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

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-07-02 14:45:58 +08:00
parent 29e76d021c
commit b50b911de0
3 changed files with 79 additions and 0 deletions
@@ -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)