165 results
DSH Web UI model seat: 3-level quick slider (low/medium/high, each preconfigured with model + reasoning effort), advanced model/effort picker, modality icons, and per-provider usage/balance display. DSH 模型选择器增强：低中高三档快切滑块 + 高级选择 + 模态图标 + 供应商用量显示。
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).
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。
DeepSeek Harness (dsh) plugin: route one request to a modality-capable fallback model instead of forcing the whole session onto a single model.
DeepSeek balance & token-cost plugin for DeepSeek Harness (dual-face): query official balances of every DeepSeek provider (multi API key), compute costs (last question / session / today-project / today-all) from token usage with a user-editable price table. Unified modal UI, bilingual (zh/en)
Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.
OmniRoute model manager: searchable/filterable multi-select UI to control which OmniRoute models DSH uses, with modality discovery and OmniRoute-backed web search.
DeepSeek Harness web plugin: a Model Capabilities settings page for declaring model input modalities, context window, output cap and image budgets without hand-editing settings.yaml.
DSH 模型视觉开关：设置页「模型视觉」行，为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态（settings.mutate 官方通道，热生效）。
DeepSeek Harness plugin: analyse images out of band with a vision model — pasted images are digested into text before admission and a describe_image tool covers image paths, all without ever changing the session's model.
Give DeepSeek Harness agents eyes: local image analysis via vision models — um_analyze_img tool + model-capability recognition + hot-switch settings UI
Read-only in-conversation file preview for DeepSeek Harness: a session-authorized host Remote and a sanitizing browser modal, installed as one profile bundle.
DeepSeek Harness plugin: PDF→Word (.docx) conversion with layout fidelity (fonts/tables/images/borders), OCR scan mode, and optional multimodal LLM verification. Registers the pdf_to_word model tool.
Voice for DeepSeek Harness backed by Xiaomi MiMo: browser-native 🎤/🔊 UI (MiMo TTS read-aloud) + voice_transcribe/voice_speak calling MiMo ASR/TTS directly, with a configurable voice map and in-conversation speech strips. Fork of zhuiyueya/dsh-voice (MIT).
Add drag, eight-way resize, pin, maximize, backdrop controls, and persistent state to DeepSeek Harness web modals.
Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes
Zero-config local vision and realtime audio routing for DeepSeek Harness
DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with toggles, refresh, and a fill report.
Image translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.
DSH 文件适配插件（面向 DSH 0.1.2-alpha.1）：拖拽/粘贴/点击上传/@ 文件引用加入本地文件，以「文件：<路径>」引用随消息发出；主模型按需调用 dshomnifile 工具解析——文本多编码直读、Office/PDF 等文档由 anydoc 提文本、文档内嵌图片与扫描/图文混排 PDF 页由进程内 pdfjs 渲染 + 配置的多模态模型识别（内容哈希缓存 + 并发排队）并组装为 Markdown；聊天内文件卡片可预览图片、本地打开源文件；识别走官方 ctx.llm.stream。
TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus multimodal and async tools.
在 dsh 模型目录的每一行直接设置该模型的思考强度范围与支持的输入模态 (Per-model reasoning-effort range and accepted input modalities, right in the dsh Models catalog)
A vision bridge for text-only DeepSeek Harness models: registers an `analyze_image` tool that answers questions about images via ANY OpenAI-compatible vision/multimodal endpoint (SiliconFlow, DashScope, Zhipu, OpenRouter, Ollama, ...).
Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images