refactor: strip AI pipeline to binary photo/other classifier

Drops face recognition, OCR, object detection, and semantic embeddings.
The sole remaining vision task is a CLIP-based binary classifier
(photography vs other); photos in "other" get needs_review=true so
screenshots, documents, memes and scans can be triaged from a new
filter pill in the UI.

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

mulita.yml

@@ -23,30 +23,12 @@ performance:
   db_pool_size: 20
   db_pool_recycle: 3600
 
-# AI vision pipeline — embedding, OCR, object detection, face recognition.
-# Runs on the dedicated `vision` Celery queue (PR4+). Set enabled: false
-# to disable all vision processing.
+# Vision pipeline — single binary classifier (photography vs other).
+# Photos landing in 'other' get needs_review=true.
 vision:
   enabled: true
-  backend: onnx            # "onnx" (CPU) | "rocm" (future GPU)
+  backend: onnx
   models_dir: /data/models
-  embedder:
-    name: openclip_vitb32
-    batch_size: 8
-  ocr:
-    enabled: true
-    languages: [en]
-    min_confidence: 0.5
-  detector:
-    enabled: true
-    min_confidence: 0.35
-    max_detections: 50
-  faces:
-    enabled: true
-    min_face_size: 40
-    recognition_threshold: 0.65
-    cluster_eps: 0.5
   classifier:
-    enabled: true
     min_confidence: 0.3
   worker_concurrency: 2