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.

Glm Quota Dock — DSH Plugin for DeepSeek Harness
← Plugins

dsh-glm-quota-dock

Glm Quota Dock

Shows GLM Coding Plan quota usage and the 5-hour window reset countdown next to the session stats row.

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

npx -y @deepseek-ai/dsh plugin --profile web add dsh-glm-quota-dock@1.3.1
READMECompatibilityVersions

Compatibility and provenance

Glm Quota Dock is published as dsh-glm-quota-dock and currently resolves to version 1.3.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
10/14/2026

Versions

1.3.1stable
10/14/2026
1.3.0stable
10/14/2026
1.2.1stable
10/14/2026
Show 2 more versionsCollapse versions
1.1.0stable
10/13/2026
1.0.0stable
10/8/2026

Related plugins

Loading related plugins…

Latest
1.3.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
61.4 kB
Files
10
Surface
web
License
Not declared
Source
npm
GitHub
★ 0
Weekly downloads
0
Last push
10/15/2026
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
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

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 editinUsage@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 rowClient Ui Model Capabilities@linxin666/dsh-client-ui-model-capabilitiesPer-model capability declarations (image input and reasoning efforts) for custom pi-ai providers, edited in place on the Models settings cards; writes the official llm-pi-ai settings namespace, no DSH source changes.Cost Meterdsh-cost-meterDeepSeek Harness session cost statistics plugin: current session cost, today’s charges, historical records, and synchronization with official pricing; supports multi-provider, multi-model price calculation (built-in pricing catalog for 170+ model IDs with automatic matching); queries and displays su

README

dsh-glm-quota-dock

DeepSeek Harness (DSH) 插件:在会话输入框下方的统计行内,常驻一个 GLM Coding Plan 额度 pill,实时显示各窗口用量百分比。

A lightweight DeepSeek Harness plugin that shows your GLM Coding Plan quota as an always-visible pill in the composer stats row.

◔ GLM 5h 9% · 周 45% · 工具 7% · 🕐 2h 15m

截图

以下为 v1.1.0 旧版纵向面板的历史截图(着色逻辑仍有效);自 v1.2.0 起面板已重构为双列卡片式(标题 + 大号百分比 + 粗进度条),新版截图待补。

正常(<80%,绿)告警(≥80%,黄)临界(≥95%,红)
详情面板 正常(45%)详情面板 告警(88%)详情面板 临界(99%)

特性

  • 实时额度:输入框统计行内常驻 pill,30 秒轮询;pill 百分比与详情卡片共用同一套强调色(5h 蓝 #0B7FFF、工具紫 #9E77ED),≥80% 琥珀、≥95% 红同步覆盖
  • 5h 重置倒计时:pill 末尾常驻 5 小时窗口的重置倒计时(悬浮看具体时刻),颜色跟随 5h 窗口;面板内 5h 卡片头部右侧展示倒计时
  • 仅在 GLM 会话显示:通过会话的模型选择投影判断,只有当前会话走 Coding Plan 路由 且使用 glm-* 模型时才渲染;纯 API 计费路由(消耗余额而非套餐)不会误亮,非 GLM 会话完全零请求
  • 点击详情:双列卡片式面板 —— 每个窗口一张卡片(标题 + 大号百分比 + 右侧重置时刻 + 5px 粗进度条,正常态按卡片着色),绝对用量(如工具调用 7/100)与各模型明细折叠进卡片悬浮提示;24 小时用量块带小时级 token sparkline,另有按模型 Token 用量、档位徽标(悬浮看套餐版本说明)、一键打开官方用量页、手动强制刷新
  • 空闲降频:页面可见但 5 分钟无操作时自动降为 5 分钟一轮,恢复操作立即刷新;最小化/切走完全停止
  • 插件版本与一键更新:面板页脚显示插件版本号(灰色小字,与套餐档位无关);每小时静默检查一次 npm 新版本(失败不打扰),有更新时出现「可更新」绿色药丸,点击弹出确认气泡,确认后由 Host 端执行 pnpm 自更新并自动刷新页面;插件配置 enableSelfUpdate: false 可关闭自更新入口
  • 套餐版本自适应:V1(5h + 月度)、V2(含周窗口)、新版积分制均按响应字段自动识别展示,未知形状优雅回退
  • 密钥不出本机:API Key 只在 Host 进程内解析与使用,浏览器仅拿到聚合后的百分比;路由挂在 DSH /api 信任栅栏与浏览器鉴权之后

要求

  • DeepSeek Harness(Desktop 或 dsh web,建议较新版本)
  • 已在 DSH 模型页配置 GLM Coding Plan 供应商(如 zai-coding-cn),其 API Key 会通过凭据引用自动解析(默认 ZAI_CODING_CN_API_KEY)

[!NOTE] 作者仅在 Lite 档(历史版本 V1:5 小时窗口 + 月度工具额度) 上实际验证过。V2(含周窗口)与新版积分制是按官方响应字段做的适配,逻辑上兼容但未经真机验证;如显示异常,欢迎提 issue 附上返回结构。

安装

插件零构建、零依赖,已发布到 npm,最简单的安装只需一条命令。

方式 A:npm(推荐)

dsh plugin --profile <你的profile> add dsh-glm-quota-dock

方式 B:让 DSH 会话里的 Agent 安装(任何 profile 通用)

把仓库地址交给 DSH 会话里的 Agent:

请用 plugin_manager 的 install_bundle 安装 https://github.com/Everglow28/dsh-glm-quota-dock

Agent 会克隆仓库并把 bundle 装进当前 profile,安装成功后按提示重启 DSH + 刷新网页即可。

方式 C:dsh CLI + git clone

git clone https://github.com/Everglow28/dsh-glm-quota-dock.git
dsh plugin --profile <你的profile> add <克隆目录的绝对路径>

方式 D:手动

把仓库克隆/复制到 ~/.dsh/profiles/<profile>/node_modules/dsh-glm-quota-dock/,并在该 profile 的 cordis.patch.yml 追加:

- insert:
    - id: glm-quota-dock
      name: 'dsh-glm-quota-dock'
      config:
        endpoint: https://open.bigmodel.cn
        minIntervalSec: 60

安装后重启 DSH(Host 半部需要随进程加载),再刷新网页(Client 半部)。

配置

在安装时生成的 Cordis entry 的 config 下调整(改完重启):

字段默认说明
endpointhttps://open.bigmodel.cn全球站用户改为 https://api.z.ai
minIntervalSec60上游最小请求间隔(秒),下限 30
apiKeyRefZAI_CODING_CN_API_KEY凭据引用名(与模型页写入的引用一致)
apiKey无直接内联 key(不推荐,优先用凭据引用)
cwd\上游请求(curl)的工作目录,一般不用改

工作原理

凭据服务解析 API Key(与 zai-coding-cn 模型路由同一把 key)
        │
        ▼
Host 半部调用官方监控端点(裸 key 鉴权,与官方 glm-plan-usage 一致):
  GET {endpoint}/api/monitor/usage/quota/limit     ← 各窗口百分比/重置时间
  GET {endpoint}/api/monitor/usage/model-usage     ← 近 24h 按模型用量
        │  60s 内存缓存 + 并发去重
        ▼
注册认证路由 GET /api/glm-quota(DSH /api 信任栅栏 + 浏览器签名 cookie)
        │
        ▼
Client 半部:同源 fetch,30s 轮询(空闲降频),渲染 pill 与详情面板

数据来自智谱官方监控接口(与官方 glm-plan-usage 插件同源),轮询频率保守,不触碰任何非公开接口。

卸载

dsh plugin --profile <你的profile> remove "dsh-glm-quota-dock"

或让 Agent 调 plugin_manager remove_bundle。移除后重启 + 刷新页面。

常见问题

  • pill 不显示? 确认当前会话使用的是 Coding Plan 路由下的 glm 模型;确认凭据引用已配置(面板报错时悬停 "GLM !" 可看原因);Host 半部改动需要重启而非刷新

License

MIT