You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Clipboard images routed directly to model instead of MCP when model lacks vision support #18437
When a clipboard image is received and the current model does not support image input, opencode attempts to attach the image directly to the model and fails with:
ERROR: Cannot read "image.png" (this model does not support image input)
This happens before any agent code can intercept the image and route it to the minimax_search_understand_image MCP tool.
Expected Behavior
There should be a config option or automatic fallback to route clipboard images directly to the minimax_media MCP's minimax_search_understand_image tool instead of passing them to the language model.
Workaround (insufficient)
Adding AGENTS.md rules to intercept clipboard images doesn't help because opencode itself tries to attach the image to the model before agent code runs.
Suggested Fixes
Add a config option like imageInput: "mcp" to route images to MCP when model lacks vision
Add automatic MCP fallback when model doesn't support image attachments
Provide a way to disable native image attachment handling
[FEATURE]:opencode桌面版和CLI都不支持剪切板粘贴的图片调用图片识别的mcp #17771: opencode doesn't support routing clipboard-pasted images to image-recognition MCP tools — also describes clipboard images not being routed to MCP tools for non-vision models
Please review these issues and comment if yours is distinct. If it is a duplicate, consider closing this one and adding your details to the existing issue.
I encountered the same problem when using GLM-5, but I had deployed a separate NewAPI instance, forked it, and had NewAPI convert the incoming image into a URL. I also specified in AGENTS.MD that xxxMCP should be used for image understanding.
(The above was translated into English using Google Translate.)
Activity
github-actions commentedon Mar 20, 2026
This issue might be a duplicate of existing issues. Please check:
Please review these issues and comment if yours is distinct. If it is a duplicate, consider closing this one and adding your details to the existing issue.
zhongruan0522 commentedon Mar 21, 2026
I encountered the same problem when using GLM-5, but I had deployed a separate NewAPI instance, forked it, and had NewAPI convert the incoming image into a URL. I also specified in AGENTS.MD that xxxMCP should be used for image understanding.
(The above was translated into English using Google Translate.)
jensenojs commentedon Apr 3, 2026
same problem with mimo v2 pro + mimo omni
zhongruan0522 commentedon Apr 3, 2026
小米的不本来就是多模态吗
jensenojs commentedon Apr 7, 2026
Omni 是, 但 V2 pro并不是啊