eval: P1 diagnostic prediction-based (flagged set +209), classifier regression suite (10 tests, stub ground truth); 34 tests green

1 files changed, 5 insertions, 2 deletions

diff --git a/tests/test_data.py b/tests/test_data.py
index cd4e620..9f651fb 100644
--- a/tests/test_data.py
+++ b/tests/test_data.py
@@ -75,7 +75,10 @@ def test_make_batch_shapes_and_padding():
 
 
 def test_flagged_composites_are_composite():
-    # sanity: the diagnostic set in eval.py really is composite and needs divisors > 7
-    for n in (121, 143, 169, 187):
+    # sanity: the diagnostic set really is composite, has no divisors <= 7, and covers
+    # the probe's candidate window [102, 211] (209 = 11*19 included — Addendum 3)
+    from src.eval import FLAGGED_SIEVE_PREDS
+    assert FLAGGED_SIEVE_PREDS == {121, 143, 169, 187, 209}
+    for n in FLAGGED_SIEVE_PREDS:
         assert any(n % d == 0 for d in range(2, int(n ** 0.5) + 1))
         assert all(n % d != 0 for d in (2, 3, 5, 7))