dsh-sensenova-vision-aid: Visual Assistance Plugin for DeepSeek Harness
The DeepSeek Harness (DSH) plugin `dsh-sensenova-vision-aid` is designed to address the inability of text-only models to receive image inputs. This plugin invokes SenseNova vision models in the background to convert images into text descriptions (such as `[Visual Observation: ...]`) for use by the main model, while the user interface continues to display the original images. Core features include a global silent image-reading bridge (supporting takeover, automatic, and disabled modes), an MCP-compatible global toolset, and a failover chain. After installation, the Profile must be restarted for the changes to take effect. It is recommended to use this plugin together with `dsh-sensenova-freeapi` to leverage its credential reuse and secure storage mechanisms, enabling efficient image-text collaboration.
Read Moredsh-minimal-vision: On-Demand Visual Assistance in DSH Minimal Mode
dsh-minimal-vision is a DSH community plugin designed to address the pain point of lacking visual evidence support in minimal mode. It is maintained by Flora233333, licensed under MIT, and requires Node >=20. The plugin enables on-demand visual capabilities by concealing context and Bash calls to `dsh-vision` without registering new chat models or modifying the system prompt, exposing only `persistent-bash` and `str_replace_editor` to the model. It supports processing images in PNG, JPEG, WebP, and GIF formats, as well as documents such as PDF, DOC, and PPT. Images are processed using `sharp` before being sent to the vision interface, while documents are handled by Agen.
Read More