Fixhancement: add automatic clearing of sessions (#14722)

docs/configuration.md

@@ -873,6 +873,14 @@ If both the [PAPERLESS_ACCOUNT_DEFAULT_GROUPS](#PAPERLESS_ACCOUNT_DEFAULT_GROUPS
 
     Defaults to 1209600 (2 weeks)
 
+#### [`PAPERLESS_SESSION_CLEANUP_TASK_CRON=<cron expression>`](#PAPERLESS_SESSION_CLEANUP_TASK_CRON) {#PAPERLESS_SESSION_CLEANUP_TASK_CRON}
+
+: Configures the schedule to remove expired sessions from the session store.
+Django does not prune these automatically, so without this they would
+accumulate indefinitely.
+
+    Defaults to `0 3 * * *`, once per day at 03:00.
+
 #### [`PAPERLESS_TOKEN_THROTTLE_RATE=<rate>`](#PAPERLESS_TOKEN_THROTTLE_RATE) {#PAPERLESS_TOKEN_THROTTLE_RATE}
 
 : Rate limit for the API token authentication endpoint (`/api/token/`), used to mitigate brute-force login attempts.

src/documents/tasks.py

@@ -12,6 +12,7 @@ from celery import Task
 from celery import shared_task
 from django.conf import settings
 from django.contrib.contenttypes.models import ContentType
+from django.contrib.sessions.models import Session
 from django.db import models
 from django.db import transaction
 from django.db.models.signals import post_save
@@ -925,3 +926,17 @@ def cleanup_expired_share_link_bundles() -> None:
             )
     if count:
         logger.info("Deleted %s expired share link bundle(s)", count)
+
+
+@shared_task
+def clear_expired_sessions() -> None:
+    """
+    Remove expired database sessions in batches to limit the size of each delete.
+    """
+    expired = Session.objects.filter(expire_date__lt=timezone.now())
+    while session_keys := list(
+        expired.order_by("expire_date").values_list("pk", flat=True)[:500],
+    ):
+        expired.filter(pk__in=session_keys).delete()
+
+    logger.info("Cleared expired sessions")

src/documents/tests/test_tasks.py

@@ -5,8 +5,11 @@ from unittest import mock
 
 import pytest
 from django.conf import settings
+from django.contrib.sessions.models import Session
+from django.db import connection
 from django.test import TestCase
 from django.test import override_settings
+from django.test.utils import CaptureQueriesContext
 from django.utils import timezone
 
 from documents import tasks
@@ -612,3 +615,36 @@ class TestApplyAISuggestionsTask(DirectoriesMixin, TestCase):
 
         apply_suggestions.assert_not_called()
         self.assertIn("no longer exists", "".join(cm.output))
+
+
+@pytest.mark.django_db
+class TestClearExpiredSessions:
+    def test_clears_only_expired_sessions_in_batches(self) -> None:
+        """
+        GIVEN:
+            - More than one batch of expired sessions and one still-valid session
+        WHEN:
+            - The clear_expired_sessions task runs
+        THEN:
+            - Only expired sessions are removed, using multiple deletes
+        """
+        now = timezone.now()
+        Session.objects.bulk_create(
+            Session(
+                session_key=f"expired-{i}",
+                session_data="",
+                expire_date=now - timedelta(days=1),
+            )
+            for i in range(501)
+        )
+        Session.objects.create(
+            session_key="valid",
+            session_data="",
+            expire_date=now + timedelta(days=1),
+        )
+
+        with CaptureQueriesContext(connection) as queries:
+            tasks.clear_expired_sessions()
+
+        assert set(Session.objects.values_list("session_key", flat=True)) == {"valid"}
+        assert sum(query["sql"].startswith("DELETE FROM") for query in queries) == 2

src/paperless/settings/custom.py

@@ -165,6 +165,17 @@ def parse_beat_schedule() -> dict:
                 "expires": 23.0 * 60.0 * 60.0,
             },
         },
+        {
+            "name": "Clear expired sessions",
+            "env_key": "PAPERLESS_SESSION_CLEANUP_TASK_CRON",
+            # Default daily at 03:00
+            "env_default": "0 3 * * *",
+            "task": "documents.tasks.clear_expired_sessions",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": 23.0 * 60.0 * 60.0,
+            },
+        },
     ]
     for task in tasks:
         # Either get the environment setting or use the default

src/paperless/tests/settings/test_custom_parsers.py

@@ -182,6 +182,7 @@ def make_expected_schedule(
     workflow_expire = 59.0 * 60.0
     llm_index_expire = 23.0 * 60.0 * 60.0
     share_link_cleanup_expire = 23.0 * 60.0 * 60.0
+    session_cleanup_expire = 23.0 * 60.0 * 60.0
 
     schedule: dict[str, Any] = {
         "Check all e-mail accounts": {
@@ -248,6 +249,14 @@ def make_expected_schedule(
                 "headers": {"trigger_source": "scheduled"},
             },
         },
+        "Clear expired sessions": {
+            "task": "documents.tasks.clear_expired_sessions",
+            "schedule": crontab(minute=0, hour="3"),
+            "options": {
+                "expires": session_cleanup_expire,
+                "headers": {"trigger_source": "scheduled"},
+            },
+        },
     }
 
     overrides = overrides or {}
@@ -298,6 +307,7 @@ class TestParseBeatSchedule:
                     "PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON": "disable",
                     "PAPERLESS_LLM_INDEX_TASK_CRON": "disable",
                     "PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON": "disable",
+                    "PAPERLESS_SESSION_CLEANUP_TASK_CRON": "disable",
                 },
                 {},
                 id="all-disabled",