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

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

docs/superpowers/plans/2026-07-02-token-usage-tracking.md

@@ -1190,7 +1190,7 @@ def test_run_writes_token_usage_to_metadata(tmp_path, monkeypatch):
         return {m: 0.9 for m in kwargs["metrics"]}
 
     monkeypatch.setattr(
-        "webapp.services.score_job_manager.inline_scorer.score", _fake_score
+        "webapp.services.inline_scorer.inline_scorer.score", _fake_score
     )
 
     request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
@@ -1216,7 +1216,7 @@ def test_run_writes_empty_token_usage_when_nothing_recorded(tmp_path, monkeypatc
         return {m: 0.9 for m in kwargs["metrics"]}
 
     monkeypatch.setattr(
-        "webapp.services.score_job_manager.inline_scorer.score", _fake_score
+        "webapp.services.inline_scorer.inline_scorer.score", _fake_score
     )
 
     request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
@@ -1399,7 +1399,7 @@ def test_session_accumulates_token_usage_across_calls(tmp_path, monkeypatch):
         return {m: 0.9 for m in kwargs["metrics"]}
 
     monkeypatch.setattr(
-        "webapp.services.session_score_manager.inline_scorer.score", _fake_score
+        "webapp.services.inline_scorer.inline_scorer.score", _fake_score
     )
 
     request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
@@ -1432,7 +1432,7 @@ def test_session_first_call_writes_token_usage_from_scratch(tmp_path, monkeypatc
         return {m: 0.9 for m in kwargs["metrics"]}
 
     monkeypatch.setattr(
-        "webapp.services.session_score_manager.inline_scorer.score", _fake_score
+        "webapp.services.inline_scorer.inline_scorer.score", _fake_score
     )
 
     request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])

tests/webapp/test_score_job_manager_token_usage.py

@@ -0,0 +1,73 @@
+"""Tests that /api/score/async persists token usage captured during scoring."""
+from __future__ import annotations
+
+import json
+import time
+
+from webapp.models import ScoreRequest
+from webapp.services.score_job_manager import ScoreJobManager
+
+
+def _wait_for_status(mgr: ScoreJobManager, job_id: str, timeout: float = 2.0):
+    deadline = time.monotonic() + timeout
+    while time.monotonic() < deadline:
+        status = mgr.get(job_id)
+        if status is not None and status.status in ("completed", "failed"):
+            return status
+        time.sleep(0.02)
+    raise TimeoutError(f"job {job_id} did not complete in time")
+
+
+def test_run_writes_token_usage_to_metadata(tmp_path, monkeypatch):
+    """_run() wraps inline_scorer.score in track_token_usage and persists totals."""
+    from rag_eval.metrics.token_tracker import get_current_tracker
+
+    mgr = ScoreJobManager(
+        output_dir=tmp_path / "score-async",
+        index_dir=tmp_path / "score-jobs",
+        max_workers=1,
+    )
+
+    def _fake_score(**kwargs):
+        tracker = get_current_tracker()
+        if tracker is not None:
+            tracker.record("gpt-5", 120, 45)
+        return {m: 0.9 for m in kwargs["metrics"]}
+
+    monkeypatch.setattr(
+        "webapp.services.inline_scorer.inline_scorer.score", _fake_score
+    )
+
+    request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
+    status = mgr.submit(request)
+    final_status = _wait_for_status(mgr, status.job_id)
+
+    assert final_status.status == "completed"
+    run_dir = tmp_path / "score-async" / final_status.run_id
+    metadata = json.loads((run_dir / "metadata.json").read_text(encoding="utf-8"))
+    assert metadata["token_usage"] == {
+        "gpt-5": {"input_tokens": 120, "output_tokens": 45, "calls": 1}
+    }
+
+
+def test_run_writes_empty_token_usage_when_nothing_recorded(tmp_path, monkeypatch):
+    mgr = ScoreJobManager(
+        output_dir=tmp_path / "score-async",
+        index_dir=tmp_path / "score-jobs",
+        max_workers=1,
+    )
+
+    def _fake_score(**kwargs):
+        return {m: 0.9 for m in kwargs["metrics"]}
+
+    monkeypatch.setattr(
+        "webapp.services.inline_scorer.inline_scorer.score", _fake_score
+    )
+
+    request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
+    status = mgr.submit(request)
+    final_status = _wait_for_status(mgr, status.job_id)
+
+    run_dir = tmp_path / "score-async" / final_status.run_id
+    metadata = json.loads((run_dir / "metadata.json").read_text(encoding="utf-8"))
+    assert metadata["token_usage"] == {}

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)