feat(token-tracking): capture token usage in /api/score/async job runs

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

webapp/services/score_job_manager.py

@@ -108,6 +108,7 @@ class ScoreJobManager:
 
         # Lazy imports to keep web server bootable if ragas is not installed.
         from rag_eval.advisor import run_advisor
+        from rag_eval.metrics.token_tracker import track_token_usage
         from rag_eval.metrics.weights import compute_weighted_score
         from rag_eval.reporting.writers import write_run_artifacts
         from rag_eval.settings import EvaluationSettings
@@ -130,20 +131,21 @@ class ScoreJobManager:
         started_at = utc_now_iso()
 
         try:
-            if effective:
-                raw_scores = inline_scorer.score(
-                    question=request.question,
-                    answer=request.answer,
-                    contexts=request.contexts_as_list(),
-                    ground_truth=request.ground_truth,
-                    metrics=effective,
-                    judge_model=judge_model,
-                    embedding_model=embedding_model,
-                    settings=settings,
-                    judge_language=judge_language,
-                )
-            else:
-                raw_scores = {}
+            with track_token_usage() as usage_tracker:
+                if effective:
+                    raw_scores = inline_scorer.score(
+                        question=request.question,
+                        answer=request.answer,
+                        contexts=request.contexts_as_list(),
+                        ground_truth=request.ground_truth,
+                        metrics=effective,
+                        judge_model=judge_model,
+                        embedding_model=embedding_model,
+                        settings=settings,
+                        judge_language=judge_language,
+                    )
+                else:
+                    raw_scores = {}
 
             latency_ms = int((time.monotonic() - t0) * 1000)
             finished_at = utc_now_iso()
@@ -201,6 +203,7 @@ class ScoreJobManager:
                 valid_samples=[sample],
                 invalid_samples=[],
                 score_rows=[score_row],
+                token_usage=usage_tracker.as_dict(),
             )
 
             write_run_artifacts(result)