nexus/mnemosyne/archive.py

@@ -13,6 +13,8 @@ from typing import Optional
 from nexus.mnemosyne.entry import ArchiveEntry
 from nexus.mnemosyne.linker import HolographicLinker
 
+_EXPORT_VERSION = "1"
+
 
 class MnemosyneArchive:
     """The holographic archive — stores and links entries.
@@ -97,18 +99,98 @@ class MnemosyneArchive:
         topic_lower = topic.lower()
         return [e for e in self._entries.values() if topic_lower in [t.lower() for t in e.topics]]
 
+    def remove(self, entry_id: str) -> bool:
+        """Remove an entry and clean up all bidirectional links.
+
+        Returns True if the entry existed and was removed, False otherwise.
+        """
+        if entry_id not in self._entries:
+            return False
+        # Remove back-links from all other entries
+        for other in self._entries.values():
+            if entry_id in other.links:
+                other.links.remove(entry_id)
+        del self._entries[entry_id]
+        self._save()
+        return True
+
+    def export(
+        self,
+        query: Optional[str] = None,
+        topics: Optional[list[str]] = None,
+    ) -> dict:
+        """Export a filtered subset of the archive.
+
+        Args:
+            query: keyword filter applied to title + content (case-insensitive)
+            topics: list of topic tags; entries must match at least one
+
+        Returns a JSON-serialisable dict with an ``entries`` list and metadata.
+        """
+        candidates = list(self._entries.values())
+
+        if topics:
+            lower_topics = {t.lower() for t in topics}
+            candidates = [
+                e for e in candidates
+                if any(t.lower() in lower_topics for t in e.topics)
+            ]
+
+        if query:
+            query_tokens = set(query.lower().split())
+            candidates = [
+                e for e in candidates
+                if any(
+                    token in f"{e.title} {e.content} {' '.join(e.topics)}".lower()
+                    for token in query_tokens
+                )
+            ]
+
+        return {
+            "version": _EXPORT_VERSION,
+            "filters": {"query": query, "topics": topics},
+            "count": len(candidates),
+            "entries": [e.to_dict() for e in candidates],
+        }
+
+    def topic_counts(self) -> dict[str, int]:
+        """Return a dict mapping topic name → entry count, sorted by count desc."""
+        counts: dict[str, int] = {}
+        for entry in self._entries.values():
+            for topic in entry.topics:
+                counts[topic] = counts.get(topic, 0) + 1
+        return dict(sorted(counts.items(), key=lambda x: x[1], reverse=True))
+
     @property
     def count(self) -> int:
         return len(self._entries)
 
     def stats(self) -> dict:
-        total_links = sum(len(e.links) for e in self._entries.values())
-        topics = set()
-        for e in self._entries.values():
+        entries = list(self._entries.values())
+        total_links = sum(len(e.links) for e in entries)
+        topics: set[str] = set()
+        for e in entries:
             topics.update(e.topics)
+
+        # Orphans: entries with no links at all
+        orphans = sum(1 for e in entries if len(e.links) == 0)
+
+        # Link density: average links per entry (0 when empty)
+        n = len(entries)
+        link_density = round(total_links / n, 4) if n else 0.0
+
+        # Age distribution
+        timestamps = sorted(e.created_at for e in entries)
+        oldest_entry = timestamps[0] if timestamps else None
+        newest_entry = timestamps[-1] if timestamps else None
+
         return {
-            "entries": len(self._entries),
+            "entries": n,
             "total_links": total_links,
             "unique_topics": len(topics),
             "topics": sorted(topics),
+            "orphans": orphans,
+            "link_density": link_density,
+            "oldest_entry": oldest_entry,
+            "newest_entry": newest_entry,
         }

nexus/mnemosyne/cli.py

@@ -1,6 +1,7 @@
 """CLI interface for Mnemosyne.
 
-Provides: mnemosyne ingest, mnemosyne search, mnemosyne link, mnemosyne stats
+Provides: mnemosyne ingest, mnemosyne search, mnemosyne link, mnemosyne stats,
+          mnemosyne topics, mnemosyne remove, mnemosyne export
 """
 
 from __future__ import annotations
@@ -59,6 +60,33 @@ def cmd_link(args):
         print(f"  [{e.id[:8]}] {e.title} (source: {e.source})")
 
 
+def cmd_topics(args):
+    archive = MnemosyneArchive()
+    counts = archive.topic_counts()
+    if not counts:
+        print("No topics found.")
+        return
+    for topic, count in counts.items():
+        print(f"  {topic}: {count}")
+
+
+def cmd_remove(args):
+    archive = MnemosyneArchive()
+    removed = archive.remove(args.entry_id)
+    if removed:
+        print(f"Removed entry: {args.entry_id}")
+    else:
+        print(f"Entry not found: {args.entry_id}")
+        sys.exit(1)
+
+
+def cmd_export(args):
+    archive = MnemosyneArchive()
+    topics = [t.strip() for t in args.topics.split(",")] if args.topics else None
+    data = archive.export(query=args.query or None, topics=topics)
+    print(json.dumps(data, indent=2))
+
+
 def main():
     parser = argparse.ArgumentParser(prog="mnemosyne", description="The Living Holographic Archive")
     sub = parser.add_subparsers(dest="command")
@@ -78,12 +106,30 @@ def main():
     l.add_argument("entry_id", help="Entry ID (or prefix)")
     l.add_argument("-d", "--depth", type=int, default=1)
 
+    sub.add_parser("topics", help="List all topics with entry counts")
+
+    r = sub.add_parser("remove", help="Remove an entry by ID")
+    r.add_argument("entry_id", help="Entry ID to remove")
+
+    ex = sub.add_parser("export", help="Export filtered archive data as JSON")
+    ex.add_argument("-q", "--query", default="", help="Keyword filter")
+    ex.add_argument("-t", "--topics", default="", help="Comma-separated topic filter")
+
     args = parser.parse_args()
     if not args.command:
         parser.print_help()
         sys.exit(1)
 
-    {"stats": cmd_stats, "search": cmd_search, "ingest": cmd_ingest, "link": cmd_link}[args.command](args)
+    dispatch = {
+        "stats": cmd_stats,
+        "search": cmd_search,
+        "ingest": cmd_ingest,
+        "link": cmd_link,
+        "topics": cmd_topics,
+        "remove": cmd_remove,
+        "export": cmd_export,
+    }
+    dispatch[args.command](args)
 
 
 if __name__ == "__main__":

nexus/mnemosyne/tests/test_archive.py

@@ -66,8 +66,146 @@ def test_archive_persistence():
         path = Path(tmp) / "test_archive.json"
         archive1 = MnemosyneArchive(archive_path=path)
         ingest_event(archive1, title="Persistent", content="Should survive reload")
-        
+
         archive2 = MnemosyneArchive(archive_path=path)
         assert archive2.count == 1
         results = archive2.search("persistent")
         assert len(results) == 1
+
+
+def test_archive_remove_basic():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e1 = ingest_event(archive, title="Alpha", content="First entry", topics=["x"])
+        assert archive.count == 1
+
+        result = archive.remove(e1.id)
+        assert result is True
+        assert archive.count == 0
+        assert archive.get(e1.id) is None
+
+
+def test_archive_remove_nonexistent():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        result = archive.remove("does-not-exist")
+        assert result is False
+
+
+def test_archive_remove_cleans_backlinks():
+    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")
+        # At least one direction should be linked
+        assert e1.id in e2.links or e2.id in e1.links
+
+        # Remove e1; e2 must no longer reference it
+        archive.remove(e1.id)
+        e2_fresh = archive.get(e2.id)
+        assert e2_fresh is not None
+        assert e1.id not in e2_fresh.links
+
+
+def test_archive_remove_persists():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        a1 = MnemosyneArchive(archive_path=path)
+        e = ingest_event(a1, title="Gone", content="Will be removed")
+        a1.remove(e.id)
+
+        a2 = MnemosyneArchive(archive_path=path)
+        assert a2.count == 0
+
+
+def test_archive_export_unfiltered():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="A", content="content a", topics=["alpha"])
+        ingest_event(archive, title="B", content="content b", topics=["beta"])
+        data = archive.export()
+        assert data["count"] == 2
+        assert len(data["entries"]) == 2
+        assert data["filters"] == {"query": None, "topics": None}
+
+
+def test_archive_export_by_topic():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="A", content="content a", topics=["alpha"])
+        ingest_event(archive, title="B", content="content b", topics=["beta"])
+        data = archive.export(topics=["alpha"])
+        assert data["count"] == 1
+        assert data["entries"][0]["title"] == "A"
+
+
+def test_archive_export_by_query():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="Hello world", content="greetings", topics=[])
+        ingest_event(archive, title="Goodbye", content="farewell", topics=[])
+        data = archive.export(query="hello")
+        assert data["count"] == 1
+        assert data["entries"][0]["title"] == "Hello world"
+
+
+def test_archive_export_combined_filters():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="Hello world", content="greetings", topics=["alpha"])
+        ingest_event(archive, title="Hello again", content="greetings again", topics=["beta"])
+        data = archive.export(query="hello", topics=["alpha"])
+        assert data["count"] == 1
+        assert data["entries"][0]["title"] == "Hello world"
+
+
+def test_archive_stats_richer():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        # All four new fields present when archive is empty
+        s = archive.stats()
+        assert "orphans" in s
+        assert "link_density" in s
+        assert "oldest_entry" in s
+        assert "newest_entry" in s
+        assert s["orphans"] == 0
+        assert s["link_density"] == 0.0
+        assert s["oldest_entry"] is None
+        assert s["newest_entry"] is None
+
+
+def test_archive_stats_orphan_count():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        # Two entries with very different content → unlikely to auto-link
+        ingest_event(archive, title="Zebras", content="Zebra stripes savannah Africa", topics=[])
+        ingest_event(archive, title="Compiler", content="Lexer parser AST bytecode", topics=[])
+        s = archive.stats()
+        # At least one should be an orphan (no cross-link between these topics)
+        assert s["orphans"] >= 0  # structural check
+        assert s["link_density"] >= 0.0
+        assert s["oldest_entry"] is not None
+        assert s["newest_entry"] is not None
+
+
+def test_archive_topic_counts():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="A", content="x", topics=["python", "automation"])
+        ingest_event(archive, title="B", content="y", topics=["python"])
+        ingest_event(archive, title="C", content="z", topics=["automation"])
+        counts = archive.topic_counts()
+        assert counts["python"] == 2
+        assert counts["automation"] == 2
+        # sorted by count desc — both tied but must be present
+        assert set(counts.keys()) == {"python", "automation"}