image 41

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool

Unified image understanding plugin for DeepSeek Harness (DSH). Visual twin adapter for native thumbnails + auto-analysis on any text-only model (incl. pi-ai providers); privacy/smart/strict routing; local tools (scan/OCR×3 engines/crop/palette/compare/bat

DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-te

Generate and display images inline in the DSH chat via API channels or local CLIs (mmx / codex / agy), and read images into structured JSON evidence (OCR / layout / semantics) on any model — with backend probing and a bundled recovery skill.

Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Doubao Web by default (zero cost, no API key), Antigravity IDE quota (flash/pro), Gemini API, or Cockpit proxy — model-invokable vision tool, wrapper adapters, evidence memory, and a

DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Display images read by the read_image tool inside the DeepSeek Harness Web GUI: a dedicated Read image row with a default thumbnail and an in-page full-resolution lightbox (zoom buttons, mouse wheel, 1:1 original size) plus the metadata envelope. 在 Web GU

Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evi

DeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool

DeepSeek Harness plugin: a model-facing `vision` tool that describes and OCRs image files by calling the free Zhipu GLM vision API directly (no external CLI required).

为 DeepSeek Harness 提供外部视觉模型能力：纯文本主模型通过 describe_image 工具调用外部视觉模型看图，拿到纯文字描述（多模态补全）。静态 Cordis 插件，随 DSH 启动自动加载。

Image viewer for the dock file explorer: renders PNG, JPEG, GIF, WebP, BMP, SVG, ICO and AVIF files.

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

DeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。

Give DeepSeek Harness free eyes — natively. Paste or drop an image into the Web GUI composer: it appears as a thumbnail attachment (like a normal AI chat), and before the text-only DeepSeek model is called, the host automatically reads the image with the

Model-facing generate_image tool for DeepSeek Harness (dsh): generates brand-new images with the Google Gemini image-generation service via the Antigravity CLI, saves them, and returns the paths. Hot-pluggable — install with `dsh plugin --profile web add

DSH 静默视觉增强：主模型照常选择，图片自动交给固定视觉模型后以隐藏上下文返回主模型。

Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.

DeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing (surface replace), with a settings page and composer controls.

Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images

DSH 图片插件：ask_user_choice 图片/图文混合选项（Web GUI 渲染图片选择卡，可放大查看）+ show_images 在回复中内嵌图片（图片与文字混排）+ 聊天栏所有图片点击放大，放大层支持滚轮/按钮缩放与拖拽平移。图片来源支持本地路径 / http(s) URL / base64 data URI。纯插件实现，不改核心包。

DSH plugin: display images inline in chat with lightbox zoom, download (save-as), and prev/next navigation

dsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.

附件自动降级：DSH 图片准入（单边 ≤2000px / ≤3.5MB / ≤4000万像素）超限图片不再拒绝，用 sharp 自动缩小/重编码后入库，用户上传手机原图不再踩线。

GLM 视觉模型插件：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。

聊天输入框图片工具(自研):上传图片(≤10MB 防烧 token) + 自定义区域截图(Electron desktopCapturer),注入 DSH 草稿图片轨。零外部依赖。

Transparent image guard + vision analysis for DeepSeek Harness: text-only models read pasted images without the 400 session deadlock.

DeepSeek Harness plugin: a configurable provider route that transcribes pasted images via free Zhipu GLM vision models before delegating to a text-only adapter.

DSH 视觉桥插件：自动区分多模态/文本模型。多模态模型直接看图；文本模型通过可配置的多模态端点（baseUrl + apiKey + model）代看，支持粘贴图片、read_image 工具、请求时图片转证据。

Universal vision bridge for DeepSeek Harness: pick how images are processed — auto-rewrite via a vision LLM, explicit tools, or hybrid. Multi-channel endpoint (DSH catalog / OpenAI-compatible / Ollama / custom), LRU description cache, settings card with c

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

图片处理：读取图片尺寸/格式、缩放与格式转换（内置 ffmpeg，跨平台）

Request image optimization, intelligent retention, and observability for DeepSeek Harness (DSH)

DSH 图片/图文混合选项插件：ask_user_choice 工具让模型给用户提供带图片的选项（本地路径 / http(s) URL / base64 data URI），Web GUI 渲染图片选择卡，点击卡片可放大查看大图。纯插件实现，不改核心包。

DSH profile plugin: converts read_image PNG/WebP attachments to opaque sRGB JPEG so LM Studio's openai-completions endpoint accepts them

Renders chat Markdown image references () as a gallery under each closing assistant message

DSH plugin: image understanding via any OpenAI-compatible vision API, paste-to-describe, and an animated whale-buddy desktop pet with status bubbles and a floating settings panel

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

Meta package: one-command installation of useful community plugins for DeepSeek Harness — upload button, document reader, vision (image reading via DeepSeek's built-in multimodal model), plugin manager, and desktop launcher.

DSH plugin: read images through a user-configured vision-capable model when the main model route cannot accept image input