dsh-agnes-omni
Agnes 全模态插件 for DeepSeek Harness:看图(agnes_vision)、生图/图生图(agnes_image)、视觉桥(带图消息可发送并自动交给 Agnes 视觉分析)。密钥经 DSH 凭据服务读取,不写入代码。
489 results
Agnes 全模态插件 for DeepSeek Harness:看图(agnes_vision)、生图/图生图(agnes_image)、视觉桥(带图消息可发送并自动交给 Agnes 视觉分析)。密钥经 DSH 凭据服务读取,不写入代码。
Guard DeepSeek Harness PowerShell, file, image, and search tools on Windows with workspace, credential, approval, and audit policy.
Permanent wallpaper skin for the DSH web UI: the host serves any local image over an HTTP route, the client pins it behind the window, makes theme surfaces translucent, and offers a Settings → 背景图 panel to change the image anytime — survives restarts, no re-define needed.
Adaptive wallpaper and appearance studio for the DeepSeek Harness Web UI, with image-derived light/dark palettes, colors, blur, fonts, radius, opacity, and scaling.
常驻视觉服务:直连视觉模型(默认 opencode-go/minimax-m3,回退 zai-coding-cn/glm-4.6v)。describe_image / subagent_vision 工具 + 粘贴图片自动转译(llm/stream 钩子)+ 输入框视觉状态小胶囊与详情页(活动日志:指令/思考过程/输出)。零子代理、零 agent 上下文开销,按会话记忆窗支持视觉追问与验收。
DeepSeek Harness (dsh) plugin for wallpaper theming — upload images from the Settings page, pick one, and the whole dsh web UI renders over it with an adjustable readability mask and blur.
让 dsh 用独立的 OpenAI 兼容视觉模型读图:主对话历史只保留纯文本描述,图片字节不进上下文,纯文本模型也能读图。
Seamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.
Image auto-describe provider for the DeepSeek Harness apiproxy admission seam: transcribes pasted images through configurable vision routes (Qwen first, GLM fallback) so text-only session models still receive image prompts.
Dream Skin theme manager for DeepSeek Harness Web: visual theme picker in Settings with custom theme create/import/export, background images, pause/resume. Never see the official palette flash on refresh.
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。
DeepSeek Harness 插件:通过本地 Doubao Relay 提供 doubao_ask 联网搜索/图片生成/多模态识图工具,并支持粘贴图片转本地路径(paste-to-path)。
Image translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.
Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers
DeepSeek Harness plugin: drag images into the composer and get a file path back, so text-only models can read them via the read tool.
DSH (DeepSeek Harness) Cordis plugin that lets the agent display images — local files or URLs — directly inside the conversation.
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.
Vision DSH bundle: give the agent screen/window vision — see tool captures via the bundled Python cvision and returns the image natively
Emu 影像工作台 for DeepSeek Harness — 多供应商生图/改图/模型可用性探测 + Emu 独家 opencode 许愿 Agent
把长文本渲染成图片发送来压缩 LLM 输入 token(DeepSeek 视觉模型、每图 384 token 封顶)— text-as-image token compression for DeepSeek Harness
Custom background image for the DeepSeek Harness web UI (theme token overlay + settings card)
DSH plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default, and automatically route requests that carry image content to a configured vision-capable model (deepseek-v4-flash-vision-exp) 鈥?no manual model switching (periscope).
Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images
DeepSeek Harness 视觉理解插件:把用户消息与工具结果中的图片翻译成文字描述,交给纯文本任务模型(如 DeepSeek)。