Skip to content

open-webui: make lemonade vision smoke robust - #682

Open
lucbruni-amd wants to merge 1 commit into
mainfrom
ci-fix-openwebui-vision-smoke
Open

open-webui: make lemonade vision smoke robust#682
lucbruni-amd wants to merge 1 commit into
mainfrom
ci-fix-openwebui-vision-smoke

Conversation

@lucbruni-amd

Copy link
Copy Markdown
Collaborator

The openwebui-lemonade-multimodal-smoke vision request sent a 1x1 pixel to Qwen3.5-4B-GGUF (a reasoning model) with max_tokens: 256. The model spends the whole budget in reasoning_content deliberating over the degenerate image (finish_reason: length) and never emits content, so the test fails with "Vision returned empty content".

Fix: send a small real 8x8 PNG instead of a 1x1 pixel, and raise max_tokens to 512 so it has room to emit content. Applied to both Windows device variants and Linux.

Refs #669, #670, #673.

The vision smoke sent a 1x1 pixel with max_tokens=256; the reasoning model
spent the whole budget deliberating over the degenerate image
(finish_reason=length) and returned empty content. Use a small real 8x8 PNG
and raise max_tokens to 512. Applies to both Windows device variants and Linux.

Refs #669, #670, #673.
@lucbruni-amd
lucbruni-amd requested review from sreeram-11 and a lite review from Copilot August 7, 2026 20:00

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Warning

Copilot couldn't run its full agentic review because it didn't start before the timeout. Make sure your repository has a runner available, or add a copilot-code-review.yml file specifying one with the runs-on attribute. See the docs for more details.

Improves reliability of the Open WebUI vision smoke test by avoiding a degenerate 1×1 image that can consume the model’s reasoning token budget without producing visible content.

Changes:

  • Replace the 1×1 base64 PNG with a small 8×8 PNG in PowerShell and Python examples.
  • Increase max_tokens from 256 to 512 for the vision request across Windows and Linux variants.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread playbooks/supplemental/open-webui-chat/README.md
})
temperature = 0
max_tokens = 256
max_tokens = 512
Comment thread playbooks/supplemental/open-webui-chat/README.md
Comment thread playbooks/supplemental/open-webui-chat/README.md
Comment thread playbooks/supplemental/open-webui-chat/README.md
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.

2 participants