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

eval/recording/model.py

@@ -0,0 +1,30 @@
+"""Transport-neutral cassette interaction model."""
+
+import base64
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class RecordedInteraction:
+    """One completed HTTP exchange with exact response chunks."""
+
+    method: str
+    url: str
+    status: int
+    request_body: bytes
+    response_chunks: tuple[bytes, ...]
+
+    def as_dict(self) -> dict[str, object]:
+        """Encode byte fields losslessly for JSON storage."""
+        return {
+            "method": self.method,
+            "url": self.url,
+            "status": self.status,
+            "request_body_base64": _encode(self.request_body),
+            "response_body_base64": _encode(b"".join(self.response_chunks)),
+            "response_chunks_base64": [_encode(chunk) for chunk in self.response_chunks],
+        }
+
+
+def _encode(value: bytes) -> str:
+    return base64.b64encode(value).decode("ascii")