omdsh-dev262Updated today
Role-based LLM retry/fallback strategy.
Practical score
85 / 100
Setup
Ready to use
License
MIT
Language
TypeScript
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/omdsh-dev/dsh-llm-fallbacks.gitPlease install the DeepSeek Harness plugin "dsh-llm-fallbacks" for me. - GitHub repository: omdsh-dev/dsh-llm-fallbacks (https://github.com/omdsh-dev/dsh-llm-fallbacks) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version…
A cleaned excerpt from the project's own documentation.
dsh-llm-fallbacks English Chinese Automatic provider/model fallback chains for dsh (DeepSeek Harness): the plugin registers N named virtual chains , each selectable in the model picker as FallbacksChain / — a session routed to one walks that chain, so an LLM request that keeps failing on a listed code (auth, quota, rate limiting 429, …) is retried on the next available provider/model and tasks are not interrupted by model problems.…
Open on GitHubSimilar tools from the same corner of the ecosystem.
shaobeichen
把 DeepSeek Harness 装进你的口袋：电脑上跑 dsh web，手机扫码即同步访问（局域网 + 公网，实时同屏）Put DeepSeek Harness in your pocket: run dsh web on your computer and access it synchronously by scanning a QR code on your phone (LAN + public network, real‑time screen mirroring)
omdsh-dev
Second model passively reviews each turn and injects notes.
zaofan-make
AI 统管 QQ 群组：审核放行、群发文件、沟通其余会话的ai! ;气氛组担当：表情包自动入库、AI 自己决定开口、多预设多人格轮班陪聊！； 远程办公：权限审批、提问卡片转发到 QQ。； 自定义互动按钮：AI 帮你轻松搭文字游戏,官机专属按钮卡片功能！ ；省 token 设计：群聊价值评分后才唤醒 AI，上下文自动压缩;结交朋友:群友画像,记忆注入；实现任意功能:提供扩展接口,示例扩展,向ai许愿！