fix: prune old detail after publication (#100)

tests/test_pruning.py

@@ -27,9 +27,14 @@ def store_conn(tmp_path: Path):
 
 
 def _insert_sample(conn, ts_iso, device="/dev/nvme0"):
+    conn.execute(
+        "INSERT OR IGNORE INTO controller_segments "
+        "(id, opened_at, identity_key) VALUES (1, '2026-01-01T00:00:00+00:00', 'test')"
+    )
     conn.execute(
         "INSERT INTO samples (ts, device, data_units_written, data_units_read, "
-        " bytes_written, bytes_read, percentage_used) VALUES (?, ?, 0, 0, 0, 0, 0)",
+        " bytes_written, bytes_read, percentage_used, segment_id, local_tz) "
+        "VALUES (?, ?, 0, 0, 0, 0, 0, 1, 'UTC')",
         (ts_iso, device),
     )
     conn.commit()
@@ -50,33 +55,30 @@ class TestPruneOldSamples:
         cursor = store_conn.execute("SELECT COUNT(*) FROM samples")
         assert cursor.fetchone()[0] == 1
 
-    def test_removes_old_samples(self, store_conn):
+    def test_keeps_old_samples_without_replacement_evidence(self, store_conn):
         now = datetime(2026, 9, 15, 12, 0, 0, tzinfo=timezone.utc)
-        # Insert samples at 10, 14, and 15 days ago
-        # All three are before the cutoff (2026-09-01T12:00:00)
-        # The 15-day-old sample is not a boundary anchor because
-        # the next sample (14 days ago) is also before the cutoff
+        # Old samples stay until UTC and local-day evidence replace them.
         for days_ago in [10, 14, 15]:
             ts = (now - timedelta(days=days_ago)).isoformat()
             _insert_sample(store_conn, ts)
 
         pruned = prune_old_samples(store_conn, now, retention_days=14)
-        assert pruned == 1  # Only the 15-day-old sample removed
+        assert pruned == 0
 
         cursor = store_conn.execute("SELECT COUNT(*) FROM samples")
-        assert cursor.fetchone()[0] == 2
+        assert cursor.fetchone()[0] == 3
 
-    def test_removes_many_old_samples(self, store_conn):
+    def test_keeps_many_old_samples_without_replacement_evidence(self, store_conn):
         now = datetime(2026, 9, 15, 12, 0, 0, tzinfo=timezone.utc)
         for days_ago in range(1, 30):
             ts = (now - timedelta(days=days_ago)).isoformat()
             _insert_sample(store_conn, ts)
 
         pruned = prune_old_samples(store_conn, now, retention_days=14)
-        assert pruned == 15  # Days 15-29 removed
+        assert pruned == 0
 
         cursor = store_conn.execute("SELECT COUNT(*) FROM samples")
-        assert cursor.fetchone()[0] == 14  # Days 1-14 kept
+        assert cursor.fetchone()[0] == 29
 
     def test_empty_store_no_error(self, store_conn):
         now = datetime(2026, 9, 15, 12, 0, 0, tzinfo=timezone.utc)
@@ -130,8 +132,8 @@ class TestPruneOldSamples:
         )
         assert cursor.fetchone()[0] == 1
 
-    def test_old_sample_with_derived_interval_removed(self, store_conn):
-        """Old samples with fully derived intervals are removed."""
+    def test_hour_rows_alone_do_not_replace_local_day_evidence(self, store_conn):
+        """An hour row alone cannot authorize source-sample deletion."""
         now = datetime(2026, 9, 30, 12, 0, 0, tzinfo=timezone.utc)
         
         # Old sample with derived interval
@@ -148,8 +150,8 @@ class TestPruneOldSamples:
         # Run pruning
         pruned = prune_old_samples(store_conn, now, retention_days=14)
         
-        # Old sample should be removed (interval is derived)
+        # Keep the source samples until local-day replacement evidence exists.
         cursor = store_conn.execute(
             "SELECT COUNT(*) FROM samples WHERE ts = '2026-09-10T10:00:00+00:00'"
         )
-        assert cursor.fetchone()[0] == 0
+        assert cursor.fetchone()[0] == 1