From 4bb1952348dadd087ebb32542257b5f69bcbcee2 Mon Sep 17 00:00:00 2001
From: wangwei <Wei.Wang@t-systems.com>
Date: Thu, 2 Jul 2026 15:14:11 +0800
Subject: [PATCH] feat(token-tracking): surface token_usage in ReportData

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 tests/test_report_builder_token_usage.py | 55 ++++++++++++++++++++++++
 webapp/models.py                         |  4 ++
 webapp/services/report_builder.py        |  6 ++-
 3 files changed, 64 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_report_builder_token_usage.py

diff --git a/tests/test_report_builder_token_usage.py b/tests/test_report_builder_token_usage.py
new file mode 100644
index 0000000..6e8a08f
--- /dev/null
+++ b/tests/test_report_builder_token_usage.py
@@ -0,0 +1,55 @@
+"""Tests for token_usage passthrough in the webapp report builder."""
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+from webapp.services.report_builder import build_report
+
+
+def _write_minimal_run(run_dir: Path, token_usage: dict | None) -> None:
+    run_dir.mkdir(parents=True, exist_ok=True)
+    (run_dir / "scores.csv").write_text(
+        "sample_id,faithfulness\ns1,0.9\n", encoding="utf-8"
+    )
+    (run_dir / "summary.md").write_text("summary", encoding="utf-8")
+    metadata = {"run_id": run_dir.name}
+    if token_usage is not None:
+        metadata["token_usage"] = token_usage
+    (run_dir / "metadata.json").write_text(json.dumps(metadata), encoding="utf-8")
+
+
+def test_build_report_passes_through_token_usage(tmp_path: Path) -> None:
+    run_dir = tmp_path / "run"
+    _write_minimal_run(
+        run_dir,
+        token_usage={"gpt-5": {"input_tokens": 100, "output_tokens": 50, "calls": 2}},
+    )
+
+    report = build_report(run_dir, ["faithfulness"])
+
+    assert report.token_usage == {
+        "gpt-5": {"input_tokens": 100, "output_tokens": 50, "calls": 2}
+    }
+
+
+def test_build_report_defaults_token_usage_to_empty_dict(tmp_path: Path) -> None:
+    run_dir = tmp_path / "run"
+    _write_minimal_run(run_dir, token_usage=None)
+
+    report = build_report(run_dir, ["faithfulness"])
+
+    assert report.token_usage == {}
+
+
+def test_build_report_early_return_branch_still_surfaces_token_usage(tmp_path: Path) -> None:
+    """metrics=[] forces the early-return branch; token_usage must still surface."""
+    run_dir = tmp_path / "run"
+    _write_minimal_run(
+        run_dir,
+        token_usage={"gpt-5": {"input_tokens": 5, "output_tokens": 5, "calls": 1}},
+    )
+
+    report = build_report(run_dir, [])
+
+    assert report.token_usage == {"gpt-5": {"input_tokens": 5, "output_tokens": 5, "calls": 1}}
diff --git a/webapp/models.py b/webapp/models.py
index 8fb7737..fe25208 100644
--- a/webapp/models.py
+++ b/webapp/models.py
@@ -99,6 +99,10 @@ class ReportData(BaseModel):
         default_factory=dict,
         description="该次运行使用的文档权重配置（来自 scenario.snapshot.yaml）。",
     )
+    token_usage: dict[str, dict[str, int]] = Field(
+        default_factory=dict,
+        description="按模型累计的 token 用量：{model: {input_tokens, output_tokens, calls}}。",
+    )
 
 
 class RunDetail(BaseModel):
diff --git a/webapp/services/report_builder.py b/webapp/services/report_builder.py
index 989fb55..887dac8 100644
--- a/webapp/services/report_builder.py
+++ b/webapp/services/report_builder.py
@@ -187,6 +187,9 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
     summary_markdown = run_reader.read_summary_markdown(run_dir)
     advice_markdown = run_reader.read_advice_markdown(run_dir)
     metric_weights, doc_weights = _read_weights_from_snapshot(run_dir)
+    # Read once up front so both the empty-frame and full branches can surface it.
+    metadata = run_reader._read_json(run_dir / "metadata.json")
+    token_usage = metadata.get("token_usage") or {}
 
     if frame.empty or not metrics:
         return ReportData(
@@ -196,6 +199,7 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
             advice_markdown=advice_markdown,
             metric_weights=metric_weights,
             doc_weights=doc_weights,
+            token_usage=token_usage,
         )
 
     score_rows_list = frame.to_dict(orient="records")
@@ -218,7 +222,6 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
 
     # Cross-run history: scores of the same question in *other* runs (Approach A —
     # on-demand global scan, excluding the run currently being viewed).
-    metadata = run_reader._read_json(run_dir / "metadata.json")
     current_run_id = str(metadata.get("run_id") or run_dir.name)
     history_index = question_history.build_question_history_index(
         exclude_run_id=current_run_id
@@ -235,4 +238,5 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
         weighted_score_mean=_round_or_none(overall_ws),
         metric_weights=metric_weights,
         doc_weights=doc_weights,
+        token_usage=token_usage,
     )