Add INFO/DEBUG logging to factory: log resolved base_url per model

build_models now logs: judge=<model>-><url> embedding=<model>-><url>

Makes it easy to confirm which gateway is actually used for each model.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

rag_eval/metrics/factory.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import logging
 from typing import Any
 
 from openai import AsyncOpenAI
@@ -28,14 +29,17 @@ from .judge_prompts import localize_pipeline_prompts
 from .pipeline import MetricPipeline
 
 
+logger = logging.getLogger("rag_eval.metrics.factory")
+
+
 def _resolve_openai_client_kwargs(
-    judge_model: str,
+    model: str,
     settings: EvaluationSettings,
 ) -> dict[str, Any]:
     """Return AsyncOpenAI kwargs, preferring a matching LLM Profile over .env settings.
 
     Lookup order:
-      1. LLM Profile whose model name equals judge_model (exact match)
+      1. LLM Profile whose model name equals `model` (exact match)
       2. Fall back to EvaluationSettings (.env)
     """
     try:
@@ -43,26 +47,35 @@ def _resolve_openai_client_kwargs(
         from webapp.services.profile_manager import profile_manager
         profiles = profile_manager.list_all()
         for profile in profiles:
-            if profile.model == judge_model:
+            if profile.model == model:
                 kwargs: dict[str, Any] = {
                     "api_key": profile.api_key or "sk-placeholder",
                     "timeout": float(profile.timeout_seconds or 30),
                 }
                 if profile.base_url and profile.base_url.strip():
                     kwargs["base_url"] = profile.base_url.strip()
+                logger.debug(
+                    "[factory] model=%s  source=profile  base_url=%s",
+                    model, kwargs.get("base_url", "(not set, using default)")
+                )
                 return kwargs
-    except Exception:  # noqa: BLE001
+    except Exception as exc:  # noqa: BLE001
         # If profile lookup fails for any reason, fall through to .env settings.
-        pass
+        logger.warning("[factory] profile lookup failed for model=%s: %s", model, exc)
 
-    return settings.openai_client_kwargs
+    fallback = settings.openai_client_kwargs
+    logger.debug(
+        "[factory] model=%s  source=env  base_url=%s",
+        model, fallback.get("base_url", "(not set)")
+    )
+    return fallback
 
 
 def resolve_openai_client_kwargs(
     judge_model: str,
     settings: EvaluationSettings,
 ) -> dict[str, Any]:
-    """Public accessor for profile-aware AsyncOpenAI kwargs (matched by judge_model).
+    """Public accessor for profile-aware AsyncOpenAI kwargs (matched by model name).
 
     Exposed so other components (e.g. the optimization advisor's direct LLM call)
     can build a client that honors the same saved-profile/.env resolution used by
@@ -106,6 +119,12 @@ def build_models(
     llm_kwargs = _resolve_openai_client_kwargs(judge_model, settings)
     emb_kwargs = _resolve_openai_client_kwargs(embedding_model, settings)
 
+    logger.info(
+        "[factory] build_models  judge=%s→%s  embedding=%s→%s",
+        judge_model, llm_kwargs.get("base_url", "(env default)"),
+        embedding_model, emb_kwargs.get("base_url", "(env default)"),
+    )
+
     llm_client = AsyncOpenAI(**llm_kwargs)
     # Only allocate a second client when the embedding model needs different settings.
     emb_client = AsyncOpenAI(**emb_kwargs) if emb_kwargs != llm_kwargs else llm_client