Find the right DSH plugin
for your next workflow

Native image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.

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-only delivery; paths are universal, pair with modlens (optional) for one-call structured evidence.

Multi-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-session quota tracking, engine failover, credential-safe config, and a result card with regenerate.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.

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 editing.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Send local images or HTTP(S) image URLs to a configured OpenAI-compatible vision endpoint with the inspect_image tool and return its text response to the conversation.

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

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

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

Codex Appshots for DSH: capture the frontmost active window via global shortcut and seamlessly mount it into the composer for agent queries.

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

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.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and render back in the transcript, so they never trip image admission. Bring your own DASHSCOPE_API_KEY; endpoint/model/budgets configurable, redirect-proof HTTP client, works in every agent preset.

Codex-style Appshots for DSH Desktop: capture the frontmost macOS window with both Command keys and attach it to the current chat.

Upgrades DSH image viewing with pointer-centered zoom, pan, galleries, downloads, keyboard support, and inline region notes (Beta).

`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 for text-only models, with native passthrough and ImageMagick transcoding of SVG/TIFF/HEIC formats.

Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).

Image understanding for any DSH model: vision, OCR, grounding, and crop tools with domain presets for histopathology, cell biology, anatomy, clinical images and scientific figures.

Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint, provides draw_image and draw_list_sources tools, supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.