Plugins

OpenDesign Go provider: 12 subscription models over Chat Completions, the real 5-hour and 7-day quota read from the local OpenDesign app, per-model parameters and switches, and multi-account failover.

Multi-agent orchestration preset: a lead agent dispatches subagents from a built-in role roster over separate read and write lane pools with per-role model binding, and collects each subagent report on a shared board; adds go_work/continue/need_help/forward tools, a tree-view panel and a settings page.

HarmonyOS development suite for DSH: a right-sidebar HiLog inspector (live stream with level/logger/text filters) and an ArkUI Inspector (screenshot pick, collapsible component tree, node properties with search, box model), two tree sources — the DevEco debug channel (declared padding/margin/border and custom component names) and the uitest accessibility tree — an .ets viewer with ArkTS syntax highlighting, DevEco Studio/CLT toolchain and device management, plus the harmony_ui_tree agent tool. 21 remote methods, 82 unit tests.

Huddo group chat for DeepSeek Harness: adds the huddoai MCP server so the agent can join a room from an invite link, read and reply to people and other agents, wait for new messages, react with emoji and send end-to-end encrypted whispers; includes a skill describing the workflow.

Tidy the model list of DeepSeek Harness: hide any model from the selector, rename models and channels while keeping the provider billing rate, and arrange both with arrows. Search, per-provider batch toggles, back to top, one-click restore. Display only — no provider configuration is rewritten.

Bring WorkBuddy's free and paid models (domestic and international) into DSH — no WorkBuddy desktop app required.

Unofficial provider that connects Tencent CodeBuddy open platform models to DeepSeek Harness, with automatic model discovery and a settings page for the API key.

Desktop half of the dsh browser extension: mounts a token-authenticated WebSocket bridge on the dsh webserver and exposes the browser_* tools that let the model read the tab you are on as text and act on it, with image recognition off until the user enables it.

Use your logged-in web AI (DeepSeek, GLM, Kimi, Qwen, Doubao...) as model providers in DeepSeek Harness. Web models emit tool calls, DSH runs them under its native permission system, and results return to the same web session. No API keys.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

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.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Reads the files that AGENTS.md references with @path imports and injects their content into model context, with byte budgets, compaction re-seeding and a six-language settings card. v0.3.x expands the imports of every instruction file the harness loaded, including a project AGENTS.md picked up mid-session (needs DSH 0.2.0+); use 0.2.x on DSH 0.1.7.

OpenCode Go subscription models as a DeepSeek Harness provider: re-resolves the live gateway catalog every few minutes, auto-adapts models the built-in table has not seen, and covers streaming, tool calls, image input and subscription usage. A maintained fork of dsh-opencode-go: a clash with the upstream package over the llm-opencode-go settings namespace makes it withdraw quietly instead of failing the whole plugin tree, and an already-claimed opencode-go route makes it serve on opencode-go-plus.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Local model plugin for DeepSeek Harness: manage GGUF models in settings, auto-launch llama.cpp on first message, and auto-unload after 5 minutes of idle time to free VRAM.

TRAE-style conversation rollback — per-turn checkpoints (10-turn sliding window) roll back touched files and truncate model context in place, keeping the same session id. Human-initiated only: a /rollback command or a per-turn Web button (works on interrupted turns too), with a preview listing each affected file and its action — restore, recover, delete, or skip.

Local OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.

Keep declared workspace subpaths (e.g. .git) read-only, honor a read-only rules file at the workspace root, grant extra writable roots under workspace-write, and let the model request session-scoped write access; enforced for sandboxed CLI commands and the write/edit tools.

Registers the MathWorks MATLAB/Simulink MCP server into a dsh profile, so agent sessions get mcp__matlab__* tools for running MATLAB code and reading, editing and testing Simulink models.

Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.

Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/中文 UI.

CLIProxyAPI quota for DeepSeek Harness: a ring beside the model picker plus a settings panel listing every account quota windows with plans and reset times.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.