Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.

Voice conversation mode for the DSH Web GUI: tap the mic to start a full-screen call, talk hands-free, and hear each reply read aloud as it streams. Bilingual (Chinese/English) UI, light and dark them

`describe_image` tool: a vision bridge that sends images to mimo-v2.5 through the opencode Zen API (credential `OPENCODE_GO_API_KEY`, free route first with paid fallback) and returns text descriptions

Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editi

Sound reminders with one-click jump for concurrent sessions: the current session gets crisp dang/dang-dang tones, other sessions a soft ding/ding-ding plus a top-right card that jumps straight to the

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in fre

Zero-dependency screen capture for DSH: Lightweight — zero deps, zero binaries; Stage & shoot — one-click full screen, window layout, hover-snap capture of occluded windows; Agent self-service — path-

Configurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then p

by 2021Heei

给 DeepSeek Harness 的语音朗读插件：AI 回复流式 TTS 朗读，思考等待期还有趣味语音短语反馈。Edge TTS 开箱即用，支持任意 OpenAI 兼容云端引擎。

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.

Let your AI agent see and operate a real Android phone: phone_look (vision + UI-tree fusion), tap/swipe/type, screenshot — over adb, for any MCP client.

Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural language for text-to-image, image-to-image, text-to-video, image-to-video, reference-image creation, task trackin

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle manag

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

Configure multiple image providers in Settings and call image_generate with the one selected model; images save under generate/image and show inline in the conversation.

Local WeChat OCR tool for DSH: `wechat_ocr_recognize` returns recognized text and the engine structured result for a local image path.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure p

Listen to Ximalaya podcasts and audiobooks inside the DSH web UI: search albums, browse paginated tracks, and play through a now-playing bar (prev/play/next, seek, volume, rate). After QR login the "M

Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).