mirror of
https://github.com/Routstr/routstr-core.git
synced 2026-10-06 04:38:22 +00:00
The generic provider computed modality as "text->text" for any vision model and "text" otherwise, discarding the source's own modality and mislabelling image-capable models. Carry OpenRouter's modality string through verbatim, and when a source doesn't supply one, derive it from the captured input/output modalities in the same "in->out" shape (e.g. "text+image->text"). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>