[ModelScope] Custom Provider with Qwen Model Cannot Recognize Images - "Image Input Not Supported" #15040

Activity

1. github-actions

   assigned

   rekram1-node

   on Feb 25, 2026
2. github-actions

   added

   acp

   coreAnything pertaining to core functionality of the application (opencode server stuff)Anything pertaining to core functionality of the application (opencode server stuff)

   on Feb 25, 2026
3. github-actions commented on Feb 25, 2026

   

   github-actionsBot

   on Feb 25, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • [DOCS] Missing documentation for modalities property in custom provider configuration #9897: Documents the modalities property that enables image/vision input for custom OpenAI-compatible providers — this is likely the solution to your problem. Try adding "modalities": { "input": ["text", "image"], "output": ["text"] } to your model config.
   • Z.AI GLM-4.7 cannot read images from Read tool (model supports vision) #13310: Same symptom ("this model does not support image input") with a custom/OpenAI-compatible provider whose model actually supports vision.
   • [FEATURE]: Add supportsAttachments/vision capability for custom providers #8875: Feature request (now closed) for adding vision capability support to custom providers — same root cause.

   👍React with 👍1Reacted by Daniel Schöni
4. github-actions commented on Apr 27, 2026

   

   github-actionsBot

   on Apr 27, 2026 – with GitHub Actions

   Contributor

   More actions

   To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.
5. github-actions

   closed this as not plannedon Apr 27, 2026