test(mnemosyne): add graph_data() tests

- empty archive returns empty nodes/edges
- nodes have all required fields
- edges have weights in [0,1]
- topic_filter returns subgraph
- bidirectional edges deduplicated

nexus/mnemosyne/archive.py

@@ -212,6 +212,65 @@ class MnemosyneArchive:
     def count(self) -> int:
         return len(self._entries)
 
+    def graph_data(
+        self,
+        topic_filter: Optional[str] = None,
+    ) -> dict:
+        """Export the full connection graph for 3D constellation visualization.
+
+        Returns a dict with:
+        - nodes: list of {id, title, topics, source, created_at}
+        - edges: list of {source, target, weight} from holographic links
+
+        Args:
+            topic_filter: If set, only include entries matching this topic
+                and edges between them.
+        """
+        entries = list(self._entries.values())
+
+        if topic_filter:
+            topic_lower = topic_filter.lower()
+            entries = [
+                e for e in entries
+                if topic_lower in [t.lower() for t in e.topics]
+            ]
+
+        entry_ids = {e.id for e in entries}
+
+        nodes = [
+            {
+                "id": e.id,
+                "title": e.title,
+                "topics": e.topics,
+                "source": e.source,
+                "created_at": e.created_at,
+            }
+            for e in entries
+        ]
+
+        # Build edges from links, dedup (A→B and B→A become one edge)
+        seen_edges: set[tuple[str, str]] = set()
+        edges = []
+        for e in entries:
+            for linked_id in e.links:
+                if linked_id not in entry_ids:
+                    continue
+                pair = (min(e.id, linked_id), max(e.id, linked_id))
+                if pair in seen_edges:
+                    continue
+                seen_edges.add(pair)
+                # Compute weight via linker for live similarity score
+                linked = self._entries.get(linked_id)
+                if linked:
+                    weight = self.linker.compute_similarity(e, linked)
+                    edges.append({
+                        "source": pair[0],
+                        "target": pair[1],
+                        "weight": round(weight, 4),
+                    })
+
+        return {"nodes": nodes, "edges": edges}
+
     def stats(self) -> dict:
         entries = list(self._entries.values())
         total_links = sum(len(e.links) for e in entries)

nexus/mnemosyne/tests/test_archive.py

@@ -262,6 +262,75 @@ def test_semantic_search_vs_keyword_relevance():
         assert results[0].title == "Python scripting"
 
 
+def test_graph_data_empty_archive():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        data = archive.graph_data()
+        assert data == {"nodes": [], "edges": []}
+
+
+def test_graph_data_nodes_and_edges():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e1 = ingest_event(archive, title="Python automation", content="Building automation tools in Python", topics=["code"])
+        e2 = ingest_event(archive, title="Python scripting", content="Writing automation scripts using Python", topics=["code"])
+        e3 = ingest_event(archive, title="Cooking", content="Making pasta carbonara", topics=["food"])
+
+        data = archive.graph_data()
+        assert len(data["nodes"]) == 3
+        # All node fields present
+        for node in data["nodes"]:
+            assert "id" in node
+            assert "title" in node
+            assert "topics" in node
+            assert "source" in node
+            assert "created_at" in node
+
+        # e1 and e2 should be linked (shared Python/automation tokens)
+        edge_pairs = {(e["source"], e["target"]) for e in data["edges"]}
+        e1e2 = (min(e1.id, e2.id), max(e1.id, e2.id))
+        assert e1e2 in edge_pairs or (e1e2[1], e1e2[0]) in edge_pairs
+
+        # All edges have weights
+        for edge in data["edges"]:
+            assert "weight" in edge
+            assert 0 <= edge["weight"] <= 1
+
+
+def test_graph_data_topic_filter():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e1 = ingest_event(archive, title="A", content="code stuff", topics=["code"])
+        e2 = ingest_event(archive, title="B", content="more code", topics=["code"])
+        ingest_event(archive, title="C", content="food stuff", topics=["food"])
+
+        data = archive.graph_data(topic_filter="code")
+        node_ids = {n["id"] for n in data["nodes"]}
+        assert e1.id in node_ids
+        assert e2.id in node_ids
+        assert len(data["nodes"]) == 2
+
+
+def test_graph_data_deduplicates_edges():
+    """Bidirectional links should produce a single edge, not two."""
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e1 = ingest_event(archive, title="Python automation", content="Building automation tools in Python")
+        e2 = ingest_event(archive, title="Python scripting", content="Writing automation scripts using Python")
+
+        data = archive.graph_data()
+        # Count how many edges connect e1 and e2
+        e1e2_edges = [
+            e for e in data["edges"]
+            if {e["source"], e["target"]} == {e1.id, e2.id}
+        ]
+        assert len(e1e2_edges) <= 1, "Should not have duplicate bidirectional edges"
+
+
 def test_archive_topic_counts():
     with tempfile.TemporaryDirectory() as tmp:
         path = Path(tmp) / "test_archive.json"