GooDAnDReaDY/dsh-model-sync

Dynamic LLM Model Catalog Synchronization & Automated Balance Monitoring for DeepSeek Harness

Project Overview项目介绍

This is a native DSH plugin built exclusively for DeepSeek Harness that handles dynamic LLM model catalog synchronization and automated account balance monitoring. It can be installed directly via the DSH CLI with the single command dsh plugin --profile web add @goodandready/dsh-model-sync, and after installation you will need to restart your DSH Web UI to activate the background synchronization feature. It pulls updated model information, including model IDs, aliases, context window limits, pricing, and capability flags from over 25 upstream providers automatically, eliminating the need for manual YAML config edits when providers update their model offerings. It supports both manual trigger via the DSH web settings panel and automatic scheduled background polling.

The plugin normalizes model data from all supported providers, tags models with their core capabilities, and reconciles changes to the active DSH model catalog automatically by default. It keeps a full sync history that tracks newly added models, deprecated model IDs, and modified capability metadata, with timestamped diff logs accessible directly in the DSH web settings panel. It also supports granular per-provider enable/disable toggles and custom endpoint inputs for users that need to connect to private gateways. It is designed for any DSH user that works with multiple LLM providers across cloud and local deployments, and helps cut down on tedious manual catalog maintenance work.

The plugin requires Node.js 20 or higher to run, and comes pre-built with adapters for over 25 popular providers including OpenAI, Anthropic, Google DeepMind, DeepSeek, Groq, Ollama, and many more. It can be configured via DSH's settings.yaml file, where you can adjust sync interval, toggle auto-reconcile and balance checks, and disable individual providers you do not use. It also monitors account balances and quotas for supported providers to help users avoid unexpected service interruptions from exhausted credits. It is released under the permissive MIT open source license, so you can use it for free for both personal and commercial projects.

这是一款专为DeepSeek Harness打造的原生插件,用于动态同步LLM模型目录并自动监控上游账户余额。它可以自动从超过25个上游AI提供商拉取最新模型列表、上下文窗口、定价信息以及能力元数据(视觉、工具调用、推理、嵌入等),无需用户在提供商新增、调整模型后手动修改DSH的YAML配置文件。

它支持定时后台轮询同步,也支持在DSH的Web设置面板点击按钮手动触发同步。同步后会自动整理模型能力标签,对比新旧目录差异,更新可见模型列表,还能跟踪新增和弃用的模型,在Web界面生成带时间戳的同步差异日志。这款插件面向所有使用DSH管理多提供商LLM模型的用户,不管是使用云端还是本地Ollama这类模型服务都适用。

插件预配置了超过25个常见AI提供商的适配器,覆盖OpenAI、Anthropic、Google、DeepSeek等主流云端服务,也支持本地Ollama等私有部署服务,还允许用户添加自定义兼容端点。安装可通过DSH CLI命令一键完成,安装完成后需要重启DSH Web UI才能激活后台同步功能。插件采用MIT许可证开源,没有使用成本。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 3 stars - very few users, little community feedback星标只有 3,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 @goodandready/dsh-model-sync

把 GooDAnDReaDY/dsh-model-sync 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

📦 @goodandready/dsh-model-sync

Dynamic LLM Model Catalog Synchronization & Automated Balance Monitoring for DeepSeek Harness

npm version license DSH Plugin Node version

All Author Projects

🇬🇧 English • 🇷🇺 Русский • 🇨🇳 中文说明

⭐ If you like this plugin, please star it on GitHub — it shows me that the plugin is useful to you and motivates me to keep developing it.

🐛 If you find a bug or would like to request a feature, open a GitHub issue in any language — I will review your proposal and implement useful suggestions in a future plugin version.

⚡ Overview

dsh-model-sync keeps your DeepSeek Harness model catalog up-to-date with upstream AI providers.

Instead of manually editing YAML configs whenever a provider launches a new model, adjusts context window limits, or changes pricing, dsh-model-sync automatically discovers new releases, updates capability metadata (vision, tools, reasoning, embeddings), tracks account balances, manages model selection visibility, and reconciles models on the fly without server restarts.

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 build-dsh-plugin 下一个 Next dsh-prompt-optimizer →