feat: support image inputs in assistant tests

backend/services/image_processing.py

@@ -0,0 +1,41 @@
+"""Shared validation and normalization for user-supplied images."""
+
+from __future__ import annotations
+
+from io import BytesIO
+
+from PIL import Image, ImageOps, UnidentifiedImageError
+
+import settings
+
+
+def normalize_image(data: bytes) -> tuple[bytes, int, int]:
+    """Return a bounded, orientation-corrected JPEG safe for model input."""
+
+    try:
+        source = Image.open(BytesIO(data))
+        width, height = source.size
+        if width <= 0 or height <= 0:
+            raise ValueError("图片尺寸无效")
+        if width * height > settings.INPUT_IMAGE_MAX_PIXELS:
+            raise ValueError("图片像素尺寸过大")
+        source.load()
+    except (UnidentifiedImageError, OSError) as exc:
+        raise ValueError("文件不是可识别的图片") from exc
+
+    image = ImageOps.exif_transpose(source)
+    image.thumbnail(
+        (settings.INPUT_IMAGE_MAX_EDGE, settings.INPUT_IMAGE_MAX_EDGE),
+        Image.Resampling.LANCZOS,
+    )
+    if image.mode in {"RGBA", "LA"} or "transparency" in image.info:
+        rgba = image.convert("RGBA")
+        background = Image.new("RGB", rgba.size, "white")
+        background.paste(rgba, mask=rgba.getchannel("A"))
+        image = background
+    else:
+        image = image.convert("RGB")
+
+    buffer = BytesIO()
+    image.save(buffer, format="JPEG", quality=85, optimize=True)
+    return buffer.getvalue(), image.width, image.height