update for ragas

tests/test_metric_presenter.py

@@ -40,7 +40,14 @@ const result = {{
   desc: p.describeMetric("faithfulness"),
   noiseDesc: p.describeMetric("noise_sensitivity"),
   noiseBin: p.binColor("noise_sensitivity", 0.0),
-  faithBin: p.binColor("faithfulness", 0.8)
+  faithBin: p.binColor("faithfulness", 0.8),
+  lowerBetterNoise: p.isLowerBetter("noise_sensitivity"),
+  lowerBetterFaith: p.isLowerBetter("faithfulness"),
+  upHigher: p.deltaInfo("faithfulness", 0.80, 0.60),
+  downHigher: p.deltaInfo("faithfulness", 0.60, 0.80),
+  noiseImproved: p.deltaInfo("noise_sensitivity", 0.10, 0.30),
+  noiseWorse: p.deltaInfo("noise_sensitivity", 0.30, 0.10),
+  noBaseline: p.deltaInfo("faithfulness", 0.80, null)
 }};
 console.log(JSON.stringify(result));
 """
@@ -55,6 +62,15 @@ console.log(JSON.stringify(result));
     assert '"noiseDesc":"' in output
     assert '"noiseBin":"#16a34a"' in output
     assert '"faithBin":"#16a34a"' in output
+    assert '"lowerBetterNoise":true' in output
+    assert '"lowerBetterFaith":false' in output
+    # higher-better: rising value is an improvement (green ▲); falling is a regression (red ▼)
+    assert '"upHigher":{"hasData":true,"delta":0.2,"improved":true,"arrow":"▲","magnitude":"0.20","cls":"delta-good"}' in output
+    assert '"downHigher":{"hasData":true,"delta":-0.2,"improved":false,"arrow":"▼","magnitude":"0.20","cls":"delta-bad"}' in output
+    # noise_sensitivity (lower-better): falling value is an improvement (green ▼)
+    assert '"noiseImproved":{"hasData":true,"delta":-0.2,"improved":true,"arrow":"▼","magnitude":"0.20","cls":"delta-good"}' in output
+    assert '"noiseWorse":{"hasData":true,"delta":0.2,"improved":false,"arrow":"▲","magnitude":"0.20","cls":"delta-bad"}' in output
+    assert '"noBaseline":{"hasData":false' in output
 
 
 def test_report_and_index_load_metric_presenter_helper() -> None:
@@ -66,3 +82,6 @@ def test_report_and_index_load_metric_presenter_helper() -> None:
     assert "js/metric_presenter.js" in index_html
     assert "MetricPresenter.describeMetric" in report_js
     assert "MetricPresenter.scoreClass" in app_js
+    # history comparison table uses the direction-aware delta helper
+    assert "MetricPresenter.deltaInfo" in report_js
+    assert "history-table" in report_js

tests/test_webapp_report_builder.py

@@ -4,8 +4,11 @@ from __future__ import annotations
 
 from pathlib import Path
 
+import pandas as pd
 import pytest
 
+from webapp.services import question_history
+from webapp.services import report_builder
 from webapp.services.report_builder import build_report
 from webapp.services.run_reader import _infer_metrics_from_scores, _read_weights_from_snapshot
 
@@ -115,3 +118,71 @@ def test_build_report_ranks_noise_sensitivity_with_lower_values_as_better(tmp_pa
         "s-warn",
         "s-good",
     ]
+
+
+def test_lowest_samples_attaches_history_from_index() -> None:
+    """Surfaced samples are annotated with the same question's prior-run scores."""
+    frame = pd.DataFrame(
+        [
+            {"sample_id": "s1", "question": "  How LONG is the tube? ", "faithfulness": 0.40},
+            {"sample_id": "s2", "question": "unrelated question", "faithfulness": 0.30},
+        ]
+    )
+    history_index = {
+        question_history.normalize_question("How long is the tube?"): [
+            {
+                "run_id": "prev",
+                "scenario_name": "scn",
+                "finished_at": "2026-01-01T00:00:00",
+                "metrics": {"faithfulness": 0.90},
+            }
+        ]
+    }
+
+    samples = report_builder._lowest_samples(frame, ["faithfulness"], history_index)
+    by_id = {s.sample_id: s for s in samples}
+
+    assert len(by_id["s1"].history) == 1
+    assert by_id["s1"].history[0].run_id == "prev"
+    assert by_id["s1"].history[0].metrics["faithfulness"] == 0.90
+    assert by_id["s2"].history == []  # no match → no history
+
+
+def test_build_report_attaches_question_history(tmp_path: Path, monkeypatch) -> None:
+    """build_report wires the question-history index into surfaced samples."""
+    run_dir = tmp_path / "run"
+    run_dir.mkdir(parents=True, exist_ok=True)
+    (run_dir / "scores.csv").write_text(
+        "\n".join(
+            [
+                "sample_id,question,faithfulness",
+                "s1,How long is the tube?,0.40",
+            ]
+        ),
+        encoding="utf-8",
+    )
+    (run_dir / "summary.md").write_text("summary", encoding="utf-8")
+    (run_dir / "optimization_advice.md").write_text("", encoding="utf-8")
+
+    captured: dict = {}
+
+    def _fake_index(exclude_run_id=None, extra_roots=None):
+        captured["exclude_run_id"] = exclude_run_id
+        return {
+            question_history.normalize_question("How long is the tube?"): [
+                {
+                    "run_id": "older",
+                    "scenario_name": "scn",
+                    "finished_at": "2026-01-01T00:00:00",
+                    "metrics": {"faithfulness": 0.95},
+                }
+            ]
+        }
+
+    monkeypatch.setattr(question_history, "build_question_history_index", _fake_index)
+
+    report = build_report(run_dir, ["faithfulness"])
+
+    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