feat: add Van's real baseline lane and stop size tokens naming products

Two review findings, both confirmed by measurement.

1. The evaluator had no always-argmax lane, so every "vs Van" claim compared
   against the *gated* matcher, which is not Van's contract - the original demo
   answered every crop with its best-scoring SKU and had no accept line. The new
   'van' lane is that contract: same scores, no gate. Against it the local lane
   wins both axes at both resolutions (full 61%/77% vs 52%/29%; live 59%/95% vs
   57%/32%), but the live coverage margin is one facing, not seven, and the 95%
   figure is live-resolution only - at full resolution the same lane reads 77%
   with 11 false accepts and a hub alarm.

2. A crop reading only "400g" scored 0.667 on three SKUs, above TEXT_ACCEPT, so
   the text lane named a product from a size line. The fill-in job now requires
   two non-digit bigrams; the veto is unchanged, so "65%" still contradicts a
   local answer. The raw OCR read travels with the ranking through
   score_crop_lanes for that check.

Tests: 3 for the size gate (policy + live) and the van lane's own row. Removing
the gate fails all three. Suite 276 -> 280.

recognization/code/eval_identity.py

@@ -59,7 +59,7 @@ UNKNOWN = "unknown"
 # Two independent label passes disagreed here, so the row is not ground truth.
 # Scoring it would be scoring a coin flip.
 EXCLUDE = "exclude"
-LANES = ("local", "matcher", "gallery", "hybrid-verify")
+LANES = ("local", "matcher", "van", "gallery", "hybrid-verify")
 # A single SKU above this share of accepts is the failure the last audit found:
 # every dark package collapsing onto one enrolled product.
 HUB_SHARE = 0.30
@@ -307,6 +307,40 @@ class MatcherLane(Lane):
         return sorted(group_by_sku(scores).items(), key=lambda kv: kv[1], reverse=True)
 
 
+class VanLane(MatcherLane):
+    """Van's contract: the matcher's top SKU, always answered.
+
+    The `matcher` lane applies `decide_identity`, which is not what the original
+    demo did - it answered every crop with its best-scoring SKU and had no
+    accept line at all. Comparing the new system against the gated matcher
+    understates the baseline's coverage and overstates its precision, so the
+    completion gate's "Van" row is this lane: same scores, no gate.
+    """
+
+    name = "van"
+
+    def decide(self, crop: Any, ranked: List[Tuple[str, float]], *, accept: float,
+               margin: float, scale: str) -> Dict[str, Any]:
+        from identity import IDENTITY_ACCEPTED
+
+        if not ranked:
+            return {
+                "status": IDENTITY_ACCEPTED, "method": self.name, "best_sku": None,
+                "score": 0.0, "confidence": 0.0, "identity_level": IDENTITY_ACCEPTED,
+                "ranked_candidates": [], "details": {}, "message": "no candidate",
+                "source": None,
+            }
+        best, score = ranked[0]
+        return {
+            "status": IDENTITY_ACCEPTED, "method": self.name, "best_sku": best,
+            "score": round(float(score), 2), "confidence": round(float(score), 4),
+            "identity_level": IDENTITY_ACCEPTED,
+            "ranked_candidates": [{"sku_id": sku, "score": round(float(v), 2)}
+                                  for sku, v in ranked[:5]],
+            "details": {}, "message": "Always-argmax baseline", "source": "van",
+        }
+
+
 class LocalLaneAdapter(Lane):
     """The shipped default: RootSIFT pyramid plus the OCR text lane.
 
@@ -333,11 +367,12 @@ class LocalLaneAdapter(Lane):
                margin: float, scale: str) -> Dict[str, Any]:
         from identity_lanes import DecisionPolicy
 
+        read = self.text_lane.read(crop)
         text_rank = sorted(
-            self.text_lane.scores_from_text(self.text_lane.read(crop)).items(),
+            self.text_lane.scores_from_text(read).items(),
             key=lambda kv: kv[1], reverse=True,
         )
-        return DecisionPolicy(local_accept=accept).decide(ranked, text_rank)
+        return DecisionPolicy(local_accept=accept).decide(ranked, text_rank, text_read=read)
 
 
 def _catalog_rows(stock_dir: str) -> List[Dict[str, Any]]:
@@ -571,8 +606,10 @@ def main() -> int:
     unenrolled = Counter(f["label"] for f in held if f["label"] != UNKNOWN and f["label"] not in enrolled_skus)
 
     lanes: Dict[str, Lane] = {}
-    if "matcher" in wanted or "hybrid-verify" in wanted:
+    if "matcher" in wanted or "hybrid-verify" in wanted or "van" in wanted:
         lanes["matcher"] = MatcherLane(args.stock_dir)
+    if "van" in wanted:
+        lanes["van"] = VanLane(args.stock_dir)
     if "local" in wanted:
         lanes["local"] = LocalLaneAdapter(args.stock_dir)
     if "gallery" in wanted or "hybrid-verify" in wanted: