플러그인

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.

채팅에서 캔버스로, 그리고 작품으로 — ComfyUI를 DSH 안의 비주얼 워크플로 IDE로 구동. ComfyUI(로컬 또는 클라우드)를 DeepSeek Harness Web에 분할 화면 캔버스로 내장하고, 에이전트가 채팅에서 쓴 프롬프트와 스크립트를 눈앞의 캔버스에 실시간 적용해 이미지·음악·영상·3D를 생성합니다. 캔버스 작업(파이프라인 구성, 워크플로 읽기/쓰기, 노드 편집, 연결, 실행, 매개변수 조정, 디버깅), 프로덕션 작업(batch_run 일괄 매개변수 스윕, get_outputs로 출력을 채팅으로 자동 회수), 환경 관리(ComfyUI 원클릭 실행, 코어와 모든 커스텀 노드 일괄 업그레이드). 본 패키지는 DSH 측 플러그인이며 ComfyUI 측 브리지 노드도 함께 제공합니다.

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.