feat(token-tracking): add Token usage section to summary.md

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

rag_eval/reporting/summary.py

@@ -35,6 +35,23 @@ def _table_from_frame(frame: pd.DataFrame) -> str:
     return "\n".join([header, separator, *body])
 
 
+def _token_usage_section(token_usage: dict[str, dict[str, int]]) -> list[str]:
+    """Render the '## Token 用量' section as a list of markdown lines."""
+    lines = ["", "## Token 用量", ""]
+    if not token_usage:
+        lines.append("未记录 token 用量。")
+        return lines
+    lines.append("| 模型 | input_tokens | output_tokens | 调用次数 |")
+    lines.append("|---|---|---|---|")
+    for model in sorted(token_usage):
+        usage = token_usage[model]
+        lines.append(
+            f"| {model} | {usage.get('input_tokens', 0)} "
+            f"| {usage.get('output_tokens', 0)} | {usage.get('calls', 0)} |"
+        )
+    return lines
+
+
 def build_summary_markdown(result: EvaluationResult) -> str:
     """Build the human-readable markdown summary written for each evaluation run."""
     total = len(result.valid_samples) + len(result.invalid_samples)
@@ -57,6 +74,7 @@ def build_summary_markdown(result: EvaluationResult) -> str:
 
     if scores.empty:
         lines.append("No valid samples were scored.")
+        lines.extend(_token_usage_section(result.token_usage))
         return "\n".join(lines) + "\n"
 
     score_rows_list = scores.to_dict(orient="records")
@@ -97,4 +115,5 @@ def build_summary_markdown(result: EvaluationResult) -> str:
         _table_from_frame(detail),
         "```",
     ])
+    lines.extend(_token_usage_section(result.token_usage))
     return "\n".join(lines) + "\n"