teknium1 ef5d811aba fix: vision auto-detection now falls back to custom/local endpoints ...

Vision auto-mode previously only tried OpenRouter, Nous, and Codex
for multimodal — deliberately skipping custom endpoints with the
assumption they 'may not handle vision input.' This caused silent
failures for users running local multimodal models (Qwen-VL, LLaVA,
Pixtral, etc.) without any cloud API keys.

Now custom endpoints are tried as a last resort in auto mode. If the
model doesn't support vision, the API call fails gracefully — but
users with local vision models no longer need to manually set
auxiliary.vision.provider: main in config.yaml.

Reported by @Spadav and @kotyKD.

2026-03-09 15:36:19 -07:00

19 KiB

Raw Blame History

View Raw