GooDAnDReaDY/dsh-vision-bridge

README 摘要

dsh-vision-bridge Vision bridge for DeepSeek Harness (dsh) — a self-contained replacement for dsh-vision-router . When the chat model has no vision (e.g. deepseek-v4-flash ) and a message contains an image, the image never reaches the text-only model. Instead, the plugin substitutes an automatic text description from the vision model you choose (Hermes-style). The text model just reads text and keeps the conversation going; the image stays in the session log and in the UI. - describe image — a tool for when you need more precise details on an image (ask a model). - Description cache by contentHash of the bytes — an image is described once, then the previous description is reused on later turns. - You pick the vision model in Settings → Vision (a top-level settings section alongside General / Models / Plugins). Install Restart the Web UI, open Settings → Vision , pick a provider and model (or leave empty — auto-picks the first vision-capable model). Replacing dsh-vision-router This does the same job but under your control and with your own vision model. If dsh-vision-router is installed, remove it: How it works (Hermes-style) 1. An image (from you or from a tool like generate image …

分类