[3.2.3] Update open-webui to 0.8.3 Full Changelog Model edit shortcut. Users can now edit models directly from the model selector dropdown menu, making it faster to modify model settings without navigating to separate admin or workspace pages. Commit Image edit API background support. The image edit API now supports the background parameter for OpenAI's gpt-image-1 model, enabling background transparency control ("transparent", "opaque", "auto") when the feature is exposed in the UI. #​21459 Faster model filtering. Model access control filtering no longer makes a redundant database query to re-fetch model info that is already available in memory, reducing latency when loading model lists for non-admin users. Commit Tool call display improvements. Tool call results now display arguments in a cleaner key-value format instead of raw JSON, with a responsive layout that shows only the tool name on narrow screens and the full label on wider screens, preventing text wrapping to multiple lines. Commit General improvements. Various improvements were implemented across the application to enhance performance, stability, and security. Translations for Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded. USER_EMAIL variable fix. The {{USER_EMAIL}} template variable now correctly returns the user's email address instead of "Unknown" in prompts. #​21479, #​21465 Image and file attachment handling fixes. Uploaded images are now correctly sent to vision-enabled models, and file attachments now work even when no user text is entered alongside a system prompt. This fixes two issues where the backend was not properly processing file attachments: images weren't converted to the expected format for API requests, and file context was dropped when the user sent only a file without accompanying text. Commit, #​21477, #​21457 Missing function error handling. Models that reference deleted functions no longer cause the entire /api/models endpoint to crash; instead, the missing functions are skipped and logged, allowing the rest of the models to load successfully. #​21476, #​21464 Startup model pre-fetch error handling. If model pre-fetching fails during app startup, the application now logs a warning and continues instead of crashing entirely. Commit