Plugins

Named model routes for subagent delegations, configured from a settings page: each alias binds a subagent provider, model and optional reasoning effort, token cap, agent preset, tags, plus a "when to use" line the model reads to pick it, so a delegation names only the alias. Adds five tools (delegate, list routes, edit config, wait, release), shows the route a child actually ran on in its session header, lets each UI element be switched off, and keeps all configuration in one local JSON file instead of YAML.

Manages the lifecycle of the local UM GenAI proxy (127.0.0.1:8788) that DSH's um-genai provider talks to: wakes it on demand for llm/stream calls, stops it after an idle period, and reports health plus a read-only status endpoint. Also ships a DSH settings page for port, always-on mode, idle minutes, interpreter and paths, plus the UM account and proxy API key, and a button that writes the providers.um-genai entry into the profile patch and fills in its model list, since a fresh profile has no provider and the model picker would otherwise stay empty. A renewal watchdog logs in to the campus gateway on a hidden Windows desktop when the upstream token expires. The proxy itself is um_opencode_setup.py, a single-file tool distributed by the University of Macau; a copy is vendored in vendor/ so a fresh install works out of the box, while a copy in ~/.um-opencode/ takes precedence when present. The plugin still does not produce tokens: those come from logging in to the campus gateway. Requires Windows (process discovery and idle shutdown use netstat/taskkill; renewal uses PowerShell and a hidden desktop), Python 3.10+ and a University of Macau account.

Connect ChatGPT subscription models to DSH via OAuth, preserving local tool-call identity across conversation replay.

Turn a logged-in DeepSeek web account into an OpenAI and Anthropic compatible endpoint, with tool calling, image input, an account pool and a local admin console. First use needs a one-time `node scripts/fetch-assets.mjs` in the installed plugin directory to download DeepSeek's PoW runtime from the vendor CDN; without it the proxy starts but every upstream request fails.

Token cost monitoring, call-efficiency analysis and reversible tool-output caching for DeepSeek Harness.

WYSIWYG Markdown notes editor in the DSH right sidebar, with tabbed documents, table editing, chat integration, assistant read/write tools, and local file export.

WeChat Reading (WeRead) right-sidebar bookshelf and chapter reader: QR or Cookie login, store search, resume reading, and weread_shelf / weread_search / weread_book / weread_chapter agent tools.

A composer control: shows the current model's context window, the tokens in use and a rough system / tools / messages breakdown, switches the model's reasoning effort in one click (writing reasoningEfforts into the model config when the provider declares none), and edits the model's contextWindow from the same panel so custom-provider models stop silently inheriting the adapter default. Makes no model calls; reads only the official session projections, model directory and config-forms services.

Live step pill in the DSH session header: folds the durable session event stream into the agent's current action (tool name plus its argument summary), the step index inside the running turn, the elapsed turn time and the todo progress, polls it every 1.2 seconds, and renders blue pulse while working, green for a finished turn and red for a failed tool call; hides itself 9 seconds after a turn ends. On Windows it also opens an always-on-top desktop HUD (set DSH_AGENT_STATUS_HUD=0 to disable).

Replaces the DSH sidebar list with a workspace rail: pinned chats and folders, projects that are folders with their own AGENTS.md and files, a virtualized Recents list ordered by the last finished turn, a project_search tool, unread markers, a collapsed icon column with an unread count and a live browser tab title.

Optional source-preserving chat rendering with selectable themes, offline Uiverse component tools and a report-local evidence workspace. Preview for DSH 0.2.1-rc.2.

把你和 AI 的全部对话，渲染成一片星海，可视化的预览

QQ2006 skin for the DeepSeek Harness Web UI: coral-blue palette, SimSun typography, classic controls, chat-window toolbar and a skin center with a pixel-accurate login window.

Remote Linux server manager in the Harness Web UI: browse and edit files, inspect host status, start/stop/restart Docker containers, inspect images, configure Docker registry mirrors, manage firewalld/ufw rules, switch apt sources, and detect developer tools or install/upgrade them with apt.

Reports conflicting DeepSeek Harness plugin composition — duplicate loader names across bundles (install-shadow), one id given two names, enable/disable fights, and config keys silently overwritten by a later layer — then emits a patch with the final merged values. Ships a CLI that runs when DSH itself will not boot, plus a fusion_report tool that reads the live loader.

Adds a Git chip beside the composer that opens a centered workbench (changes, history, files, tags, stash) plus a Git section in settings. Supports multi-account OAuth device flow and PAT with per-repository permissions (full, read, none), gates writes behind a global switch and reads behind an allowed-directory list, and refuses a push whose target remote belongs to no writable account. Diffs preview in place with line numbers, four layouts, word-level emphasis, syntax highlighting and Ctrl/⌘+F find; Markdown and images render inline, commit messages are searchable, and commit messages can be generated from the staged diff through the host LLM service. Ships 8 Agent tools, 51 local HTTP endpoints and 8 languages, with tokens encrypted at rest by AES-256-GCM.

Delivery workflow preset for DeepSeek Harness: an agent protocol plus seven tools that keep user requests verbatim, record feedback decisions, plan tasks with acceptance criteria, log real verification commands and exit codes, and write completion summaries as per-project JSONL files.

Asks the few key questions that decide the approach before work starts — one shot, about 200 tokens per session, no tool registration and no extra model call.

Searches medical and life-science literature by topic, keyword or DOI through Europe PMC, PubMed, OpenAlex and Crossref; decides open-access status through Unpaywall/OpenAlex/Europe PMC; downloads the PDF when an OA route exists (verified by magic bytes and page count) and otherwise writes a decision card with the exact failure reason plus four manual fallback channels: AbleSci assistance, Sci-Hub, SciDown and X-MOL. The bundled Python tool uses only the standard library.

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR 0.6B 4bit on MLX/Metal by default, SenseVoice and mlx-whisper fallbacks), zero external APIs, launchd self-healing service and an 8-point diagnose script. The bundled skill lets the agent install, configure (Karabiner hotkey wiring, launchd, engine switching) and troubleshoot the whole toolchain for you.

Prepares files before read, read_image and the vision tools open them: downscales images over 2048 px or 8 MB (one retry at 1280 px within the same turn), converts BMP/TIFF to PNG, relabels mislabeled uploads by sniffing their bytes, and turns docx/xlsx/pptx, text-layer PDF, csv/tsv and html into Markdown with no external programs.

Keyless image generation with two tools: generate_image (no API key, one call at a time, bounded rate-limit retries) and list_image_models.

Starts the published local BeatDesign 0.2.5 workspace and connects 30 MCP tools for projects, Canvas, Assets and Timeline, with a shared-project Skill and remote-generation approval guidance. Requires Node.js 22.12+ and a free port 3020; frame extraction and timeline rendering also need ffmpeg/ffprobe on PATH (browser export does not).

Read-first VPS operations tools: systemd status and actions, disk usage, Docker status, log tails, configured backups, and quiet-hours schedules.