vault backup: 2026-02-26 21:10:47

.scripts/memory/incremental_ingest.py

@@ -14,6 +14,7 @@ from index_common import (
 )
 
 MIN_TEXT_LEN = 50
+PRIMARY_DIRS = {'01_Projects', '02_Areas'}
 
 
 def parse_changes(changes_file: Path) -> list[dict]:
@@ -35,11 +36,17 @@ def parse_changes(changes_file: Path) -> list[dict]:
 
 
 def upsert_file(cur, rel_path: str) -> None:
+    top_dir = Path(rel_path).parts[0] if Path(rel_path).parts else ''
+    if top_dir not in PRIMARY_DIRS:
+        print(f'[SKIPPED-OUT-OF-SCOPE] {rel_path}')
+        return
+
     abs_path = VAULT_ROOT / rel_path
     if not abs_path.exists() or abs_path.suffix.lower() != '.md':
         return
 
-    if is_excluded(abs_path):
+    reason = is_excluded(abs_path)
+    if reason:
         cur.execute('DELETE FROM memory_primary WHERE id=%s', (rel_path,))
         cur.execute(
             '''
@@ -49,7 +56,7 @@ def upsert_file(cur, rel_path: str) -> None:
               risk = EXCLUDED.risk,
               updated_at = now()
             ''',
-            (rel_path, rel_path, 'excluded_or_sensitive'),
+            (rel_path, rel_path, reason),
         )
         print(f'[QUARANTINED] {rel_path}')
         return
@@ -61,6 +68,13 @@ def upsert_file(cur, rel_path: str) -> None:
         print(f'[PRUNED] {rel_path}')
         return
 
+    new_hash = sha256_text(text)
+    cur.execute('SELECT content_hash FROM memory_primary WHERE id=%s', (rel_path,))
+    row = cur.fetchone()
+    if row and row[0] == new_hash:
+        print(f'[SKIPPED] {rel_path}')
+        return
+
     try:
         embedding = embed_text(text)
     except Exception as error: