diff --git a/src/iai_mcp/qdrant_store.py b/src/iai_mcp/qdrant_store.py
index 1cc21da..ec6222d 100644
--- a/src/iai_mcp/qdrant_store.py
+++ b/src/iai_mcp/qdrant_store.py
@@ -644,7 +644,6 @@ class QdrantStore:
                 offset=offset,
                 scroll_filter=table_filter,
                 with_payload=True,
-                with_vectors=True,
             )
             all_points.extend(points)
             if next_offset is None:
diff --git a/src/iai_mcp/sleep.py b/src/iai_mcp/sleep.py
index f2d9b1c..e3e6c5b 100644
--- a/src/iai_mcp/sleep.py
+++ b/src/iai_mcp/sleep.py
@@ -296,22 +296,16 @@ def run_light_consolidation(
 
 
 def _build_hebbian_clusters(store: MemoryStore) -> list[list[UUID]]:
-    """Find connected components in the hebbian+temporal_next edge graph
-    with size >= CLUSTER_MIN_SIZE.
-
-    Hebbian edges capture semantic similarity (dedup/reinforce);
-    temporal_next edges capture sequential proximity (same-session inserts
-    within 5 minutes). Both are valid signals for CLS clustering.
-    """
+    """Find connected components in the hebbian edge graph with size >= CLUSTER_MIN_SIZE."""
     edges_df = store.db.open_table(EDGES_TABLE).to_pandas()
     if edges_df.empty:
         return []
-    relevant = edges_df[edges_df["edge_type"].isin(("hebbian", "temporal_next"))]
-    if relevant.empty:
+    hebbian = edges_df[edges_df["edge_type"] == "hebbian"]
+    if hebbian.empty:
         return []
 
     adj: dict[UUID, set[UUID]] = {}
-    for _, row in relevant.iterrows():
+    for _, row in hebbian.iterrows():
         src = UUID(row["src"])
         dst = UUID(row["dst"])
         adj.setdefault(src, set()).add(dst)