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)