feat: a live path that uses the enrolled store, and a demo server a phone can reach

The live session scored crops with the matcher regardless of the configured identity
backend, so a live scan used the old mechanism while the still path used the enrolled
gallery - measured, the matcher accepts look-alikes and cannot say "unknown", which is
exactly what a real shelf needs it to do. score_crop now routes to the gallery, and
the decision uses a similarity scale (accept at 0.60 with a 0.04 margin) rather than
inlier-count thresholds that mean nothing on a cosine.

The synthetic walk is gone: demo.py, demo_replay.py, the /v1/demo endpoints and the
walk benchmark are deleted, and the app's frame source is the camera on a device (the
single-image replay stays for the simulator, which has no camera).

stock-demo merges both demo shelves (27 products, 62 views, trained head) so one
server recognises either image, and run-demo-server.sh starts it bound to 0.0.0.0 and
prints the exact URL to put in Config.xcconfig.

Verified over the LAN with 1280x960 frames: 40 frames in 5.3s, 9 products recognised
on demo image 1.

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

recognization/code/identity.py

@@ -25,6 +25,13 @@ def relative_confidence(top_score: float, runner_up_score: float) -> float:
     return round(min(1.0, top_score / max(1.0, (top_score + runner_up_score * 0.5))), 4)
 
 
+# The gallery's scale is a cosine similarity, where same-product pairs sit above 0.6
+# and different products below 0.5 - not an inlier count, which has no such meaning.
+COSINE_ACCEPT = 0.60
+COSINE_AMBIGUOUS = 0.50
+COSINE_MARGIN = 0.04
+
+
 def decide_identity(
     scores: Dict[str, float],
     *,
@@ -33,6 +40,7 @@ def decide_identity(
     min_confidence: float = DEFAULT_MIN_CONFIDENCE,
     details: Optional[Dict[str, Any]] = None,
     method: str = "hybrid",
+    scale: str = "inlier",
 ) -> Dict[str, Any]:
     """Rank catalog scores into accepted / ambiguous / unknown / rejected.
 
@@ -56,6 +64,30 @@ def decide_identity(
     sorted_candidates: List[Tuple[str, float]] = sorted(
         scores.items(), key=lambda x: x[1], reverse=True
     )
+    if scale == "cosine":
+        # Thresholds that mean something on a similarity scale.
+        top_sku, top_score = sorted_candidates[0]
+        runner_score = sorted_candidates[1][1] if len(sorted_candidates) > 1 else 0.0
+        margin = top_score - runner_score
+        if top_score >= COSINE_ACCEPT and margin >= COSINE_MARGIN:
+            level = IDENTITY_ACCEPTED
+        elif top_score >= COSINE_AMBIGUOUS:
+            level = IDENTITY_AMBIGUOUS
+        else:
+            level = IDENTITY_REJECTED
+        return {
+            "status": level,
+            "method": method,
+            "best_sku": top_sku if level == IDENTITY_ACCEPTED else None,
+            "score": float(top_score),
+            "confidence": float(top_score),
+            "identity_level": level,
+            "ranked_candidates": [
+                {"sku_id": sku, "score": float(value)} for sku, value in sorted_candidates[:3]
+            ],
+            "details": details or {},
+            "message": None,
+        }
     top_sku, top_score = sorted_candidates[0]
     runner_up_sku, runner_up_score = (
         sorted_candidates[1] if len(sorted_candidates) > 1 else (None, 0.0)