Brand Ingestion

app/infrastructure/settings.py

@@ -316,6 +316,37 @@ BRAND_SYNC_INTERVAL_SECONDS = int(os.getenv("BRAND_SYNC_INTERVAL_SECONDS", "300"
 # See app/services/active_brands.py.
 ACTIVE_BRANDS = os.getenv("ACTIVE_BRANDS", "")
 
+# ---------------------------------------------------------------------------
+# Brand discovery (brand name -> the 11-stage pipeline)
+# ---------------------------------------------------------------------------
+# Discovery turns a brand NAME into rows the ordinary catalog pipeline ingests.
+# See app/services/brand_discovery.py. Every value below has a working default,
+# so the feature needs no configuration to run.
+#
+# Open Food Facts is the primary source and the language model is the
+# supplement, not the reverse: OFF returns real products carrying a real GTIN,
+# while the default OLLAMA_MODEL_NAME (qwen2.5:1.5b) invents plausible ones that
+# nothing downstream can catch. Turning BRAND_DISCOVERY_USE_OFF off leaves the
+# result resting on the model alone.
+BRAND_DISCOVERY_USE_OFF = _bool("BRAND_DISCOVERY_USE_OFF", "true")
+BRAND_DISCOVERY_USE_LLM = _bool("BRAND_DISCOVERY_USE_LLM", "true")
+
+# Products per discovery run. One CSV row per product; pack-size explosion
+# happens later in stage 4, so this is well inside the 2000-row per-file cap.
+BRAND_DISCOVERY_MAX_PRODUCTS = int(os.getenv("BRAND_DISCOVERY_MAX_PRODUCTS", "200"))
+
+# Pack sizes kept per product when only the language model offers any. Stage 6
+# runs an image search per exploded row, so this multiplies the slowest part of
+# the run; 3 keeps a large brand inside a sane wall-clock.
+BRAND_DISCOVERY_MAX_SIZES = int(os.getenv("BRAND_DISCOVERY_MAX_SIZES", "3"))
+
+# Wall-clock ceiling on the LLM half of a run, checked between prompts. Open
+# Food Facts runs first and is never subject to it, so a run that hits this
+# still returns the evidence-backed products.
+BRAND_DISCOVERY_DEADLINE_SECONDS = float(
+    os.getenv("BRAND_DISCOVERY_DEADLINE_SECONDS", "300")
+)
+
 # ---------------------------------------------------------------------------
 # S3 / DigitalOcean Spaces (product image storage) - optional
 # ---------------------------------------------------------------------------