Give DeepSeek Harness agents native image reading
zcXie777/dsh-image-reader · model-adapters
Give DeepSeek Harness agents native image reading: a readimage tool backed by any OpenAI-compatible vision endpoint.
★ 2GitHub stars
0Forks
2026-08-24Last updated
TypeScriptLanguage
MITLicense
Key features
- Not yet verifieda real end-to-end read against a live vision endpoint.
- Inputs resolve against the workspace and allowedDirs through realpath, so a symlink cannot escape the fence.
- The request/response logic is covered by a mocked-fetch unit test, but the plugin has not been smoke-tested inside a running dsh profile against a real multimodal model.
- Do that once with a real VISION_API_KEY before relying on it.
- Images are size-limited and extension-checked before upload.
Install command
dsh plugin --profile web add github:zcXie777/dsh-image-reader