Compare commits

..
Author SHA1 Message Date
shamoonandGitHub 855669ddf9 Fix: fixes for workflow assign custom field values (#13630) 2026-08-10 07:38:07 -07:00
GitHub Actions 62089df2d8 Auto translate strings 2026-08-10 02:26:58 +00:00
Trenton HandGitHub 5e5f6a88a3 Fix: deny deactivated users in permission filtering and auto-login (#13623)
* Fix: Hardening sweep, ensure a user is active, not just authenticated

* Missed this test
2026-08-10 02:25:06 +00:00
shamoonandGitHub 02e6c49c62 Chore: update fpdf2 to 2.8.8 (#13629) 2026-08-10 02:07:13 +00:00
shamoonandGitHub 3be64da4cb Chore: udpate pnpm, add blockExoticSubdeps (#13628) 2026-08-09 18:59:26 -07:00
Trenton HandGitHub c28c532bef Fix: check bulk mail delete permissions for the whole batch up front (#13620)
ProcessedMailViewSet.bulk_delete checked permissions inside the delete loop, so an unpermitted id returned 403 only after the mails ahead of it had already been deleted. Resolve the permitted set once via permitted_object_ids and reject before deleting anything, which also drops the per-mail permission queries.
2026-08-09 13:55:49 +00:00
GitHub Actions 1d61f7fc62 Auto translate strings 2026-08-09 07:16:59 +00:00
shamoonandGitHub aa67fd3aef Tweak: improve no ML suggestions UX (#13621) 2026-08-09 00:15:27 -07:00
Trenton HandGitHub 17dc482872 Fix: Allow DRF to validate the maximum API key length (#13614) 2026-08-08 19:51:27 +00:00
GitHub Actions b0e0e8a353 Auto translate strings 2026-08-08 14:29:01 +00:00
27 changed files with 423 additions and 189 deletions
+3 -1
View File
@@ -576,7 +576,9 @@ The following workflow action types are available:
- Tags, correspondent, document type and storage path
- Document owner
- View and / or edit permissions to users or groups
- Custom fields. Note that no value for the field will be set
- Custom fields, optionally with a value. If no value is set, the field is only added to the
document and any value it may already have is left untouched. If a value is set, it will
overwrite an existing value of that field on the document.
##### Removal {#workflow-action-removal}
+13 -6
View File
@@ -1703,7 +1703,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">28</context>
<context context-type="linenumber">34</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
@@ -3279,7 +3279,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">40</context>
<context context-type="linenumber">46</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
@@ -7070,32 +7070,39 @@
<context context-type="linenumber">143</context>
</context-group>
</trans-unit>
<trans-unit id="8336346011691074629" datatype="html">
<source>No suggestions</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">11,12</context>
</context-group>
</trans-unit>
<trans-unit id="5320136382998259826" datatype="html">
<source>Suggest</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">8,9</context>
<context context-type="linenumber">13,14</context>
</context-group>
</trans-unit>
<trans-unit id="6934085657687954669" datatype="html">
<source>Show suggestions</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">17,18</context>
<context context-type="linenumber">23,24</context>
</context-group>
</trans-unit>
<trans-unit id="3834115140127576673" datatype="html">
<source>No novel suggestions</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">24,25</context>
<context context-type="linenumber">30,31</context>
</context-group>
</trans-unit>
<trans-unit id="4369111787961525769" datatype="html">
<source>Document Types</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">34</context>
<context context-type="linenumber">40</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
+1 -1
View File
@@ -66,5 +66,5 @@
"ts-node": "~10.9.1",
"typescript": "^6.0.3"
},
"packageManager": "pnpm@10.26.0"
"packageManager": "pnpm@11.15.1"
}
+1
View File
@@ -5,6 +5,7 @@ trustPolicy: no-downgrade
trustPolicyExclude:
- "chokidar@4.0.3"
- "semver@6.3.1 || 5.7.2"
blockExoticSubdeps: true
allowBuilds:
"@parcel/watcher": true
canvas: true
@@ -52,10 +52,10 @@ describe('CustomFieldsValuesComponent', () => {
})
it('should set selectedFields and map values correctly', () => {
component.value = { 1: 'value1' }
component.selectedFields = [1, 2]
expect(component.selectedFields).toEqual([1, 2])
expect(component.value).toEqual({ 1: 'value1', 2: null })
component.value = { 1: 'value1', 3: 0, 4: false }
component.selectedFields = [1, 2, 3, 4]
expect(component.selectedFields).toEqual([1, 2, 3, 4])
expect(component.value).toEqual({ 1: 'value1', 2: null, 3: 0, 4: false })
})
it('should return the correct custom field by id', () => {
@@ -77,7 +77,7 @@ export class CustomFieldsValuesComponent extends AbstractInputComponent<Object>
this._selectedFields = newFields
// map the selected fields to an object with field_id as key and value as value
this.value = newFields.reduce((acc, fieldId) => {
acc[fieldId] = this.value?.[fieldId] || null
acc[fieldId] = this.value?.[fieldId] ?? null
return acc
}, {})
this.onChange(this.value)
@@ -2,10 +2,16 @@
<button type="button" class="btn btn-sm btn-outline-primary" (click)="clickSuggest()" [disabled]="disabled() || loading() || (suggestions() && !aiEnabled())">
@if (loading()) {
<div class="spinner-border spinner-border-sm" role="status"></div>
} @else if (noSuggestions) {
<i-bs width="1.2em" height="1.2em" name="check-circle"></i-bs>
} @else {
<i-bs width="1.2em" height="1.2em" name="stars"></i-bs>
}
<span class="d-none d-lg-inline ps-1" i18n>Suggest</span>
@if (noSuggestions) {
<span class="d-none d-lg-inline ps-1" i18n>No suggestions</span>
} @else {
<span class="d-none d-lg-inline ps-1" i18n>Suggest</span>
}
@if (totalSuggestions > 0) {
<span class="badge bg-primary ms-2">{{ totalSuggestions }}</span>
}
@@ -19,7 +25,7 @@
<div ngbDropdownMenu aria-labelledby="suggestionsDropdown" class="shadow suggestions-dropdown">
<div class="list-group list-group-flush small pb-0">
@if (!suggestions()?.suggested_tags && !suggestions()?.suggested_document_types && !suggestions()?.suggested_correspondents) {
@if (totalSuggestions === 0) {
<div class="list-group-item text-muted fst-italic">
<small class="text-muted small fst-italic" i18n>No novel suggestions</small>
</div>
@@ -30,6 +30,34 @@ describe('SuggestionsDropdownComponent', () => {
expect(component.totalSuggestions).toBe(4)
})
it('should show when a completed request returned no suggestions', () => {
fixture.componentRef.setInput('suggestions', {
correspondents: [],
tags: [],
document_types: [],
storage_paths: [],
dates: [],
})
fixture.detectChanges()
expect(component.noSuggestions).toBeTruthy()
expect(fixture.nativeElement.textContent).toContain('No suggestions')
})
it('should not show the empty state before a request or with suggestions', () => {
expect(component.noSuggestions).toBeFalsy()
fixture.componentRef.setInput('suggestions', {
correspondents: [],
tags: [42],
document_types: [],
storage_paths: [],
dates: [],
})
expect(component.noSuggestions).toBeFalsy()
})
it('should emit getSuggestions when clickSuggest is called and suggestions are null', () => {
jest.spyOn(component.getSuggestions, 'emit')
fixture.componentRef.setInput('suggestions', null)
@@ -59,5 +87,6 @@ describe('SuggestionsDropdownComponent', () => {
})
component.clickSuggest()
expect(component.dropdown.open).toBeTruthy()
expect(fixture.nativeElement.textContent).toContain('No novel suggestions')
})
})
@@ -61,4 +61,21 @@ export class SuggestionsDropdownComponent {
this.suggestions()?.suggested_document_types?.length || 0
)
}
get noSuggestions(): boolean {
const suggestions = this.suggestions()
return (
suggestions != null &&
!suggestions.title &&
!suggestions.tags?.length &&
!suggestions.suggested_tags?.length &&
!suggestions.correspondents?.length &&
!suggestions.suggested_correspondents?.length &&
!suggestions.document_types?.length &&
!suggestions.suggested_document_types?.length &&
!suggestions.storage_paths?.length &&
!suggestions.suggested_storage_paths?.length &&
!suggestions.dates?.length
)
}
}
+6
View File
@@ -1047,6 +1047,12 @@ class PermittedObjectsFilter(BaseFilterBackend):
perm_codename: str | None = None
def filter_queryset(self, request, queryset, view):
# Before the superuser and owner-only paths, neither of which consults
# permitted_object_ids. Scoped to authenticated users so anonymous
# access (AnonymousUser.is_active is False) keeps its existing
# unowned-only behaviour.
if request.user.is_authenticated and not request.user.is_active:
return queryset.none()
if request.user.is_superuser:
return queryset
if not self.include_granted:
+18 -3
View File
@@ -54,11 +54,15 @@ class PaperlessObjectPermissions(DjangoObjectPermissions):
class PaperlessAdminPermissions(BasePermission):
def has_permission(self, request, view):
return request.user.is_staff
return request.user.is_active and request.user.is_staff
def has_global_statistics_permission(user: User | None) -> bool:
if user is None or not getattr(user, "is_authenticated", False):
if (
user is None
or not getattr(user, "is_active", False)
or not getattr(user, "is_authenticated", False)
):
return False
return getattr(user, "is_superuser", False) or user.has_perm(
@@ -67,7 +71,11 @@ def has_global_statistics_permission(user: User | None) -> bool:
def has_system_status_permission(user: User | None) -> bool:
if user is None or not getattr(user, "is_authenticated", False):
if (
user is None
or not getattr(user, "is_active", False)
or not getattr(user, "is_authenticated", False)
):
return False
return (
@@ -188,6 +196,13 @@ def permitted_object_ids(
if user is None or not getattr(user, "is_authenticated", False):
return base_qs.filter(owner__isnull=True).values_list("id", flat=True)
# Deactivated users get nothing, deactivated superusers included, so this
# has to come before the superuser shortcut. guardian's
# ObjectPermissionChecker denies inactive users, but get_objects_for_user
# (the pattern this replaces) does not, so it would not be inherited.
if not getattr(user, "is_active", False):
return base_qs.none().values_list("id", flat=True)
if getattr(user, "is_superuser", False):
return base_qs.values_list("id", flat=True)
+7
View File
@@ -3213,6 +3213,13 @@ class WorkflowActionSerializer(serializers.ModelSerializer[WorkflowAction]):
{"assign_title": f'Invalid f-string detected: "{e.args[0]}"'},
)
if attrs.get("assign_custom_fields_values"):
# Empty strings treated as None to avoid unexpected behavior
attrs["assign_custom_fields_values"] = {
field_id: (None if value == "" else value)
for field_id, value in attrs["assign_custom_fields_values"].items()
}
if (
"type" in attrs
and attrs["type"] == WorkflowAction.WorkflowActionType.EMAIL
@@ -422,6 +422,11 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
json.dumps(
{
"assign_title": "",
"assign_custom_fields": [self.cf1.id, self.cf2.id],
"assign_custom_fields_values": {
str(self.cf1.id): "",
str(self.cf2.id): 0,
},
},
),
content_type="application/json",
@@ -429,6 +434,10 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
action = WorkflowAction.objects.get(id=response.data["id"])
self.assertIsNone(action.assign_title)
self.assertEqual(
action.assign_custom_fields_values,
{str(self.cf1.id): None, str(self.cf2.id): 0},
)
response = self.client.post(
self.ENDPOINT_TRIGGERS,
@@ -496,6 +496,28 @@ class TestPermittedObjectIdsGenericModels:
expected_hidden=[strangers.pk],
)
@pytest.mark.parametrize("is_superuser", [False, True])
def test_inactive_user_sees_nothing(self, model, factory, perm, is_superuser):
suffix = f"{model.__name__}_{is_superuser}"
user = User.objects.create_user(
username=f"inactive_{suffix}",
is_active=False,
is_superuser=is_superuser,
)
other = User.objects.create_user(username=f"other_{suffix}")
granted = factory(owner=other)
assign_perm(perm, user, granted)
assert_visible_document_ids(
permitted_object_ids(user, model, perm),
expected_visible=[],
expected_hidden=[
factory(owner=None).pk,
factory(owner=user).pk,
granted.pk,
],
)
def test_unowned_object_visible_to_everyone(self, model, factory, perm):
user = User.objects.create_user(username=f"user_{model.__name__}")
unowned = factory(owner=None)
@@ -68,3 +68,44 @@ class TestPermittedObjectsFilter:
visible_ids = set(result.values_list("id", flat=True))
assert visible_ids == {owned.pk}
assert granted.pk not in visible_ids
@pytest.mark.parametrize(
("username", "is_superuser"),
[("inactive", False), ("inactive_super", True)],
)
def test_inactive_user_sees_nothing(self, username: str, *, is_superuser: bool):
user = User.objects.create_user(
username=username,
is_active=False,
is_superuser=is_superuser,
)
TagFactory(owner=None)
TagFactory(owner=user)
granted = TagFactory(owner=User.objects.create_user(username=f"o_{username}"))
assign_perm("view_tag", user, granted)
request = APIRequestFactory().get("/")
request.user = user
result = PermittedObjectsFilter().filter_queryset(
request,
Tag.objects.all(),
_DummyView(),
)
assert result.count() == 0
def test_inactive_user_sees_nothing_with_include_granted_false(self):
user = User.objects.create_user(username="inactive_owner", is_active=False)
TagFactory(owner=user)
TagFactory(owner=None)
request = APIRequestFactory().get("/")
request.user = user
class _OwnerOnlyFilter(PermittedObjectsFilter):
include_granted = False
result = _OwnerOnlyFilter().filter_queryset(
request,
Tag.objects.all(),
_DummyView(),
)
assert result.count() == 0
+49
View File
@@ -2000,6 +2000,55 @@ class TestWorkflows(
r"Doc added in \w{3,}",
) # Match any 3-letter month name
def test_document_updated_workflow_existing_custom_field_empty_value(self) -> None:
"""
GIVEN:
- Existing workflow with UPDATED trigger and action that assigns a custom field
with an empty value
WHEN:
- Document is updated that already contains the field with a value
THEN:
- The existing value is left untouched, see GH #13627
"""
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
filter_has_document_type=self.dt,
)
action = WorkflowAction.objects.create()
action.assign_custom_fields.add(self.cf1)
action.assign_custom_fields_values = {self.cf1.pk: ""}
action.save()
w = Workflow.objects.create(
name="Workflow 1",
order=0,
)
w.triggers.add(trigger)
w.actions.add(action)
w.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
CustomFieldInstance.objects.create(
document=doc,
field=self.cf1,
value_text="existing value",
)
superuser = User.objects.create_superuser("superuser")
self.client.force_authenticate(user=superuser)
self.client.patch(
f"/api/documents/{doc.id}/",
{"document_type": self.dt.id},
format="json",
)
doc.refresh_from_db()
self.assertEqual(doc.custom_fields.get(field=self.cf1).value, "existing value")
def test_document_updated_workflow_existing_custom_field(self) -> None:
"""
GIVEN:
+1 -1
View File
@@ -2267,7 +2267,7 @@ class ChatStreamingView(GenericAPIView[Any]):
if not has_perms_owner_aware(request.user, "view_document", document):
return HttpResponseForbidden("Insufficient permissions")
documents = Document.objects.filter(pk=document.pk)
documents = [document]
else:
documents = Document.objects.filter(
id__in=permitted_document_ids(request.user),
+2 -1
View File
@@ -105,7 +105,8 @@ def apply_assignment_to_document(
field=field,
document=document,
).first()
if instance and args[value_field_name] is not None:
# empty string is indistinguishable from no value in the UI
if instance and args[value_field_name] not in (None, ""):
setattr(instance, value_field_name, args[value_field_name])
instance.save()
elif not instance:
+20 -20
View File
@@ -2,7 +2,7 @@ msgid ""
msgstr ""
"Project-Id-Version: paperless-ngx\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2026-08-07 20:00+0000\n"
"POT-Creation-Date: 2026-08-10 02:25+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:472
#: documents/filters.py:471
msgid "Value must be valid JSON."
msgstr ""
#: documents/filters.py:491
#: documents/filters.py:490
msgid "Invalid custom field query expression"
msgstr ""
#: documents/filters.py:501
#: documents/filters.py:500
msgid "Invalid expression list. Must be nonempty."
msgstr ""
#: documents/filters.py:522
#: documents/filters.py:521
msgid "Invalid logical operator {op!r}"
msgstr ""
#: documents/filters.py:536
#: documents/filters.py:535
msgid "Maximum number of query conditions exceeded."
msgstr ""
#: documents/filters.py:600
#: documents/filters.py:599
msgid "{name!r} is not a valid custom field."
msgstr ""
#: documents/filters.py:637
#: documents/filters.py:636
msgid "{data_type} does not support query expr {expr!r}."
msgstr ""
#: documents/filters.py:756 documents/models.py:136
#: documents/filters.py:755 documents/models.py:136
msgid "Maximum nesting depth exceeded."
msgstr ""
#: documents/filters.py:1098
#: documents/filters.py:1079
msgid "Custom field not found"
msgstr ""
@@ -1352,7 +1352,7 @@ msgid "workflow runs"
msgstr ""
#: documents/serialisers.py:521 documents/serialisers.py:873
#: documents/serialisers.py:2767 documents/views.py:300 documents/views.py:2556
#: documents/serialisers.py:2767 documents/views.py:299 documents/views.py:2555
#: paperless_mail/serialisers.py:155
msgid "Insufficient permissions."
msgstr ""
@@ -1393,7 +1393,7 @@ msgstr ""
msgid "Duplicate document identifiers are not allowed."
msgstr ""
#: documents/serialisers.py:2853 documents/views.py:4510
#: documents/serialisers.py:2853 documents/views.py:4509
#, python-format
msgid "Documents not found: %(ids)s"
msgstr ""
@@ -1661,36 +1661,36 @@ msgstr ""
msgid "Unable to parse URI {value}"
msgstr ""
#: documents/views.py:293 documents/views.py:2553
#: documents/views.py:292 documents/views.py:2552
msgid "Invalid more_like_id"
msgstr ""
#: documents/views.py:1567
#: documents/views.py:1566
msgid "Invalid AI configuration."
msgstr ""
#: documents/views.py:1576
#: documents/views.py:1575
msgid "AI backend request timed out."
msgstr ""
#: documents/views.py:2378 documents/views.py:2699
#: documents/views.py:2377 documents/views.py:2698
msgid "Specify only one of text, title_search, query, or more_like_id."
msgstr ""
#: documents/views.py:4523
#: documents/views.py:4522
#, python-format
msgid "Insufficient permissions to share document %(id)s."
msgstr ""
#: documents/views.py:4569
#: documents/views.py:4568
msgid "Bundle is already being processed."
msgstr ""
#: documents/views.py:4630
#: documents/views.py:4629
msgid "The share link bundle is still being prepared. Please try again later."
msgstr ""
#: documents/views.py:4640
#: documents/views.py:4639
msgid "The share link bundle is unavailable."
msgstr ""
+4 -1
View File
@@ -19,7 +19,10 @@ class AutoLoginMiddleware(MiddlewareMixin):
if request.path.startswith("/api/token/") and request.method == "POST":
return None
try:
request.user = User.objects.get(username=settings.AUTO_LOGIN_USERNAME)
request.user = User.objects.get(
username=settings.AUTO_LOGIN_USERNAME,
is_active=True,
)
auth.login(
request=request,
user=request.user,
+1
View File
@@ -217,6 +217,7 @@ class ApplicationConfigurationSerializer(
llm_api_key = ObfuscatedPasswordField(
required=False,
allow_null=True,
max_length=1024,
)
def run_validation(self, data):
@@ -0,0 +1,53 @@
from django.contrib.auth.models import AnonymousUser
from django.contrib.auth.models import User
from django.test import RequestFactory
from django.test import TestCase
from django.test import override_settings
from paperless.auth import AutoLoginMiddleware
@override_settings(AUTO_LOGIN_USERNAME="autologin")
class TestAutoLoginMiddleware(TestCase):
def setUp(self) -> None:
super().setUp()
self.factory = RequestFactory()
self.middleware = AutoLoginMiddleware(lambda request: None)
def _process(self, request):
# login() needs a session to write to
request.session = self.client.session
self.middleware.process_request(request)
return request
def test_active_user_is_logged_in(self) -> None:
"""
GIVEN:
- AUTO_LOGIN_USERNAME names an active user
WHEN:
- A request is processed by the middleware
THEN:
- That user is attached to the request
"""
user = User.objects.create_user(username="autologin")
request = self._process(self.factory.get("/"))
self.assertEqual(request.user, user)
def test_deactivated_user_is_not_logged_in(self) -> None:
"""
GIVEN:
- AUTO_LOGIN_USERNAME names a user who has been deactivated
WHEN:
- A request is processed by the middleware
THEN:
- The request is left anonymous rather than authenticated as them
"""
User.objects.create_user(username="autologin", is_active=False)
request = self.factory.get("/")
request.user = AnonymousUser()
self._process(request)
self.assertFalse(request.user.is_authenticated)
+6 -21
View File
@@ -2,8 +2,6 @@ import json
import logging
import sys
from django.db.models import QuerySet
from documents.models import Document
from paperless.config import AIConfig
from paperless_ai.client import AIClient
@@ -84,21 +82,10 @@ def _build_document_reference(
def _get_document_references(
documents: QuerySet[Document],
documents: list[Document],
top_nodes: list,
) -> list[dict[str, int | str]]:
candidate_ids: set[int] = set()
for node in top_nodes:
try:
candidate_ids.add(int(node.metadata["document_id"]))
except (KeyError, TypeError, ValueError): # pragma: no cover
continue
if not candidate_ids:
return []
allowed_documents = {doc.pk: doc for doc in documents.filter(pk__in=candidate_ids)}
allowed_documents = {doc.pk: doc for doc in documents}
references: list[dict[str, int | str]] = []
seen_document_ids: set[int] = set()
@@ -132,7 +119,7 @@ def _format_chat_metadata_trailer(references: list[dict[str, int | str]]) -> str
def stream_chat_with_documents(
query_str: str,
documents: QuerySet[Document],
documents: list[Document],
output_language: str | None = None,
):
try:
@@ -148,10 +135,10 @@ def stream_chat_with_documents(
def _stream_chat_with_documents(
query_str: str,
documents: QuerySet[Document],
documents: list[Document],
output_language: str | None = None,
):
if not documents.exists():
if not documents:
yield CHAT_NO_CONTENT_MESSAGE
return
@@ -161,9 +148,7 @@ def _stream_chat_with_documents(
from llama_index.core.retrievers import VectorIndexRetriever
config = AIConfig()
filters = _document_id_filters(
str(pk) for pk in documents.values_list("pk", flat=True)
)
filters = _document_id_filters(str(doc.pk) for doc in documents)
# Hold the shared read lock for the whole operation: the query engine
# retrieves from the vector store again during synthesis, so the connection
+46 -101
View File
@@ -3,12 +3,10 @@ from unittest.mock import MagicMock
from unittest.mock import patch
import pytest
from django.db.models.signals import post_init
from llama_index.core import settings as llama_settings
from llama_index.core.embeddings.mock_embed_model import MockEmbedding
from llama_index.core.schema import TextNode
from documents.models import Document
from documents.tests.factories import DocumentFactory
from paperless_ai import chat
from paperless_ai import indexing
@@ -38,6 +36,16 @@ def patch_embed_nodes():
yield mock_embed_nodes
@pytest.fixture
def mock_document():
doc = MagicMock()
doc.pk = 1
doc.title = "Test Document"
doc.filename = "test_file.pdf"
doc.content = "This is the document content."
return doc
def assert_chat_output(
output: list[str],
*,
@@ -53,13 +61,6 @@ def assert_chat_output(
}
def _fake_documents_queryset(pks: list[int]) -> MagicMock:
qs = MagicMock()
qs.exists.return_value = bool(pks)
qs.values_list.return_value = pks
return qs
@pytest.mark.parametrize(
("output_language", "expected_language_line"),
[
@@ -106,10 +107,9 @@ def test_build_refine_prompt(
@pytest.mark.django_db
def test_stream_chat_with_one_document_retrieval(
mock_document,
patch_embed_nodes,
) -> None:
document = DocumentFactory.create(title="Test Document", content="ignored")
documents = Document.objects.filter(pk=document.pk)
with (
patch("paperless_ai.chat.AIClient") as mock_client_cls,
patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
@@ -124,19 +124,22 @@ def test_stream_chat_with_one_document_retrieval(
mock_client_cls.return_value = mock_client
mock_client.llm = MagicMock()
mock_node = TextNode(
text="This is node content.",
metadata={"document_id": str(mock_document.pk), "title": "Test Document"},
)
mock_index = MagicMock()
mock_index.vector_store.get_nodes.return_value = [
TextNode(
text="This is node content.",
metadata={"document_id": str(document.pk), "title": "Test Document"},
),
]
# Simulate get_nodes returning nodes (content exists)
mock_index.vector_store.get_nodes.return_value = [mock_node]
mock_load_index.return_value = mock_index
mock_retriever_instance = MagicMock()
mock_retriever_instance.retrieve.return_value = [
MagicMock(
metadata={"document_id": str(document.pk), "title": "Test Document"},
metadata={
"document_id": str(mock_document.pk),
"title": "Test Document",
},
),
]
@@ -150,7 +153,7 @@ def test_stream_chat_with_one_document_retrieval(
"llama_index.core.retrievers.VectorIndexRetriever",
return_value=mock_retriever_instance,
):
output = list(stream_chat_with_documents("What is this?", documents))
output = list(stream_chat_with_documents("What is this?", [mock_document]))
mock_query_engine.query.assert_called_once_with("What is this?")
synthesizer_kwargs = mock_get_response_synthesizer.call_args.kwargs
@@ -163,16 +166,13 @@ def test_stream_chat_with_one_document_retrieval(
output,
expected_chunks=["chunk1", "chunk2"],
expected_references=[
{"id": document.pk, "title": "Test Document"},
{"id": mock_document.pk, "title": "Test Document"},
],
)
@pytest.mark.django_db
def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> None:
doc1 = DocumentFactory.create(title="Document 1", content="ignored")
doc2 = DocumentFactory.create(title="Document 2", content="ignored")
documents = Document.objects.filter(pk__in=[doc1.pk, doc2.pk])
with (
patch("paperless_ai.chat.AIClient") as mock_client_cls,
patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
@@ -184,23 +184,23 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
mock_client_cls.return_value = mock_client
mock_client.llm = MagicMock()
mock_node1 = TextNode(
text="Content for doc 1.",
metadata={"document_id": "1", "title": "Document 1"},
)
mock_node2 = TextNode(
text="Content for doc 2.",
metadata={"document_id": "2", "title": "Document 2"},
)
mock_index = MagicMock()
mock_index.vector_store.get_nodes.return_value = [
TextNode(
text="Content for doc 1.",
metadata={"document_id": str(doc1.pk), "title": "Document 1"},
),
TextNode(
text="Content for doc 2.",
metadata={"document_id": str(doc2.pk), "title": "Document 2"},
),
]
# Simulate get_nodes returning nodes (content exists)
mock_index.vector_store.get_nodes.return_value = [mock_node1, mock_node2]
mock_load_index.return_value = mock_index
mock_retriever_instance = MagicMock()
mock_retriever_instance.retrieve.return_value = [
MagicMock(metadata={"document_id": str(doc1.pk), "title": "Document 1"}),
MagicMock(metadata={"document_id": str(doc2.pk), "title": "Document 2"}),
MagicMock(metadata={"document_id": "1", "title": "Document 1"}),
MagicMock(metadata={"document_id": "2", "title": "Document 2"}),
]
mock_response_stream = MagicMock()
@@ -210,11 +210,14 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
mock_query_engine_cls.return_value = mock_query_engine
mock_query_engine.query.return_value = mock_response_stream
doc1 = MagicMock(pk=1, title="Document 1", filename="doc1.pdf")
doc2 = MagicMock(pk=2, title="Document 2", filename="doc2.pdf")
with patch(
"llama_index.core.retrievers.VectorIndexRetriever",
return_value=mock_retriever_instance,
):
output = list(stream_chat_with_documents("What's up?", documents))
output = list(stream_chat_with_documents("What's up?", [doc1, doc2]))
mock_query_engine.query.assert_called_once_with("What's up?")
patch_embed_nodes.assert_not_called()
@@ -222,15 +225,15 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
output,
expected_chunks=["chunk1", "chunk2"],
expected_references=[
{"id": doc1.pk, "title": "Document 1"},
{"id": doc2.pk, "title": "Document 2"},
{"id": 1, "title": "Document 1"},
{"id": 2, "title": "Document 2"},
],
)
def test_stream_chat_empty_document_list() -> None:
with patch("paperless_ai.chat.load_or_build_index") as mock_load_index:
output = list(stream_chat_with_documents("Any info?", Document.objects.none()))
output = list(stream_chat_with_documents("Any info?", []))
mock_load_index.assert_not_called()
assert output == ["Sorry, I couldn't find any content to answer your question."]
@@ -250,9 +253,7 @@ def test_stream_chat_no_matching_nodes() -> None:
mock_index.vector_store.get_nodes.return_value = []
mock_load_index.return_value = mock_index
output = list(
stream_chat_with_documents("Any info?", _fake_documents_queryset([1])),
)
output = list(stream_chat_with_documents("Any info?", [MagicMock(pk=1)]))
assert output == ["Sorry, I couldn't find any content to answer your question."]
@@ -281,9 +282,7 @@ def test_stream_chat_unexpected_failure_returns_generic_error(caplog) -> None:
)
mock_retriever_cls.return_value = mock_retriever
output = list(
stream_chat_with_documents("Any info?", _fake_documents_queryset([1])),
)
output = list(stream_chat_with_documents("Any info?", [MagicMock(pk=1)]))
assert output == [CHAT_ERROR_MESSAGE]
assert "Failed to stream document chat response" in caplog.text
@@ -299,12 +298,7 @@ class TestStreamChatRetrieval:
) -> None:
doc = DocumentFactory.create(content="hello world")
# Nothing indexed for this document yet.
out = list(
chat.stream_chat_with_documents(
"question?",
Document.objects.filter(pk=doc.pk),
),
)
out = list(chat.stream_chat_with_documents("question?", [doc]))
assert chat.CHAT_NO_CONTENT_MESSAGE in out
def test_chat_filter_contains_only_requested_document_ids(
@@ -338,12 +332,7 @@ class TestStreamChatRetrieval:
side_effect=capture_retriever,
)
list(
chat.stream_chat_with_documents(
"question?",
Document.objects.filter(pk=included.pk),
),
)
list(chat.stream_chat_with_documents("question?", [included]))
assert captured_filters, "VectorIndexRetriever was never constructed"
filt = captured_filters[0]
@@ -351,47 +340,3 @@ class TestStreamChatRetrieval:
filter_values = filt.filters[0].value
assert str(included.pk) in filter_values
assert str(excluded.pk) not in filter_values
@pytest.mark.django_db
def test_get_document_references_only_queries_referenced_documents(
self,
django_assert_num_queries,
) -> None:
"""Building references must not hydrate every document the caller is
permitted to see -- only the (<= CHAT_RETRIEVER_TOP_K) documents that
the retriever actually returned nodes for.
"""
referenced = DocumentFactory.create(title="Referenced Document")
# Many more documents are "accessible" but never referenced by a node.
DocumentFactory.create_batch(200)
documents = Document.objects.all()
top_nodes = [
MagicMock(
metadata={
"document_id": str(referenced.pk),
"title": "Referenced Document",
},
),
]
hydrated_count = 0
def _count_hydration(sender, instance, **kwargs):
nonlocal hydrated_count
hydrated_count += 1
post_init.connect(_count_hydration, sender=Document)
try:
# One query: `documents.filter(pk__in=candidate_ids)` for the single
# referenced id. No query should scale with the 200 unreferenced documents.
with django_assert_num_queries(1):
references = chat._get_document_references(documents, top_nodes)
finally:
post_init.disconnect(_count_hydration, sender=Document)
# The bug this guards against: the old code hydrated all 201 accessible
# documents via `{doc.pk: doc for doc in documents}` before filtering by
# top_nodes. Only the referenced document should ever be constructed.
assert hydrated_count == 1
assert references == [{"id": referenced.pk, "title": "Referenced Document"}]
+27
View File
@@ -757,3 +757,30 @@ class TestAPIProcessedMails(DirectoriesMixin, APITestCase):
format="json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
def test_bulk_delete_processed_mails_rejects_mixed_batch_atomically(self) -> None:
"""
GIVEN:
- A permitted processed mail and one the user may not delete
WHEN:
- API call bulk deletes both in a single request
THEN:
- The request is rejected and neither mail is deleted
"""
user2 = User.objects.create_user(username="temp_admin2")
rule = MailRuleFactory()
# Created first so it sorts ahead of the forbidden mail, i.e. the
# permission check has to cover the whole batch before deleting rather
# than rejecting only once it reaches the forbidden one.
pm_owned = ProcessedMailFactory(rule=rule, owner=self.user)
pm_forbidden = ProcessedMailFactory(rule=rule, owner=user2)
response = self.client.post(
f"{self.ENDPOINT}bulk_delete/",
data={"mail_ids": [pm_owned.id, pm_forbidden.id]},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
self.assertTrue(ProcessedMail.objects.filter(id=pm_owned.id).exists())
self.assertTrue(ProcessedMail.objects.filter(id=pm_forbidden.id).exists())
+12 -4
View File
@@ -27,6 +27,7 @@ from documents.filters import PermittedObjectsFilter
from documents.models import PaperlessTask
from documents.permissions import PaperlessObjectPermissions
from documents.permissions import has_perms_owner_aware
from documents.permissions import permitted_object_ids
from documents.views import PassUserMixin
from paperless.views import StandardPagination
from paperless_mail.filters import ProcessedMailFilterSet
@@ -211,10 +212,17 @@ class ProcessedMailViewSet(PassUserMixin, ReadOnlyModelViewSet[ProcessedMail]):
):
return HttpResponseBadRequest("mail_ids must be a list of integers")
mails = ProcessedMail.objects.filter(id__in=mail_ids)
for mail in mails:
if not has_perms_owner_aware(request.user, "delete_processedmail", mail):
return HttpResponseForbidden("Insufficient permissions")
mail.delete()
# Check every id up front so an unpermitted one rejects the whole
# request rather than deleting the mails ahead of it first.
if mails.exclude(
pk__in=permitted_object_ids(
request.user,
ProcessedMail,
"delete_processedmail",
),
).exists():
return HttpResponseForbidden("Insufficient permissions")
mails.delete()
return Response({"result": "OK", "deleted_mail_ids": mail_ids})
Generated
+22 -22
View File
@@ -1298,16 +1298,16 @@ wheels = [
[[package]]
name = "fpdf2"
version = "2.8.7"
version = "2.8.8"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "defusedxml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/27/f2/72feae0b2827ed38013e4307b14f95bf0b3d124adfef4d38a7d57533f7be/fpdf2-2.8.7.tar.gz", hash = "sha256:7060ccee5a9c7ab0a271fb765a36a23639f83ef8996c34e3d46af0a17ede57f9", size = 362351, upload-time = "2026-02-28T05:39:16.456Z" }
sdist = { url = "https://files.pythonhosted.org/packages/1e/bc/8fd4321aed40cadadddc8f311c65b6082346b252bca048f7b476d8f35d72/fpdf2-2.8.8.tar.gz", hash = "sha256:9e94e155e85e8053329a9a1fce8b566fd7a7c5bb79e98a1a3952d379b947c5b9", size = 374689, upload-time = "2026-08-09T23:32:45.334Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/66/0a/cf50ecffa1e3747ed9380a3adfc829259f1f86b3fdbd9e505af789003141/fpdf2-2.8.7-py3-none-any.whl", hash = "sha256:d391fc508a3ce02fc43a577c830cda4fe6f37646f2d143d489839940932fbc19", size = 327056, upload-time = "2026-02-28T05:39:14.619Z" },
{ url = "https://files.pythonhosted.org/packages/f5/be/af012eda9507494f28b99b077423806c43a11573eb6225dd46f19ae2d263/fpdf2-2.8.8-py3-none-any.whl", hash = "sha256:3557a478fc577a929c94aace9666aed4dcc432b5ab6764232e6a59f1ccd75f17", size = 337000, upload-time = "2026-08-09T23:32:43.728Z" },
]
[[package]]
@@ -2927,8 +2927,8 @@ dependencies = [
{ name = "sqlite-vec", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "tantivy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "tika-client", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'linux'" },
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "watchfiles", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "whitenoise", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "zxing-cpp", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -4511,8 +4511,8 @@ dependencies = [
{ name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "scikit-learn", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "scipy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'linux'" },
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "tqdm", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "transformers", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -4957,18 +4957,17 @@ name = "torch"
version = "2.13.0"
source = { registry = "https://download.pytorch.org/whl/cpu" }
resolution-markers = [
"python_full_version >= '3.15' and sys_platform == 'darwin'",
"python_full_version >= '3.12' and python_full_version < '3.15' and sys_platform == 'darwin'",
"python_full_version < '3.12' and sys_platform == 'darwin'",
]
dependencies = [
{ name = "filelock", marker = "sys_platform == 'darwin'" },
{ name = "fsspec", marker = "sys_platform == 'darwin'" },
{ name = "jinja2", marker = "sys_platform == 'darwin'" },
{ name = "networkx", marker = "sys_platform == 'darwin'" },
{ name = "setuptools", marker = "sys_platform == 'darwin'" },
{ name = "sympy", marker = "sys_platform == 'darwin'" },
{ name = "typing-extensions", marker = "sys_platform == 'darwin'" },
{ name = "filelock", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "fsspec", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "jinja2", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "networkx", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "setuptools", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "sympy", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "typing-extensions", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
]
wheels = [
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.13.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:e76f9bcecc52b8ff711239a2f7547d5353df95878ab232f0773c1d95928b92f8", upload-time = "2026-07-08T12:26:13Z" },
@@ -4983,6 +4982,7 @@ name = "torch"
version = "2.13.0+cpu"
source = { registry = "https://download.pytorch.org/whl/cpu" }
resolution-markers = [
"python_full_version >= '3.15' and sys_platform == 'darwin'",
"python_full_version == '3.12.*' and platform_machine == 'x86_64' and sys_platform == 'linux'",
"python_full_version == '3.12.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
"python_full_version >= '3.15' and sys_platform == 'linux'",
@@ -4990,13 +4990,13 @@ resolution-markers = [
"python_full_version < '3.12' and sys_platform == 'linux'",
]
dependencies = [
{ name = "filelock", marker = "sys_platform == 'linux'" },
{ name = "fsspec", marker = "sys_platform == 'linux'" },
{ name = "jinja2", marker = "sys_platform == 'linux'" },
{ name = "networkx", marker = "sys_platform == 'linux'" },
{ name = "setuptools", marker = "sys_platform == 'linux'" },
{ name = "sympy", marker = "sys_platform == 'linux'" },
{ name = "typing-extensions", marker = "sys_platform == 'linux'" },
{ name = "filelock", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "fsspec", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "jinja2", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "networkx", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "setuptools", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "sympy", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
{ name = "typing-extensions", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
]
wheels = [
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.13.0%2Bcpu-cp311-cp311-linux_s390x.whl", hash = "sha256:6e9817dbdf5ea76789babd46e457eac5bf14ff566cf85f8addbfdff2d56601ce", upload-time = "2026-07-08T19:27:52Z" },