Plugins

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 passed to the main model as text, while image-input support is advertised. The API key auth scheme is selectable — OpenAI, Anthropic, Gemini or Azure style request headers — and a missing key is reported before any request is sent.

Token attention management panel for DeepSeek Harness: per-task/day/week/month token usage and cost tracking (input hit/miss, output, reasoning), DeepSeek peak/off-peak pricing, task-type recognition, and advice on when to switch sessions, write a hand-off, or compact context.

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Access defaults to strict (only registered devices are served); the phone channel's permission preset is wide by design - see the README security section before sharing the bot.

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.

Johari cognition-quadrant dialog prompt composer — adds a button above the composer that opens a 2×2 quadrant panel (known/unknown × AI-known/AI-unknown) to groom conversation context into a structured prompt written back into the draft.

Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.

A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.

Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.

DeepSeek Harness (dsh) plugin that bridges the local 'Screen Automation Helper' desktop platform (Windows/macOS) into the Agent tool system. Exposes status, capabilities, workflow list/run/stop, run management, screen capture, local recognition primitives

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.

Minimal English-only voice input for the DeepSeek Harness Web UI: a mic button in the composer that transcribes speech into the draft via the browser's native SpeechRecognition API. No dependencies, no subprocess, no network calls beyond whatever the brow

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

Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.

Browser Web Speech dictation for the Composer: recognition needs no dedicated ASR server, key, or model download; reuses Session text and a configured DSH model for contextual phrase hints and optional transcript polishing.

明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别，把识别文字喂回主模型，无感、可配置、升级不丢

DeepSeek Harness OCR plugin — offline image text recognition powered by PaddleOCR-json (primary) and RapidOCR-json (fallback). 让 DeepSeek Harness 直接识别图片中的文字，无需视觉模型、完全本地离线运行。

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.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).