Plugins

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

Standalone mobile surface for dsh: scan-to-pair device trust, realtime SSE sync, three-channel completion notifications (in-app / Web Push / Server酱·Bark·Telegram), offline outbox, approval & question panels, per-provider usage meters, PWA; a native narrow-screen phone UI.

Audits every plugin HTTP route in a profile for a browser-trust fence: plugin routes win the web server's longest-prefix match ahead of the /api gateway, so they never see its trust check and must pin the Host to loopback themselves. Grades PASS/WARN/FAIL per route and fails a fence that compares Origin to Host without pinning it (bypassable by DNS rebinding). Ships as a CLI for CI and a route_fence_scan tool.

ServerChan3 (Server酱) push notifications when a turn finishes — title, model, project directory, git branch, status and a reply excerpt, with subagent filtering and fire-and-forget delivery.

GLM (Zhipu bigmodel) web search provider - routes ctx.web search through Zhipu's Anthropic-compatible endpoint with the native web_search server tool, billing your existing GLM quota or Coding Plan instead of the DeepSeek platform. Includes a translation layer for Zhipu's non-standard tool_result response layout.

Sidebar disk browser for DeepSeek Harness - browse any folder on the server (including hidden ones) with text preview, streaming download and upload (multi-select / drag-and-drop, overwrite confirm), responsive on desktop and mobile.

Folds the tool-definition prompt surface when many MCP servers are installed: a static KV-cache-stable catalog plus BM25/bge-m3 hybrid tools_search and batch tools_schema expansion, so hundreds of tools stay discoverable without spending their full schemas every turn.

Bridges the agent to a persistent OKF memory vault over MCP stdio: a Python server (SQLite FTS5 + Markdown) with 10 tools for searching and storing decisions, facts, learnings, conventions, profiles and sources.

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

Floating todo panel for DSH sessions with server-side cross-device persistence and pending-task badges in the session list.

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.

Aipx toolkit: skills plus a Hub Console that fronts every MCP server with ~4 meta tools — server pool health, per-tool enable/disable, a tool catalog, and a search playground showing exactly what mcp_search hands the model.

In-session "Files" tab (conversation.view, order 20) for dsh Web that browses the active session's workspace directory with breadcrumbs and previews files inline — sanitized Markdown (marked + DOMPurify), images, line-numbered text and PDF — served by read-only /dsh-files host routes registered on ctx.webServer; no write endpoints. Bilingual zh/en.

DeepSeek Harness (DSH) bundle: wires Kimi Computer Use's stdio MCP server through the generic dsh-mcp-client bridge, plus a bundled skill for driving it.

A xiuxian (Chinese cultivation-fantasy) world where agents create a cultivator and play through 16 tools - cultivate, roam 22 areas, delve 8 dungeons, chat with 4 builtin NPC cultivators - and on exit export a self-contained HTML replay plus a Markdown journey diary, fully offline with zero servers.

Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.

Adds a restart button next to the shutdown button in the bottom-right of the DSH Web GUI; the server comes back up and the browser reopens.

Task-completion notifications: desktop alerts via macOS Notification Center and Windows Toast, plus mobile push through Bark, ntfy, ServerChan or any webhook when an agent run goes idle, errors or blocks.

Expose a local MCP server to remote agents through an outbound-only tunnel stack (mcp-proxy + cloudflared Quick Tunnel), then register the public URL into dsh-mcp-client streamable-http config.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

Expose DeepSeek Harness tools as a standard MCP server (streamable HTTP) — drive dsh from Claude Code, Codex, or any MCP client

DeepSeek Harness (DSH) bundle: wires Kimi Computer Use's stdio MCP server through the generic dsh-mcp-client bridge, plus a bundled skill for driving it.

A derived fork of @zebbkira/dsh-skills-mcp-manager (the original Skills & MCP manager) that adds a local-CLI tool layer. Skills, MCP & CLI manager for the dsh web GUI: browse/enable/import/delete skills across project and user roots; manage MCP servers wi

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).