Zhou 1ced6e977c fix(backend): preserve viewed image reducer metadata (#1900) ... Fix concurrent viewed_images state updates for multi-image input by preserving the reducer metadata in the vision middleware state schema.		2026-04-06 16:47:19 +08:00
..
deerflow	fix(backend): preserve viewed image reducer metadata (#1900)	2026-04-06 16:47:19 +08:00
pyproject.toml	feat(uploads): add pymupdf4llm PDF converter with auto-fallback and async offload (#1727)	2026-04-03 21:59:45 +08:00