Plugins

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

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.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Drive the user's real browser through the local Kimi WebBridge daemon: navigate, find-tab, snapshot, click, fill, evaluate, CDP, screenshot, network, upload, PDF export and tab-management tools that reuse existing login sessions.

Docker tools for agents: ps/images/logs/inspect/exec/manage/health with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.

MuApi media-generation tool: a muapi_generate tool that submits and polls jobs against any of MuApi's 100+ image, video, audio, and 3D models through one x-api-key.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Lets sandboxed agents reach the web through your local proxy: net_fetch fetches pages, net_proxy_status reports proxy status.

Zero-dependency MCP client bridge that connects stdio and HTTP MCP servers and registers their tools as mcp_<server>_<tool> for the agent.

Persistent background watchers that wake the agent on new messages (file inbox or command-output delta) — the harness analog of Claude Code's Monitor tool.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Export sessions to Markdown/JSON for review, replay, and per-session cost summaries.

Incognito sessions: a standalone ephemeral sub-agent with its own preset (no parent context) and full toolset, draggable floating window, burned to zero traces on close.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Wallpaper backgrounds for the DSH web GUI. Windows: reads your Wallpaper Engine (Steam) library and plays video/web wallpapers behind the chat. macOS: scans the WaifuX download folder and loose media folders automatically — anything saved in WaifuX becomes a DSH background with zero setup. Liquid-glass blur, dim and border sliders.

OpenCode Go plan usage display for the DSH web GUI: a persistent badge under the composer shows rolling/weekly/monthly usage percents with reset countdowns; click to expand a card; agents can query the balance via the `opencode_go_usage` tool.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.

Mobile UI for the Web GUI on narrow screens: full-width responsive layout, overlay session drawer, 44px touch targets, safe-area support, and reading enhancements with zero desktop impact.

Model sampling sliders (temperature / maxTokens) in the composer: override every model request for all providers via the agent/request hook, with hot/persist modes.

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.

Reverse tunnel for the DSH Web GUI: exposes a `dsh --profile web` deployment at a public frp URL and switches the directory picker to the in-app browser, so a phone or remote machine can open and manage the workspace.