fix(context): make ContextGraph.add_edge idempotent by deduping on edge_id

semantica/context/context_graph.py

@@ -455,6 +455,7 @@ def __init__(self, config: Optional[Dict[str, Any]] = None, **kwargs):
 
         self.nodes: Dict[str, ContextNode] = {}
         self.edges: List[ContextEdge] = []
+        self._edge_index: Dict[str, ContextEdge] = {}
 
         self._adjacency: Dict[str, List[ContextEdge]] = defaultdict(list)
 
@@ -1043,6 +1044,7 @@ def load_from_file(self, path: str) -> None:
             # Clear existing
             self.nodes.clear()
             self.edges.clear()
+            self._edge_index.clear()
             self._adjacency.clear()
             self.node_type_index.clear()
             self.edge_type_index.clear()
@@ -1436,6 +1438,7 @@ def clear(self) -> None:
         with self._lock:
             self.nodes.clear()
             self.edges.clear()
+            self._edge_index.clear()
             self._adjacency.clear()
             self.node_type_index.clear()
             self.edge_type_index.clear()
@@ -1508,6 +1511,11 @@ def _add_internal_edge(self, edge: ContextEdge) -> bool:
             self.logger.warning("Skipping internal edge with invalid endpoints: %r", edge)
             return False
         with self._lock:
+            # Edge identity is content-derived, so an existing edge_id means this
+            # exact edge is already stored; re-adding it is a no-op (issue #922).
+            if edge.edge_id in self._edge_index:
+                return False
+
             # Ensure nodes exist
             if edge.source_id not in self.nodes:
                 self._add_internal_node(
@@ -1518,6 +1526,7 @@ def _add_internal_edge(self, edge: ContextEdge) -> bool:
                     ContextNode(edge.target_id, "entity", edge.target_id)
                 )
 
+            self._edge_index[edge.edge_id] = edge
             self.edges.append(edge)
             self.edge_type_index[edge.edge_type].append(edge)
             self._adjacency[edge.source_id].append(edge)

tests/context/test_context.py

@@ -109,6 +109,61 @@ def test_context_graph_operations(self):
         self.assertEqual(neighbors[0]["id"], "n2")
         self.assertEqual(neighbors[0]["relationship"], "knows")
 
+    def test_add_edge_is_idempotent(self):
+        graph = ContextGraph()
+        graph.add_node("a", "t")
+        graph.add_node("b", "t")
+
+        self.assertTrue(graph.add_edge("a", "b", "rel"))
+        self.assertFalse(graph.add_edge("a", "b", "rel"))
+        self.assertFalse(graph.add_edge("a", "b", "rel"))
+
+        self.assertEqual(len(graph.edges), 1)
+        self.assertEqual(len(graph.edge_type_index["rel"]), 1)
+        self.assertEqual(len(graph._adjacency["a"]), 1)
+        self.assertEqual(graph.stats()["edge_count"], 1)
+        self.assertLessEqual(graph.density(), 1.0)
+
+    def test_parallel_edges_with_distinct_attributes_are_kept(self):
+        graph = ContextGraph()
+        graph.add_node("a", "t")
+        graph.add_node("b", "t")
+
+        graph.add_edge("a", "b", "rel", confidence=0.9)
+        graph.add_edge("a", "b", "rel", confidence=0.5)
+        graph.add_edge("a", "b", "other")
+
+        self.assertEqual(len(graph.edges), 3)
+        self.assertEqual(len({e.edge_id for e in graph.edges}), 3)
+
+    def test_reingest_does_not_duplicate_edges(self):
+        graph = ContextGraph()
+        entities = [
+            {"id": "alice", "type": "person"},
+            {"id": "acme", "type": "org"},
+        ]
+        relationships = [
+            {"source_id": "alice", "target_id": "acme", "type": "works_at"}
+        ]
+
+        for _ in range(3):
+            graph.build_from_entities_and_relationships(entities, relationships)
+
+        self.assertEqual(len(graph.edges), 1)
+
+    def test_clear_resets_edge_dedupe_index(self):
+        graph = ContextGraph()
+        graph.add_node("a", "t")
+        graph.add_node("b", "t")
+        graph.add_edge("a", "b", "rel")
+
+        graph.clear()
+
+        graph.add_node("a", "t")
+        graph.add_node("b", "t")
+        self.assertTrue(graph.add_edge("a", "b", "rel"))
+        self.assertEqual(len(graph.edges), 1)
+
     def test_get_nodes_by_label_returns_metadata_copy(self):
         graph = ContextGraph()
         graph.add_node("n1", "person", "Alice", role="engineer")