Route pasted images to a cheap vision model in opencode so text-only main agents work from its text output.
Version 0.2.2, 28 weekly downloads, rank 684. Judged from its declared dependencies.
| @opencode-ai/plugin | ^1.18.34 |
|---|---|
| @opencode/plugin | ^2.0.22 |
[](https://rafal-one.github.io/opencode-v2-ready/p/opencode-vision-router.html)
It ships both implementations.