OCR de imagenes con Mistral: ImageProcessor (png/jpg/webp/gif/bmp/tiff), modelo mistral-ocr-latest y recuperacion de fuentes unknown

backend/app/managers/knowledge_manager.py

@@ -378,6 +378,18 @@ class KnowledgeManager:
             raise ValueError("Fuente no encontrada")
         return dict(row)
 
+    def refresh_source_type(self, source_id: int) -> str:
+        """Recalcula y persiste el tipo de una fuente guardada como ``unknown``.
+
+        Permite reprocesar archivos subidos antes de soportar su formato
+        (por ejemplo, imagenes que quedaron como ``unknown`` y fallaban).
+        """
+        source = self.get_source(source_id)
+        source_type = self.detect_source_type(Path(source["stored_path"]))
+        with self._connect() as conn:
+            conn.execute("update sources set source_type = ? where id = ?", (source_type, source_id))
+        return source_type
+
     def list_sources(self, subject_id: int, week_number: int) -> list[dict[str, Any]]:
         week = self.get_week(subject_id, week_number)
         with self._connect() as conn:
@@ -552,6 +564,8 @@ class KnowledgeManager:
             return "docx"
         if ext == "pdf":
             return "pdf"
+        if ext in {"png", "jpg", "jpeg", "webp", "gif", "bmp", "tif", "tiff"}:
+            return "image"
         if ext in {"mp3", "wav", "m4a", "ogg", "flac", "webm"}:
             return "audio"
         if ext in {"mp4", "mov", "mkv", "avi"}: