Brand Discovery-LLM Updates

app/infrastructure/settings.py

@@ -347,6 +347,25 @@ BRAND_DISCOVERY_DEADLINE_SECONDS = float(
     os.getenv("BRAND_DISCOVERY_DEADLINE_SECONDS", "300")
 )
 
+# Web & retail listing discovery (app/services/web_discovery/) - the optional
+# Brand Discovery source for brands Open Food Facts does not carry. It reads
+# ONLY search-engine results (title, URL, snippet) that point at Indian
+# retailers' product pages; it never fetches a retailer page and never asks a
+# language model. A product is kept only when a real listing names the brand
+# and states a pack size. Off in a request unless the admin ticks it.
+WEB_DISCOVERY_ENABLED = _bool("WEB_DISCOVERY_ENABLED", "true")
+# Searches per brand job. A parent brand fans out to its sub-brands (Reckitt ->
+# Dettol, Harpic, Lizol, ...) times the retailers, so this is the cost ceiling.
+WEB_DISCOVERY_MAX_QUERIES = int(os.getenv("WEB_DISCOVERY_MAX_QUERIES", "80"))
+# Seconds between two LIVE searches (cached ones are free). DuckDuckGo throttles
+# a burst; a throttled search is "could not ask", never "nothing found".
+WEB_DISCOVERY_PAUSE_SECONDS = float(os.getenv("WEB_DISCOVERY_PAUSE_SECONDS", "2.0"))
+WEB_DISCOVERY_RESULTS_PER_QUERY = int(os.getenv("WEB_DISCOVERY_RESULTS_PER_QUERY", "20"))
+# How long a search answer is reused. An EMPTY answer is kept one day only:
+# search reach is unstable, and a flaky empty page must not become a week-long fact.
+WEB_DISCOVERY_CACHE_DAYS = float(os.getenv("WEB_DISCOVERY_CACHE_DAYS", "7"))
+WEB_DISCOVERY_DIR = _dir("WEB_DISCOVERY_DIR", DATA_DIR / "cache" / "web_discovery")
+
 # ---------------------------------------------------------------------------
 # S3 / DigitalOcean Spaces (product image storage) - optional
 # ---------------------------------------------------------------------------