feat(advisor-comparison): wire build_advisor_comparison into report_builder

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

tests/test_webapp_report_builder.py

@@ -2,11 +2,13 @@
 
 from __future__ import annotations
 
+import json
 from pathlib import Path
 
 import pandas as pd
 import pytest
 
+from webapp.models import AdvisorComparison, AdvisorComparisonEntry
 from webapp.services import question_history
 from webapp.services import report_builder
 from webapp.services.report_builder import build_report
@@ -186,3 +188,63 @@ def test_build_report_attaches_question_history(tmp_path: Path, monkeypatch) ->
     assert captured["exclude_run_id"] == "run"  # current run excluded from history
     assert report.lowest_samples[0].history[0].run_id == "older"
     assert report.lowest_samples[0].history[0].metrics["faithfulness"] == 0.95
+
+
+def test_build_report_attaches_advisor_comparison(tmp_path: Path, monkeypatch) -> None:
+    """build_report wires advisor_comparison.build_advisor_comparison() into ReportData."""
+    run_dir = tmp_path / "run"
+    _write_run_artifacts(run_dir)
+    (run_dir / "metadata.json").write_text(
+        json.dumps({"run_id": "run-1", "scenario_name": "my-scenario"}), encoding="utf-8"
+    )
+
+    fake_comparison = AdvisorComparison(
+        previous_run_id="prev-1",
+        previous_finished_at="2026-01-01T00:00:00+00:00",
+        entries=[
+            AdvisorComparisonEntry(
+                metric="faithfulness",
+                status="resolved",
+                previous_score=0.5,
+                previous_severity="warning",
+                current_score=None,
+                current_severity=None,
+            )
+        ],
+    )
+
+    captured_args = {}
+
+    def _fake_build(run_dir_arg, scenario_name_arg, metrics_arg):
+        captured_args["scenario_name"] = scenario_name_arg
+        captured_args["metrics"] = metrics_arg
+        return fake_comparison
+
+    monkeypatch.setattr(
+        report_builder.advisor_comparison, "build_advisor_comparison", _fake_build
+    )
+
+    report = build_report(run_dir, ["faithfulness", "context_recall"])
+
+    assert report.advisor_comparison == fake_comparison
+    assert captured_args["scenario_name"] == "my-scenario"
+    assert captured_args["metrics"] == ["faithfulness", "context_recall"]
+
+
+def test_build_report_advisor_comparison_none_when_no_previous_run(
+    tmp_path: Path, monkeypatch
+) -> None:
+    """build_report leaves advisor_comparison as None when no predecessor exists."""
+    run_dir = tmp_path / "run"
+    _write_run_artifacts(run_dir)
+    (run_dir / "metadata.json").write_text(
+        json.dumps({"run_id": "run-1", "scenario_name": "my-scenario"}), encoding="utf-8"
+    )
+
+    monkeypatch.setattr(
+        report_builder.advisor_comparison, "build_advisor_comparison", lambda *a, **k: None
+    )
+
+    report = build_report(run_dir, ["faithfulness", "context_recall"])
+
+    assert report.advisor_comparison is None

webapp/services/report_builder.py

@@ -26,7 +26,7 @@ from webapp.models import (
     SampleHistoryEntry,
     SampleScore,
 )
-from webapp.services import question_history, run_reader
+from webapp.services import advisor_comparison, question_history, run_reader
 
 
 # Number of equal-width buckets used for metric score histograms.
@@ -200,6 +200,7 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
             metric_weights=metric_weights,
             doc_weights=doc_weights,
             token_usage=token_usage,
+            advisor_comparison=None,
         )
 
     score_rows_list = frame.to_dict(orient="records")
@@ -227,6 +228,13 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
         exclude_run_id=current_run_id
     )
 
+    scenario_name = str(metadata.get("scenario_name") or "")
+    comparison = (
+        advisor_comparison.build_advisor_comparison(run_dir, scenario_name, metrics)
+        if scenario_name
+        else None
+    )
+
     return ReportData(
         metrics=metrics,
         metric_means=rounded_means,
@@ -239,4 +247,5 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
         metric_weights=metric_weights,
         doc_weights=doc_weights,
         token_usage=token_usage,
+        advisor_comparison=comparison,
     )