updates on catalog search and suggestions in backend

app/infrastructure/settings.py

@@ -357,3 +357,24 @@ RAG_MAX_CONTEXT_CHARS = int(os.getenv("RAG_MAX_CONTEXT_CHARS", "4000"))
 # if you want an extra cutoff on top of that.
 _raw_max_distance = os.getenv("RAG_MAX_DISTANCE", "").strip()
 RAG_MAX_DISTANCE = float(_raw_max_distance) if _raw_max_distance else None
+
+# ---------------------------------------------------------------------------
+# Catalog search (GET /api/search) and suggest (GET /api/suggest)
+# ---------------------------------------------------------------------------
+# Deliberately separate from RAG_MAX_TOP_K above. That ceiling exists to protect
+# the LLM prompt budget in /api/chat, and raising it would degrade every chat
+# answer. /api/search feeds a product grid, which has no such budget - sharing
+# the constant is what silently truncated every brand search to 15 products.
+SEARCH_DEFAULT_TOP_K = int(os.getenv("SEARCH_DEFAULT_TOP_K", "60"))
+# Mirrors the browse endpoints' le=100000 so a brand search can return exactly
+# the same set as GET /api/brands/{brand}/products.
+SEARCH_MAX_TOP_K = int(os.getenv("SEARCH_MAX_TOP_K", "100000"))
+# Separate, much smaller ceiling for the hybrid path: semantic_search multiplies
+# top_k by 5 per brand table when a category/price filter is present, and every
+# read does SELECT * (which drags the vector(384) embedding column over the wire).
+SEARCH_HYBRID_MAX_TOP_K = int(os.getenv("SEARCH_HYBRID_MAX_TOP_K", "100"))
+SEARCH_LEXICAL_CANDIDATES = int(os.getenv("SEARCH_LEXICAL_CANDIDATES", "200"))
+
+SUGGEST_DEFAULT_LIMIT = int(os.getenv("SUGGEST_DEFAULT_LIMIT", "8"))
+SUGGEST_MIN_QUERY_LEN = int(os.getenv("SUGGEST_MIN_QUERY_LEN", "2"))
+SUGGEST_FUZZY_MIN_RATIO = float(os.getenv("SUGGEST_FUZZY_MIN_RATIO", "0.72"))