ziyou979/dsh-llm-oauth

Name: ziyou979/dsh-llm-oauth
Author: ziyou979

Plugin插件 Native原生 ⭐ 5 MIT Models & Routing模型与路由 Dev Workflow开发与代码工作流

DeepSeek Harness 插件：OAuth / 订阅制 LLM 提供商（Grok、GitHub Copilot、OpenAI Codex、Anthropic、OpenRouter）

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-llm-oauth is a standalone LLM plugin built specifically for DeepSeek Harness that adds support for OAuth and subscription-based large language model access. You can install it directly to your DSH profile with the command dsh plugin add github:ziyou979/dsh-llm-oauth, and it does not require patching or modifying the core DSH repository. It reuses the existing @earendil-works/pi-ai model catalog package, but adds a durable credential store that automatically refreshes subscription tokens for all supported providers, which include Grok, GitHub Copilot, OpenAI Codex, Anthropic, OpenRouter, and Kimi For Coding.

After installation, the plugin is dormant by default, so it will not flood your model picker with hundreds of extra entries. You can enable, sign into, disable, or sign out of any supported provider either through the dedicated OAuth/Subscriptions section added to the DSH web settings UI, or via chat commands like /oauth enable xai or a terminal login script. Only providers you explicitly enable will appear in your model picker, alongside your existing API key-based providers, making this plugin ideal for any DSH user who wants to access subscription LLM services.

This plugin is released under the permissive MIT license, and it depends on core DSH platform packages and the @earendil-works/pi-ai catalog for all model list data. It has several documented limits: it does not support image or vision model paths, it does not maintain a private model table, and all model updates come from bumping the upstream @earendil-works/pi-ai dependency. If you use the OpenAI Codex integration, note that there is a risk of your OpenAI account being banned, so it is recommended that you only use a disposable test account for this provider.

这是一款面向 DeepSeek Harness (DSH) 的原生 OAuth 订阅型 LLM 接入插件，可直接通过 dsh plugin add 命令安装到个人配置，无需修改 DSH 源码。它复用了现有的 @earendil-works/pi-ai 模型目录，新增了持久化凭证存储来实现订阅令牌自动刷新，目前已支持 Grok、GitHub Copilot、OpenAI Codex、Anthropic、OpenRouter、Kimi 等多个主流订阅制大模型服务。

插件安装完成后默认处于休眠状态，不会挤占模型选择器的显示位置。用户既可以通过网页端设置面板，也可以使用终端命令来完成对应提供商的启用、登录、禁用或退出操作，只有完成启用的服务商才会出现在模型选择列表中，和原有的 API 密钥服务商并列显示。该插件适合需要在 DSH 中使用订阅制大模型而非官方 API 密钥服务的开发者。

该插件遵循 MIT 许可证，依赖 DSH 原生的插件框架和 @earendil-works/pi-ai 目录包，模型列表完全跟随上游目录更新，不维护私有模型表。使用 OpenAI Codex 时存在账号被封禁的风险，建议使用一次性测试账号；插件本身不支持图像/视觉能力，也不提供内置 OAuth 回调服务。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-llm-oauth（ziyou979/dsh-llm-oauth）
仓库：https://github.com/ziyou979/dsh-llm-oauth
本站详情页：https://www.yhbd.top/plugins/ziyou979-dsh-llm-oauth/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 5 · 最近提交 2026-09-15 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 5 stars - very few users, little community feedback星标只有 5，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:ziyou979/dsh-llm-oauth

把 ziyou979/dsh-llm-oauth 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

8.1 KB · 缓存于 2026-09-15 19:39:56 · 8.1 KB

dsh-llm-oauth

English | 中文

Standalone OAuth / subscription-plan LLM plugin for DeepSeek Harness. Install it into your own profile with dsh plugin add — it does not patch the Harness repo.

Settings → OAuth / Subscriptions

Official dsh-llm-pi-ai authenticates with API keys only and never runs an OAuth login or refresh. This plugin reuses the same catalog package, @earendil-works/pi-ai, but constructs Models with a durable CredentialStore so subscription tokens refresh on the request path.

Packaging follows the official plugin guides — your first plugin and publish / install:

package.json → dsh.bundle.patch plus optional dsh.client (Web Settings face)
cordis.patch.yml inserts one plugin row
prepare bundles src/ → lib/ (including lib/client.js) on git install
function plugin: export name, inject, Config, apply — no export default

Providers

Subscription	Provider id	Notes
Grok (SuperGrok / X Premium)	`xai`	Model ids come from the installed pi-ai catalog.
GitHub Copilot	`github-copilot`	Optional Enterprise URL defaults to public `github.com`.
ChatGPT / Codex plan	`openai-codex`	Not the `openai` API-key route. Needs device-code authorization enabled in ChatGPT — see below. Account-ban risk.
Anthropic subscription	`anthropic`
OpenRouter	`openrouter`	Large catalog — enable only if you need it.
Kimi For Coding	`kimi-coding`

Model ids come from the installed @earendil-works/pi-ai catalog, not from this plugin. Bump that dependency and rebuild when you want a newer catalog.

Enable vs sign-in

After install the plugin is dormant: the catalog lists the providers above, but providers: {}, so the model picker is not flooded with hundreds of models.

Concept	Meaning	How
Enable	Register the LLM route; provider appears in the picker	Settings → OAuth / Subscriptions, `/oauth enable xai`, or auto on login
Sign in	Store tokens in `pi-ai-oauth.json`	Settings panel, `/oauth login xai`, or `bin/login.mjs`
Disable	Remove from picker; keep stored tokens	Settings panel or `/oauth disable xai`

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 ziyou979/dsh-llm-oauth 的 README.md。在 GitHub 查看原文 →