🌐 Multi-provider web search plugin for DeepSeek Harness: Zero-key Bing/Baidu direct search, free-tier APIs (Tavily/Brave/Serper/Bocha), SearXNG token auth, auto-fallback, and a built-in Web Settings GUI.
DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.
Two-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback
Firefox browser-control plugin for DeepSeek Harness: one DSH plugin + one Firefox extension, driving your own Firefox over a token-authenticated WebSocket. Text-first toolset (snapshot/click/type/navigate/tab-stack) with screenshot as visual fallback. Firefox add-on available on AMO. Ported from Lum1104/dsh-browser (MIT).
One-click portable launcher for DeepSeek Harness (dsh) Web UI on Windows. Auto-installs Node.js and dsh with China mirror fallback, 3-stage progress with retries and resume, zero-download fast path when ready. No admin needed.
Give your text-only LLM eyes: zero-dependency MCP server that reads images via external OpenAI-compatible vision models with automatic provider fallback, plus a one-command patch for DSH image-attachment degradation.
DSH Cordis plugin: two-level (category + skill) recall index over all local SKILL.md files with intent routing (hit/low/miss fallback), read-only on source dirs.