And the rest of it

.pre-commit-config.yaml

@@ -37,7 +37,7 @@ repos:
           - json
   # See https://github.com/prettier/prettier/issues/15742 for the fork reason
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: 'v3.6.2'
+    rev: 'v3.8.0'
     hooks:
       - id: prettier
         types_or:
@@ -49,7 +49,7 @@ repos:
           - 'prettier-plugin-organize-imports@4.1.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.5
+    rev: v0.14.13
     hooks:
       - id: ruff-check
       - id: ruff-format
@@ -76,7 +76,7 @@ repos:
     hooks:
       - id: shellcheck
   - repo: https://github.com/google/yamlfmt
-    rev: v0.20.0
+    rev: v0.21.0
     hooks:
       - id: yamlfmt
         exclude: "^src-ui/pnpm-lock.yaml"

docs/configuration.md

@@ -1146,9 +1146,8 @@ via the consumption directory, you can disable the consumer to save resources.
 
 #### [`PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>`](#PAPERLESS_CONSUMER_DELETE_DUPLICATES) {#PAPERLESS_CONSUMER_DELETE_DUPLICATES}
 
-: As of version 3.0 Paperless-ngx allows duplicate documents to be consumed by default, _except_ when
+: When the consumer detects a duplicate document, it will not touch
-this setting is enabled. When enabled, Paperless will check if a document with the same hash already
+the original document. This default behavior can be changed here.
-exists in the system and delete the duplicate file from the consumption directory without consuming it.
 
     Defaults to false.
 

pyproject.toml

@@ -19,15 +19,15 @@ dependencies = [
   "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.3.0",
-  "celery[redis]~=5.5.1",
+  "celery[redis]~=5.6.2",
   "channels~=4.2",
   "channels-redis~=4.2",
   "concurrent-log-handler~=0.9.25",
   "dateparser~=1.2",
   # WARNING: django does not use semver.
   #          Only patch versions are guaranteed to not introduce breaking changes.
-  "django~=5.2.5",
+  "django==5.2.10",
-  "django-allauth[mfa,socialaccount]~=65.12.1",
+  "django-allauth[mfa,socialaccount]~=65.13.0",
   "django-auditlog~=3.4.1",
   "django-cachalot~=2.8.0",
   "django-celery-results~=2.6.0",
@@ -80,7 +80,7 @@ dependencies = [
   "torch~=2.9.1",
   "tqdm~=4.67.1",
   "watchdog~=6.0",
-  "whitenoise~=6.9",
+  "whitenoise~=6.11",
   "whoosh-reloaded>=2.7.5",
   "zxing-cpp~=2.3.0",
 ]
@@ -89,13 +89,13 @@ optional-dependencies.mariadb = [
   "mysqlclient~=2.2.7",
 ]
 optional-dependencies.postgres = [
-  "psycopg[c,pool]==3.2.12",
+  "psycopg[c,pool]==3.3",
   # Direct dependency for proper resolution of the pre-built wheels
-  "psycopg-c==3.2.12",
+  "psycopg-c==3.3",
   "psycopg-pool==3.3",
 ]
 optional-dependencies.webserver = [
-  "granian[uvloop]~=2.5.1",
+  "granian[uvloop]~=2.6.0",
 ]
 
 [dependency-groups]
@@ -152,7 +152,7 @@ typing = [
 ]
 
 [tool.uv]
-required-version = ">=0.5.14"
+required-version = ">=0.9.0"
 package = false
 environments = [
   "sys_platform == 'darwin'",
@@ -162,8 +162,8 @@ environments = [
 [tool.uv.sources]
 # Markers are chosen to select these almost exclusively when building the Docker image
 psycopg-c = [
-  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-bookworm-3.2.12/psycopg_c-3.2.12-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
+  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
-  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-bookworm-3.2.12/psycopg_c-3.2.12-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
+  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
 ]
 zxing-cpp = [
   { url = "https://github.com/paperless-ngx/builder/releases/download/zxing-2.3.0/zxing_cpp-2.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },

src-ui/src/app/components/admin/tasks/tasks.component.html

@@ -97,12 +97,6 @@
                   <br/><em>(<ng-container i18n>click for full output</ng-container>)</em>
                 }
               </ng-template>
-              @if (task.duplicate_documents?.length > 0) {
-                <div class="small text-warning-emphasis d-flex align-items-center gap-1">
-                  <i-bs class="lh-1" width="1em" height="1em" name="exclamation-triangle"></i-bs>
-                  <span i18n>Duplicate(s) detected</span>
-                </div>
-              }
             </td>
           }
           <td class="d-lg-none">

src-ui/src/app/components/common/input/tags/tags.component.html

@@ -28,7 +28,7 @@
             </button>
           </ng-template>
           <ng-template ng-option-tmp let-item="item" let-index="index" let-search="searchTerm">
-            <div class="tag-option-row d-flex align-items-center" [class.w-auto]="!getTag(item.id)?.parent">
+            <div class="tag-option-row d-flex align-items-center">
               @if (item.id && tags) {
                 @if (getTag(item.id)?.parent) {
                   <i-bs name="list-nested" class="me-1"></i-bs>

src-ui/src/app/components/common/input/tags/tags.component.scss

@@ -23,7 +23,7 @@
 
 // Dropdown hierarchy reveal for ng-select options
 ::ng-deep .ng-dropdown-panel .ng-option {
-  overflow-x: scroll !important;
+  overflow-x: scroll;
 
   .tag-option-row {
     font-size: 1rem;

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -370,37 +370,6 @@
             </ng-template>
           </li>
         }
-
-        @if (document?.duplicate_documents?.length) {
-          <li [ngbNavItem]="DocumentDetailNavIDs.Duplicates">
-            <a class="text-nowrap" ngbNavLink i18n>
-              Duplicates
-              <span class="badge text-bg-secondary ms-1">{{ document.duplicate_documents.length }}</span>
-            </a>
-            <ng-template ngbNavContent>
-              <div class="d-flex flex-column gap-2">
-                <div class="fst-italic" i18n>Duplicate documents detected:</div>
-                <div class="list-group">
-                  @for (duplicate of document.duplicate_documents; track duplicate.id) {
-                    <a
-                      class="list-group-item list-group-item-action d-flex justify-content-between align-items-center"
-                      [routerLink]="['/documents', duplicate.id, 'details']"
-                      [class.disabled]="duplicate.deleted_at"
-                    >
-                      <span class="d-flex align-items-center gap-2">
-                        <span>{{ duplicate.title || ('#' + duplicate.id) }}</span>
-                        @if (duplicate.deleted_at) {
-                          <span class="badge text-bg-secondary" i18n>In trash</span>
-                        }
-                      </span>
-                      <span class="text-secondary">#{{ duplicate.id }}</span>
-                    </a>
-                  }
-                </div>
-              </div>
-            </ng-template>
-          </li>
-        }
       </ul>
 
       <div [ngbNavOutlet]="nav" class="mt-3"></div>

src-ui/src/app/components/document-detail/document-detail.component.spec.ts

@@ -301,16 +301,16 @@ describe('DocumentDetailComponent', () => {
       .spyOn(openDocumentsService, 'openDocument')
       .mockReturnValueOnce(of(true))
     fixture.detectChanges()
-    expect(component.activeNavID).toEqual(component.DocumentDetailNavIDs.Notes)
+    expect(component.activeNavID).toEqual(5) // DocumentDetailNavIDs.Notes
   })
 
   it('should change url on tab switch', () => {
     initNormally()
     const navigateSpy = jest.spyOn(router, 'navigate')
-    component.nav.select(component.DocumentDetailNavIDs.Notes)
+    component.nav.select(5)
     component.nav.navChange.next({
       activeId: 1,
-      nextId: component.DocumentDetailNavIDs.Notes,
+      nextId: 5,
       preventDefault: () => {},
     })
     fixture.detectChanges()
@@ -352,18 +352,6 @@ describe('DocumentDetailComponent', () => {
     expect(component.document).toEqual(doc)
   })
 
-  it('should fall back to details tab when duplicates tab is active but no duplicates', () => {
-    initNormally()
-    component.activeNavID = component.DocumentDetailNavIDs.Duplicates
-    const noDupDoc = { ...doc, duplicate_documents: [] }
-
-    component.updateComponent(noDupDoc)
-
-    expect(component.activeNavID).toEqual(
-      component.DocumentDetailNavIDs.Details
-    )
-  })
-
   it('should load already-opened document via param', () => {
     initNormally()
     jest.spyOn(documentService, 'get').mockReturnValueOnce(of(doc))
@@ -379,38 +367,6 @@ describe('DocumentDetailComponent', () => {
     expect(component.document).toEqual(doc)
   })
 
-  it('should update cached open document duplicates when reloading an open doc', () => {
-    const openDoc = { ...doc, duplicate_documents: [{ id: 1, title: 'Old' }] }
-    const updatedDuplicates = [
-      { id: 2, title: 'Newer duplicate', deleted_at: null },
-    ]
-    jest
-      .spyOn(activatedRoute, 'paramMap', 'get')
-      .mockReturnValue(of(convertToParamMap({ id: 3, section: 'details' })))
-    jest.spyOn(documentService, 'get').mockReturnValue(
-      of({
-        ...doc,
-        modified: new Date('2024-01-02T00:00:00Z'),
-        duplicate_documents: updatedDuplicates,
-      })
-    )
-    jest.spyOn(openDocumentsService, 'getOpenDocument').mockReturnValue(openDoc)
-    const saveSpy = jest.spyOn(openDocumentsService, 'save')
-    jest.spyOn(openDocumentsService, 'openDocument').mockReturnValue(of(true))
-    jest.spyOn(customFieldsService, 'listAll').mockReturnValue(
-      of({
-        count: customFields.length,
-        all: customFields.map((f) => f.id),
-        results: customFields,
-      })
-    )
-
-    fixture.detectChanges()
-
-    expect(openDoc.duplicate_documents).toEqual(updatedDuplicates)
-    expect(saveSpy).toHaveBeenCalled()
-  })
-
   it('should disable form if user cannot edit', () => {
     currentUserHasObjectPermissions = false
     initNormally()

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -8,7 +8,7 @@ import {
   FormsModule,
   ReactiveFormsModule,
 } from '@angular/forms'
-import { ActivatedRoute, Router, RouterModule } from '@angular/router'
+import { ActivatedRoute, Router } from '@angular/router'
 import {
   NgbDateStruct,
   NgbDropdownModule,
@@ -124,7 +124,6 @@ enum DocumentDetailNavIDs {
   Notes = 5,
   Permissions = 6,
   History = 7,
-  Duplicates = 8,
 }
 
 enum ContentRenderType {
@@ -182,7 +181,6 @@ export enum ZoomSetting {
     NgxBootstrapIconsModule,
     PdfViewerModule,
     TextAreaComponent,
-    RouterModule,
   ],
 })
 export class DocumentDetailComponent
@@ -287,10 +285,10 @@ export class DocumentDetailComponent
     if (
       element &&
       element.nativeElement.offsetParent !== null &&
-      this.nav?.activeId == DocumentDetailNavIDs.Preview
+      this.nav?.activeId == 4
     ) {
       // its visible
-      setTimeout(() => this.nav?.select(DocumentDetailNavIDs.Details))
+      setTimeout(() => this.nav?.select(1))
     }
   }
 
@@ -456,11 +454,6 @@ export class DocumentDetailComponent
           const openDocument = this.openDocumentService.getOpenDocument(
             this.documentId
           )
-          // update duplicate documents if present
-          if (openDocument && doc?.duplicate_documents) {
-            openDocument.duplicate_documents = doc.duplicate_documents
-            this.openDocumentService.save()
-          }
           const useDoc = openDocument || doc
           if (openDocument) {
             if (
@@ -711,13 +704,6 @@ export class DocumentDetailComponent
     }
     this.title = this.documentTitlePipe.transform(doc.title)
     this.prepareForm(doc)
-
-    if (
-      this.activeNavID === DocumentDetailNavIDs.Duplicates &&
-      !doc?.duplicate_documents?.length
-    ) {
-      this.activeNavID = DocumentDetailNavIDs.Details
-    }
   }
 
   get customFieldFormFields(): FormArray {

src-ui/src/app/data/document.ts

@@ -159,8 +159,6 @@ export interface Document extends ObjectWithPermissions {
 
   page_count?: number
 
-  duplicate_documents?: Document[]
-
   // Frontend only
   __changedFields?: string[]
 }

src-ui/src/app/data/paperless-task.ts

@@ -1,4 +1,3 @@
-import { Document } from './document'
 import { ObjectWithId } from './object-with-id'
 
 export enum PaperlessTaskType {
@@ -43,7 +42,5 @@ export interface PaperlessTask extends ObjectWithId {
 
   related_document?: number
 
-  duplicate_documents?: Document[]
-
   owner?: number
 }

src/documents/consumer.py

@@ -785,45 +785,19 @@ class ConsumerPreflightPlugin(
             Q(checksum=checksum) | Q(archive_checksum=checksum),
         )
         if existing_doc.exists():
-            existing_doc = existing_doc.order_by("-created")
+            msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS
-            duplicates_in_trash = existing_doc.filter(deleted_at__isnull=False)
+            log_msg = f"Not consuming {self.filename}: It is a duplicate of {existing_doc.get().title} (#{existing_doc.get().pk})."
-            log_msg = (
-                f"Consuming duplicate {self.filename}: "
-                f"{existing_doc.count()} existing document(s) share the same content."
-            )
 
-            if duplicates_in_trash.exists():
+            if existing_doc.first().deleted_at is not None:
-                log_msg += " Note: at least one existing document is in the trash."
+                msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH
-
+                log_msg += " Note: existing document is in the trash."
-            self.log.warning(log_msg)
 
             if settings.CONSUMER_DELETE_DUPLICATES:
-                duplicate = existing_doc.first()
-                duplicate_label = (
-                    duplicate.title
-                    or duplicate.original_filename
-                    or (Path(duplicate.filename).name if duplicate.filename else None)
-                    or str(duplicate.pk)
-                )
-
                 Path(self.input_doc.original_file).unlink()
-
+            self._fail(
-                failure_msg = (
+                msg,
-                    f"Not consuming {self.filename}: "
+                log_msg,
-                    f"It is a duplicate of {duplicate_label} (#{duplicate.pk})"
+            )
-                )
-                status_msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS
-
-                if duplicates_in_trash.exists():
-                    status_msg = (
-                        ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH
-                    )
-                    failure_msg += " Note: existing document is in the trash."
-
-                self._fail(
-                    status_msg,
-                    failure_msg,
-                )
 
     def pre_check_directories(self):
         """

src/documents/migrations/1075_alter_paperlesstask_task_name.py

@@ -6,7 +6,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "1075_workflowaction_order"),
+        ("documents", "1074_workflowrun_deleted_at_workflowrun_restored_at_and_more"),
     ]
 
     operations = [

src/documents/migrations/1076_workflowaction_order.py

@@ -12,7 +12,7 @@ def populate_action_order(apps, schema_editor):
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "1074_workflowrun_deleted_at_workflowrun_restored_at_and_more"),
+        ("documents", "1075_alter_paperlesstask_task_name"),
     ]
 
     operations = [

src/documents/migrations/1077_alter_document_checksum_unique.py

@@ -1,23 +0,0 @@
-# Generated by Django 5.2.7 on 2026-01-14 17:45
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1076_alter_paperlesstask_task_name"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                editable=False,
-                max_length=32,
-                verbose_name="checksum",
-                help_text="The checksum of the original document.",
-            ),
-        ),
-    ]

src/documents/models.py

@@ -212,6 +212,7 @@ class Document(SoftDeleteModel, ModelWithOwner):
         _("checksum"),
         max_length=32,
         editable=False,
+        unique=True,
         help_text=_("The checksum of the original document."),
     )
 

src/documents/permissions.py

@@ -148,29 +148,13 @@ def get_document_count_filter_for_user(user):
     )
 
 
-def get_objects_for_user_owner_aware(
+def get_objects_for_user_owner_aware(user, perms, Model) -> QuerySet:
-    user,
+    objects_owned = Model.objects.filter(owner=user)
-    perms,
+    objects_unowned = Model.objects.filter(owner__isnull=True)
-    Model,
-    *,
-    include_deleted=False,
-) -> QuerySet:
-    """
-    Returns objects the user owns, are unowned, or has explicit perms.
-    When include_deleted is True, soft-deleted items are also included.
-    """
-    manager = (
-        Model.global_objects
-        if include_deleted and hasattr(Model, "global_objects")
-        else Model.objects
-    )
-
-    objects_owned = manager.filter(owner=user)
-    objects_unowned = manager.filter(owner__isnull=True)
     objects_with_perms = get_objects_for_user(
         user=user,
         perms=perms,
-        klass=manager.all(),
+        klass=Model,
         accept_global_perms=False,
     )
     return objects_owned | objects_unowned | objects_with_perms

src/documents/serialisers.py

@@ -23,7 +23,6 @@ from django.core.validators import MinValueValidator
 from django.core.validators import RegexValidator
 from django.core.validators import integer_validator
 from django.db.models import Count
-from django.db.models import Q
 from django.db.models.functions import Lower
 from django.utils.crypto import get_random_string
 from django.utils.dateparse import parse_datetime
@@ -73,7 +72,6 @@ from documents.models import WorkflowTrigger
 from documents.parsers import is_mime_type_supported
 from documents.permissions import get_document_count_filter_for_user
 from documents.permissions import get_groups_with_only_permission
-from documents.permissions import get_objects_for_user_owner_aware
 from documents.permissions import set_permissions_for_object
 from documents.regex import validate_regex_pattern
 from documents.templating.filepath import validate_filepath_template_and_render
@@ -1016,29 +1014,6 @@ class NotesSerializer(serializers.ModelSerializer):
         return ret
 
 
-def _get_viewable_duplicates(document: Document, user: User | None):
-    checksums = {document.checksum}
-    if document.archive_checksum:
-        checksums.add(document.archive_checksum)
-    duplicates = Document.global_objects.filter(
-        Q(checksum__in=checksums) | Q(archive_checksum__in=checksums),
-    ).exclude(pk=document.pk)
-    duplicates = duplicates.order_by("-created")
-    allowed = get_objects_for_user_owner_aware(
-        user,
-        "documents.view_document",
-        Document,
-        include_deleted=True,
-    )
-    return duplicates.filter(id__in=allowed.values_list("id", flat=True))
-
-
-class DuplicateDocumentSummarySerializer(serializers.Serializer):
-    id = serializers.IntegerField()
-    title = serializers.CharField()
-    deleted_at = serializers.DateTimeField(allow_null=True)
-
-
 @extend_schema_serializer(
     deprecate_fields=["created_date"],
 )
@@ -1056,7 +1031,6 @@ class DocumentSerializer(
     archived_file_name = SerializerMethodField()
     created_date = serializers.DateField(required=False)
     page_count = SerializerMethodField()
-    duplicate_documents = SerializerMethodField()
 
     notes = NotesSerializer(many=True, required=False, read_only=True)
 
@@ -1082,16 +1056,6 @@ class DocumentSerializer(
     def get_page_count(self, obj) -> int | None:
         return obj.page_count
 
-    @extend_schema_field(DuplicateDocumentSummarySerializer(many=True))
-    def get_duplicate_documents(self, obj):
-        view = self.context.get("view")
-        if view and getattr(view, "action", None) != "retrieve":
-            return []
-        request = self.context.get("request")
-        user = request.user if request else None
-        duplicates = _get_viewable_duplicates(obj, user)
-        return list(duplicates.values("id", "title", "deleted_at"))
-
     def get_original_file_name(self, obj) -> str | None:
         return obj.original_filename
 
@@ -1269,7 +1233,6 @@ class DocumentSerializer(
             "archive_serial_number",
             "original_file_name",
             "archived_file_name",
-            "duplicate_documents",
             "owner",
             "permissions",
             "user_can_change",
@@ -2131,12 +2094,10 @@ class TasksViewSerializer(OwnedObjectSerializer):
             "result",
             "acknowledged",
             "related_document",
-            "duplicate_documents",
             "owner",
         )
 
     related_document = serializers.SerializerMethodField()
-    duplicate_documents = serializers.SerializerMethodField()
     created_doc_re = re.compile(r"New document id (\d+) created")
     duplicate_doc_re = re.compile(r"It is a duplicate of .* \(#(\d+)\)")
 
@@ -2161,17 +2122,6 @@ class TasksViewSerializer(OwnedObjectSerializer):
 
         return result
 
-    @extend_schema_field(DuplicateDocumentSummarySerializer(many=True))
-    def get_duplicate_documents(self, obj):
-        related_document = self.get_related_document(obj)
-        request = self.context.get("request")
-        user = request.user if request else None
-        document = Document.global_objects.filter(pk=related_document).first()
-        if not related_document or not user or not document:
-            return []
-        duplicates = _get_viewable_duplicates(document, user)
-        return list(duplicates.values("id", "title", "deleted_at"))
-
 
 class RunTaskViewSerializer(serializers.Serializer):
     task_name = serializers.ChoiceField(

src/documents/tests/test_api_tasks.py

@@ -7,7 +7,6 @@ from django.contrib.auth.models import User
 from rest_framework import status
 from rest_framework.test import APITestCase
 
-from documents.models import Document
 from documents.models import PaperlessTask
 from documents.tests.utils import DirectoriesMixin
 from documents.views import TasksViewSet
@@ -259,7 +258,7 @@ class TestTasks(DirectoriesMixin, APITestCase):
             task_id=str(uuid.uuid4()),
             task_file_name="task_one.pdf",
             status=celery.states.FAILURE,
-            result="test.pdf: Unexpected error during ingestion.",
+            result="test.pdf: Not consuming test.pdf: It is a duplicate.",
         )
 
         response = self.client.get(self.ENDPOINT)
@@ -271,7 +270,7 @@ class TestTasks(DirectoriesMixin, APITestCase):
 
         self.assertEqual(
             returned_data["result"],
-            "test.pdf: Unexpected error during ingestion.",
+            "test.pdf: Not consuming test.pdf: It is a duplicate.",
         )
 
     def test_task_name_webui(self):
@@ -326,34 +325,20 @@ class TestTasks(DirectoriesMixin, APITestCase):
 
         self.assertEqual(returned_data["task_file_name"], "anothertest.pdf")
 
-    def test_task_result_duplicate_warning_includes_count(self):
+    def test_task_result_failed_duplicate_includes_related_doc(self):
         """
         GIVEN:
-            - A celery task succeeds, but a duplicate exists
+            - A celery task failed with a duplicate error
         WHEN:
             - API call is made to get tasks
         THEN:
-            - The returned data includes duplicate warning metadata
+            - The returned data includes a related document link
         """
-        checksum = "duplicate-checksum"
-        Document.objects.create(
-            title="Existing",
-            content="",
-            mime_type="application/pdf",
-            checksum=checksum,
-        )
-        created_doc = Document.objects.create(
-            title="Created",
-            content="",
-            mime_type="application/pdf",
-            checksum=checksum,
-            archive_checksum="another-checksum",
-        )
         PaperlessTask.objects.create(
             task_id=str(uuid.uuid4()),
             task_file_name="task_one.pdf",
-            status=celery.states.SUCCESS,
+            status=celery.states.FAILURE,
-            result=f"Success. New document id {created_doc.pk} created",
+            result="Not consuming task_one.pdf: It is a duplicate of task_one_existing.pdf (#1234).",
         )
 
         response = self.client.get(self.ENDPOINT)
@@ -363,7 +348,7 @@ class TestTasks(DirectoriesMixin, APITestCase):
 
         returned_data = response.data[0]
 
-        self.assertEqual(returned_data["related_document"], str(created_doc.pk))
+        self.assertEqual(returned_data["related_document"], "1234")
 
     def test_run_train_classifier_task(self):
         """

src/documents/tests/test_consumer.py

@@ -485,21 +485,21 @@ class TestConsumer(
         with self.get_consumer(self.get_test_file()) as consumer:
             consumer.run()
 
-        with self.get_consumer(self.get_test_file()) as consumer:
+        with self.assertRaisesMessage(ConsumerError, "It is a duplicate"):
-            consumer.run()
+            with self.get_consumer(self.get_test_file()) as consumer:
+                consumer.run()
 
-        self.assertEqual(Document.objects.count(), 2)
+        self._assert_first_last_send_progress(last_status="FAILED")
-        self._assert_first_last_send_progress()
 
     def testDuplicates2(self):
         with self.get_consumer(self.get_test_file()) as consumer:
             consumer.run()
 
-        with self.get_consumer(self.get_test_archive_file()) as consumer:
+        with self.assertRaisesMessage(ConsumerError, "It is a duplicate"):
-            consumer.run()
+            with self.get_consumer(self.get_test_archive_file()) as consumer:
+                consumer.run()
 
-        self.assertEqual(Document.objects.count(), 2)
+        self._assert_first_last_send_progress(last_status="FAILED")
-        self._assert_first_last_send_progress()
 
     def testDuplicates3(self):
         with self.get_consumer(self.get_test_archive_file()) as consumer:
@@ -513,10 +513,9 @@ class TestConsumer(
 
         Document.objects.all().delete()
 
-        with self.get_consumer(self.get_test_file()) as consumer:
+        with self.assertRaisesMessage(ConsumerError, "document is in the trash"):
-            consumer.run()
+            with self.get_consumer(self.get_test_file()) as consumer:
-
+                consumer.run()
-        self.assertEqual(Document.objects.count(), 1)
 
     def testAsnExists(self):
         with self.get_consumer(
@@ -719,45 +718,12 @@ class TestConsumer(
         dst = self.get_test_file()
         self.assertIsFile(dst)
 
-        expected_message = (
+        with self.assertRaises(ConsumerError):
-            f"{dst.name}: Not consuming {dst.name}: "
-            f"It is a duplicate of {document.title} (#{document.pk})"
-        )
-
-        with self.assertRaisesMessage(ConsumerError, expected_message):
             with self.get_consumer(dst) as consumer:
                 consumer.run()
 
         self.assertIsNotFile(dst)
-        self.assertEqual(Document.objects.count(), 1)
+        self._assert_first_last_send_progress(last_status="FAILED")
-        self._assert_first_last_send_progress(last_status=ProgressStatusOptions.FAILED)
-
-    @override_settings(CONSUMER_DELETE_DUPLICATES=True)
-    def test_delete_duplicate_in_trash(self):
-        dst = self.get_test_file()
-        with self.get_consumer(dst) as consumer:
-            consumer.run()
-
-        # Move the existing document to trash
-        document = Document.objects.first()
-        document.delete()
-
-        dst = self.get_test_file()
-        self.assertIsFile(dst)
-
-        expected_message = (
-            f"{dst.name}: Not consuming {dst.name}: "
-            f"It is a duplicate of {document.title} (#{document.pk})"
-            f" Note: existing document is in the trash."
-        )
-
-        with self.assertRaisesMessage(ConsumerError, expected_message):
-            with self.get_consumer(dst) as consumer:
-                consumer.run()
-
-        self.assertIsNotFile(dst)
-        self.assertEqual(Document.global_objects.count(), 1)
-        self.assertEqual(Document.objects.count(), 0)
 
     @override_settings(CONSUMER_DELETE_DUPLICATES=False)
     def test_no_delete_duplicate(self):
@@ -777,12 +743,15 @@ class TestConsumer(
         dst = self.get_test_file()
         self.assertIsFile(dst)
 
-        with self.get_consumer(dst) as consumer:
+        with self.assertRaisesRegex(
-            consumer.run()
+            ConsumerError,
+            r"sample\.pdf: Not consuming sample\.pdf: It is a duplicate of sample \(#\d+\)",
+        ):
+            with self.get_consumer(dst) as consumer:
+                consumer.run()
 
-        self.assertIsNotFile(dst)
+        self.assertIsFile(dst)
-        self.assertEqual(Document.objects.count(), 2)
+        self._assert_first_last_send_progress(last_status="FAILED")
-        self._assert_first_last_send_progress()
 
     @override_settings(FILENAME_FORMAT="{title}")
     @mock.patch("documents.parsers.document_consumer_declaration.send")