Silent vision bridge for DeepSeek Harness
1HelloMan1/dsh-vision-fallback · model-adapters
Silent vision bridge for DeepSeek Harness: route chat images to a fixed vision model, preserve UI originals, and reuse observations across compaction and restarts.
★ 2GitHub stars
0Forks
2026-09-03Last updated
JavaScriptLanguage
MITLicense
Key features
- DeepSeek V4 Flash / Pro and other strong coding models are text-only: dropping an image into the chat box fails with "model does not support image input".
- MCP / ACP durable attachments are read by attachmentId, not temporary file paths
- The config route is loopback-only and same-origin checked
- Modelmimo-v2.5 · Endpoint: · Credential: OPENCODE_GO_API_KEY
- Existing "vision tool" plugins require saving images as files and invoking a see_image(path) tool — clunky, and the main model still can't see chat attachments.
Requirements
- Verified on 2026-09-03 with Node.js 24.16.0 and a separate disposable DSH_HOME for each release
- The Profile operations use the official CLI with plugin --profile web add -w and remove -w dsh-vision-fallback.
Install command
dsh plugin --profile web add github:1HelloMan1/dsh-vision-fallback