Merge nucleic/sleek-ember-seal-uady into dev

tests/test_eval.py

@@ -0,0 +1,27 @@
+import sys
+import unittest
+from pathlib import Path
+
+
+MODULE_DIR = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(MODULE_DIR))
+
+import eval as purpose_eval
+
+
+class TierDriftTests(unittest.TestCase):
+    def test_current_routing_matrix_bounds_every_label_pair(self):
+        records = [{"prompt": f"prompt {index}"} for index in range(8 * 8)]
+        actual = []
+        predicted = []
+        for expected in range(8):
+            for got in range(8):
+                actual.append(expected)
+                predicted.append(got)
+        report = purpose_eval.routing_tier_drift(records, actual, predicted)
+        self.assertTrue(report["passed"])
+        self.assertLessEqual(report["maximumTierDrift"], 1)
+
+
+if __name__ == "__main__":
+    unittest.main()