harden community serialization fallbacks

Use safe JSON serialization fallbacks for deterministic sort keys in clustering and graph canonicalization, and skip invalid community IDs with a stderr warning instead of raising during update rebuilds.

Co-authored-by: Cursor <cursoragent@cursor.com>

graphify/cluster.py

@@ -32,7 +32,11 @@ def _partition(G: nx.Graph) -> dict[str, int]:
     stable.add_nodes_from(sorted(G.nodes(), key=str))
     edge_rows = sorted(
         G.edges(data=True),
-        key=lambda row: (str(row[0]), str(row[1]), json.dumps(row[2], sort_keys=True, ensure_ascii=False)),
+        key=lambda row: (
+            str(row[0]),
+            str(row[1]),
+            json.dumps(row[2], sort_keys=True, ensure_ascii=False, default=str),
+        ),
     )
     for src, tgt, attrs in edge_rows:
         stable.add_edge(src, tgt, **attrs)

graphify/watch.py

@@ -123,7 +123,15 @@ def _node_community_map(graph_data: dict) -> dict[str, int]:
         cid = node.get("community")
         if node_id is None or cid is None:
             continue
-        out[str(node_id)] = int(cid)
+        try:
+            out[str(node_id)] = int(cid)
+        except (TypeError, ValueError):
+            print(
+                f"[graphify watch] Skipping node with invalid community id: "
+                f"node_id={node_id!r} community={cid!r}",
+                file=sys.stderr,
+            )
+            continue
     return out
 
 
@@ -134,7 +142,7 @@ def _canonical_graph_for_compare(graph_data: dict) -> dict:
         if key in canonical and isinstance(canonical[key], list):
             canonical[key] = sorted(
                 canonical[key],
-                key=lambda item: json.dumps(item, sort_keys=True, ensure_ascii=False),
+                key=lambda item: json.dumps(item, sort_keys=True, ensure_ascii=False, default=str),
             )
     return canonical