TIME_LIMIT(usage 总额、currentValue 已用)—
套餐data.level—

两家返回的都是已用百分比,面板统一按 剩余 = 100 - 已用 显示。

相关插件

插件说明
dsh-plugin-composer-predict预测下一条指令并显示为占位文字,Tab 采纳
dsh-plugin-composer-history输入框中按 ↑ / ↓ 回填历史消息
dsh-plugin-subagent-bridge让 Codex 通过本机 MCP 把 DSH 当 subagent 用(spawn / wait / followup),反向也能把任务派给 Codex
dsh-plugin-usage-panel(本仓库)在模型选择器旁显示供应商套餐额度余量(GLM Coding Plan / OpenCode Go),点开是明细浮层
dsh-plugin-provider-icons在模型名旁显示供应商品牌 logo(24 个厂商,支持前缀匹配)