Plugins

Conversation enhancements: a history-input overlay (Alt+Up with workspace/session/global/prompt scopes), recall of unapplied interjected messages, conversation forking with fork-family version switching, and optional auto-resend after forking (off by default).

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).

Records real clicks, inputs, navigation and network traffic in a user-guided browser session for DSH, then generates a Markdown timeline report (report.md + events.jsonl) to build API-level skills.

Input-bar prompt optimizer: rewrites drafts with 6 strategies × 3 languages plus custom instructions, optional goal/todo/compaction-summary/tool-result and chat context, a confirm dialog, last-5 history and three-tier settings persistence.

Config-driven development-task orchestration for DSH: graph workflows (task/gateway/human nodes) with per-stage persistence, plus an in-editor AI assistant that configures workflows through conversation with live validation. Hand documents to nodes as generic attachments (no declaration needed): files land in the task workspace and ${inputs.附件} gives the newline-joined absolute paths, so a node parses them with its own prompt.

Liquid Glass refraction input card for the DSH web GUI, with coupled-spring press animation. Published on npm: dsh plugin --profile web add dsh-liquid-glass-input.

Windows system-level notifications when the agent finishes a task or needs your input: task-done, question, approval and plan-review alerts via the browser Notification API, click-to-open the session, background-only mode, and a first-level settings page (Settings → 任务提示).

Smooth comet-mode animated caret for the DSH Web composer: a glowing comet trail replaces the native blinking caret and glides across the input as you type, with configurable accent color, thickness, and trail, IME-aware for CJK input.

Generate and edit AI media (image, video, audio, 3D) with WaveSpeed models via the open-source wavespeed CLI: live catalog search, per-model input-schema introspection, local-file upload with @path markers, and price checks before running.

Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Installs an image-input checkbox into the Models catalog so a custom model can declare image input and receive images directly; includes an optional BYO vision relay.

Common Word Box (常用词盒子) — DeepSeek Harness web client plugin: a persistent slide-up word/phrase panel next to the composer input, with global/current-project buckets and one-click insert. Works in every workspace.

Microphone voice input for the composer: browser Web Speech API live transcription, dedupe/auto-continue, smart punctuation, language and auto-send settings.

A skills button at the bottom-right of the input box: one click opens every installed skill with search, categories and favourites, and the skill you pick is inserted into the box. Each answer also lists the skills that turn actually used.

Manage which models appear in the composer model menu. A settings page lists every provider's models with a per-model switch, provider-level show/hide, collapsible groups and filters by kind; switched-off models leave the menu while the model in use in the current session stays. The list can be searched by name or ID and filtered by capability (multimodal, reasoning) and by minimum context window (128K / 256K / 512K / 1M). Rows show the model kind, and chat models also show reasoning support with the adapter's effort levels, their context window and input modalities. Labels merge manual overrides, the settings document, the adapter, the relay's GET /models response, a built-in pi-ai / models.dev catalog, name inference and vendor corrections in that priority order, with the source named on hover and dashed borders marking inferred values. Any model can be edited by hand (kind, context window, modalities, effort levels); those edits are stored outside the profile and can be written back into the model provider's settings. A hard re-fetch drops every cache and asks the adapter and all relays again. A switch, on by default, lets relay routes whose models declare text-only input accept images in memory, without editing configuration files. The hidden list is stored in the profile patch and mirrored to $DSH_HOME.

Obsidian-style notes panel in the DSH right sidebar: a tree over a local folder, Markdown preview with line numbers, edit and save, Obsidian callouts, tables and wikilinks, screenshot paste into the vault, one-click insert of a note path into the chat input, and batch archive or delete for sessions and workspaces.

Desktop pet for DSH with voice chat, personas, memory, Bilibili and QQ context, and command-gated computer control; enable DSH built-in voice input first to use voice chat. A fork of dsh-pet (MIT), not installable alongside the original.

Manages a Magpie model list and writes the checked models into a Magpie provider group: full sync from /v1/models, manual entries, per-model context, output limit, image input and reasoning efforts, sorting and drag reordering. On Windows x64/ARM64 it also downloads and upgrades Magpie from yetone/magpie-releases with SHA-256 verification and rollback, auto-upgrades once a release is 30 minutes old and all conversations are idle, starts Magpie in the tray with DSH, and toggles its lite mode and sleep prevention.

Per-session note list beside the conversation: a button at the top right of the chat badges the open count and opens a resizable right-side panel where notes are added, checked off, copied, edited or appended to the chat input, with panel size and drafts kept in the browser.

Composer-side prompt library: a button next to the input opens a picker with group chips and word-split AND search over saved snippets, inserting one into the draft or appending it, filling {{variables}} before insertion, with 13 built-in templates. Snippets live in one local JSON file behind a rev lock, a per-save backup, and whole-library JSON import/export; a settings page handles editing, grouping, pinning and a 6-second delete undo.

NURBS BRep solid modeling studio with natural-language input, live 3D viewport (measure/wireframe/fit), STEP export, and agent tools driving NVIDIA usd-brep through a managed CPython venv. Needs CPython 3.12; usd-brep wheels cover 64-bit Windows and Linux only.

AI animated themes, computer control, standalone windows, attachment previews, Git management, session pop-outs and annotations, cross-app file drag-and-drop, and AI prompt suggestions. Computer control is enabled from the settings; on macOS it needs Screen Recording, Accessibility and Input Monitoring permission, Windows standalone windows need the Edge WebView2 runtime, and prompt suggestions and AI themes consume extra model usage.