feat: add recommendation service adapters

backend/app/config.py

@@ -41,6 +41,8 @@ class Settings(BaseSettings):
     llm_model: str = "claude-sonnet-5"
     intent_effort: str = "low"
     rerank_effort: str = "medium"
+    intent_max_tokens: int = 8192
+    rerank_max_tokens: int = 4096
 
     # Pipeline shape. candidate_count is the main call-1 latency lever and
     # the hallucination budget: at "new to you" familiarity a large share of