test: add scenario eval runner, recorded fixtures, and baseline comparison

eval/recording/storage.py

@@ -0,0 +1,32 @@
+"""Persist raw and redacted cassette stores."""
+
+import json
+from pathlib import Path
+
+from recording.model import RecordedInteraction
+from recording.redaction import redact_cassette
+
+
+def write_cassettes(
+    fixture_root: Path,
+    scenario_key: str,
+    recordings: dict[str, list[RecordedInteraction]],
+) -> tuple[Path, Path]:
+    """Write ignored raw data first, then separately mapped safe cassettes."""
+    raw_root = fixture_root / "raw" / scenario_key
+    redacted_root = fixture_root / scenario_key
+    raw_root.mkdir(parents=True, exist_ok=True)
+    redacted_root.mkdir(parents=True, exist_ok=True)
+    for service, interactions in recordings.items():
+        raw_payload = [interaction.as_dict() for interaction in interactions]
+        _write_json(raw_root / f"{service}.json", raw_payload)
+        redacted_payload = redact_cassette(raw_payload)
+        _write_json(redacted_root / f"{service}.json", redacted_payload)
+    return raw_root, redacted_root
+
+
+def _write_json(path: Path, payload: object) -> None:
+    path.write_text(
+        json.dumps(payload, ensure_ascii=True, indent=2, sort_keys=True) + "\n",
+        encoding="ascii",
+    )