Fix: index document versions as their root document

The search index and the LLM index hold root documents only, a root being
indexed with its newest version's content. Every write path therefore had to
remember to hand them the root. Several did not: adding or deleting a note on
a version, restoring a trashed document together with its versions, and
reprocessing a version all wrote the version into the index under its own id,
where it could be returned as a separate search result. The paths that walk the
whole library did the same: the document_index reindex command put every
version in the search index, a full LLM index rebuild embedded every version,
and an incremental LLM update scoped to a version id indexed it under its own
id. Asking for documents like a version looked the version's own id up in the
index and silently found nothing.

WriteBatch.add_or_update, WriteBatch.add_or_update_ids and
llm_index_add_or_update_document now resolve a version to its root themselves.
The reindex command and update_llm_index only walk root documents, and an
incremental LLM update is scoped to the roots of the given ids through
versioning.root_document_ids, which add_or_update_ids shares. more_like_id
returns the root's id for a version. The reprocess task no longer picks the root
for the indexes and only still clears the caches of both documents.

src/documents/management/commands/document_index.py

@@ -67,18 +67,22 @@ class Command(PaperlessCommand):
                 if options.get("recreate"):
                     wipe_index(settings.INDEX_DIR)
 
-                documents = Document.objects.select_related(
+                documents = (
-                    "correspondent",
+                    Document.objects.filter(root_document__isnull=True)
-                    "document_type",
+                    .select_related(
-                    "storage_path",
+                        "correspondent",
-                    "owner",
+                        "document_type",
-                ).prefetch_related(
+                        "storage_path",
-                    "tags",
+                        "owner",
-                    "notes__user",
+                    )
-                    "custom_fields__field",
+                    .prefetch_related(
-                    "versions",
+                        "tags",
-                    "barcodes",
+                        "notes__user",
-                    "versions__barcodes",
+                        "custom_fields__field",
+                        "versions",
+                        "barcodes",
+                        "versions__barcodes",
+                    )
                 )
                 total = documents.count()
                 rebuild_kwargs = {}

src/documents/permissions.py

@@ -6,9 +6,13 @@ from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
 from django.db.models import Case
+from django.db.models import CharField
 from django.db.models import Count
+from django.db.models import Exists
+from django.db.models import F
 from django.db.models import IntegerField
 from django.db.models import Model
+from django.db.models import OuterRef
 from django.db.models import Q
 from django.db.models import QuerySet
 from django.db.models import Value
@@ -26,6 +30,7 @@ from rest_framework.permissions import BasePermission
 from rest_framework.permissions import DjangoObjectPermissions
 
 from documents.models import Document
+from documents.versioning import get_root_document
 
 
 class PaperlessObjectPermissions(DjangoObjectPermissions):
@@ -349,6 +354,7 @@ def permitted_object_ids(
     perm: str,
     *,
     include_deleted: bool = False,
+    parent_field: str | None = None,
 ) -> QuerySet[int]:
     """
     Generic version of ``permitted_document_ids`` for any model with an
@@ -357,6 +363,20 @@ def permitted_object_ids(
     soft-delete pattern (currently only ``Document``); for every other model
     it is accepted but has no effect, since those models have no soft-delete
     concept.
+
+    ``parent_field`` names a self-referencing foreign key whose target
+    authorizes the row (``Document.root_document``). A row with a parent is
+    visible exactly when its parent is, judged by the parent's owner and
+    grants, so the row's own owner and grants are ignored.
+
+    Guardian stores ``object_pk`` as a string, so each grant is an ``EXISTS``
+    keyed on the row's id cast to a string, which can use guardian's
+    (user, permission, object_pk) unique index. Casting every ``object_pk`` to
+    an integer for an ``id IN (...)`` is not indexable, and MariaDB cannot
+    materialize it inside the owner ``OR``, so it re-scans the user's grants
+    for every row. The user's groups are matched with an ``IN`` subquery
+    rather than a join through the membership table, which SQLite plans badly
+    once the grant tables grow.
     """
     has_soft_delete = hasattr(model, "global_objects")
     manager = (
@@ -364,8 +384,21 @@ def permitted_object_ids(
     )
     base_qs = manager.all().only("id", "owner")
 
+    owner_field, key_field = "owner", "pk"
+    if parent_field is not None:
+        owner_field, key_field = "authorizing_owner", "authorizing_id"
+        base_qs = base_qs.annotate(
+            authorizing_id=Coalesce(f"{parent_field}_id", "id"),
+            authorizing_owner=Case(
+                When(**{f"{parent_field}_id__isnull": True}, then=F("owner_id")),
+                default=F(f"{parent_field}__owner_id"),
+                output_field=IntegerField(),
+            ),
+        )
+    unowned = Q(**{f"{owner_field}__isnull": True})
+
     if user is None or not getattr(user, "is_authenticated", False):
-        return base_qs.filter(owner__isnull=True).values_list("id", flat=True)
+        return base_qs.filter(unowned).values_list("id", flat=True)
 
     # Deactivated users get nothing, deactivated superusers included, so this
     # has to come before the superuser shortcut. guardian's
@@ -389,20 +422,24 @@ def permitted_object_ids(
         "permission__content_type": content_type,
     }
 
-    user_perm_ids = (
+    key_as_text = Cast(OuterRef(key_field), CharField(max_length=64))
-        UserObjectPermission.objects.filter(user=user, **perm_filter)
+    granted_to_user = Exists(
-        .annotate(object_pk_int=Cast("object_pk", IntegerField()))
+        UserObjectPermission.objects.filter(
-        .values_list("object_pk_int", flat=True)
+            user=user,
+            object_pk=key_as_text,
+            **perm_filter,
+        ),
     )
-    group_perm_ids = (
+    granted_to_group = Exists(
-        GroupObjectPermission.objects.filter(group__user=user, **perm_filter)
+        GroupObjectPermission.objects.filter(
-        .annotate(object_pk_int=Cast("object_pk", IntegerField()))
+            group_id__in=user.groups.values("id"),
-        .values_list("object_pk_int", flat=True)
+            object_pk=key_as_text,
+            **perm_filter,
+        ),
     )
-    permitted_ids = user_perm_ids.union(group_perm_ids)
 
     return base_qs.filter(
-        Q(owner=user) | Q(owner__isnull=True) | Q(id__in=permitted_ids),
+        Q(**{owner_field: user.pk}) | unowned | granted_to_user | granted_to_group,
     ).values_list("id", flat=True)
 
 
@@ -471,30 +508,16 @@ def permitted_document_ids(
     ``include_deleted=True`` for callers that need to check permission on
     soft-deleted documents (e.g. trash restore). This intentionally avoids
     ``get_objects_for_user`` to keep the subquery small and index-friendly.
-    """
-    return permitted_object_ids(user, Document, perm, include_deleted=include_deleted)
 
-
+    A version is authorized by its root document, so a version's own owner and
-def documents_without_permitted_root(
+    grants never matter.
-    documents: QuerySet[Document],
-    user: User | None,
-    *,
-    perm: str = "view_document",
-    include_deleted: bool = False,
-) -> QuerySet[Document]:
     """
-    The documents the user lacks ``perm`` on. Versions are authorized by their
+    return permitted_object_ids(
-    root document, so a version's own owner is ignored. A single query, without
+        user,
-    loading the documents or joining the root.
+        Document,
-    """
+        perm,
-    return documents.annotate(
+        include_deleted=include_deleted,
-        root_id=Coalesce("root_document_id", "id"),
+        parent_field="root_document",
-    ).exclude(
-        root_id__in=permitted_document_ids(
-            user,
-            perm=perm,
-            include_deleted=include_deleted,
-        ),
     )
 
 
@@ -654,7 +677,14 @@ def has_perms_owner_aware(user, perms, obj):
     single-object check still has many production callers. Several callers
     remain across ``documents/``, ``paperless_mail/``, and ``paperless_ai/``
     -- grep for this function name before removing it.
+
+    A document version is authorized by its root document, like in
+    ``permitted_document_ids``, so a version's own owner and grants never
+    matter. Fetch the root with ``select_related("root_document__owner")`` to
+    avoid extra queries.
     """
+    if isinstance(obj, Document):
+        obj = get_root_document(obj)
     checker = ObjectPermissionChecker(user)
     return obj.owner is None or obj.owner == user or checker.has_perm(perms, obj)
 

src/documents/search/_backend.py

@@ -284,9 +284,14 @@ class WriteBatch:
         and adding the new version. This ensures stale document data (e.g., after
         permission changes) doesn't persist in the index.
 
+        Only root documents are indexed, with their effective content, so a
+        version is indexed as its root document.
+
         Args:
             document: Django Document instance to index
         """
+        if document.root_document_id is not None:
+            document = document.root_document
         self.remove(document.pk)
         doc = self._backend._build_tantivy_doc(document)
         self._writer.add_document(doc)
@@ -311,20 +316,22 @@ class WriteBatch:
         An id with no matching document (e.g. deleted between the caller
         collecting ids and the batch running) is silently skipped, matching
         ``add_or_update()``'s existing single-document deferred-task behavior
-        rather than erroring or leaving a stale index entry.
+        rather than erroring or leaving a stale index entry. The id of a
+        version stands for its root document.
 
         Args:
             ids: Primary keys of Document instances to index
         """
         from documents.models import Document
         from documents.versioning import annotate_effective_content
+        from documents.versioning import root_document_ids
 
         ids = list(ids)
         if not ids:
             return
 
         queryset = annotate_effective_content(
-            Document.objects.filter(pk__in=ids)
+            Document.objects.filter(pk__in=root_document_ids(ids))
             .select_related("correspondent", "document_type", "storage_path", "owner")
             .prefetch_related(
                 "tags",

src/documents/serialisers.py

@@ -90,7 +90,6 @@ from documents.templating.utils import convert_format_str_to_template_format
 from documents.templating.workflows import validate_workflow_template
 from documents.validators import uri_validator
 from documents.validators import url_validator
-from documents.versioning import get_root_document
 from documents.versioning import has_prefetched_effective_content
 from documents.versioning import sort_versions_newest_first
 
@@ -2895,7 +2894,7 @@ class ShareLinkSerializer(OwnedObjectSerializer):
             and has_perms_owner_aware(
                 self.user,
                 "view_document",
-                get_root_document(document),
+                document,
             )
         ):
             return document

src/documents/tasks.py

@@ -490,23 +490,20 @@ def update_document_content_maybe_archive_file(
                     shutil.move(thumbnail, document.thumbnail_path)
 
             document.refresh_from_db()
-            root_document = (
-                document.root_document if document.root_document_id else document
-            )
             logger.info(
-                f"Updating index for document {root_document.pk} ({document.archive_checksum})",
+                f"Updating index for document {document_id} ({document.archive_checksum})",
             )
             from documents.search import get_backend
 
-            get_backend().add_or_update(root_document)
+            get_backend().add_or_update(document)
 
             ai_config = AIConfig()
             if ai_config.llm_index_enabled:
-                llm_index_add_or_update_document(root_document)
+                llm_index_add_or_update_document(document)
 
             clear_document_caches(document.pk)
-            if root_document.pk != document.pk:
+            if document.root_document_id is not None:
-                clear_document_caches(root_document.pk)
+                clear_document_caches(document.root_document_id)
 
         except Exception:
             logger.exception(

src/documents/tests/search/test_backend.py

@@ -293,6 +293,80 @@ class TestAddOrUpdateIds:
         assert backend.search_ids("updated", user=None) == [doc.pk]
 
 
+class TestVersionsAreIndexedAsTheirRoot:
+    """Only root documents are indexed, with their effective content, so
+    every write path that is handed a version indexes its root instead."""
+
+    @staticmethod
+    def _root_with_version() -> tuple[Document, Document]:
+        root = DocumentFactory(title="Statement", content="stale text")
+        version = DocumentFactory(
+            title="Statement",
+            content="latest text",
+            root_document=root,
+            version_index=1,
+        )
+        return root, version
+
+    def test_add_or_update_indexes_the_root_of_a_version(
+        self,
+        backend: TantivyBackend,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - The version is passed to add_or_update
+        THEN:
+            - The root is indexed with the version's text, and the version is not
+        """
+        root, version = self._root_with_version()
+
+        backend.add_or_update(version)
+
+        assert backend.search_ids("latest", user=None) == [root.pk]
+        assert backend.search_ids("stale", user=None) == []
+
+    def test_add_or_update_ids_indexes_each_root_once(
+        self,
+        backend: TantivyBackend,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - Both ids are passed to add_or_update_ids
+        THEN:
+            - The root is indexed once and the version is not indexed
+        """
+        root, version = self._root_with_version()
+
+        with backend.batch_update() as batch:
+            batch.add_or_update_ids([version.pk, root.pk])
+
+        assert backend.search_ids("Statement", user=None) == [root.pk]
+        assert backend.search_ids("latest", user=None) == [root.pk]
+
+    def test_add_or_update_ids_resolves_a_lone_version(
+        self,
+        backend: TantivyBackend,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - Only the version's id is passed to add_or_update_ids
+        THEN:
+            - The root is indexed
+        """
+        root, version = self._root_with_version()
+
+        with backend.batch_update() as batch:
+            batch.add_or_update_ids([version.pk])
+
+        assert backend.search_ids("latest", user=None) == [root.pk]
+
+
 class TestSearch:
     """Test search query parsing and matching via search_ids."""
 

src/documents/tests/test_api_search.py

@@ -1196,6 +1196,59 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertIn(d3.id, result_ids)
         self.assertNotIn(d4.id, result_ids)
 
+    def test_search_more_like_version_uses_its_root(self) -> None:
+        """
+        GIVEN:
+            - A document similar in content to a root document, and one that is not
+            - A version of the root document, which is never indexed
+        WHEN:
+            - API request for more like the version
+        THEN:
+            - The documents similar to the root are returned, not the version
+        """
+        indexed = {}
+        for name, title, content, day in (
+            ("root", "bank statement 1", "things i paid for in august", (2019, 3, 4)),
+            (
+                "similar",
+                "bank statement 3",
+                "things i paid for in september",
+                (2020, 7, 9),
+            ),
+            (
+                "other",
+                "Quarterly Report",
+                "quarterly revenue profit margin",
+                (2021, 11, 30),
+            ),
+        ):
+            with time_machine.travel(
+                timezone.make_aware(datetime.datetime(*day)),
+                tick=False,
+            ):
+                indexed[name] = DocumentFactory(
+                    title=title,
+                    content=content,
+                    created=datetime.date(*day),
+                    added=timezone.make_aware(datetime.datetime(*day)),
+                )
+        version = DocumentFactory(
+            root_document=indexed["root"],
+            version_index=1,
+            content="things i paid for in august",
+        )
+        backend = get_backend()
+        for document in indexed.values():
+            backend.add_or_update(document)
+
+        response = self.client.get(f"/api/documents/?more_like_id={version.id}")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        result_ids = [r["id"] for r in response.data["results"]]
+        self.assertIn(indexed["similar"].id, result_ids)
+        self.assertNotIn(indexed["other"].id, result_ids)
+        self.assertNotIn(version.id, result_ids)
+
     def test_more_like_requires_id_of_existing_document(self) -> None:
         """
         GIVEN:

src/documents/tests/test_management.py

@@ -22,6 +22,7 @@ from documents.models import Document
 from documents.tasks import update_document_content_maybe_archive_file
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
+from paperless_testing.factories import DocumentFactory
 
 sample_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
 
@@ -116,6 +117,27 @@ class TestMakeIndex:
         call_command("document_index", "reindex", skip_checks=True)
         mock_get_backend.return_value.rebuild.assert_called_once()
 
+    def test_reindex_skips_versions(self, mocker: MockerFixture) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - The reindex command runs
+        THEN:
+            - Only the root document is handed to the rebuild, since a version
+              is indexed as its root
+        """
+        root = DocumentFactory()
+        DocumentFactory(root_document=root, version_index=1)
+        mock_get_backend = mocker.patch(
+            "documents.management.commands.document_index.get_backend",
+        )
+
+        call_command("document_index", "reindex", skip_checks=True)
+
+        documents = mock_get_backend.return_value.rebuild.call_args.args[0]
+        assert list(documents.values_list("pk", flat=True)) == [root.pk]
+
     def test_optimize(self) -> None:
         """Optimize command must execute without error (Tantivy handles optimization automatically)."""
         call_command("document_index", "optimize", skip_checks=True)

src/documents/tests/test_permission_filtering_security.py

@@ -18,6 +18,7 @@ from documents.models import Correspondent
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
+from documents.permissions import has_perms_owner_aware
 from documents.permissions import permitted_document_ids
 from documents.permissions import permitted_object_ids
 from documents.permissions import restrict_queryset_to_visible
@@ -32,6 +33,8 @@ from paperless_testing.permissions import grant_global
 from paperless_testing.permissions import grant_object
 
 if TYPE_CHECKING:
+    from django.contrib.auth.models import User
+
     from paperless_testing.dirs import PaperlessDirs
 
 
@@ -178,6 +181,382 @@ class TestPermittedDocumentIdsIncludeDeleted:
         )
 
 
+@pytest.mark.django_db
+class TestPermittedDocumentIdsVersions:
+    """
+    A version is authorized by its root document: the version's own owner and
+    grants never matter.
+    """
+
+    @pytest.mark.parametrize(
+        ("root_owner", "version_owner", "expected_visible"),
+        [
+            pytest.param(
+                "other",
+                "nobody",
+                False,
+                id="unowned-version-of-private-root",
+            ),
+            pytest.param("other", "user", False, id="own-version-of-private-root"),
+            pytest.param("user", "other", True, id="foreign-version-of-own-root"),
+            pytest.param("user", "nobody", True, id="unowned-version-of-own-root"),
+            pytest.param("nobody", "other", True, id="private-version-of-unowned-root"),
+        ],
+    )
+    def test_version_follows_root_owner(
+        self,
+        root_owner: str,
+        version_owner: str,
+        *,
+        expected_visible: bool,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document and a version with differing owners
+        WHEN:
+            - The permitted document ids are resolved for the user
+        THEN:
+            - The version is visible exactly when its root is
+        """
+        user = UserFactory()
+        owners = {"user": user, "other": UserFactory(), "nobody": None}
+        root = DocumentFactory(owner=owners[root_owner])
+        version = DocumentFactory(root_document=root, owner=owners[version_owner])
+
+        visible = set(permitted_document_ids(user))
+
+        assert (version.pk in visible) is expected_visible
+        assert (root.pk in visible) is expected_visible
+
+    @staticmethod
+    def grantee(user: User, kind: str) -> User | Group:
+        """The user itself, or a new group the user belongs to."""
+        if kind == "user":
+            return user
+        group = Group.objects.create(name="shared")
+        user.groups.add(group)
+        return group
+
+    @pytest.mark.parametrize(
+        "grantee_kind",
+        [pytest.param("user", id="user"), pytest.param("group", id="group")],
+    )
+    def test_grant_on_root_applies_to_version(self, grantee_kind: str) -> None:
+        """
+        GIVEN:
+            - A private root document shared with a user or one of their groups
+            - A version of it owned by someone else
+        WHEN:
+            - The permitted document ids are resolved for the user
+        THEN:
+            - Both the root and the version are visible
+            - A user without the grant sees neither
+        """
+        user = UserFactory()
+        stranger = UserFactory()
+        root = DocumentFactory(owner=UserFactory())
+        version = DocumentFactory(root_document=root, owner=UserFactory())
+        grant_object(self.grantee(user, grantee_kind), root, "view_document")
+
+        assert_visible_document_ids(
+            permitted_document_ids(user),
+            expected_visible=[root.pk, version.pk],
+            expected_hidden=[],
+        )
+        assert_visible_document_ids(
+            permitted_document_ids(stranger),
+            expected_visible=[],
+            expected_hidden=[root.pk, version.pk],
+        )
+
+    @pytest.mark.parametrize(
+        "grantee_kind",
+        [pytest.param("user", id="user"), pytest.param("group", id="group")],
+    )
+    def test_grant_on_version_is_ignored(self, grantee_kind: str) -> None:
+        """
+        GIVEN:
+            - A private root document
+            - A version with an explicit grant for the user or one of their groups
+        WHEN:
+            - The permitted document ids are resolved for the user
+        THEN:
+            - Neither the root nor the version is visible
+        """
+        user = UserFactory()
+        root = DocumentFactory(owner=UserFactory())
+        version = DocumentFactory(root_document=root, owner=UserFactory())
+        grant_object(self.grantee(user, grantee_kind), version, "view_document")
+
+        assert_visible_document_ids(
+            permitted_document_ids(user),
+            expected_visible=[],
+            expected_hidden=[root.pk, version.pk],
+        )
+
+    def test_grant_on_one_root_does_not_reach_another_roots_version(self) -> None:
+        """
+        GIVEN:
+            - Two private roots, each with a version
+            - The user may view only the first root
+        WHEN:
+            - The permitted document ids are resolved for the user
+        THEN:
+            - Only the first root and its version are visible
+        """
+        user = UserFactory()
+        first = DocumentFactory(owner=UserFactory())
+        first_version = DocumentFactory(root_document=first, owner=UserFactory())
+        second = DocumentFactory(owner=UserFactory())
+        second_version = DocumentFactory(root_document=second, owner=user)
+        grant_object(user, first, "view_document")
+
+        assert_visible_document_ids(
+            permitted_document_ids(user),
+            expected_visible=[first.pk, first_version.pk],
+            expected_hidden=[second.pk, second_version.pk],
+        )
+
+    def test_user_in_several_groups(self) -> None:
+        """
+        GIVEN:
+            - A user in two groups
+            - Two private roots shared with one group each, and a third shared with nobody
+            - A version of each root
+        WHEN:
+            - The permitted document ids are resolved for the user
+        THEN:
+            - The two shared roots and their versions are visible
+            - The third root and its version are not
+        """
+        user = UserFactory()
+        groups = [Group.objects.create(name=f"group{i}") for i in range(2)]
+        user.groups.add(*groups)
+        shared = [DocumentFactory(owner=UserFactory()) for _ in groups]
+        for root, group in zip(shared, groups, strict=True):
+            grant_object(group, root, "view_document")
+        unshared = DocumentFactory(owner=UserFactory())
+        shared_versions = [
+            DocumentFactory(root_document=root, owner=UserFactory()) for root in shared
+        ]
+        unshared_version = DocumentFactory(root_document=unshared, owner=None)
+
+        assert_visible_document_ids(
+            permitted_document_ids(user),
+            expected_visible=[
+                *(root.pk for root in shared),
+                *(version.pk for version in shared_versions),
+            ],
+            expected_hidden=[unshared.pk, unshared_version.pk],
+        )
+
+    def test_permission_is_resolved_through_the_root(self) -> None:
+        """
+        GIVEN:
+            - A private root document where the user may view and change
+        WHEN:
+            - The permitted ids are resolved for view, change and delete
+        THEN:
+            - The version is visible for view and change only
+        """
+        user = UserFactory()
+        root = DocumentFactory(owner=UserFactory())
+        version = DocumentFactory(root_document=root, owner=UserFactory())
+        grant_object(user, root, "view_document", "change_document")
+
+        assert version.pk in set(permitted_document_ids(user))
+        assert version.pk in set(permitted_document_ids(user, perm="change_document"))
+        assert version.pk in set(
+            permitted_document_ids(user, perm="documents.change_document"),
+        )
+        assert version.pk not in set(
+            permitted_document_ids(user, perm="delete_document"),
+        )
+
+    def test_anonymous_sees_versions_of_unowned_roots_only(self) -> None:
+        """
+        GIVEN:
+            - A version owned by nobody under a private root
+            - A version owned by someone under an unowned root
+        WHEN:
+            - The permitted document ids are resolved for an anonymous user
+        THEN:
+            - Only the version of the unowned root is visible
+        """
+        private_root = DocumentFactory(owner=UserFactory())
+        private_version = DocumentFactory(root_document=private_root, owner=None)
+        open_root = DocumentFactory(owner=None)
+        open_version = DocumentFactory(root_document=open_root, owner=UserFactory())
+
+        assert_visible_document_ids(
+            permitted_document_ids(AnonymousUser()),
+            expected_visible=[open_root.pk, open_version.pk],
+            expected_hidden=[private_root.pk, private_version.pk],
+        )
+
+    def test_deleted_versions_follow_their_deleted_root(self) -> None:
+        """
+        GIVEN:
+            - A soft-deleted root document and its version, which deleting the
+              root soft-deletes too; the version is owned by someone else
+        WHEN:
+            - The permitted document ids are resolved with and without deleted
+              documents
+        THEN:
+            - Nothing is visible by default
+            - With deleted documents included, the version is visible to the
+              root's owner and not to the version's own owner
+        """
+        owner = UserFactory()
+        version_owner = UserFactory()
+        root = DocumentFactory(owner=owner)
+        version = DocumentFactory(root_document=root, owner=version_owner)
+        root.delete()
+
+        assert not {root.pk, version.pk} & set(permitted_document_ids(owner))
+        assert_visible_document_ids(
+            permitted_document_ids(owner, include_deleted=True),
+            expected_visible=[root.pk, version.pk],
+            expected_hidden=[],
+        )
+        assert_visible_document_ids(
+            permitted_document_ids(version_owner, include_deleted=True),
+            expected_visible=[],
+            expected_hidden=[root.pk, version.pk],
+        )
+
+    @pytest.mark.parametrize(
+        "is_superuser",
+        [
+            pytest.param(False, id="regular-user"),
+            pytest.param(True, id="superuser"),
+        ],
+    )
+    def test_inactive_user_sees_no_versions(self, *, is_superuser: bool) -> None:
+        """
+        GIVEN:
+            - An inactive user, possibly a superuser, who owns a root and its version
+        WHEN:
+            - The permitted document ids are resolved for them
+        THEN:
+            - Nothing is visible
+        """
+        user = UserFactory(is_active=False, is_superuser=is_superuser)
+        root = DocumentFactory(owner=user)
+        version = DocumentFactory(root_document=root, owner=user)
+
+        assert_visible_document_ids(
+            permitted_document_ids(user),
+            expected_visible=[],
+            expected_hidden=[root.pk, version.pk],
+        )
+
+    def test_superuser_sees_all_versions(self) -> None:
+        """
+        GIVEN:
+            - A private root owned by someone else, with a version
+        WHEN:
+            - The permitted document ids are resolved for a superuser
+        THEN:
+            - Both the root and the version are visible
+        """
+        superuser = UserFactory(superuser=True)
+        root = DocumentFactory(owner=UserFactory())
+        version = DocumentFactory(root_document=root, owner=UserFactory())
+
+        assert_visible_document_ids(
+            permitted_document_ids(superuser),
+            expected_visible=[root.pk, version.pk],
+            expected_hidden=[],
+        )
+
+
+@pytest.mark.django_db
+class TestHasPermsOwnerAwareVersions:
+    """
+    The single-object check agrees with permitted_document_ids: a version is
+    authorized by its root document.
+    """
+
+    @pytest.mark.parametrize(
+        ("root_owner", "version_owner", "expected"),
+        [
+            pytest.param(
+                "other",
+                "nobody",
+                False,
+                id="unowned-version-of-private-root",
+            ),
+            pytest.param("other", "user", False, id="own-version-of-private-root"),
+            pytest.param("user", "other", True, id="foreign-version-of-own-root"),
+            pytest.param("nobody", "other", True, id="private-version-of-unowned-root"),
+        ],
+    )
+    def test_version_follows_root_owner(
+        self,
+        root_owner: str,
+        version_owner: str,
+        *,
+        expected: bool,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document and a version with differing owners
+        WHEN:
+            - The single-object check runs for the version
+        THEN:
+            - The version is allowed exactly when its root is
+        """
+        user = UserFactory()
+        owners = {"user": user, "other": UserFactory(), "nobody": None}
+        root = DocumentFactory(owner=owners[root_owner])
+        version = DocumentFactory(root_document=root, owner=owners[version_owner])
+
+        assert has_perms_owner_aware(user, "view_document", version) is expected
+        assert has_perms_owner_aware(user, "view_document", root) is expected
+
+    def test_grant_on_root_applies_and_grant_on_version_does_not(self) -> None:
+        """
+        GIVEN:
+            - A private root with a version, and a second private root with a version
+            - The user may change only the first root, and was granted the second
+              root's version directly
+        WHEN:
+            - The single-object check runs for each version
+        THEN:
+            - Only the first root's version is allowed
+        """
+        user = UserFactory()
+        shared_root = DocumentFactory(owner=UserFactory())
+        shared_version = DocumentFactory(root_document=shared_root, owner=UserFactory())
+        private_root = DocumentFactory(owner=UserFactory())
+        private_version = DocumentFactory(
+            root_document=private_root,
+            owner=UserFactory(),
+        )
+        grant_object(user, shared_root, "change_document")
+        grant_object(user, private_version, "change_document")
+
+        assert has_perms_owner_aware(user, "change_document", shared_version)
+        assert not has_perms_owner_aware(user, "change_document", private_version)
+
+    def test_other_models_use_their_own_owner(self) -> None:
+        """
+        GIVEN:
+            - A tag owned by someone else, and one owned by the user
+        WHEN:
+            - The single-object check runs for each
+        THEN:
+            - Only the user's own tag is allowed without a grant
+        """
+        user = UserFactory()
+        mine = TagFactory(owner=user)
+        theirs = TagFactory(owner=UserFactory())
+
+        assert has_perms_owner_aware(user, "view_tag", mine)
+        assert not has_perms_owner_aware(user, "view_tag", theirs)
+
+
 @pytest.mark.django_db
 class TestAiChatAllDocumentsPermissionBoundary:
     """

src/documents/tests/test_tasks.py

@@ -310,7 +310,7 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
 
     @mock.patch("documents.tasks.clear_document_caches")
     @mock.patch("documents.search.get_backend")
-    def test_update_content_version_indexes_root(
+    def test_update_content_version_clears_caches_for_root(
         self,
         mock_get_backend: mock.Mock,
         mock_clear_caches: mock.Mock,
@@ -321,8 +321,8 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         WHEN:
             - Update content task is called for the version
         THEN:
-            - The version's content is updated
+            - The version's content is updated, not the root's
-            - The root document is indexed rather than the version
+            - The document is indexed
             - Caches are cleared for both
         """
         root, version = self._create_root_with_version()
@@ -334,8 +334,7 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
             "my document",
         )
         self.assertEqual(Document.objects.get(pk=root.pk).content, "root content")
-        indexed = mock_get_backend.return_value.add_or_update.call_args.args[0]
+        mock_get_backend.return_value.add_or_update.assert_called_once()
-        self.assertEqual(indexed.pk, root.pk)
         mock_clear_caches.assert_has_calls(
             [mock.call(version.pk), mock.call(root.pk)],
         )
@@ -343,7 +342,7 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
     @override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="huggingface")
     @mock.patch("documents.tasks.llm_index_add_or_update_document")
     @mock.patch("documents.search.get_backend")
-    def test_update_content_version_updates_llm_index_for_root(
+    def test_update_content_version_updates_llm_index(
         self,
         mock_get_backend: mock.Mock,
         mock_llm_index: mock.Mock,
@@ -355,14 +354,13 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         WHEN:
             - Update content task is called for the version
         THEN:
-            - The LLM index is updated for the root document, not the version
+            - The LLM index is updated
         """
-        root, version = self._create_root_with_version()
+        _, version = self._create_root_with_version()
 
         tasks.update_document_content_maybe_archive_file(version.pk)
 
         mock_llm_index.assert_called_once()
-        self.assertEqual(mock_llm_index.call_args.args[0].pk, root.pk)
 
 
 class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):

src/documents/versioning.py

@@ -17,9 +17,26 @@ from django.db.models.functions import RowNumber
 from documents.models import Document
 
 if TYPE_CHECKING:
+    from collections.abc import Iterable
+
     from rest_framework.request import Request
 
 
+def root_document_ids(ids: Iterable[int]) -> QuerySet[int]:
+    """
+    The ids of the root documents of the given documents: a root stands for
+    itself and a version for its root. Only the indexes' bookkeeping needs
+    this, since they hold root documents only.
+    """
+    return (
+        Document.objects.filter(pk__in=ids)
+        .annotate(root_id=Coalesce("root_document_id", "id"))
+        .order_by()
+        .values_list("root_id", flat=True)
+        .distinct()
+    )
+
+
 def versions_newest_first(documents: QuerySet[Document]) -> QuerySet[Document]:
     """
     Sorts versions so the newest one comes first using version_index and not on id,

src/documents/views.py

@@ -174,7 +174,6 @@ from documents.permissions import TrashPermissions
 from documents.permissions import ViewDocumentsPermissions
 from documents.permissions import annotate_document_count_by_ids
 from documents.permissions import annotate_document_count_for_related_queryset
-from documents.permissions import documents_without_permitted_root
 from documents.permissions import get_document_count_filter_for_user
 from documents.permissions import get_objects_for_user_owner_aware
 from documents.permissions import has_global_statistics_permission
@@ -330,9 +329,10 @@ def _get_tantivy_query_and_mode(params):
 def _get_more_like_id(query_params: dict[str, Any], user: User | None) -> int:
     try:
         more_like_doc_id = int(query_params["more_like_id"])
-        more_like_doc = Document.objects.select_related("owner").get(
+        more_like_doc = Document.objects.select_related(
-            pk=more_like_doc_id,
+            "owner",
-        )
+            "root_document__owner",
+        ).get(pk=more_like_doc_id)
     except (TypeError, ValueError, Document.DoesNotExist):
         raise PermissionDenied(_("Invalid more_like_id"))
 
@@ -343,7 +343,8 @@ def _get_more_like_id(query_params: dict[str, Any], user: User | None) -> int:
     ):
         raise PermissionDenied(_("Insufficient permissions."))
 
-    return more_like_doc_id
+    # Only root documents are indexed, a version stands for its root
+    return more_like_doc.root_document_id or more_like_doc.pk
 
 
 class SearchParams(NamedTuple):
@@ -1560,7 +1561,7 @@ class DocumentViewSet(
         if request.user is not None and not has_perms_owner_aware(
             request.user,
             "change_document",
-            get_root_document(doc),
+            doc,
         ):
             return HttpResponseForbidden("Insufficient permissions")
 
@@ -1623,7 +1624,7 @@ class DocumentViewSet(
         if request.user is not None and not has_perms_owner_aware(
             request.user,
             "change_document",
-            get_root_document(doc),
+            doc,
         ):
             return HttpResponseForbidden("Insufficient permissions")
 
@@ -1876,7 +1877,7 @@ class DocumentViewSet(
             if currentUser is not None and not has_perms_owner_aware(
                 currentUser,
                 "view_document",
-                get_root_document(doc),
+                doc,
             ):
                 return HttpResponseForbidden("Insufficient permissions to view notes")
         except Document.DoesNotExist:
@@ -1898,7 +1899,7 @@ class DocumentViewSet(
                 if currentUser is not None and not has_perms_owner_aware(
                     currentUser,
                     "change_document",
-                    get_root_document(doc),
+                    doc,
                 ):
                     return HttpResponseForbidden(
                         "Insufficient permissions to create notes",
@@ -1941,7 +1942,7 @@ class DocumentViewSet(
             if currentUser is not None and not has_perms_owner_aware(
                 currentUser,
                 "change_document",
-                get_root_document(doc),
+                doc,
             ):
                 return HttpResponseForbidden("Insufficient permissions to delete notes")
 
@@ -1991,7 +1992,7 @@ class DocumentViewSet(
             if currentUser is not None and not has_perms_owner_aware(
                 currentUser,
                 "change_document",
-                get_root_document(doc),
+                doc,
             ):
                 return HttpResponseForbidden(
                     "Insufficient permissions to add share link",
@@ -2117,7 +2118,7 @@ class DocumentViewSet(
         documents = Document.objects.filter(pk__in=document_ids)
         if (
             request.user is not None
-            and documents_without_permitted_root(documents, request.user).exists()
+            and documents.exclude(id__in=permitted_document_ids(request.user)).exists()
         ):
             return HttpResponseForbidden("Insufficient permissions")
 
@@ -2452,7 +2453,7 @@ class ChatStreamingView(GenericAPIView[Any]):
             if not has_perms_owner_aware(
                 request.user,
                 "view_document",
-                get_root_document(document),
+                document,
             ):
                 return HttpResponseForbidden("Insufficient permissions")
 
@@ -3009,12 +3010,8 @@ class DocumentOperationPermissionMixin(PassUserMixin, DocumentSelectionMixin):
             user.has_perm(
                 "documents.change_document",
             )
-            and not Document.global_objects.filter(
+            and not Document.global_objects.filter(pk__in=documents)
-                pk__in=[doc.pk for doc in root_docs],
+            .exclude(pk__in=permitted_document_ids(user, perm="change_document"))
-            )
-            .exclude(
-                pk__in=permitted_document_ids(user, perm="change_document"),
-            )
             .exists()
         )
 
@@ -3627,7 +3624,7 @@ class SelectionDataView(DocumentSelectionMixin, GenericAPIView[Any]):
         documents = Document.objects.filter(pk__in=ids)
         if (
             documents.count() != len(ids)
-            or documents_without_permitted_root(documents, request.user).exists()
+            or documents.exclude(id__in=permitted_document_ids(request.user)).exists()
         ):
             return HttpResponseForbidden("Insufficient permissions")
 
@@ -4124,21 +4121,16 @@ class BulkDownloadView(DocumentSelectionMixin, GenericAPIView[Any]):
             validated_data=serializer.validated_data,
         )
         documents = Document.objects.filter(pk__in=ids)
-        versioned_documents = []
         compression = serializer.validated_data.get("compression")
         content = serializer.validated_data.get("content")
         follow_filename_format = serializer.validated_data.get("follow_formatting")
 
-        permitted_ids = set(permitted_document_ids(request.user))
+        if documents.exclude(id__in=permitted_document_ids(request.user)).exists():
-        for document in documents:
+            return HttpResponseForbidden("Insufficient permissions")
-            root_doc = get_root_document(document)
+        versioned_documents = [
-            if root_doc.pk not in permitted_ids:
+            get_latest_version_for_root(get_root_document(document))
-                return HttpResponseForbidden("Insufficient permissions")
+            for document in documents
-            versioned_documents.append(
+        ]
-                get_latest_version_for_root(
-                    root_doc,
-                ),
-            )
 
         if content == "both":
             strategy_class = OriginalAndArchiveStrategy
@@ -4811,7 +4803,7 @@ class ShareLinkBundleViewSet(PassUserMixin, ModelViewSet[ShareLinkBundle]):
             )
 
         denied_id = (
-            documents_without_permitted_root(documents_qs, request.user)
+            documents_qs.exclude(id__in=permitted_document_ids(request.user))
             .order_by("pk")
             .values_list("pk", flat=True)
             .first()
@@ -5657,11 +5649,12 @@ class TrashView(ListModelMixin, PassUserMixin):
             if doc_ids is not None
             else self.filter_queryset(self.get_queryset()).all()
         )
-        if documents_without_permitted_root(
+        if docs.exclude(
-            docs,
+            id__in=permitted_document_ids(
-            request.user,
+                request.user,
-            perm="delete_document",
+                perm="delete_document",
-            include_deleted=True,
+                include_deleted=True,
+            ),
         ).exists():
             return HttpResponseForbidden("Insufficient permissions")
         action = serializer.validated_data.get("action")

src/paperless_ai/indexing.py

@@ -17,6 +17,7 @@ from documents.models import PaperlessTask
 from documents.utils import IterWrapper
 from documents.utils import QuerySetStream
 from documents.utils import identity
+from documents.versioning import root_document_ids
 from paperless.config import AIConfig
 from paperless_ai.db import db_connection_released
 from paperless_ai.embedding import build_llm_index_text
@@ -443,11 +444,11 @@ def update_llm_index(
                 "Skipping LLM index update: migration check deferred; "
                 "will retry next run."
             )
-    documents = Document.objects.select_related(
+    documents = (
-        "correspondent",
+        Document.objects.filter(root_document__isnull=True)
-        "document_type",
+        .select_related("correspondent", "document_type", "storage_path")
-        "storage_path",
+        .prefetch_related("tags", "notes", "custom_fields__field")
-    ).prefetch_related("tags", "notes", "custom_fields__field")
+    )
     no_documents = not documents.exists()
 
     # Fast exit before touching config: nothing to index and no existing index.
@@ -483,7 +484,7 @@ def update_llm_index(
             msg = "LLM index rebuilt successfully."
         else:
             scoped_documents = (
-                documents.filter(id__in=document_ids)
+                documents.filter(id__in=root_document_ids(document_ids))
                 if document_ids is not None
                 else documents
             )
@@ -510,7 +511,12 @@ def update_llm_index(
 
 
 def llm_index_add_or_update_document(document: Document):
-    """Add or atomically replace a document's chunks in the index."""
+    """
+    Add or atomically replace a document's chunks in the index. Only root
+    documents are indexed, so a version is indexed as its root document.
+    """
+    if document.root_document_id is not None:
+        document = document.root_document
     config = AIConfig()
     new_nodes = build_document_node(
         document,

src/paperless_ai/tests/test_ai_indexing.py

@@ -388,6 +388,83 @@ def test_update_llm_index_partial_update(
     assert after[str(doc2.pk)] == before[str(doc2.pk)]
 
 
+@pytest.mark.django_db
+class TestLlmIndexVersions:
+    """The LLM index holds root documents only: a version is indexed as its root."""
+
+    def test_add_or_update_document_indexes_a_version_as_its_root(
+        self,
+        temp_llm_index_dir: Path,
+        mock_embed_model: FakeEmbedding,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - The version is passed to llm_index_add_or_update_document
+        THEN:
+            - Only the root document is in the index
+        """
+        root = DocumentFactory(content="root content")
+        version = DocumentFactory(root_document=root, version_index=1)
+
+        indexing.llm_index_add_or_update_document(version)
+
+        with indexing.get_vector_store() as store:
+            indexed = store.get_modified_times()
+
+        assert set(indexed) == {str(root.pk)}
+
+    def test_rebuild_skips_versions(
+        self,
+        temp_llm_index_dir: Path,
+        mock_embed_model: FakeEmbedding,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - The LLM index is rebuilt
+        THEN:
+            - Only the root document is in the index
+        """
+        root = DocumentFactory()
+        DocumentFactory(root_document=root, version_index=1)
+
+        indexing.update_llm_index(rebuild=True)
+
+        with indexing.get_vector_store() as store:
+            indexed = store.get_modified_times()
+
+        assert set(indexed) == {str(root.pk)}
+
+    def test_incremental_update_by_version_id_refreshes_the_root(
+        self,
+        temp_llm_index_dir: Path,
+        mock_embed_model: FakeEmbedding,
+    ) -> None:
+        """
+        GIVEN:
+            - An indexed root document with a version whose root was modified since
+        WHEN:
+            - An incremental update is scoped to the version's id
+        THEN:
+            - The root's entry is refreshed and no entry exists for the version
+        """
+        root = DocumentFactory()
+        version = DocumentFactory(root_document=root, version_index=1)
+        indexing.update_llm_index(rebuild=True)
+        Document.objects.filter(pk=root.pk).update(modified=timezone.now())
+        root.refresh_from_db()
+
+        indexing.update_llm_index(document_ids=[version.pk])
+
+        with indexing.get_vector_store() as store:
+            indexed = store.get_modified_times()
+
+        assert indexed == {str(root.pk): root.modified.isoformat()}
+
+
 @pytest.mark.django_db
 def test_add_or_update_document_updates_existing_entry(
     temp_llm_index_dir: Path,
@@ -637,6 +714,7 @@ class TestLlmIndexAddOrUpdateDocumentEmptyContent:
 
         doc = MagicMock(spec=Document)
         doc.id = 42
+        doc.root_document_id = None
         # Must not raise
         indexing.llm_index_add_or_update_document(doc)