Fix: prevent overlapping mail-account processing runs

process_mail_accounts had no guard against a scheduled run still being
in progress when the next one fires (e.g. a large attachment batch
taking longer than the check interval). ProcessedMail dedup only
records a message once handling finishes, so an overlapping run could
still pick up the same not-yet-recorded message. Skip a run outright
if another MAIL_FETCH task is already PENDING/STARTED.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

src/documents/filters.py

@@ -12,7 +12,6 @@ from typing import TYPE_CHECKING
 from typing import Any
 
 from django.contrib.contenttypes.models import ContentType
-from django.core.exceptions import FieldError
 from django.db.models import Case
 from django.db.models import CharField
 from django.db.models import Count
@@ -53,6 +52,7 @@ from documents.models import StoragePath
 from documents.models import Tag
 from documents.permissions import permitted_document_ids
 from documents.permissions import permitted_object_ids
+from documents.versioning import annotate_effective_content
 
 if TYPE_CHECKING:
     from collections.abc import Callable
@@ -182,14 +182,9 @@ class TitleContentFilter(Filter):
             logger.warning(
                 "Deprecated document filter parameter 'title_content' used; use `text` instead.",
             )
-            try:
-                return qs.filter(
-                    Q(title__icontains=value) | Q(effective_content__icontains=value),
-                )
-            except FieldError:
-                return qs.filter(
-                    Q(title__icontains=value) | Q(content__icontains=value),
-                )
+            return annotate_effective_content(qs).filter(
+                Q(title__icontains=value) | Q(effective_content__icontains=value),
+            )
         else:
             return qs
 
@@ -200,14 +195,9 @@ class EffectiveContentFilter(Filter):
         value = value.strip() if isinstance(value, str) else value
         if not value:
             return qs
-        try:
-            return qs.filter(
-                **{f"effective_content__{self.lookup_expr}": value},
-            )
-        except FieldError:
-            return qs.filter(
-                **{f"content__{self.lookup_expr}": value},
-            )
+        return annotate_effective_content(qs).filter(
+            **{f"effective_content__{self.lookup_expr}": value},
+        )
 
 
 @extend_schema_field(serializers.BooleanField)

src/documents/tests/test_api_document_versions.py

@@ -2,14 +2,12 @@ from __future__ import annotations
 
 import datetime
 from typing import TYPE_CHECKING
-from unittest import TestCase
 from unittest import mock
 
 from auditlog.models import LogEntry  # type: ignore[import-untyped]
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
-from django.core.exceptions import FieldError
 from django.core.files.uploadedfile import SimpleUploadedFile
 from django.test import TestCase as DjangoTestCase
 from django.utils import timezone
@@ -22,6 +20,7 @@ from documents.filters import TitleContentFilter
 from documents.models import Document
 from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import read_streaming_response
+from documents.versioning import annotate_effective_content
 from documents.views import DocumentSelectionMixin
 
 if TYPE_CHECKING:
@@ -892,32 +891,104 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
         )
 
 
-class TestVersionAwareFilters(TestCase):
-    def test_title_content_filter_falls_back_to_content(self) -> None:
-        queryset = mock.Mock()
-        fallback_queryset = mock.Mock()
-        queryset.filter.side_effect = [FieldError("missing field"), fallback_queryset]
+class TestVersionAwareFilters(DjangoTestCase):
+    """
+    The filters annotate effective_content themselves rather than relying on
+    the caller's queryset carrying it, so they stay version-aware on a plain
+    Document queryset (e.g. the bulk-edit "select all matching" path).
+    """
 
-        result = TitleContentFilter().filter(queryset, " latest ")
+    def setUp(self) -> None:
+        super().setUp()
+        self.root = Document.objects.create(
+            title="root",
+            checksum="root",
+            mime_type="application/pdf",
+            content="superseded-content",
+        )
+        Document.objects.create(
+            title="version",
+            checksum="version",
+            mime_type="application/pdf",
+            root_document=self.root,
+            version_index=1,
+            content="latest-content",
+        )
+        self.unversioned = Document.objects.create(
+            title="unversioned",
+            checksum="unversioned",
+            mime_type="application/pdf",
+            content="latest-content",
+        )
 
-        self.assertIs(result, fallback_queryset)
-        self.assertEqual(queryset.filter.call_count, 2)
-
-    def test_effective_content_filter_falls_back_to_content_lookup(self) -> None:
-        queryset = mock.Mock()
-        fallback_queryset = mock.Mock()
-        queryset.filter.side_effect = [FieldError("missing field"), fallback_queryset]
-
-        result = EffectiveContentFilter(lookup_expr="icontains").filter(
-            queryset,
+    def test_title_content_filter_matches_latest_version_content(self) -> None:
+        result = TitleContentFilter().filter(
+            Document.objects.filter(root_document__isnull=True),
             " latest ",
         )
 
-        self.assertIs(result, fallback_queryset)
-        first_kwargs = queryset.filter.call_args_list[0].kwargs
-        second_kwargs = queryset.filter.call_args_list[1].kwargs
-        self.assertEqual(first_kwargs, {"effective_content__icontains": "latest"})
-        self.assertEqual(second_kwargs, {"content__icontains": "latest"})
+        self.assertCountEqual(
+            [doc.id for doc in result],
+            [self.root.id, self.unversioned.id],
+        )
+
+    def test_effective_content_filter_matches_latest_version_content(self) -> None:
+        result = EffectiveContentFilter(lookup_expr="icontains").filter(
+            Document.objects.filter(root_document__isnull=True),
+            " latest ",
+        )
+
+        self.assertCountEqual(
+            [doc.id for doc in result],
+            [self.root.id, self.unversioned.id],
+        )
+
+    def test_effective_content_filter_ignores_superseded_content(self) -> None:
+        result = EffectiveContentFilter(lookup_expr="icontains").filter(
+            Document.objects.filter(root_document__isnull=True),
+            "superseded",
+        )
+
+        self.assertEqual(list(result), [])
+
+    def test_filters_reuse_an_existing_annotation(self) -> None:
+        """
+        Annotating twice under the same alias is an error, so an already
+        annotated queryset (the search path) has to be left alone.
+        """
+        annotated = annotate_effective_content(
+            Document.objects.filter(root_document__isnull=True),
+        )
+        self.assertIs(annotate_effective_content(annotated), annotated)
+
+        result = EffectiveContentFilter(lookup_expr="icontains").filter(
+            annotated,
+            "latest",
+        )
+
+        self.assertCountEqual(
+            [doc.id for doc in result],
+            [self.root.id, self.unversioned.id],
+        )
+
+    def test_bulk_selection_does_not_match_superseded_content(self) -> None:
+        """
+        Bulk edit's "select all matching" builds its own queryset, so before
+        the filters annotated for themselves it matched the root document's
+        superseded content -- selecting documents the list view, filtered by
+        the same term, does not show.
+        """
+        user = User.objects.create_superuser(username="bulk_selection")
+
+        selected = DocumentSelectionMixin()._resolve_document_ids(
+            user=user,
+            validated_data={
+                "all": True,
+                "filters": {"content__icontains": "superseded"},
+            },
+        )
+
+        self.assertEqual(selected, [])
 
     def test_effective_content_filter_returns_input_for_empty_values(self) -> None:
         queryset = mock.Mock()

src/documents/tests/test_api_search.py

@@ -1947,6 +1947,29 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertEqual(len(response.data["documents"]), 1)
         self.assertEqual(response.data["documents"][0]["id"], title_match.id)
 
+    def test_global_search_returns_latest_version_content(self) -> None:
+        root = Document.objects.create(
+            title="bank statement",
+            content="superseded content",
+            checksum="GSV1",
+            pk=23,
+        )
+        Document.objects.create(
+            title="bank statement v2",
+            content="latest content",
+            checksum="GSV2",
+            pk=24,
+            root_document=root,
+            version_index=1,
+        )
+
+        self.client.force_authenticate(self.user)
+
+        response = self.client.get("/api/search/?query=bank&db_only=true")
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        returned = {doc["id"]: doc["content"] for doc in response.data["documents"]}
+        self.assertEqual(returned.get(root.id), "latest content")
+
     def test_global_search_filters_owned_mail_objects(self) -> None:
         user1 = User.objects.create_user("mail-search-user")
         user2 = User.objects.create_user("other-mail-search-user")

src/documents/versioning.py

@@ -27,10 +27,13 @@ def versions_newest_first(documents: QuerySet[Document]) -> QuerySet[Document]:
 
 def annotate_effective_content(documents: QuerySet[Document]) -> QuerySet[Document]:
     """
-    Annotates documents with the content of their newest version, falling back
-    to their own, so get_effective_content() can answer from the row rather
-    than querying for the versions of each document
+    Annotates documents with the content of their newest version unless the
+    queryset already carries the annotation, falling back to their own, so
+    get_effective_content() can answer from the row rather than querying for
+    the versions of each document.
     """
+    if "effective_content" in documents.query.annotations:
+        return documents
     return documents.annotate(
         effective_content=Coalesce(
             Subquery(

src/documents/views.py

@@ -232,6 +232,7 @@ from documents.tasks import train_classifier
 from documents.tasks import update_document_parent_tags
 from documents.utils import get_boolean
 from documents.versioning import VersionResolutionError
+from documents.versioning import annotate_effective_content
 from documents.versioning import get_latest_version_for_root
 from documents.versioning import get_request_version_param
 from documents.versioning import get_root_document
@@ -3632,8 +3633,13 @@ class GlobalSearchView(PassUserMixin):
         OBJECT_LIMIT = 3
         docs = []
         if request.user.has_perm("documents.view_document"):
-            all_docs = Document.objects.filter(
-                id__in=permitted_document_ids(request.user),
+            # Never more than OBJECT_LIMIT rows come back here, so annotating
+            # is cheap -- and without it these results show the root
+            # document's superseded content.
+            all_docs = annotate_effective_content(
+                Document.objects.filter(
+                    id__in=permitted_document_ids(request.user),
+                ),
             )
             if db_only:
                 docs = all_docs.filter(title__icontains=query)[:OBJECT_LIMIT]

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-09-08 15:31+0000\n"
+"POT-Creation-Date: 2026-09-08 15:56+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -21,39 +21,39 @@ msgstr ""
 msgid "Documents"
 msgstr ""
 
-#: documents/filters.py:473
+#: documents/filters.py:463
 msgid "Value must be valid JSON."
 msgstr ""
 
-#: documents/filters.py:492
+#: documents/filters.py:482
 msgid "Invalid custom field query expression"
 msgstr ""
 
-#: documents/filters.py:502
+#: documents/filters.py:492
 msgid "Invalid expression list. Must be nonempty."
 msgstr ""
 
-#: documents/filters.py:523
+#: documents/filters.py:513
 msgid "Invalid logical operator {op!r}"
 msgstr ""
 
-#: documents/filters.py:537
+#: documents/filters.py:527
 msgid "Maximum number of query conditions exceeded."
 msgstr ""
 
-#: documents/filters.py:601
+#: documents/filters.py:591
 msgid "{name!r} is not a valid custom field."
 msgstr ""
 
-#: documents/filters.py:638
+#: documents/filters.py:628
 msgid "{data_type} does not support query expr {expr!r}."
 msgstr ""
 
-#: documents/filters.py:757 documents/models.py:136
+#: documents/filters.py:747 documents/models.py:136
 msgid "Maximum nesting depth exceeded."
 msgstr ""
 
-#: documents/filters.py:1119
+#: documents/filters.py:1109
 msgid "Custom field not found"
 msgstr ""
 
@@ -1632,7 +1632,7 @@ msgid "workflow runs"
 msgstr ""
 
 #: documents/serialisers.py:524 documents/serialisers.py:881
-#: documents/serialisers.py:2841 documents/views.py:314 documents/views.py:2624
+#: documents/serialisers.py:2841 documents/views.py:315 documents/views.py:2625
 #: paperless_mail/serialisers.py:156
 msgid "Insufficient permissions."
 msgstr ""
@@ -1673,7 +1673,7 @@ msgstr ""
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2927 documents/views.py:4626
+#: documents/serialisers.py:2927 documents/views.py:4632
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1941,36 +1941,36 @@ msgstr ""
 msgid "Unable to parse URI {value}"
 msgstr ""
 
-#: documents/views.py:307 documents/views.py:2621
+#: documents/views.py:308 documents/views.py:2622
 msgid "Invalid more_like_id"
 msgstr ""
 
-#: documents/views.py:1591
+#: documents/views.py:1592
 msgid "Invalid AI configuration."
 msgstr ""
 
-#: documents/views.py:1602
+#: documents/views.py:1603
 msgid "AI backend request timed out."
 msgstr ""
 
-#: documents/views.py:2446 documents/views.py:2767
+#: documents/views.py:2447 documents/views.py:2768
 msgid "Specify only one of text, title_search, query, or more_like_id."
 msgstr ""
 
-#: documents/views.py:4639
+#: documents/views.py:4645
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:4685
+#: documents/views.py:4691
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:4749
+#: documents/views.py:4755
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:4763
+#: documents/views.py:4769
 msgid "The share link bundle is unavailable."
 msgstr ""
 

src/paperless_mail/tasks.py

@@ -1,7 +1,9 @@
 import logging
 
+from celery import Task
 from celery import shared_task
 
+from documents.models import PaperlessTask
 from paperless_mail.mail import MailAccountHandler
 from paperless_mail.mail import MailError
 from paperless_mail.models import MailAccount
@@ -10,8 +12,27 @@ from paperless_mail.models import MailRule
 logger = logging.getLogger("paperless.mail.tasks")
 
 
-@shared_task
-def process_mail_accounts(account_ids: list[int] | None = None) -> str:
+@shared_task(bind=True)
+def process_mail_accounts(self: Task, account_ids: list[int] | None = None) -> str:
+    # A scheduled check can still be running (or queued) when the next one
+    # fires, e.g. a large attachment batch that takes longer to process than
+    # the check interval. ProcessedMail dedup only records a message once its
+    # handling has finished, so an overlapping run can still pick up the same
+    # not-yet-recorded message. Skip outright rather than race it.
+    other_mail_fetch_running = (
+        PaperlessTask.objects.filter(
+            task_type=PaperlessTask.TaskType.MAIL_FETCH,
+            status__in=[PaperlessTask.Status.PENDING, PaperlessTask.Status.STARTED],
+        )
+        .exclude(task_id=self.request.id)
+        .exists()
+    )
+    if other_mail_fetch_running:
+        logger.info(
+            "Mail account processing is already running; skipping this run.",
+        )
+        return "Skipped: mail account processing already in progress."
+
     total_new_documents = 0
     accounts = (
         MailAccount.objects.filter(pk__in=account_ids)

src/paperless_mail/tests/test_process_mail_accounts_overlap.py

@@ -0,0 +1,89 @@
+from unittest import mock
+
+import pytest
+
+from documents.models import PaperlessTask
+from paperless_mail import tasks
+from paperless_mail.tests.factories import MailAccountFactory
+from paperless_mail.tests.factories import MailRuleFactory
+
+
+@pytest.mark.django_db
+class TestProcessMailAccountsOverlap:
+    def test_skips_when_another_mail_fetch_task_is_running(self) -> None:
+        account = MailAccountFactory.create()
+        MailRuleFactory.create(account=account, enabled=True)
+
+        PaperlessTask.objects.create(
+            task_id="other-running-task",
+            task_type=PaperlessTask.TaskType.MAIL_FETCH,
+            trigger_source=PaperlessTask.TriggerSource.SCHEDULED,
+            status=PaperlessTask.Status.STARTED,
+        )
+
+        with mock.patch.object(
+            tasks.MailAccountHandler,
+            "handle_mail_account",
+        ) as mocked_handle:
+            result = tasks.process_mail_accounts()
+
+        mocked_handle.assert_not_called()
+        assert result == "Skipped: mail account processing already in progress."
+
+    def test_runs_when_no_other_mail_fetch_task_is_running(self) -> None:
+        account = MailAccountFactory.create()
+        MailRuleFactory.create(account=account, enabled=True)
+
+        with mock.patch.object(
+            tasks.MailAccountHandler,
+            "handle_mail_account",
+            return_value=0,
+        ) as mocked_handle:
+            result = tasks.process_mail_accounts()
+
+        mocked_handle.assert_called_once()
+        assert result == "No new documents were added."
+
+    def test_ignores_completed_mail_fetch_tasks(self) -> None:
+        account = MailAccountFactory.create()
+        MailRuleFactory.create(account=account, enabled=True)
+
+        PaperlessTask.objects.create(
+            task_id="finished-task",
+            task_type=PaperlessTask.TaskType.MAIL_FETCH,
+            trigger_source=PaperlessTask.TriggerSource.SCHEDULED,
+            status=PaperlessTask.Status.SUCCESS,
+        )
+
+        with mock.patch.object(
+            tasks.MailAccountHandler,
+            "handle_mail_account",
+            return_value=0,
+        ) as mocked_handle:
+            result = tasks.process_mail_accounts()
+
+        mocked_handle.assert_called_once()
+        assert result == "No new documents were added."
+
+    def test_does_not_skip_due_to_its_own_task_row(self) -> None:
+        account = MailAccountFactory.create()
+        MailRuleFactory.create(account=account, enabled=True)
+
+        PaperlessTask.objects.create(
+            task_id="self-task-id",
+            task_type=PaperlessTask.TaskType.MAIL_FETCH,
+            trigger_source=PaperlessTask.TriggerSource.SCHEDULED,
+            status=PaperlessTask.Status.STARTED,
+        )
+
+        with mock.patch.object(
+            tasks.MailAccountHandler,
+            "handle_mail_account",
+            return_value=0,
+        ) as mocked_handle:
+            result = tasks.process_mail_accounts.apply(
+                task_id="self-task-id",
+            ).result
+
+        mocked_handle.assert_called_once()
+        assert result == "No new documents were added."