feat: implement repair and retention for observation history (issue #74)

tests/test_pruning.py

@@ -1,7 +1,9 @@
 """Raw sample pruning tests.
 
 Spec §3.4, ST-5: Raw samples pruned to 14 days; hour observations and
-day aggregates retained indefinitely.
+day aggregates are retained indefinitely.
+
+Issue #74: Boundary anchors required for successor evidence are retained.
 """
 import sqlite3
 import sys
@@ -51,6 +53,9 @@ class TestPruneOldSamples:
     def test_removes_old_samples(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
         for days_ago in [10, 14, 15]:
             ts = (now - timedelta(days=days_ago)).isoformat()
             _insert_sample(store_conn, ts)
@@ -82,6 +87,7 @@ class TestPruneOldSamples:
         """Hour observations are retained indefinitely."""
         now = datetime(2026, 9, 15, 12, 0, 0, tzinfo=timezone.utc)
         # Insert an old sample and a recent sample
+        # The old sample is a boundary anchor (needed for derivation)
         _insert_sample(store_conn, (now - timedelta(days=20)).isoformat())
         _insert_sample(store_conn, (now - timedelta(days=1)).isoformat())
 
@@ -95,10 +101,55 @@ class TestPruneOldSamples:
 
         prune_old_samples(store_conn, now, retention_days=14)
 
-        # Sample removed
+        # Old sample is retained as boundary anchor (needed for derivation)
         cursor = store_conn.execute("SELECT COUNT(*) FROM samples")
-        assert cursor.fetchone()[0] == 1
+        assert cursor.fetchone()[0] == 2
 
         # Hour observation retained
         cursor = store_conn.execute("SELECT COUNT(*) FROM hour_observations")
         assert cursor.fetchone()[0] == 1
+
+    def test_boundary_anchor_retained(self, store_conn):
+        """Boundary anchors required for derivation are retained."""
+        now = datetime(2026, 9, 30, 12, 0, 0, tzinfo=timezone.utc)
+        
+        # Old sample before boundary (2026-09-14T23:55:00)
+        # is 15 days and 0.75 hours old (before cutoff at 2026-09-16T12:00:00)
+        _insert_sample(store_conn, "2026-09-14T23:55:00+00:00", 1000000)
+        
+        # Sample after boundary (2026-09-16T12:30:00)
+        # is 13 days and 23.5 hours old (within retention)
+        _insert_sample(store_conn, "2026-09-16T12:30:00+00:00", 2000000)
+        
+        # Run pruning
+        pruned = prune_old_samples(store_conn, now, retention_days=14)
+        
+        # The boundary anchor should be retained
+        cursor = store_conn.execute(
+            "SELECT COUNT(*) FROM samples WHERE ts = '2026-09-14T23:55:00+00:00'"
+        )
+        assert cursor.fetchone()[0] == 1
+
+    def test_old_sample_with_derived_interval_removed(self, store_conn):
+        """Old samples with fully derived intervals are removed."""
+        now = datetime(2026, 9, 30, 12, 0, 0, tzinfo=timezone.utc)
+        
+        # Old sample with derived interval
+        _insert_sample(store_conn, "2026-09-10T10:00:00+00:00", 1000000)
+        _insert_sample(store_conn, "2026-09-10T10:30:00+00:00", 2000000)
+        
+        # Hour observation exists for the interval
+        store_conn.execute(
+            "INSERT INTO hour_observations (hour, active_seconds, bytes_written_delta, bytes_read_delta, sample_count, coverage) "
+            "VALUES ('2026-09-10T10:00:00+00:00', 3600, 1000000, 0, 1, 1.0)",
+        )
+        store_conn.commit()
+        
+        # Run pruning
+        pruned = prune_old_samples(store_conn, now, retention_days=14)
+        
+        # Old sample should be removed (interval is derived)
+        cursor = store_conn.execute(
+            "SELECT COUNT(*) FROM samples WHERE ts = '2026-09-10T10:00:00+00:00'"
+        )
+        assert cursor.fetchone()[0] == 0