fix: normalize vector store scores to similarity (higher = better)

The threshold parameter in Memory.search() was silently broken for 11
vector stores because they returned raw distance scores (lower = better)
while the threshold check assumed similarity scores (higher = better).
This caused threshold filtering to be inverted — good matches got
dropped and bad matches passed through.

Convert all affected vector stores to return similarity scores:
- Cosine distance stores: score = max(0.0, 1.0 - distance)
- L2 distance stores: score = 1.0 / (1.0 + distance)
- Stores computing similarity then discarding it: return similarity directly

Fixes #4453
Related: #3283

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/vector_stores/test_s3_vectors.py

@@ -157,7 +157,7 @@ def test_search(mock_boto_client):
     mock_boto_client.query_vectors.assert_called_once()
     assert len(results) == 1
     assert results[0].id == "id1"
-    assert results[0].score == 0.9
+    assert abs(results[0].score - 0.1) < 1e-9  # distance 0.9 -> similarity 0.1
 
 
 def test_get(mock_boto_client):