V1ki/dsh-plugin-subscriptions 预览 preview

V1ki/dsh-plugin-subscriptions

Plugin插件 Native原生 ⭐ 418 MIT Models & Routing模型与路由

使用ChatGPT(Codex)、Claude和Grok(X Premium)订阅作为DeepSeek Harness LLM提供商——在Web界面中进行OAuth登录,无需API密钥

Project Overview项目介绍

V1ki/dsh-plugin-subscriptions is a native plugin built exclusively for DeepSeek Harness, with an official DSH bundle manifest. It lets users connect their existing paid LLM subscriptions to DSH as native providers, eliminating the need for separate paid API keys from OpenAI, Anthropic, X, GitHub, or Google. The plugin is installed directly via DSH's built-in plugin manager, and all provider authentication happens through OAuth in DSH's web UI under the Settings > Subscriptions menu. Authenticated tokens are stored securely on your local machine with 0600 file permissions, and they refresh automatically without user intervention.

After installation and login, subscribed models automatically appear in DSH's model picker, so users can select them for any new chat session. Users can configure reasoning effort, toggle provider-specific tools like X search, image generation, and video generation per provider, and view real-time rate limit usage for each of their active subscriptions. For users who already have Claude Code installed, the plugin automatically pulls existing Claude credentials from the local system, so no extra login step is required. This saves time for users who already use Claude Code on their local machine, and avoids the need for a separate OAuth flow.

The plugin is released under the open-source MIT license, with no associated costs for personal or commercial use. To contribute to development, clone the repository, install dependencies with pnpm install, build the plugin with pnpm build, and run unit tests with pnpm test. It does not support SOCKS proxies, and all configuration changes take effect immediately without requiring a restart of the DSH web server. First-time users only need to install the plugin via DSH's plugin catalog, log into their subscriptions, and start using their subscribed models right away. All user data is stored locally on the user's machine, with no third-party data collection.

这是一个专为DeepSeek Harness开发的原生插件,核心功能是让用户直接将已订阅的ChatGPT Plus/Pro、Claude Pro/Max、Grok X Premium、GitHub Copilot、Google Antigravity等服务作为LLM提供商接入DSH,不需要额外申请这些服务的API密钥。它通过DSH的插件管理器安装,所有提供商的OAuth登录流程都可以在DSH网页端的设置→订阅页面完成,用户凭据会自动刷新并安全保存在本地。

登录完成后,已授权的订阅服务模型会直接出现在DSH的模型选择列表中,用户可以针对每个模型配置推理强度、服务商工具(搜索、图文生成等)的开启状态,还能实时查看当前订阅的速率限制剩余额度。对于已安装Claude Code CLI的用户,插件会自动导入已有凭据,不需要重复登录。它适合已有多个LLM订阅、不想重复付费购买API密钥的DeepSeek Harness用户。

本插件使用MIT许可证开源,开发依赖pnpm包管理器,编译需要TypeScript和tsdown工具。它不支持SOCKS代理,OAuth授权页面会跟随系统浏览器代理,所有配置变更无需重启DSH即可生效。首次使用需要在DSH的插件商店搜索安装,完成后进入设置页面登录对应订阅账户即可开始使用,所有数据都存储在用户本地,不会上传到第三方服务器。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号
  • This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号(星标、许可证、更新活跃度、清单完整度)
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 dsh-plugin-subscriptions

把 V1ki/dsh-plugin-subscriptions 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-plugin-subscriptions Awesome DSH Plugin

English | 中文

Use your ChatGPT (Codex), Claude, Grok (X Premium), GitHub Copilot, and Google Antigravity subscriptions as LLM providers in DeepSeek Harness — no API keys. Codex, Grok, and Antigravity log in via OAuth in the dsh web UI (Settings → Subscriptions), while Copilot uses the GitHub OAuth device flow; Claude imports credentials from an existing Claude Code session when there is one (macOS Keychain or ~/.claude/.credentials.json) and otherwise falls back to the same browser OAuth flow, so the Claude Code CLI is not required. Tokens live at ~/.dsh/plugins/subscriptions/auth.json (mode 0600) and refresh automatically.

Demo

Settings → Subscriptions: per-provider login/logout, no API keys. Claude imports credentials from Claude Code when available and otherwise uses OAuth, as Codex and Grok always do (settings screenshots use demo accounts and catalog data):

Subscriptions settings page

Configure visibility, default reasoning effort, and context together in Edit model list, with shared Save and Cancel actions:

Model settings

Configure image generation, video generation, and X search per provider. Tool switches apply only to sessions created after saving:

Provider tools

Logged-in providers join the session model picker with their live model catalogs:

Model picker with subscription models

Models that advertise reasoning levels get an Effort selector in the same menu — Codex models, Grok 4.6 / 4.5, and Copilot's reasoning models (levels and defaults come from each provider's live catalog, not a hardcoded list; Copilot's capabilities.supports.reasoning_effort array is sent as reasoning_effort on chat completions and reasoning.effort on the Responses wire). Models listing both Copilot endpoints (gpt-5.4, gpt-5-mini) normally speak chat completions but reroute to /responses when a request combines function tools with an effort — Copilot rejects that combination on the chat wire:

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 →

← 上一个 Prev Awesome-AI-Pedia 下一个 Next DSH-Transparent-UI-Plugin →