DSH Plugin HubDSH 插件市场

Luck9Star/dsh-gateway-provider

Plugin插件 Native原生 ⭐ 4 MIT Models & Routing模型与路由Notifications & Remote通知与远程

DeepSeek Harness 的通用 LLM 网关提供商插件：newapi / LiteLLM / Higress / 任何兼容 OpenAI 的网关，通过 pi-ai SDK 支持多协议（OpenAI/Anthropic/Gemini），利用 models.dev 增强功能。

Project Overview项目介绍

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

This is a native plugin built exclusively for DeepSeek Harness (DSH) that lets users integrate all models hosted behind OpenAI-compatible LLM gateways including NewAPI, LiteLLM, and Higress. To install the plugin, users run the command dsh plugin --profile web add dsh-gateway-provider from their terminal, then add their gateway API key to DSH's credential file or export it as an environment variable. After restarting DSH with the web profile, all gateway models are automatically added to DSH's model picker, with real model parameters fetched automatically from models.dev so users don't need to input data manually.

This plugin is designed for DSH users who host their own LLMs behind a shared gateway, eliminating the need to manually maintain a static list of models with guessed parameters. After initial setup, all daily management happens through the web UI's Settings → Gateway Models page, where users can add multiple additional gateways with different pre-built templates. Users can filter out non-chat models by adjusting regex rules, hide or rename existing models, add custom models manually, and edit per-model parameters like context window and output cap directly from the UI.

The plugin requires a DSH instance running the web profile to access the full settings UI, though the LLM provider itself works on any DSH profile. Users must have a valid API key for their LLM gateway to use the plugin, and model catalogs are cached for 30 minutes by default, which users can adjust in their configuration. The project is released under the permissive MIT license, keys are never stored in plaintext configuration files, and all CI runs include a gitleaks check to prevent accidental secret leaks into the repository.

这是一款DeepSeek Harness（DSH）原生插件，可将NewAPI、LiteLLM、Higress等所有OpenAI兼容端点的LLM网关模型接入DSH。安装完成后输入API密钥，网关所有模型会自动出现在DSH模型选择器中，上下文窗口、输出上限、推理支持等参数都会从models.dev拉取真实数据，无需手动填写。请求会按照对应模型的原生协议转发，保障工具调用和流式输出符合模型预期。

适合将自有模型托管在LLM网关后的DSH用户使用。常规工作流为，先通过DSH命令行安装插件，再将网关API密钥存入DSH凭证文件或设置为环境变量，重启DSH后进入设置页的「网关模型」面板添加网关。用户可选择对应网关模板、测试连接、同步模型列表，还可以手动隐藏或覆写任意模型参数。

该插件依赖带有web profile的DSH环境，同时要求用户持有可用的LLM网关API密钥。默认每30分钟缓存一次模型列表，非对话模型默认通过正则规则过滤，用户可自行调整过滤规则。项目采用MIT许可证开源，密钥仅存在于DSH凭证仓库或环境变量，CI会通过gitleaks检查防止密钥泄露。

View on GitHub在 GitHub 查看

Recommended强烈推荐 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-gateway-provider（Luck9Star/dsh-gateway-provider）
仓库：https://github.com/Luck9Star/dsh-gateway-provider
本站详情页：https://www.yhbd.top/plugins/luck9star-dsh-gateway-provider/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 4 · 最近提交 2026-09-30 · 主语言 JavaScript

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 4 stars - very few users, little community feedback星标只有 4，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 dsh-gateway-provider

把 Luck9Star/dsh-gateway-provider 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

9.2 KB · 缓存于 2026-09-30 22:11:43 · 9.2 KB

dsh-gateway-provider

gitleaks

中文文档：docs/README.zh.md

Use all the models behind your LLM gateway — newapi, LiteLLM, Higress, or any OpenAI-compatible endpoint — directly in DeepSeek Harness.

Install the plugin, paste your API key, and every gateway model shows up in dsh's model picker with its real parameters (context window, output cap, reasoning support) fetched from models.dev. Requests go out over each model's own native protocol — OpenAI, Anthropic, or Gemini — so tool calls and streaming behave the way that model's maker intended.

Why this exists

dsh ships one adapter per official provider. If your models live behind a gateway, the manual alternative is a hand-maintained static model list with guessed context windows and output caps. This plugin mounts the gateway itself instead:

  • Nothing to maintain by hand — the model list is read from the gateway (GET /v1/models, with a management-API fallback for newapi); add a model on the gateway side and it appears in dsh, no re-deploy.
  • Real numbers, not guesses — models.dev data fills context window, output cap, reasoning levels, release date; config defaults only fill gaps.
  • Every wire format, one plugin — each model routes over its own protocol (OpenAI chat completions / OpenAI responses / Anthropic messages / Gemini), handled by the same pi-ai SDK the official dsh adapter uses.
  • Multiple gateways at once — a default newapi route plus one gateway:<id> route per extra gateway, each with its own cache and key.
  • A settings page instead of YAML — Settings → Gateway Models: add gateways from templates (NewAPI / LiteLLM / Higress / OpenAI-compatible / fully custom), test connections, sync models, hide or override any model, add custom models.

Requirements

  • DeepSeek Harness (dsh) with a web profile (the settings page is a web-UI extension; the provider itself works in any profile).
  • A gateway API key (e.g. a newapi token).

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 Luck9Star/dsh-gateway-provider 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-compact-button 下一个 Next dsh-plugin-market →