From 9bdf27bc9009f4ff97a24404a752efc03ad3555f Mon Sep 17 00:00:00 2001
From: Trenton Holmes <797416+stumpylog@users.noreply.github.com>
Date: Mon, 4 May 2026 13:49:41 -0700
Subject: [PATCH] fix(importer): avoid guardian lru_cache poisoning; include
 M2M through tables in check_constraints

clear_cache() inside the import transaction emptied Django's ContentType
manager cache while fixture PKs were live, causing downstream ContentType
lookups to repopulate guardian's separate @lru_cache(None) with
fixture-PK objects. After the TestCase transaction rolled back to
original PKs, guardian's lru_cache held stale fixture ContentType
objects, causing MixedContentTypeError in unrelated subsequent tests.

Remove clear_cache() since it was defending against a theoretical
stale-cache scenario that doesn't occur in a proper same-install restore.

Fix check_constraints() to explicitly include auto-created M2M through
tables (populated by .set() after bulk_create) alongside the model tables,
addressing the gap where join-table FK violations would have gone
undetected.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 .../management/commands/document_importer.py     | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/src/documents/management/commands/document_importer.py b/src/documents/management/commands/document_importer.py
index c604f8d2d..46415b4a2 100644
--- a/src/documents/management/commands/document_importer.py
+++ b/src/documents/management/commands/document_importer.py
@@ -383,13 +383,19 @@ class Command(CryptMixin, PaperlessCommand):
 
                     flush_all()
 
-                # Stale ContentType objects cached in Python would cause lookups
-                # against the freshly re-imported rows to return wrong PKs.
-                ContentType.objects.clear_cache()
-
                 # Verify referential integrity now that all rows are inserted,
                 # including M2M through tables written by .set() above.
-                connection.check_constraints()
+                through_tables = {
+                    field.remote_field.through._meta.db_table
+                    for model in loaded_models
+                    for field in model._meta.many_to_many
+                    if field.remote_field.through._meta.auto_created
+                }
+                table_names = [m._meta.db_table for m in loaded_models] + list(
+                    through_tables,
+                )
+                if table_names:
+                    connection.check_constraints(table_names=table_names)
 
                 # Sequences must be reset after inserting rows with explicit PKs
                 # or the next auto-increment insert will collide with an existing PK.