Plugins

Multi-machine, multi-agent orchestration and control plane for DSH: discovers Agents and workspaces across devices, routes tasks by machine, repository, capability, and load to local or remote Agent runtimes, streams progress and results, forwards approvals, and recovers durable tasks after disconnections.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Registers Baidu, Doubao, Tavily, and Exa backends into ctx.web so official web_search can use them, and routes web_fetch through Tavily Extract or Exa Contents when that backend is active.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy authentication, and dynamic model discovery.

Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai provider routes.

Routes the DSH web_search tool through Ollama's web search API, reusing OLLAMA_API_KEY. No DeepSeek official key needed.

Configure default model routes for DeepSeek Harness subagents, with single-model, round-robin, random, and per-route reasoning-effort options.

DSH web plugin: open .docx/.xlsx/.pptx in the better-sidebar editor through a self-hosted ONLYOFFICE Document Server (JWT-signed config, in-network document/callback routes, save-back to disk).

Ownership-checked tools and HTTP routes to list, release and permanently delete subagent sessions, with automatic web UI refresh after deletion.

World-model research toolkit: inspect frames, name 3D / pixel / latent routes, score pred vs GT, and RSI skills / wm.yaml.

Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.

Drive DSH from anything that speaks HTTP: 47 routes (REST + SSE) for workspaces, sessions (create/prompt, live SSE generation, history, stats, todos, cancel, ask-user Q&A), models and the global default model, providers, agent presets, settings namespaces, skills, and workspace files including resumable chunked upload — plus an OpenAI-compatible /chat/completions, a built-in OpenAPI 3.0 spec and an interactive request page. It only injects the host webServer and tools, so it rides on the DSH webserver (default prefix /api/v1) or its own port with optional API-key auth, and it ships a skill that teaches the DSH agent to call the API.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Plugin-author upgrade skill for DeepSeek Harness: one package carrying a corridor index, which detects the caller peer band and routes to the closed corridor card that matches it (0.1.3-alpha.1 -> 0.1.5-rc.1 as legs A+B, 0.1.5-rc.2 -> 0.1.6-alpha.2 as leg C), plus a zero-dependency seam scanner shipped as a bundle skill and an npx CLI.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.

Beginner panel for DeepSeek Harness: routes a plain-language request into ready-to-use plans (prompt variants, matching skills, advanced moves) with a local keyword engine and fills the chosen plan into a new session in one click.

Web search provider for the ctx.web seam that routes the DeepSeek web_search tool through a LiteLLM proxy using the OpenAI Responses API, reusing LITELLM_API_KEY.