Plugins

Windows-only computer use for DeepSeek Harness: captures the virtual screen and drives mouse & keyboard through 9 tools built on PowerShell and Win32 SendInput; pairs with picturereader so text-only models can complete the screenshot-analyze-act-verify loop fully locally.

DeepSeek Harness plugin that locks the web chat composer Enter-send. Toggle with a lock button or Ctrl+Alt+L to prevent accidental sends while typing or editing long prompts; unlock to send. IME-safe and per-session.

Map and routing tools: driving/transit/walking/bicycling route planning, geocoding and POI search via free OSM/OSRM data by default, with an optional Amap (高德) key for better China coverage.

Web search pool for the native web_search tool: fails over across 8 free/paid backends with quota-aware circuit breaking, settings-page API key management, custom SearXNG instances, failover/rotate strategy switching and live SerpApi quota.

Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

Keep the built-in web_search tool without an official DeepSeek API key: disable web-search-deepseek and use Tavily keyless by default.

RSS/Atom subscription tools (list/add/remove/fetch/check/search/opml_import/opml_export/health) with cross-feed keyword search, cursor-based incremental fetch and OPML import/export, persisted to settings.

Cross-session archive: overview workbench, folded timeline, subagent lineage, full-text search, rule+LLM summaries, ZIP export, live tracking. Native session-page embeds: turn rail, docked right panel (live mode, pinned to original session on switch), rename (official-synced), conclusion digest, health monitoring + persistent header chip (idle / active / tool-wait / stalled). dsh v0.1.2+: fuses with the official TurnNavigatorRail — vector-icon info chips (duration, tool calls, errors, thinking) plus lazy tool distribution inside the official preview card, right-click opens the workbench; the classic piano-key strip is on by default and delegates unloaded-turn jumps to the official auto-load engine; the official rail can be hidden entirely. Settings dialog section with 10 tunable behavior params.

Deterministic keyword routing, allowlisted model switching, and an isolated image_gen channel for DeepSeek Harness.

A DeepSeek Harness plugin that binds a separate DeepSeek API key to each workspace, or to a single session, so the spend of one key stays with the sessions you choose.

Unofficial FreeCodeGo for DeepSeek Harness: DeepSeek, Codex and Claude engines over one session and toolchain, with a 0-token free access channel for deepseek-v4.1-flash, deepseek-v4-pro, deepseek-v4-flash-free, glm-5.3-flash, grok-4.6, kimi-k3, nemotron-3-ultra-free, muse-spark-1.3, Qwen 3.8 Flash and mimo-v2.6-flash-free, plus a keyless private-key gateway.

Connects seven Wind financial MCP domains and Wind Alice to DSH while resolving WIND_API_KEY only inside the host credential boundary.

Exposes OpenCode Zen free models to DeepSeek Harness with no API key, tracking Zen gateway changes.

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).

Desktop computer-use for DSH: captures the Windows screen into the agent vision channel and drives mouse/keyboard through a Codex-style overlay with Esc abort; auto-detects Windows native or WSL hosts.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Recalls prompts sent earlier in the current session with the up and down keys in an empty composer, and shows a position badge while browsing.

Request-level one-time prompt injection without further context pollution. SillyTavern-style UI and data compatibility, keyword/regex/constant triggers, and a lore_lookup tool for on-demand searching.

Routes the DSH web_search tool through Ollama's web search API, reusing OLLAMA_API_KEY. No DeepSeek official key needed.

Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.