feat(thumb-backfill): _thumb_is_valid helper — JPEG/PNG magic-byte check on the on-disk thumbnail file

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/app/tasks/thumbnail.py

@@ -17,6 +17,30 @@ from ._sync_engine import sync_session_factory as _sync_session_factory
 
 IMAGES_ROOT = Path("/images")
 
+THUMB_MAGIC_JPEG = b"\xff\xd8\xff"
+THUMB_MAGIC_PNG = b"\x89PNG\r\n\x1a\n"
+
+
+def _thumb_is_valid(path: Path) -> bool:
+    """Return True iff `path` exists and starts with a JPEG or PNG magic header.
+
+    The on-disk thumbnail format is set by services/thumbnailer.py — JPEG for
+    opaque sources, PNG for alpha sources. Anything else (missing file, OSError,
+    truncated, wrong magic) is invalid.
+    """
+    try:
+        with path.open("rb") as f:
+            head = f.read(12)
+    except OSError:
+        return False
+    if len(head) < 8:
+        return False
+    if head[:3] == THUMB_MAGIC_JPEG:
+        return True
+    if head[:8] == THUMB_MAGIC_PNG:
+        return True
+    return False
+
 
 @celery.task(
     name="backend.app.tasks.thumbnail.generate_thumbnail",

tests/test_backfill_thumbnails.py

@@ -0,0 +1,35 @@
+"""Thumbnail backfill: _thumb_is_valid helper + backfill_thumbnails planner."""
+
+import pytest
+
+from backend.app.tasks.thumbnail import _thumb_is_valid
+
+pytestmark = pytest.mark.integration
+
+
+def test_thumb_is_valid_jpeg(tmp_path):
+    p = tmp_path / "good.jpg"
+    p.write_bytes(b"\xff\xd8\xff\xe0" + b"\x00" * 100)
+    assert _thumb_is_valid(p) is True
+
+
+def test_thumb_is_valid_png(tmp_path):
+    p = tmp_path / "good.png"
+    p.write_bytes(b"\x89PNG\r\n\x1a\n" + b"\x00" * 100)
+    assert _thumb_is_valid(p) is True
+
+
+def test_thumb_is_valid_too_short(tmp_path):
+    p = tmp_path / "tiny"
+    p.write_bytes(b"\xff\xd8")
+    assert _thumb_is_valid(p) is False
+
+
+def test_thumb_is_valid_wrong_magic(tmp_path):
+    p = tmp_path / "garbage"
+    p.write_bytes(b"\x00" * 12)
+    assert _thumb_is_valid(p) is False
+
+
+def test_thumb_is_valid_missing_file(tmp_path):
+    assert _thumb_is_valid(tmp_path / "nope") is False