multimodal 75

DeepSeek Harness plugin: trims the oldest images from outgoing chat requests and, when the provider rejects the image count with HTTP 400, parses the limit from the error and retries with fewer images. · DSH 插件：裁剪即将发出请求中的历史图片，并在上游因图片数量返回 400 时解析该上限并按更少的图片

Agnes AI 多模态融合插件：一个包同时提供「多模态配置」设置页（账号池，写入 $DSH_HOME/ag-multimodal.json）、generate_image 图片生成工具与 generate_video 视频生成工具，以及三者共用的一套会话内卡片 UI。融合自 dsh-agconfig + dsh-agimage + dsh-agvideo。

让纯文本会话模型也能读取用户上传的图片——包装原生 deepseek-official 适配器：声明图片输入能力放行附件，把图片交给视觉模型转成文字，再委托给纯文本 DeepSeek。

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

为 DSH 非视觉模型提供基于 DeepSeek V4 Flash Vision Exp 的会话图片分析工具

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

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.

A vision bridge profile bundle for DeepSeek Harness (dsh): gives non-vision models image-reading capability by delegating transcription to a vision-capable model, with GUI paste admission and a web settings page for vision model selection.

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

TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus multimodal and async tools.

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。

Native-vision capability manager and lightweight external vision fallback for DeepSeek Harness

Vision tools (analyze_image, locate_element) for DeepSeek Harness: local ollama, DSH subagent (qwen-vl etc), or OpenAI-compatible HTTP endpoints

Describe images with a vision model so text-only DeepSeek Harness models can read them

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

Give text-only DeepSeek-V4-Pro real vision with zero new dependencies and DeepSeek-only routing: images are described by deepseek-v4-flash-vision-exp (your existing DEEPSEEK_API_KEY), then the text is handed to V4-Pro.

Persistent vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.

DeepSeek Harness plugin: a vision worker over Cloudflare Workers AI (@cf/moonshotai/kimi-k2.6) that routes image requests from text-only callers, returns a versioned righthand.vision.v1 envelope, and supports follow-up questions.

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

给 DeepSeek Harness 加视觉能力：可视化设置页选视觉厂商（Kimi/智谱/通义/OpenAI/Gemini/豆包/MiniMax/阶跃星辰）并粘贴 API Key，聊天里即可拖图识别——图片走视觉模型、文字走 DeepSeek 推理。

DeepSeek Harness 生图插件：侧边栏全局画廊（Cherry Studio 式绘画页）、对话生图/编辑、可自定义 Provider 端点与代理。

Lets a text-only agent call a multimodal model mid-task: the vision tool sends one image file to Qwen, Kimi, OpenAI, Claude, Gemini or a self-hosted endpoint and returns structured evidence — summary, verbatim OCR, layout, entities, and what the model cou

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

mm-vision (通感编码器) for DeepSeek Harness — give any text-only LLM the ability to see images via structured spatial text encoding. Registers the mm_vision tool.

DSH 图片插件，三个工具覆盖三种场景：ask_user_choice 图片/图文混合选择卡（Web GUI 渲染，可放大查看）+ show_images 回复内嵌图片（图文混排）+ save_received_images 盲模型收图存为工作区文件；聊天栏所有图片点击放大，支持滚轮缩放与拖拽平移。来源支持本地路径 / http(s) URL / base64 data URI。零 token 本地渲染，纯插件实现不改核心包。