feat: upgrade to SigLIP2 ViT-B/16 for semantic search

Replace OpenCLIP ViT-B/32 (512-d, ~78% recall) with SigLIP2 ViT-B/16
(768-d, ~84% recall) as the default embedding model for significantly
better image-text retrieval quality.

- New SigLIP2Embedder class with 384px input and SigLIP normalization
- ONNX export pipeline for SigLIP2 visual + textual encoders
- Migration 0010: resize embeddings.vector from 512 to 768 dimensions
- Config-driven model selection: "siglip2_vitb16" (default) or
  "openclip_vitb32" (legacy) — both models can coexist
- Content classifier follows the configured embedder family
- Existing embeddings cleared on migration; vision backfill regenerates

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

backend/app/services/vision/classify.py

@@ -57,14 +57,25 @@ class CLIPContentClassifier(ContentClassifier):
 
         self._min_confidence = settings.classifier.min_confidence
 
-        # Load native model for text encoding only
-        logger.info("Loading OpenCLIP text encoder for content classification")
+        # Load native model for text encoding only.
+        # Use whichever model family the embedder is configured for so
+        # the classification text vectors live in the same space as the
+        # image embeddings.
+        embedder_name = settings.embedder.name
+        if embedder_name.startswith("siglip2"):
+            model_arch = "ViT-B-16-SigLIP2"
+            pretrained = "webli"
+        else:
+            model_arch = "ViT-B-32"
+            pretrained = "laion2b_s34b_b79k"
+
+        logger.info("Loading %s text encoder for content classification", model_arch)
         model, _, _ = open_clip.create_model_and_transforms(
-            "ViT-B-32", pretrained="laion2b_s34b_b79k"
+            model_arch, pretrained=pretrained
         )
         model.eval()
         self._model = model
-        self._tokenizer = open_clip.get_tokenizer("ViT-B-32")
+        self._tokenizer = open_clip.get_tokenizer(model_arch)
 
         # Get the ONNX image embedder from the registry
         from app.services.vision.registry import registry