feat(token-tracking): wrap CLI evaluator metric scoring in track_token_usage

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.token_tracker import track_token_usage
 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
@@ -67,14 +68,16 @@ class Evaluator:
 
         logger.info("[eval] scoring %d samples with metric pipeline ...", len(samples))
         t0 = time.monotonic()
-        metric_scores = asyncio.run(
-            self.metric_pipeline.score_samples(
-                samples,
-                max_concurrency=self.scenario.runtime.metric_limit(),
+        with track_token_usage() as usage_tracker:
+            metric_scores = asyncio.run(
+                self.metric_pipeline.score_samples(
+                    samples,
+                    max_concurrency=self.scenario.runtime.metric_limit(),
+                )
             )
-        )
         elapsed = time.monotonic() - t0
         logger.info("[eval] metric scoring done  elapsed=%.1fs", elapsed)
+        logger.info("[eval] token_usage=%s", usage_tracker.as_dict())
 
         finished_at = utc_now_iso()
         score_rows = [self._merge_score(sample, score) for sample, score in zip(samples, metric_scores)]
@@ -99,6 +102,7 @@ class Evaluator:
             valid_samples=samples,
             invalid_samples=invalid_samples,
             score_rows=score_rows,
+            token_usage=usage_tracker.as_dict(),
         )
 
     async def _enrich_online_samples(