@eric.wen/dsh-sight: DSH Multimodal Image Direct Upload and Figma MCP Plugin
The DSH plugin `@eric.wen/dsh-sight` aims to address specific issues in multimodal dialogue, primarily offering four core functions. First is direct multimodal image upload, allowing users to paste or drag images into the input box to send them to supported multimodal models as native content blocks. Second, it features session image clearing, which removes images from the model's visible history. This resolves the issue of being unable to switch back to text-only models caused by historical images, and this operation is persistent. Third, the automatic inference level completion feature automatically populates official supported tiers for third-party models without declared reasoning levels based on an internal dictionary, optimizing configuration. Finally, through the Figma MCP bridge, it supports two modes: converting design drafts to code using Figma Tokens and REST API, or implementing AI-driven design via a local bridge without requiring Figma membership. The plugin is distributed via npm.
Read Moredsh-sight: Plug-and-Play Visual Capabilities for Text-Only DSH Models
dsh-sight is an MIT-licensed plugin designed for DSH (DeepSeek Harness) text-only models, aiming to endow them with image understanding capabilities through a built-in VLM backend. By wrapping the prompt admission process, the plugin automatically saves pasted images as local-path prompts and allows the model to invoke the `vision` tool. This tool supports passing in up to 10 local paths or URLs at a time, with the backend VLM generating individually annotated text descriptions. The plugin offers free presets such as `opencode-zen` and `gemini-flash`, and also supports connecting to any OpenAI-compatible endpoint. Users can configure it via the web settings page or environment variables (which take precedence over the configuration file), and it supports
Read More