OoWJZZoO/dsh-read-image

README 摘要

dsh-read-image 简体中文 Plug-and-play image reading for text-only DeepSeek Harness models: pasted images are admitted, projected as [Image N] , and read back through a first-class read image tool backed by a configurable vision model — no preset changes required. A DeepSeek Harness plugin that lets non-multimodal models "see" images . - Pasted images are no longer rejected — text-only routes are declared to accept image input, so the api-proxy admission gate lets them through. - [Image N] projection — on text-only routes, image blocks in the model request are replaced in place with [Image N] text; pixels never reach a text API. Native multimodal routes pass through untouched. - First-class read image tool (registered automatically in every session, shadowing the built-in tool of the same name): - image index — read the Nth image in the conversation ( [Image N] ); - file path — read an image file from a path (PNG/JPEG/WebP/GIF); - prompt / reasoning effort / timeout ms / max tokens / max thinking tokens — optional overrides; omitted parameters use the configured defaults (the current real defaults are interpolated into the tool description, so the agent never has to guess); - on text-on…

分类