feat(token-tracking): add EvaluationResult.token_usage and persist to metadata.json

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

rag_eval/reporting/writers.py

@@ -45,6 +45,7 @@ def write_run_artifacts(result: EvaluationResult) -> None:
         "dataset": result.scenario.dataset.path.as_posix(),
         "valid_samples": len(result.valid_samples),
         "invalid_samples": len(result.invalid_samples),
+        "token_usage": result.token_usage,
     }
     artifact_paths.metadata_json.write_text(
         json.dumps(metadata, ensure_ascii=False, indent=2),

rag_eval/shared/models.py

@@ -153,6 +153,9 @@ class EvaluationResult:
     valid_samples: list[NormalizedSample]
     invalid_samples: list[InvalidSample]
     score_rows: list[dict[str, Any]]
+    # Token usage grouped by model name: {model: {input_tokens, output_tokens, calls}}.
+    # Populated by callers via rag_eval.metrics.token_tracker.track_token_usage().
+    token_usage: dict[str, dict[str, int]] = field(default_factory=dict)
 
 
 @dataclass(slots=True)