fix: vision tasks inherit user_id, admin owns mount root

- detect_objects, classify_content, recluster_faces now look up the
  photo's user_id and set it on created Tag rows — fixes tags being
  invisible to the owning user due to NULL user_id
- Initial admin setup creates source root at the mount root (/photos)
  instead of a subdirectory, since the admin owns the entire library
- Revert to OpenCLIP ViT-B/32 (512-d) as default embedder — SigLIP
  requires transformers version alignment not yet available in the
  Docker image. SigLIP2 code remains for future enablement.
- Add transformers to requirements for future SigLIP support

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/app/services/vision/bootstrap_models.py

@@ -29,8 +29,6 @@ DOWNLOADS = []
 EXPORTS = [
     ("embed/visual.onnx", "OpenCLIP ViT-B/32 visual encoder"),
     ("embed/textual.onnx", "OpenCLIP ViT-B/32 textual encoder"),
-    ("embed_siglip2/visual.onnx", "SigLIP2 ViT-B/16 visual encoder"),
-    ("embed_siglip2/textual.onnx", "SigLIP2 ViT-B/16 textual encoder"),
     ("detect/yolov8n.onnx", "YOLOv8n object detector"),
 ]
 

backend/app/services/vision/classify.py

@@ -63,7 +63,7 @@ class CLIPContentClassifier(ContentClassifier):
         # image embeddings.
         embedder_name = settings.embedder.name
         if embedder_name.startswith("siglip2"):
-            model_arch = "ViT-B-16-SigLIP2"
+            model_arch = "ViT-B-16-SigLIP-384"
             pretrained = "webli"
         else:
             model_arch = "ViT-B-32"

backend/app/services/vision/embed.py

@@ -129,7 +129,7 @@ class SigLIP2Embedder(Embedder):
 
     def embed_text(self, text: str) -> np.ndarray:
         import open_clip
-        tokenizer = open_clip.get_tokenizer("ViT-B-16-SigLIP2")
+        tokenizer = open_clip.get_tokenizer("ViT-B-16-SigLIP-384")
         tokens = tokenizer([text]).numpy().astype(np.int64)
         inputs = self._textual.get_inputs()
         feed = {inputs[0].name: tokens}

backend/app/services/vision/export_models.py

@@ -135,9 +135,9 @@ def export_siglip2(models_dir: Path):
         logger.info("SigLIP2 ONNX files already exist, skipping export")
         return
 
-    logger.info("Loading SigLIP2 ViT-B-16-SigLIP2 webli...")
+    logger.info("Loading SigLIP2 ViT-B-16-SigLIP-384 webli...")
     model, _, preprocess = open_clip.create_model_and_transforms(
-        "ViT-B-16-SigLIP2", pretrained="webli"
+        "ViT-B-16-SigLIP-384", pretrained="webli"
     )
     model.eval()
 
@@ -162,7 +162,7 @@ def export_siglip2(models_dir: Path):
     # ── Textual encoder ───────────────────────────────────────────────
     if not textual_path.exists():
         logger.info("Exporting SigLIP2 textual encoder → %s", textual_path)
-        tokenizer = open_clip.get_tokenizer("ViT-B-16-SigLIP2")
+        tokenizer = open_clip.get_tokenizer("ViT-B-16-SigLIP-384")
         dummy_text = tokenizer(["a photo"]).to(torch.int64)
 
         class SigLIP2TextEncoder(torch.nn.Module):