Extract shared build_metric_registry factory (DRY)

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

rag_eval/metrics/factory.py

@@ -57,6 +57,39 @@ def _resolve_openai_client_kwargs(
     return settings.openai_client_kwargs
 
 
+def resolve_openai_client_kwargs(
+    judge_model: str,
+    settings: EvaluationSettings,
+) -> dict[str, Any]:
+    """Public accessor for profile-aware AsyncOpenAI kwargs (matched by judge_model).
+
+    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
+    the scoring pipeline, instead of duplicating the lookup logic.
+    """
+    return _resolve_openai_client_kwargs(judge_model, settings)
+
+
+def build_metric_registry(llm: Any, embeddings: Any) -> dict[str, Any]:
+    """Instantiate the full set of supported RAGAS metrics keyed by canonical name.
+
+    Shared by the scenario pipeline, the inline scorer, and the prompt-cache
+    bootstrap so the metric set is defined in exactly one place.
+    """
+    return {
+        "faithfulness": Faithfulness(llm=llm),
+        "answer_relevancy": AnswerRelevancy(llm=llm, embeddings=embeddings),
+        "context_recall": ContextRecall(llm=llm),
+        "context_precision": ContextPrecision(llm=llm),
+        # NoiseSensitivity mode='relevant': sensitivity to noise from relevant contexts.
+        "noise_sensitivity": NoiseSensitivity(llm=llm),
+        # FactualCorrectness mode='f1': balances claim precision and recall vs. ground truth.
+        "factual_correctness": FactualCorrectness(llm=llm),
+        # SemanticSimilarity: embedding cosine between answer and ground truth (no LLM call).
+        "semantic_similarity": SemanticSimilarity(embeddings=embeddings),
+    }
+
+
 def build_models(
     judge_model: str,
     embedding_model: str,
@@ -98,20 +131,8 @@ def build_metric_pipeline(
             settings,
         )
 
-    # Build the full registry once, then slice it by configured metric names.
-    registry: dict[str, Any] = {
-        "faithfulness": Faithfulness(llm=llm),
-        "answer_relevancy": AnswerRelevancy(llm=llm, embeddings=embeddings),
-        "context_recall": ContextRecall(llm=llm),
-        "context_precision": ContextPrecision(llm=llm),
-        # Robustness / end-to-end metrics (架构设计 §10.2).
-        # NoiseSensitivity mode='relevant': sensitivity to noise from relevant contexts.
-        "noise_sensitivity": NoiseSensitivity(llm=llm),
-        # FactualCorrectness mode='f1': balances claim precision and recall vs. ground truth.
-        "factual_correctness": FactualCorrectness(llm=llm),
-        # SemanticSimilarity: embedding cosine between answer and ground truth (no LLM call).
-        "semantic_similarity": SemanticSimilarity(embeddings=embeddings),
-    }
+    # Build the full registry once using the shared factory, then slice by requested metrics.
+    registry = build_metric_registry(llm, embeddings)
     return MetricPipeline(
         metrics={name: registry[name] for name in scenario.metrics},
         metric_timeout_seconds=settings.ragas_metric_timeout_seconds,