Skip to content

v2026.03.04.3

Choose a tag to compare

@elophanto elophanto released this 04 Mar 17:28
· 510 commits to main since this release

Hotfix: Vision model proxy for screenshots

Problem: Non-vision planning models (e.g. glm-4.7) received raw base64 image_url content from both desktop and browser screenshots, causing Z.ai 400 errors and uncontrolled fallback to Sonnet.

Fix: All screenshots (desktop + browser) are now routed through the configured browser.vision_model (e.g. google/gemini-3-flash-preview) for text descriptions before reaching the planning model. The planning model only sees concise text descriptions, never raw images.

  • Desktop desktop_screenshot results: base64 stripped, replaced with desktop_description text
  • Browser EKO auto-screenshots: vision model describes page state, injected as plain text
  • Legacy raw image injection preserved as fallback when no vision model is configured