Skip to content

feat(providers): curate Qwen3.8-Max-Preview as vision-capable - #492

Open
AliAltivate wants to merge 1 commit into
andrewyng:mainfrom
AliAltivate:fix/qwen38-vision
Open

feat(providers): curate Qwen3.8-Max-Preview as vision-capable#492
AliAltivate wants to merge 1 commit into
andrewyng:mainfrom
AliAltivate:fix/qwen38-vision

Conversation

@AliAltivate

Copy link
Copy Markdown

The qwen prefix heuristic in capabilities.py hardcodes vision=False, so Qwen3.8-Max-Preview — multimodal per Alibaba's model card — had its image attachments silently stripped before the request reached the model. A curated matrix entry restores vision and gives the GUI an accurate 1M-token context meter.

Fixes #401.

The qwen prefix heuristic in capabilities.py hardcodes vision=False, so
Qwen3.8-Max-Preview — multimodal per Alibaba's model card — had its image
attachments silently stripped. A curated matrix entry restores vision and
gives the GUI an accurate 1M-token context meter. Fixes andrewyng#401.
@AliAltivate

Copy link
Copy Markdown
Author

Hi — just a friendly ping on this one. It's a small fix with a test included; would appreciate a review whenever you get a chance.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Feature request: mark Qwen3.8-Max-Preview as vision-capable (currently stripped by the qwen heuristic)

1 participant