feat(benchmark): add BenchmarkRun and RegressionReport models

Data models for benchmark runs and regression reports using Pydantic.

src/veritext/benchmark/models.py

@@ -0,0 +1,72 @@
+"""Benchmark data models."""
+
+from datetime import datetime
+from typing import Any
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class BenchmarkRun(BaseModel):
+    """Record of a single benchmark execution."""
+
+    model_config = ConfigDict(frozen=True)
+
+    id: str
+    """UUID for this run."""
+
+    benchmark_name: str
+    """Name identifying this benchmark suite."""
+
+    timestamp: datetime
+    """When the benchmark was executed."""
+
+    veritext_version: str
+    """Version of veritext used."""
+
+    metrics: dict[str, float]
+    """Metric results, e.g. {"rouge_l": 0.82, "bleu4": 0.71}."""
+
+    sample_count: int
+    """Number of samples evaluated."""
+
+    metadata: dict[str, Any] = Field(default_factory=dict)
+    """Optional metadata (git_sha, model version, etc.)."""
+
+
+class RegressionReport(BaseModel):
+    """Report comparing current run against baseline."""
+
+    model_config = ConfigDict(frozen=True)
+
+    detected: bool
+    """Whether a regression was detected."""
+
+    baseline: dict[str, float]
+    """Baseline metric values (rolling average)."""
+
+    current: dict[str, float]
+    """Current run metric values."""
+
+    deltas: dict[str, float]
+    """Difference from baseline (negative = regression)."""
+
+    tolerance: float
+    """Tolerance threshold used for detection."""
+
+    @property
+    def summary(self) -> str:
+        """Human-readable summary of the report."""
+        if not self.detected:
+            return "No regression detected. All metrics within tolerance."
+
+        regressions = [
+            f"  {metric}: {self.current.get(metric, 0.0):.4f} "
+            f"(baseline: {self.baseline.get(metric, 0.0):.4f}, "
+            f"delta: {delta:+.4f})"
+            for metric, delta in self.deltas.items()
+            if delta < -self.tolerance
+        ]
+
+        return f"Regression detected (tolerance: {self.tolerance:.2%}):\n" + "\n".join(
+            regressions
+        )