Plugins

Continuous voice conversations for DSH with hands-free listening, push-to-talk, speech recognition, TTS replies, and background Agent delegation.

Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant, a read-aloud button, and a settings panel for the GSV-TTS-Lite engine.

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.

Runs AItelier pipelines from DSH over MCP: 39 tools (22 read, 17 write) to generate, run, inspect, edit, export and import multi-step SkillFlow pipelines. The steps execute in AItelier rather than in the DSH session and are polled by run_id, pause at engine-enforced checkpoints answered with answer_checkpoint, and leave per-step traces and step outputs to read afterwards; add_provider / map_model / edit_role point an individual role at a local or cheaper endpoint. Bundles an aitelier-pipelines skill.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.

AI UI automation via Midscene — android_ui and web_ui tools that tap, type, query, and assert on a real Android device or an already-running Chrome through the ctx.midscene seam.

Vertical message pointer rail on the left edge of the chat: one dash per user message, click to scroll to that message, hover for a preview bubble.

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.

Search AIGC Radar's curated GitHub AI project library (500-star admission, bilingual zh/en tags, star-growth snapshots) over its MCP endpoint with native result cards; an agent/pre-step listener proactively suggests a reuse check before the agent writes code.

Adds the DeepSeek Harness homepage background to dsh web: WebGL fluid light, dot-line grid and a digital point-cloud whale, with dark and light palettes.

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.

Agent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Mounts the hosted Exa search MCP endpoint (https://mcp.exa.ai/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge: web_search_exa and web_fetch_exa tools, anonymous on the free tier or with your own EXA_API_KEY.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Notification outbox: agent proactively notifies via toast / Chinese TTS voice / sound effects (explosion, victory, alarm), 60s confirmation window voice-calls you back, volume boost, settings panel.

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, one-click interrupt and breakpoint fork via official APIs, independent GUI tab.

Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.

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

The generic New Session action opens a default-directory workspace instead of requiring a folder pick, and the workspace picker lists that workspace as a no-folder choice.

The built-in web_search bills a full model turn against DeepSeek's own endpoint; this runs it on an OpenRouter-compatible gateway instead, so search is billed where your chat already is, at the model and price you pick.

Comet-mode animated caret for the DSH Web composer: a glowing trail glides to the text position, with configurable accent color, thickness, trail, and a 500 ms idle blink. Extends the surface to ask-question card inputs, and fixes the caret vanishing on an empty composer or first focus, forward drag-selection not following the pointer, soft line breaks measuring against the previous line, and the caret painting outside the composer when long input scrolls. Maintained fork of Lacquervii/smooth-cursor.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.