feat(token-tracking): accumulate token usage across session_async calls

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

webapp/services/session_score_manager.py

@@ -193,6 +193,7 @@ class SessionScoreJobManager:
 
         # Lazy imports — 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
@@ -215,20 +216,21 @@ class SessionScoreJobManager:
 
         try:
             # --- Scoring (can run concurrently for the same session) ----------
-            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()
@@ -250,6 +252,14 @@ class SessionScoreJobManager:
                 run_dir = self._output_dir / run_id
                 run_dir.mkdir(parents=True, exist_ok=True)
 
+                # Merge this call's token usage into the session's running total, so
+                # repeated calls accumulate instead of overwriting (mirrors the
+                # scores.csv append-only accumulation below).
+                existing_metadata = self._read_metadata(run_dir)
+                merged_token_usage = usage_tracker.merge_into(
+                    existing_metadata.get("token_usage", {})
+                )
+
                 # Read all existing rows, then append the new one
                 existing_rows = self._read_score_rows(run_dir)
                 call_number = len(existing_rows) + 1
@@ -312,6 +322,7 @@ class SessionScoreJobManager:
                     valid_samples=valid_samples,
                     invalid_samples=[],
                     score_rows=all_rows,
+                    token_usage=merged_token_usage,
                 )
 
                 write_run_artifacts(result)
@@ -376,6 +387,16 @@ class SessionScoreJobManager:
         except (OSError, ValueError):
             return []
 
+    def _read_metadata(self, run_dir: Path) -> dict[str, Any]:
+        """Read this session's existing metadata.json, returning {} if absent/unreadable."""
+        metadata_path = run_dir / "metadata.json"
+        if not metadata_path.is_file():
+            return {}
+        try:
+            return json.loads(metadata_path.read_text(encoding="utf-8"))
+        except (OSError, ValueError):
+            return {}
+
     def _read_metric_means(self, run_dir: Path) -> dict[str, float | None]:
         """Compute per-metric means from the session's scores.csv."""
         scores_path = run_dir / "scores.csv"