diff --git a/src/iai_mcp/qdrant_store.py b/src/iai_mcp/qdrant_store.py
index ec6222d..1cc21da 100644
--- a/src/iai_mcp/qdrant_store.py
+++ b/src/iai_mcp/qdrant_store.py
@@ -644,6 +644,7 @@ 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 e3e6c5b..f2d9b1c 100644
--- a/src/iai_mcp/sleep.py
+++ b/src/iai_mcp/sleep.py
@@ -296,16 +296,22 @@ def run_light_consolidation(
 
 
 def _build_hebbian_clusters(store: MemoryStore) -> list[list[UUID]]:
-    """Find connected components in the hebbian edge graph with size >= CLUSTER_MIN_SIZE."""
+    """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.
+    """
     edges_df = store.db.open_table(EDGES_TABLE).to_pandas()
     if edges_df.empty:
         return []
-    hebbian = edges_df[edges_df["edge_type"] == "hebbian"]
-    if hebbian.empty:
+    relevant = edges_df[edges_df["edge_type"].isin(("hebbian", "temporal_next"))]
+    if relevant.empty:
         return []
 
     adj: dict[UUID, set[UUID]] = {}
-    for _, row in hebbian.iterrows():
+    for _, row in relevant.iterrows():
         src = UUID(row["src"])
         dst = UUID(row["dst"])
         adj.setdefault(src, set()).add(dst)