feat(attachments): scan enumerates all; import_file maps 'attached' + member ML

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

backend/app/tasks/import_file.py

@@ -26,11 +26,12 @@ IMAGES_ROOT = Path("/images")
 
 def _map_result_to_status(result):
     """(ImportTask.status, should_requeue_ml_and_thumb) for an ImportResult.
-    'superseded' = the kept row's file/ML changed → complete + re-derive."""
-    if result.status == "imported":
-        return ("complete", True)
-    if result.status == "superseded":
+    'superseded' = the kept row's file/ML changed → complete + re-derive.
+    'attached' = a non-art file preserved → complete, no ML/thumb."""
+    if result.status in ("imported", "superseded"):
         return ("complete", True)
+    if result.status == "attached":
+        return ("complete", False)
     if result.status == "skipped":
         return ("skipped", False)
     return ("failed", False)
@@ -82,6 +83,10 @@ def import_media_file(self, import_task_id: int) -> dict:
             task.result_image_id = result.image_id
             counter_col_name = "imported"
             counter_col = ImportBatch.imported
+        elif result.status == "attached":
+            task.status = "complete"
+            counter_col_name = "attachments"
+            counter_col = ImportBatch.attachments
         elif result.status == "skipped":
             task.status = "skipped"
             task.error = (
@@ -109,15 +114,16 @@ def import_media_file(self, import_task_id: int) -> dict:
 
         # Enqueue thumbnail + ML for newly imported AND superseded images
         # (a superseded row has cleared ML + no thumbnail).
-        if (
-            result.status in ("imported", "superseded")
-            and result.image_id is not None
-        ):
+        if result.status in ("imported", "superseded"):
             from .ml import tag_and_embed
             from .thumbnail import generate_thumbnail
 
-            generate_thumbnail.delay(result.image_id)
-            tag_and_embed.delay(result.image_id)
+            ids = list(result.member_image_ids)
+            if result.image_id is not None and result.image_id not in ids:
+                ids.append(result.image_id)
+            for img_id in ids:
+                generate_thumbnail.delay(img_id)
+                tag_and_embed.delay(img_id)
 
         # If this was the last task in the batch, mark the batch complete.
         remaining = session.execute(

backend/app/tasks/scan.py

@@ -11,7 +11,20 @@ from sqlalchemy.orm import sessionmaker
 from ..celery_app import celery
 from ..config import get_config
 from ..models import ImportBatch, ImportSettings, ImportTask
-from ..services.importer import is_supported
+
+
+def _iter_import_files(import_root: Path):
+    """Every regular file except sidecar .json, dotfiles, and .partial
+    temp files. The Importer dispatches by kind (media / archive /
+    other) — scan no longer filters to media (FC-2d-iii)."""
+    for entry in import_root.rglob("*"):
+        if not entry.is_file():
+            continue
+        if entry.name.startswith("."):
+            continue
+        if entry.suffix.lower() in (".json", ".partial"):
+            continue
+        yield entry
 
 
 def _sync_session_factory():
@@ -42,11 +55,7 @@ def scan_directory(self, triggered_by: str = "manual") -> int:
 
         # Walk and enumerate.
         files_seen = 0
-        for entry in import_root.rglob("*"):
-            if not entry.is_file():
-                continue
-            if not is_supported(entry):
-                continue
+        for entry in _iter_import_files(import_root):
             try:
                 size = entry.stat().st_size
             except OSError:

tests/test_import_file_attached.py

@@ -0,0 +1,24 @@
+"""FC-2d-iii: import_file maps 'attached' + enqueues ML for members."""
+
+import pytest
+
+from backend.app.services.importer import ImportResult
+from backend.app.tasks.import_file import _map_result_to_status
+
+pytestmark = pytest.mark.integration  # imports the celery app graph
+
+
+def test_attached_maps_to_complete_no_requeue():
+    status, requeue = _map_result_to_status(
+        ImportResult(status="attached")
+    )
+    assert status == "complete"
+    assert requeue is False
+
+
+def test_imported_still_requeues():
+    status, requeue = _map_result_to_status(
+        ImportResult(status="imported", image_id=5)
+    )
+    assert status == "complete"
+    assert requeue is True

tests/test_scan_enumerates_all.py

@@ -0,0 +1,20 @@
+"""FC-2d-iii: scan no longer filters to media-only."""
+
+import pytest
+
+pytestmark = pytest.mark.integration
+
+
+def test_scan_includes_non_media(tmp_path):
+    from backend.app.tasks import scan as scan_mod
+
+    root = tmp_path / "imp"
+    (root / "Alice").mkdir(parents=True)
+    (root / "Alice" / "pic.jpg").write_bytes(b"x")
+    (root / "Alice" / "pack.zip").write_bytes(b"x")
+    (root / "Alice" / "doc.pdf").write_bytes(b"x")
+    (root / "Alice" / "meta.json").write_text("{}")
+    (root / "Alice" / ".hidden").write_text("x")
+
+    seen = sorted(p.name for p in scan_mod._iter_import_files(root))
+    assert seen == ["doc.pdf", "pack.zip", "pic.jpg"]  # no json/dotfile