dsh-local-vision
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
274 results
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
Let DeepSeek-V4-Pro (text-only) use V4-Flash-Vision-Exp for attached images. Mac/Windows/Linux.
DSH 视觉桥接插件:让无视觉能力的主模型看图(会话收图 + 自动转文字 + view_image 工具)
DSH plugin: prompt the agent to dispatch image recognition to an opencode-go mimo-v2.5 subagent
Eight DeepSeek Harness plugins: persona, language guard, vision fallback, python workdir guard, windows encoding guard, cross-agent memory, image generation, and skill shell injection.
DSH-native vision bridge for text-only models with native image attachments, multi-image evidence batching, and session-scoped validated Evidence caching.
Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.
Gives a text-only LLM vision capability
Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.
Popper: a falsification-driven correction loop for agent sessions — claim commitment, gate falsification, and mutually exclusive hypothesis revision, with an append-only evidence ledger
DSH agent tools: slice a large image into labeled tiles (size or columns x rows) with an overview and a visual workbench; read_tiles selects only what the vision model needs.
DeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
OmniVision for DeepSeek Harness: an OmniParser-powered GUI agent plugin — screen capture, element recognition, click/type automation and a browser vision dock with recognition history, diffing and summary
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.
Transparent image preprocessing route for DeepSeek Harness
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 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。
DeepSeek Harness 原生插件:让纯文本模型(如 DeepSeek)经 agent/pre-step 劫持 + resolveModelInfo 包装自动识别上传图片(qwen-vl),使纯文本对话也能“看见”图片。
DSH 视觉插件(Edge 豆包桥接):通用识图 + 数学建模图专项(几何图形/流程图/图表/表格/公式)+ 不确定项澄清闭环。零成本,免 API Key。
Image routing for text-only models in DeepSeek Harness: a global analyze_image tool (Kimi vision) plus automatic rewriting of pasted images into attachment references when the active model cannot see images.
为 dsh-tool-vision 桥接导出的图片提供对话内联预览:用户粘贴的图片在气泡中显示缩略图,不改变桥接文本与模型行为
Remote SSH workspace and closed-loop deployment Agent for DeepSeek Harness: SSH Files, terminal, remote editing, zero-to-one Bootstrap, Runbooks, automation, Vision/OCR and safe recovery.
DSH plugin: a persistent, per-session Python interpreter provisioned with Biomni's biomedical tool library, plus a Settings section that reports what the interpreter can actually do.