dsh-coding-plan-usage
IdentifiedShows Qwen Token Plan, Z.ai GLM Coding Plan and MiniMax Coding Plan quota usage in three cards under Settings → Models, reusing the configured provider API keys for Z.ai and MiniMax and a dedicated br
Coding Plan usage for DeepSeek Harness
Show your coding-plan quotas in DeepSeek Harness. Three cards appear at the bottom of Settings → Models:
- Qwen Token Plan — monthly / 5-hour / weekly quota, whichever Qwen returns.
- Z.ai GLM Coding Plan — session (5h), weekly token usage, and web-search count.
- MiniMax Coding Plan — session and weekly prompt usage.
This is an unofficial plugin. It is not affiliated with Alibaba/Qwen, Z.ai (Zhipu), MiniMax, or DeepSeek. The usage endpoints are undocumented provider APIs and can change.
How each provider authenticates
- Z.ai and MiniMax use the provider API key. If you already configured the
zai/minimaxmodel provider in DSH, the plugin readsZAI_API_KEY/MINIMAX_API_KEYfrom the DSH credential store automatically — nothing to paste. Otherwise each card has a paste box that stores the key locally. - Qwen cannot use the inference API key for quota. Sign-in opens a dedicated Edge/Chrome window (not your everyday browser), you log in to Qwen Cloud there, and the plugin reads only
qwencloud.comcookies, then closes the window.
Install
From npm (one-click, shows in the in-app Plugin Center):
dsh plugin --profile desktop add @alvinlui-hk/dsh-coding-plan-usage
Or from a DSH session, ask the agent to install this repository:
dsh plugin --profile desktop add github:alvinlui-hk/dsh-coding-plan-usage
That needs git on PATH. Without Git, use the tarball:
dsh plugin --profile desktop add https://codeload.github.com/alvinlui-hk/dsh-coding-plan-usage/tar.gz/refs/heads/main
Use --profile web instead of --profile desktop if that is the profile with the Web UI. Then restart DeepSeek Harness and open Settings → Models.
Requirements
- DeepSeek Harness
0.2.1or later, with a Web UI profile. Verified on0.2.1-rc.2,0.2.1-rc.3, and0.2.2-rc.1. - Z.ai: a GLM Coding Plan and its API key. MiniMax: a Coding Plan and its API key.
- Qwen: a Qwen Cloud Token Plan, plus Microsoft Edge or Google Chrome for the sign-in window.
Privacy
See SECURITY.md. In short: secrets stay in the local DSH credential store, requests go only to each provider's own API, the Qwen debugger listens on 127.0.0.1 and refuses browser origins, and sign-out deletes the stored record.
License
Comments
Loading…
Similar plugins
by Thedeergod666
Shows coding-plan usage and balance for 5 AI providers (MiniMax, DeepSeek, Kimi, OpenRouter, Zhipu) beside the composer input, switching with the selected model and reusing API keys configured in DSH
★ 6
MIT
JavaScript
Aug 31, 2026
dsh plugin --profile web add dsh-musageShows MiniMax Token Plan usage in the Settings page through webServer routes and reads either subscription key name from environment or credentials file.
★ 0
dsh plugin --profile web add dsh-minimax-usage-pro把 ZCode 的 Z.ai / Start Plan 额度接进 DeepSeek Harness,作为原生 GLM 模型提供方使用,并在 DSH 内管理额度。
★ 0
MIT
JavaScript
dsh plugin --profile web add dsh-zcode-startToken usage statistics by model, session and date in a sidebar panel, plus OpenCode Go quota, DeepSeek balance and Z.ai quota monitoring.
★ 1
↓ 409/wk
MIT
TypeScript
dsh plugin --profile web add @xfqz86/dsh-usage-statsby pan17
Shows MiniMax Token Plan usage beside the DSH Web UI model selector with compact 5h/7d bars, click-to-refresh, automatic idle and heartbeat refreshes, and endpoint fallback. Reuses subscription keys c
★ 0
MIT
TypeScript
Sep 5, 2026
dsh plugin --profile web add dsh-minimax-usageby Dogtiti
Provider usage panel for DeepSeek Harness: shows the remaining share of each quota window (GLM Coding Plan today) as a chip beside the model selector, with a detail popover.
★ 0
JavaScript
Oct 26, 2026
dsh plugin --profile web add dsh-plugin-usage-panel