[Bug]: Model with Vision Support not recognized as image-capable in OpenHands #9750
Description
Is there an existing issue for the same bug? (If one exists, thumbs up or comment on the issue instead).
- I have checked the existing issues.
Describe the bug and reproduction steps
Description
I’m using OpenHands together with LM Studio to serve the model bartowski/mistralai_Devstral-Small-2505-GGUF.
This model is supposed to support vision input (image support) according to its description.
Problem:
When I upload an image in the OpenHands chat input, I get the following error message:
It seems OpenHands does not detect that the model supports image input.
OpenHands Installation
Docker command in README
OpenHands Version
main
Model Name
bartowski/mistralai_Devstral-Small-2505-GGUF
Operating System
None
Logs, Errors, Screenshots, and Additional Context
No response