DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Login Chatgpt — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins
L

dsh-login-chatgpt

Login Chatgpt

带有 ChatGPT OAuth 登录界面的 DeepSeek Harness openai-codex 别名。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add github:jiangliuhong/dsh-gpt-oauth#abd0cf7cde21a0a71f902aeb32a9c4cef454e817
README兼容性版本

兼容性与来源证明

Login Chatgpt 以 dsh-login-chatgpt 发布,当前版本为 0.2.6。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
github
Registry 更新时间
2026/8/27

版本

0.2.6stable
2026/8/27

相关插件

正在加载相关插件…

最新版
0.2.6
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
未提供
文件数
未提供
Surface
web
许可证
MIT
发布源
github
GitHub
★ 1
周下载
0
最近提交
2026/8/27
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 security-access 分类下经过校验的插件。

Doctor@linxin666/dsh-doctorDSH 配置档案的事务性救援模式,配备受监督的启动器、隔离的恢复容器、确定性修复、健康监控以及本地 Web 恢复控制台Mobiledsh-mobileDeepSeek Harness 移动端适配与安全访问插件,支持局域网、远程连接、Android App 和手机浏览器。DSCODE@toddzheng024/dscode-bundle完整的 DeepSeek 编码代理,支持持久化 shell、Ultra 协作和自动权限审查。Auto Reviewdsh-auto-review针对 DeepSeek Harness 审批请求的第二模型 AI 自动审查:只读审查子代理在审批应答链上决定允许或拒绝,并采用故障关闭回退机制和完整的会话日志审计。

README

dsh-login-chatgpt

English | 中文

DeepSeek Harness plugin that adds an openai-codex-gptoauth provider route and an independent ChatGPT Login settings page. The route mirrors the installed openai-codex catalog and uses Pi's official ChatGPT OAuth device-code flow; no OpenAI API key is requested.

Install

Install from npm (recommended)

dsh plugin --profile web add dsh-login-chatgpt

To install a specific version:

dsh plugin --profile web add dsh-login-chatgpt@0.2.5

Package: https://www.npmjs.com/package/dsh-login-chatgpt

Install from a local checkout (development)

git clone git@github.com:jiangliuhong/dsh-gpt-oauth.git
cd dsh-gpt-oauth
npm install
dsh plugin --profile web add "$PWD"

The bundle installs the authorization service and uses the llm and credentials services supplied by the standard web profile.

Start Harness:

dsh web

Use

  1. Open Settings → ChatGPT Login.
  2. Select Login with ChatGPT.
  3. Open the displayed OpenAI authorization URL and enter the one-time code.
  4. Wait until the settings page reports Connected.
  5. In the conversation composer click Select model.
  6. Click the Model / Select model row to open the full catalog.
  7. Scroll to openai-codex-gptoauth and choose one of its GPT models.

The route appears in the conversation model selector, not on the Models settings page.

The login grant is stored by the DSH credentials service under llm-pi-ai/openai-codex-gptoauth. Model requests reuse that grant and its refresh flow automatically. OAuth tokens are never returned to the browser; only login status, the verification URL, and the one-time device code are shown.

Local login endpoint

The client bundle talks to a loopback-only helper on 127.0.0.1:3091. The helper accepts browser requests only from loopback origins. A port conflict fails plugin startup rather than silently disabling login.

Development checks

node --check index.js
node --check login-manager.js
node --check client.js
node --test login-manager.test.js

Release

Set the version in package.json and package-lock.json, commit it, then push a matching tag. Both 0.2.0 and v0.2.0 tag forms are accepted:

npm version 0.2.1 --no-git-tag-version
git add package.json package-lock.json
git commit -m "release: v0.2.1"
git tag v0.2.1
git push origin main v0.2.1

The tag workflow runs checks, publishes the exact package.json version to npm with provenance, and creates a GitHub Release through npm Trusted Publishing (OIDC). After the initial package bootstrap, no npm token or local publish is needed for subsequent releases.

Acknowledgements

Thanks to the LINUX DO community for its continued support.