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

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

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"] == {}