Fu3rte/dsh-sight

README excerpt

dsh-sight Plug-in vision for text-only DeepSeek Harness (dsh) models — paste an image, get a text description through a built-in VLM backend, no model switching. 中文版 → README.zh-CN.md Features - Built-in VLM presets — OpenCode Zen (free, keyless) and Gemini Flash (free tier), plus a custom mode for any OpenAI-compatible endpoint. Pick one in the web settings page, done. - Multi-image batch — the vision tool takes up to 10 paths/URLs and describes all of them in ONE request, labeled per image. How it works 1. Prompt-admission override — dsh refuses image pastes for text-only models. dsh-sight wraps apiProxy.sessions.prompt : the paste is accepted, the bytes land in /tmp/dsh-sight/image{N}/{hash}.png , and the image block becomes a path hint before entering history. Works with any provider — no model variant to switch. 2. vision tool — the model calls it with the hint path (or any local path / http(s) URL); the plugin reads the bytes and answers through the configured OpenAI-compatible VLM backend. 3. System-prompt section — teaches the model the hint → vision tool flow. 4. Web settings page (Settings → Vision) — backend source (preset or custom endpoint), an effective-config preview…

Category