Backend catalog recent updates

app/infrastructure/settings.py

@@ -385,6 +385,37 @@ BARCODE_LOOKUP_CACHE_TTL_SECONDS = float(os.getenv("BARCODE_LOOKUP_CACHE_TTL_SEC
 BARCODE_LOOKUP_MAX_CONCURRENCY = int(os.getenv("BARCODE_LOOKUP_MAX_CONCURRENCY", "5"))
 BARCODE_COUNTRY_TAG = os.getenv("BARCODE_COUNTRY_TAG", "india")
 
+# How similar a candidate's product name must be to ours before its barcode is
+# believed. Applies to BOTH directions: looking a barcode up from a name, and
+# looking a product up from a barcode.
+#
+# RAISED FROM matching.py's OWN 0.45 DEFAULT, ON EVIDENCE. That default is a
+# reasonable general floor, but by the time a candidate reaches this gate its
+# brand and pack size have ALREADY been matched - so the name is the only thing
+# left doing any discriminating, and it has to carry the whole decision.
+#
+# At 0.45 it did not. Scored across every catalogue barcode Open Food Facts
+# knows, more than half the accepted matches were a different product:
+#
+#     floor   accepted   wrong
+#      0.45         15       8
+#      0.70          7       2
+#      0.78          2       0
+#
+#     0.761  "Tata Tea Gold 500g"       -> "Tata Tea Gold Care"      different
+#     0.658  "MTR Masala 300g"          -> "MTR Chana Masala"        different
+#     0.538  "Aachi Chicken Masala 50g" -> "Chicken Kabab/65 Masala" different
+#     0.097  "Lion Dates Powder 100g"   -> "PEPER NOTEN"             different
+#
+# 0.78 is where the sample is clean, NOT where the yield is good, and it is a
+# judgement rather than a separation: two products tie at 0.773 with opposite
+# verdicts. It is set for precision because a WRONG barcode is worse than no
+# barcode - it is an identifier other systems join on, and 33 of the 95 already
+# in the catalogue are wrong, all of them accepted at the old floor.
+#
+# Lower it only with the yield/error numbers in front of you.
+BARCODE_MIN_NAME_SIMILARITY = float(os.getenv("BARCODE_MIN_NAME_SIMILARITY", "0.78"))
+
 # Optional barcode source credentials. Each source disables itself when its
 # key is blank, so leaving these unset simply narrows the lookup cascade.
 GS1_INDIA_API_BASE_URL = os.getenv("GS1_INDIA_API_BASE_URL", "")