YZz-S/dsh-modlens

README excerpt

dsh-modlens English · 中文 A fork of liustack/modlens — the vision plugin for DeepSeek Harness (dsh) — with multi-engine support and per-call engine selection. 这是 liustack/modlens 的 分支 ——DeepSeek Harness（dsh）的视觉插件，支持多引擎与按调用选择引擎。 English 中文 · ← Back to DeepSeekHarnessPlugins Plug-in vision for text-only LLMs. ModLens converts an image into structured JSON evidence (OCR, layout, semantics) so a text-only model can "see". This fork keeps all upstream behavior and adds: - provider argument on modlens read image — pin the vision engine per call ( -p passthrough). - "Ask which engine" behavior — the tool description instructs the model to ask the user which engine to use whenever more than one is configured. - Doubao / Volcengine Ark recipe — a tested setup for doubao-seed-2.1-turbo via the Ark ark-coding-plan endpoint (OpenAI-compatible), alongside Gemini, Anthropic, and Claude Code. Why a fork Upstream ModLens is under active development. This fork carries the provider passthrough and the doubao/ark recipe until they land upstream. Prefer upstream for everything else: . Install (DeepSeek Harness) Restart dsh, then look for the (modlens vision) model entries and the modlens read image too…

Category