Plugins

Local file upload: paperclip button and drag-and-drop, per-session storage under .dsh-uploads, and a read_document tool that pages text and OCRs images.

Scan, view, and safely clean local AI terminal session histories (Claude Code, Codex CLI, WorkBuddy, DSH) from a settings card — quarantine-first with SHA-256 manifests, one-click restore, audit log, and phrase-confirmed hard delete.

Live DeepSeek API balance in the sidebar footer plus an always-visible bottom-right pill: status dot and amount, refreshed every 60 seconds, the API key is read from the local credential store and never embedded.

View tab manager for the DeepSeek Harness Web GUI session header: enable, hide, reorder and rename the conversation view tabs (Chat / Trajectory), with locale-aware zh/en copy and npm update reminders.

DeepSeek Harness plugin: a model-facing show_image tool that presents a local image to the human viewer in the conversation.

Local-first control plane for managing multiple DSH runtimes, profiles, presets, sessions, plans, and knowledge references.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home, powered by the local yeelight-home runtime.

From chat to canvas to artwork — drive ComfyUI as a visual workflow IDE inside DSH. Embed ComfyUI (local or cloud) as a split-screen canvas in DeepSeek Harness Web: the agent sparks ideas, writes prompts and scripts right in the chat, applies them live to the canvas in front of you, and produces images, music, video, and 3D. From idea to finished output without ever leaving the conversation or switching front-ends: Canvas ops — compose and arrange pipelines, read/write workflows, edit nodes, wire links, run, tune parameters, and debug errors, all live and WYSIWYG on the exact canvas you are looking at; Production tasks — batch parameter sweeps (batch_run) and automatic output-image retrieval back into the chat (get_outputs), powering multi-modal creative and batch generation across images, music, video, and 3D; Environment upkeep — one-click launch of ComfyUI and one-click upgrade of the core plus every custom node (upgrade), keeping the stack healthy without interruption. This package is the DSH-side plugin, and it ships the ComfyUI-side bridge node too.

Local Qimen business-timing workbench for DeepSeek Harness, with nine palaces, deterministic scoring, future-window ranking, and direction advice.

Bridge local projects into Obsidian: bounded manifest scanning, deterministic dependency/tech/topic edges, and wiki-linked notes written into a managed graph/ vault namespace via the Local REST API or the vault filesystem.

Mine local DSH session logs (JSONL) into personal usage & impact receipts: Markdown day/week/month reports plus a self-contained HTML receipt, cross-referenced with local git log — zero-network, privacy-first.

Native WCAG accessibility scanner: runs axe-core over local HTML files / build output / URLs and reports violations (rule id, impact, WCAG 2.1 mapping, element targeting, fix suggestions) as Markdown/HTML/JSON. Read-only, CI-able.

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

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.

Local-first personal usage insights in Settings, with 1/7/30-day token heatmaps and a 30-day calendar, token composition, model mix, and skill-call status.

Renders local audio/video paths as inline, playable previews in DSH chat: replaces paths with <audio>/<video> players backed by same-origin /api/media-preview/* route, with explicit error statuses.

Composer button that opens a panel listing every skill available to the current session with Chinese titles, purposes and usage examples, and lets you catalogue newly installed skills in one click (saved locally).

Manchester United 2026/27 fixtures in the sidebar with kickoff times in your local timezone, finished matches with W/L/D results.

Drag or paste any local file onto the DSH page; it resolves the real absolute path (Spotlight + size/mtime + head/tail fingerprint match) and inserts it into the composer, with a content-cache fallback.

Keeps a local model's context at a size the GPU handles well: measures prefill speed on every request and, before each step, warns or compacts early on a hard token ceiling, an observed time-to-first-token budget, or a predicted cold-prefill budget; /context-budget shows the numbers and the cost of compacting now.

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

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and stops partial work from being reported as the whole task done.