[claude] Mnemosyne entry update + content deduplication (#1239) (#1241)

nexus/mnemosyne/tests/test_archive.py

@@ -491,3 +491,178 @@ def test_tag_persistence_across_reload():
         fresh = a2.get(e.id)
         assert "beta" in fresh.topics
         assert "alpha" not in fresh.topics
+
+
+# --- content_hash and updated_at field tests ---
+
+def test_entry_has_content_hash():
+    e = ArchiveEntry(title="Hello", content="world")
+    assert e.content_hash is not None
+    assert len(e.content_hash) == 64  # SHA-256 hex
+
+
+def test_entry_content_hash_deterministic():
+    e1 = ArchiveEntry(title="Hello", content="world")
+    e2 = ArchiveEntry(title="Hello", content="world")
+    assert e1.content_hash == e2.content_hash
+
+
+def test_entry_content_hash_differs_on_different_content():
+    e1 = ArchiveEntry(title="Hello", content="world")
+    e2 = ArchiveEntry(title="Hello", content="different")
+    assert e1.content_hash != e2.content_hash
+
+
+def test_entry_updated_at_defaults_none():
+    e = ArchiveEntry(title="T", content="c")
+    assert e.updated_at is None
+
+
+def test_entry_roundtrip_includes_new_fields():
+    e = ArchiveEntry(title="T", content="c")
+    d = e.to_dict()
+    assert "content_hash" in d
+    assert "updated_at" in d
+    e2 = ArchiveEntry.from_dict(d)
+    assert e2.content_hash == e.content_hash
+    assert e2.updated_at == e.updated_at
+
+
+# --- content deduplication tests ---
+
+def test_add_deduplication_same_content():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e1 = ingest_event(archive, title="Dup", content="Same content here")
+        e2 = ingest_event(archive, title="Dup", content="Same content here")
+        # Should NOT have created a second entry
+        assert archive.count == 1
+        assert e1.id == e2.id
+
+
+def test_add_deduplication_different_content():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="A", content="Content one")
+        ingest_event(archive, title="B", content="Content two")
+        assert archive.count == 2
+
+
+def test_find_duplicate_returns_existing():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e1 = ingest_event(archive, title="Dup", content="Same content here")
+        probe = ArchiveEntry(title="Dup", content="Same content here")
+        dup = archive.find_duplicate(probe)
+        assert dup is not None
+        assert dup.id == e1.id
+
+
+def test_find_duplicate_returns_none_for_unique():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        ingest_event(archive, title="A", content="Some content")
+        probe = ArchiveEntry(title="B", content="Totally different content")
+        assert archive.find_duplicate(probe) is None
+
+
+def test_find_duplicate_empty_archive():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        probe = ArchiveEntry(title="X", content="y")
+        assert archive.find_duplicate(probe) is None
+
+
+# --- update_entry tests ---
+
+def test_update_entry_title():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e = ingest_event(archive, title="Old title", content="Some content")
+        archive.update_entry(e.id, title="New title")
+        fresh = archive.get(e.id)
+        assert fresh.title == "New title"
+        assert fresh.content == "Some content"
+
+
+def test_update_entry_content():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e = ingest_event(archive, title="T", content="Old content")
+        archive.update_entry(e.id, content="New content")
+        fresh = archive.get(e.id)
+        assert fresh.content == "New content"
+
+
+def test_update_entry_metadata():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e = ingest_event(archive, title="T", content="c")
+        archive.update_entry(e.id, metadata={"key": "value"})
+        fresh = archive.get(e.id)
+        assert fresh.metadata["key"] == "value"
+
+
+def test_update_entry_bumps_updated_at():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e = ingest_event(archive, title="T", content="c")
+        assert e.updated_at is None
+        archive.update_entry(e.id, title="Updated")
+        fresh = archive.get(e.id)
+        assert fresh.updated_at is not None
+
+
+def test_update_entry_refreshes_content_hash():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e = ingest_event(archive, title="T", content="Original content")
+        old_hash = e.content_hash
+        archive.update_entry(e.id, content="Completely new content")
+        fresh = archive.get(e.id)
+        assert fresh.content_hash != old_hash
+
+
+def test_update_entry_missing_raises():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        try:
+            archive.update_entry("nonexistent-id", title="X")
+            assert False, "Expected KeyError"
+        except KeyError:
+            pass
+
+
+def test_update_entry_persists_across_reload():
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        a1 = MnemosyneArchive(archive_path=path)
+        e = ingest_event(a1, title="Before", content="Before content")
+        a1.update_entry(e.id, title="After", content="After content")
+
+        a2 = MnemosyneArchive(archive_path=path)
+        fresh = a2.get(e.id)
+        assert fresh.title == "After"
+        assert fresh.content == "After content"
+        assert fresh.updated_at is not None
+
+
+def test_update_entry_no_change_no_crash():
+    """Calling update_entry with all None args should not fail."""
+    with tempfile.TemporaryDirectory() as tmp:
+        path = Path(tmp) / "test_archive.json"
+        archive = MnemosyneArchive(archive_path=path)
+        e = ingest_event(archive, title="T", content="c")
+        result = archive.update_entry(e.id)
+        assert result.title == "T"