visail/dsh-vision-tool

README 摘要

dsh-vision-tool Image routing for text-only models in DeepSeek Harness (DSH). Text-only models (e.g. deepseek-v4-flash ) cannot see images. This bundle gives them eyes in two coordinated steps: 1. vision-prompt — shadows POST /api/session.prompt . When the active session model does not support image input, pasted images are persisted as content-addressed attachments and rewritten in place into text prompts that carry the full attachment reference JSON. Any other request (no image, or a model that already supports images) is forwarded unchanged , with the official /api trust fence (DNS rebinding / cross-site defense) reimplemented. 2. vision-tool — registers a global analyze image tool. The model calls it with the attachment reference (or a local file path ); the tool routes the image to a vision model and returns its text answer. Verified end-to-end: paste an image → attachment persisted → model calls analyze image → vision model describes the image. Install Requires the dsh CLI (see package and install a plugin). The bundle's cordis.patch.yml inserts two rows: vision-tool and vision-prompt . Restart the profile afterwards: Verify the layer landed without booting: Configuration Cre…

分类