feat: add weighted_score and sample_weight columns to score rows

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

rag_eval/execution/evaluator.py

@@ -12,6 +12,7 @@ from rag_eval.datasets.loader import load_dataset_records
 from rag_eval.datasets.normalizers import normalize_records
 from rag_eval.execution.concurrency import gather_with_limit
 from rag_eval.metrics.pipeline import MetricPipeline
+from rag_eval.metrics.weights import compute_weighted_score, resolve_weight
 from rag_eval.shared.models import EvaluationResult, InvalidSample, NormalizedSample, Scenario
 from rag_eval.shared.utils import utc_now_iso
 
@@ -171,7 +172,7 @@ class Evaluator:
         return valid, invalid
 
     def _merge_score(self, sample: NormalizedSample, score: Any) -> dict[str, Any]:
-        """Combine sample data, metric results, and run metadata into one output row."""
+        """Combine sample data, metric results, run metadata, and weight columns."""
         record = sample.to_record()
         record["contexts"] = sample.contexts
         record.update(score.metrics)
@@ -179,4 +180,12 @@ class Evaluator:
         record["judge_model"] = self.scenario.judge_model
         record["embedding_model"] = self.scenario.embedding_model
         record["run_id"] = self.scenario.scenario_name
+        # Weighted score columns — enable post-hoc weighted aggregation in reporting.
+        record["weighted_score"] = compute_weighted_score(
+            score.metrics, self.scenario.metric_weights
+        )
+        doc_name = str(sample.metadata.get("doc_name", "") or "")
+        record["sample_weight"] = resolve_weight(
+            self.scenario.doc_weights, doc_name, default=1.0
+        )
         return record