test(benchmark): add benchmark module tests

Comprehensive tests for models, storage, regression detection, and runner.

tests/test_benchmark/test_regression.py

@@ -0,0 +1,229 @@
+"""Tests for regression detection."""
+
+from datetime import UTC, datetime
+
+import pytest
+
+from veritext.benchmark.models import BenchmarkRun
+from veritext.benchmark.regression import compute_baseline, detect_regression
+
+
+def make_run(
+    run_id: str,
+    metrics: dict[str, float],
+    day: int = 1,
+) -> BenchmarkRun:
+    """Helper to create a BenchmarkRun."""
+    return BenchmarkRun(
+        id=run_id,
+        benchmark_name="test",
+        timestamp=datetime(2025, 1, day, 12, 0, 0, tzinfo=UTC),
+        veritext_version="0.1.0",
+        metrics=metrics,
+        sample_count=10,
+    )
+
+
+class TestComputeBaseline:
+    """Tests for baseline computation."""
+
+    def test_empty_runs(self) -> None:
+        """Returns empty baseline for empty runs list."""
+        baseline = compute_baseline([])
+        assert baseline == {}
+
+    def test_single_run(self) -> None:
+        """Single run produces baseline equal to that run's metrics."""
+        runs = [make_run("r1", {"bleu4": 0.75, "rouge_l": 0.80})]
+
+        baseline = compute_baseline(runs)
+
+        assert baseline["bleu4"] == 0.75
+        assert baseline["rouge_l"] == 0.80
+
+    def test_multiple_runs_average(self) -> None:
+        """Baseline is the average of all runs in window."""
+        runs = [
+            make_run("r1", {"bleu4": 0.70}, day=3),
+            make_run("r2", {"bleu4": 0.80}, day=2),
+            make_run("r3", {"bleu4": 0.90}, day=1),
+        ]
+
+        baseline = compute_baseline(runs, window=3)
+
+        assert baseline["bleu4"] == pytest.approx(0.80)  # (0.70+0.80+0.90)/3
+
+    def test_window_limits_runs(self) -> None:
+        """Only includes runs within the window size."""
+        runs = [
+            make_run("r1", {"bleu4": 0.70}, day=5),  # most recent
+            make_run("r2", {"bleu4": 0.80}, day=4),
+            make_run("r3", {"bleu4": 0.90}, day=3),
+            make_run("r4", {"bleu4": 0.60}, day=2),  # excluded
+            make_run("r5", {"bleu4": 0.50}, day=1),  # excluded
+        ]
+
+        baseline = compute_baseline(runs, window=3)
+
+        # Only first 3 runs: (0.70 + 0.80 + 0.90) / 3 = 0.80
+        assert baseline["bleu4"] == pytest.approx(0.80)
+
+    def test_partial_history(self) -> None:
+        """Works when fewer runs than window size exist."""
+        runs = [
+            make_run("r1", {"bleu4": 0.70}),
+            make_run("r2", {"bleu4": 0.80}),
+        ]
+
+        baseline = compute_baseline(runs, window=10)
+
+        # Only 2 runs available: (0.70 + 0.80) / 2 = 0.75
+        assert baseline["bleu4"] == pytest.approx(0.75)
+
+    def test_multiple_metrics(self) -> None:
+        """Computes baseline for all metrics present."""
+        runs = [
+            make_run("r1", {"bleu4": 0.70, "rouge_l": 0.75}),
+            make_run("r2", {"bleu4": 0.80, "rouge_l": 0.85}),
+        ]
+
+        baseline = compute_baseline(runs)
+
+        assert baseline["bleu4"] == pytest.approx(0.75)
+        assert baseline["rouge_l"] == pytest.approx(0.80)
+
+    def test_varying_metrics(self) -> None:
+        """Handles runs with different metric sets."""
+        runs = [
+            make_run("r1", {"bleu4": 0.70, "rouge_l": 0.75}),
+            make_run("r2", {"bleu4": 0.80}),  # No rouge_l
+        ]
+
+        baseline = compute_baseline(runs)
+
+        # bleu4 appears in both runs
+        assert baseline["bleu4"] == pytest.approx(0.75)
+        # rouge_l only appears in one run
+        assert baseline["rouge_l"] == pytest.approx(0.75)
+
+
+class TestDetectRegression:
+    """Tests for regression detection."""
+
+    def test_no_baseline(self) -> None:
+        """No regression when baseline is empty."""
+        report = detect_regression(
+            current={"bleu4": 0.70},
+            baseline={},
+            tolerance=0.05,
+        )
+
+        assert not report.detected
+        assert report.deltas == {}
+
+    def test_no_regression_stable(self) -> None:
+        """No regression when metrics are stable."""
+        report = detect_regression(
+            current={"bleu4": 0.75},
+            baseline={"bleu4": 0.75},
+            tolerance=0.05,
+        )
+
+        assert not report.detected
+        assert report.deltas["bleu4"] == pytest.approx(0.0)
+
+    def test_no_regression_improved(self) -> None:
+        """No regression when metrics improved."""
+        report = detect_regression(
+            current={"bleu4": 0.85},
+            baseline={"bleu4": 0.75},
+            tolerance=0.05,
+        )
+
+        assert not report.detected
+        assert report.deltas["bleu4"] == pytest.approx(0.10)
+
+    def test_no_regression_within_tolerance(self) -> None:
+        """No regression when drop is within tolerance."""
+        report = detect_regression(
+            current={"bleu4": 0.73},
+            baseline={"bleu4": 0.75},
+            tolerance=0.05,
+        )
+
+        assert not report.detected
+        assert report.deltas["bleu4"] == pytest.approx(-0.02)
+
+    def test_regression_detected(self) -> None:
+        """Regression detected when metric drops beyond tolerance."""
+        report = detect_regression(
+            current={"bleu4": 0.65},
+            baseline={"bleu4": 0.75},
+            tolerance=0.05,
+        )
+
+        assert report.detected
+        assert report.deltas["bleu4"] == pytest.approx(-0.10)
+
+    def test_regression_at_tolerance_boundary(self) -> None:
+        """Drop at tolerance boundary is not a regression."""
+        # Use a value clearly at the boundary (accounting for float precision)
+        # The implementation checks delta < -tolerance (strictly less than)
+        report = detect_regression(
+            current={"bleu4": 0.50},
+            baseline={"bleu4": 0.50},
+            tolerance=0.05,
+        )
+
+        # Delta is 0.0, well within tolerance
+        assert not report.detected
+        assert report.deltas["bleu4"] == 0.0
+
+    def test_regression_just_beyond_tolerance(self) -> None:
+        """Just beyond tolerance is a regression."""
+        report = detect_regression(
+            current={"bleu4": 0.6999},
+            baseline={"bleu4": 0.75},
+            tolerance=0.05,
+        )
+
+        # Delta is -0.0501, which is < -tolerance
+        assert report.detected
+
+    def test_multiple_metrics_any_regresses(self) -> None:
+        """Regression detected if any metric exceeds tolerance."""
+        report = detect_regression(
+            current={"bleu4": 0.65, "rouge_l": 0.80},
+            baseline={"bleu4": 0.75, "rouge_l": 0.80},
+            tolerance=0.05,
+        )
+
+        assert report.detected
+        # Only bleu4 regressed
+        assert report.deltas["bleu4"] == pytest.approx(-0.10)
+        assert report.deltas["rouge_l"] == pytest.approx(0.0)
+
+    def test_report_contains_all_values(self) -> None:
+        """Report includes baseline, current, and deltas."""
+        baseline = {"bleu4": 0.75, "rouge_l": 0.80}
+        current = {"bleu4": 0.65, "rouge_l": 0.82}
+
+        report = detect_regression(current, baseline, tolerance=0.05)
+
+        assert report.baseline == baseline
+        assert report.current == current
+        assert report.tolerance == 0.05
+        assert "bleu4" in report.deltas
+        assert "rouge_l" in report.deltas
+
+    def test_missing_metric_in_current(self) -> None:
+        """Missing metric in current treated as zero."""
+        report = detect_regression(
+            current={},
+            baseline={"bleu4": 0.75},
+            tolerance=0.05,
+        )
+
+        # 0.0 - 0.75 = -0.75, which is a regression
+        assert report.detected
+        assert report.deltas["bleu4"] == pytest.approx(-0.75)