Docs

* Fix: Hardening sweep, ensure a user is active, not just authenticated

* Missed this test

docs/api.md

@@ -301,7 +301,8 @@ The following methods are supported:
 - `delete`
   - No `parameters` required
 - `reprocess`
-  - No `parameters` required
+  - Optional `parameters`: `{ "remote_ocr": true }` to send the documents to the
+    remote OCR engine, see [Remote OCR](usage.md#remote-ocr). Defaults to false.
 - `set_permissions`
   - Requires `parameters`:
     - `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or

docs/configuration.md

@@ -2047,6 +2047,18 @@ password. All of these options come from their similarly-named [Django settings]
 
     Defaults to None.
 
+#### [`PAPERLESS_REMOTE_OCR_MODE=<str>`](#PAPERLESS_REMOTE_OCR_MODE) {#PAPERLESS_REMOTE_OCR_MODE}
+
+: Which documents are sent to the remote OCR engine.
+
+    - `always`: every document of a supported file type is sent to the remote
+      engine, bypassing the local OCR engine.
+    - `workflow_only`: documents are processed locally unless a workflow
+      explicitly enables remote OCR for them, letting you use the remote engine
+      selectively.
+
+    Defaults to "always".
+
 ## AI {#ai}
 
 #### [`PAPERLESS_AI_ENABLED=<bool>`](#PAPERLESS_AI_ENABLED) {#PAPERLESS_AI_ENABLED}

docs/development.md

@@ -456,6 +456,20 @@ def score(
     return 10
 ```
 
+**Remote services**
+
+If your parser sends document content to a remote service, declare it:
+
+```python
+class MyCustomParser:
+    uses_remote_service = True
+```
+
+Paperless-ngx excludes such parsers when the document being consumed has not
+been marked for remote processing, so users can keep remote OCR off by default
+and enable it selectively with a workflow. Parsers that do not declare the
+attribute are treated as fully local and are always considered.
+
 **Archive and rendition flags**
 
 ```python

docs/usage.md

@@ -1084,11 +1084,18 @@ Paperless-ngx supports performing OCR on documents using remote services. At the
 [Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
 This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
 Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
-the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
+the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details. These
+settings can be supplied as environment variables or via **Application Configuration**.
 
 Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
 or page limitations (e.g. with a free tier).
 
+By default, every document of a supported file type is sent to the remote engine. To use it more selectively, set the
+[remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE) to `workflow_only`. Documents are then processed locally
+unless a workflow explicitly enables remote OCR for them, so you can limit the remote engine to particular documents.
+
+Setting the mode to `workflow_only` also allows the **Reprocess** actions to selectively use remote OCR for individual documents.
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

src-ui/package.json

@@ -66,5 +66,5 @@
     "ts-node": "~10.9.1",
     "typescript": "^6.0.3"
   },
-  "packageManager": "pnpm@10.26.0"
+  "packageManager": "pnpm@11.15.1"
 }

src-ui/pnpm-workspace.yaml

@@ -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

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

@@ -14,8 +14,12 @@
                 <a ngbNavLink>{{category}}</a>
                 <ng-template ngbNavContent>
                     <div class="p-3">
+                        @for (section of getCategorySections(category); track section) {
+                            @if (section) {
+                                <h5 class="mt-4 mb-3">{{section}}</h5>
+                            }
                             <div class="row row-cols-1 row-cols-md-2 row-cols-lg-3 g-2">
-                            @for (option of getCategoryOptions(category); track option.key) {
+                                @for (option of getCategoryOptions(category, section); track option.key) {
                                     <div class="col">
                                         <div class="card bg-light">
                                             <div class="card-body">
@@ -51,6 +55,7 @@
                                     </div>
                                 }
                             </div>
+                        }
                     </div>
                 </ng-template>
             </li>

src-ui/src/app/components/admin/config/config.component.spec.ts

@@ -8,7 +8,11 @@ import { NgbModule } from '@ng-bootstrap/ng-bootstrap'
 import { NgSelectModule } from '@ng-select/ng-select'
 import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
 import { of, throwError } from 'rxjs'
-import { OutputTypeConfig } from 'src/app/data/paperless-config'
+import {
+  ConfigCategory,
+  ConfigSection,
+  OutputTypeConfig,
+} from 'src/app/data/paperless-config'
 import { ConfigService } from 'src/app/services/config.service'
 import { SettingsService } from 'src/app/services/settings.service'
 import { ToastService } from 'src/app/services/toast.service'
@@ -158,4 +162,24 @@ describe('ConfigComponent', () => {
     component.resetOption('barcodes_enabled')
     expect(component.configForm.get('barcodes_enabled').value).toBeNull()
   })
+
+  it('should group options into sections within a category, or not', () => {
+    const sections = component.getCategorySections(ConfigCategory.OCR)
+    expect(sections).toEqual([null, ConfigSection.RemoteOCR])
+    expect(
+      component
+        .getCategoryOptions(ConfigCategory.OCR)
+        .map((option) => option.key)
+    ).toContain('output_type')
+    expect(
+      component
+        .getCategoryOptions(ConfigCategory.OCR, ConfigSection.RemoteOCR)
+        .map((option) => option.key)
+    ).toEqual([
+      'remote_ocr_engine',
+      'remote_ocr_api_key',
+      'remote_ocr_endpoint',
+      'remote_ocr_mode',
+    ])
+  })
 })

src-ui/src/app/components/admin/config/config.component.ts

@@ -74,8 +74,20 @@ export class ConfigComponent
     return Object.values(ConfigCategory)
   }
 
-  getCategoryOptions(category: string): ConfigOption[] {
+  getCategorySections(category: string): string[] {
-    return PaperlessConfigOptions.filter((o) => o.category === category)
+    return [
+      ...new Set(
+        PaperlessConfigOptions.filter((o) => o.category === category).map(
+          (o) => o.section ?? null // null means no section
+        )
+      ),
+    ]
+  }
+
+  getCategoryOptions(category: string, section: string = null): ConfigOption[] {
+    return PaperlessConfigOptions.filter(
+      (o) => o.category === category && (o.section ?? null) === section
+    )
   }
 
   initialConfig: PaperlessConfig

src-ui/src/app/components/common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component.html

@@ -0,0 +1,28 @@
+<div class="modal-header">
+  <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
+  <button type="button" class="btn-close" aria-label="Close" (click)="cancel()">
+  </button>
+</div>
+<div class="modal-body">
+  @if (messageBold) {
+    <p class="text-break"><b>{{messageBold}}</b></p>
+  }
+  @if (message) {
+    <p class="mb-0 text-break" [innerHTML]="message"></p>
+  }
+  @if (showRemoteOcr) {
+    <div class="form-check mt-3">
+      <input class="form-check-input" type="checkbox" id="reprocessRemoteOcr" [(ngModel)]="remoteOcr" />
+      <label class="form-check-label" for="reprocessRemoteOcr" i18n>Use remote OCR</label>
+      <div class="form-text" i18n>Sends the document to the configured remote OCR service, which may incur costs.</div>
+    </div>
+  }
+</div>
+<div class="modal-footer">
+  <button type="button" class="btn" [class]="cancelBtnClass" (click)="cancel()" [disabled]="!buttonsEnabled">
+    <span class="d-inline-block" style="padding-bottom: 1px;">{{cancelBtnCaption}}</span>
+  </button>
+  <button type="button" class="btn" [class]="btnClass" (click)="confirm()" [disabled]="!confirmButtonEnabled || !buttonsEnabled">
+    {{btnCaption}}
+  </button>
+</div>

src-ui/src/app/components/common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component.spec.ts

@@ -0,0 +1,72 @@
+import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
+import { provideHttpClientTesting } from '@angular/common/http/testing'
+import { ComponentFixture, TestBed } from '@angular/core/testing'
+import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
+import { RemoteOCRModeConfig } from 'src/app/data/paperless-config'
+import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
+import { SettingsService } from 'src/app/services/settings.service'
+import { ReprocessConfirmDialogComponent } from './reprocess-confirm-dialog.component'
+
+describe('ReprocessConfirmDialogComponent', () => {
+  let component: ReprocessConfirmDialogComponent
+  let fixture: ComponentFixture<ReprocessConfirmDialogComponent>
+  let settingsService: SettingsService
+
+  const createComponent = (configured: boolean, mode: string) => {
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, configured)
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_MODE, mode)
+
+    fixture = TestBed.createComponent(ReprocessConfirmDialogComponent)
+    component = fixture.componentInstance
+    fixture.detectChanges()
+  }
+
+  beforeEach(async () => {
+    TestBed.configureTestingModule({
+      providers: [
+        NgbActiveModal,
+        provideHttpClient(withInterceptorsFromDi()),
+        provideHttpClientTesting(),
+      ],
+      imports: [ReprocessConfirmDialogComponent],
+    }).compileComponents()
+
+    settingsService = TestBed.inject(SettingsService)
+  })
+
+  it('should not request remote OCR by default', () => {
+    createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
+
+    expect(component.remoteOcr).toBeFalsy()
+  })
+
+  it('should not offer remote OCR when no engine is configured', () => {
+    createComponent(false, RemoteOCRModeConfig.WORKFLOW_ONLY)
+
+    expect(component.showRemoteOcr).toBeFalsy()
+    expect(
+      fixture.nativeElement.querySelector('#reprocessRemoteOcr')
+    ).toBeNull()
+  })
+
+  it('should not offer remote OCR when it already handles every document', () => {
+    createComponent(true, RemoteOCRModeConfig.ALWAYS)
+
+    expect(component.showRemoteOcr).toBeFalsy()
+    expect(
+      fixture.nativeElement.querySelector('#reprocessRemoteOcr')
+    ).toBeNull()
+  })
+
+  it('should offer remote OCR when configured and selective', () => {
+    createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
+
+    expect(component.showRemoteOcr).toBeTruthy()
+    const checkbox = fixture.nativeElement.querySelector('#reprocessRemoteOcr')
+    expect(checkbox).not.toBeNull()
+
+    checkbox.click()
+    fixture.detectChanges()
+    expect(component.remoteOcr).toBeTruthy()
+  })
+})

src-ui/src/app/components/common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component.ts

@@ -0,0 +1,20 @@
+import { Component, inject } from '@angular/core'
+import { FormsModule } from '@angular/forms'
+import { SettingsService } from 'src/app/services/settings.service'
+import { ConfirmDialogComponent } from '../confirm-dialog.component'
+
+@Component({
+  selector: 'pngx-reprocess-confirm-dialog',
+  templateUrl: './reprocess-confirm-dialog.component.html',
+  imports: [FormsModule],
+})
+export class ReprocessConfirmDialogComponent extends ConfirmDialogComponent {
+  private settings = inject(SettingsService)
+
+  remoteOcr: boolean = false
+
+  public get showRemoteOcr(): boolean {
+    // Hidden when it is not configured, or when it already handles every document anyway.
+    return this.settings.remoteOCRIsSelectable
+  }
+}

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

@@ -963,12 +963,24 @@ describe('DocumentDetailComponent', () => {
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
     openModal.componentInstance.confirmClicked.next()
-    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] })
+    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, false)
     expect(modalSpy).toHaveBeenCalled()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).toHaveBeenCalled()
   })
 
+  it('should pass remote OCR choice when reprocessing', () => {
+    initNormally()
+    const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
+    reprocessSpy.mockReturnValue(of(true))
+    let openModal: NgbModalRef
+    modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
+    component.reprocess()
+    openModal.componentInstance.remoteOcr = true
+    openModal.componentInstance.confirmClicked.next()
+    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, true)
+  })
+
   it('should show error if redo ocr call fails', () => {
     initNormally()
     const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')

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

@@ -97,6 +97,7 @@ import { ISODateAdapter } from 'src/app/utils/ngb-iso-date-adapter'
 import * as UTIF from 'utif'
 import { DocumentDetailFieldID } from '../admin/settings/settings.component'
 import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
+import { ReprocessConfirmDialogComponent } from '../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
 import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component'
 import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component'
 import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
@@ -1402,7 +1403,7 @@ export class DocumentDetailComponent
   }
 
   reprocess() {
-    let modal = this.modalService.open(ConfirmDialogComponent, {
+    let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
       backdrop: 'static',
     })
     modal.componentInstance.title = $localize`Reprocess confirm`
@@ -1413,7 +1414,10 @@ export class DocumentDetailComponent
     modal.componentInstance.confirmClicked.subscribe(() => {
       modal.componentInstance.buttonsEnabled = false
       this.documentsService
-        .reprocessDocuments({ documents: [this.document().id] })
+        .reprocessDocuments(
+          { documents: [this.document().id] },
+          modal.componentInstance.remoteOcr
+        )
         .subscribe({
           next: () => {
             this.toastService.showInfo(

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.spec.ts

@@ -1122,6 +1122,7 @@ describe('BulkEditorComponent', () => {
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
+      remote_ocr: false,
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.ts

@@ -51,6 +51,7 @@ import { ToastService } from 'src/app/services/toast.service'
 import { flattenTags } from 'src/app/utils/flatten-tags'
 import { queryParamsFromFilterRules } from 'src/app/utils/query-params'
 import { MergeConfirmDialogComponent } from '../../common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component'
+import { ReprocessConfirmDialogComponent } from '../../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
 import { RotateConfirmDialogComponent } from '../../common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component'
 import { CorrespondentEditDialogComponent } from '../../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
 import { CustomFieldEditDialogComponent } from '../../common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component'
@@ -909,7 +910,7 @@ export class BulkEditorComponent
   }
 
   reprocessSelected() {
-    let modal = this.modalService.open(ConfirmDialogComponent, {
+    let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
       backdrop: 'static',
     })
     modal.componentInstance.title = $localize`Reprocess confirm`
@@ -923,7 +924,10 @@ export class BulkEditorComponent
         modal.componentInstance.buttonsEnabled = false
         this.executeDocumentAction(
           modal,
-          this.documentService.reprocessDocuments(this.getSelectionQuery())
+          this.documentService.reprocessDocuments(
+            this.getSelectionQuery(),
+            modal.componentInstance.remoteOcr
+          )
         )
       })
   }

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

@@ -54,6 +54,10 @@ export const ConfigCategory = {
   AI: $localize`AI Settings`,
 }
 
+export const ConfigSection = {
+  RemoteOCR: $localize`Remote OCR`,
+}
+
 export const LLMEmbeddingBackendConfig = {
   OPENAI_LIKE: 'openai-like',
   HUGGINGFACE: 'huggingface',
@@ -65,6 +69,15 @@ export const LLMBackendConfig = {
   OLLAMA: 'ollama',
 }
 
+export const RemoteOCREngineConfig = {
+  AZURE_AI: 'azureai',
+}
+
+export const RemoteOCRModeConfig = {
+  ALWAYS: 'always',
+  WORKFLOW_ONLY: 'workflow_only',
+}
+
 export interface ConfigOption {
   key: string
   title: string
@@ -72,6 +85,7 @@ export interface ConfigOption {
   choices?: Array<{ id: string; name: string }>
   config_key?: string
   category: string
+  section?: string
   note?: string
 }
 
@@ -181,6 +195,43 @@ export const PaperlessConfigOptions: ConfigOption[] = [
     config_key: 'PAPERLESS_OCR_USER_ARGS',
     category: ConfigCategory.OCR,
   },
+  {
+    key: 'remote_ocr_engine',
+    title: $localize`Remote OCR Engine`,
+    type: ConfigOptionType.Select,
+    choices: mapToItems(RemoteOCREngineConfig),
+    config_key: 'PAPERLESS_REMOTE_OCR_ENGINE',
+    category: ConfigCategory.OCR,
+    section: ConfigSection.RemoteOCR,
+    note: $localize`Enabling remote OCR sends documents to a third-party service for processing. Consider the privacy implications as well as potential costs before enabling.`,
+  },
+  {
+    key: 'remote_ocr_api_key',
+    title: $localize`Remote OCR API Key`,
+    type: ConfigOptionType.Password,
+    config_key: 'PAPERLESS_REMOTE_OCR_API_KEY',
+    category: ConfigCategory.OCR,
+    section: ConfigSection.RemoteOCR,
+  },
+  {
+    key: 'remote_ocr_endpoint',
+    title: $localize`Remote OCR Endpoint`,
+    type: ConfigOptionType.String,
+    config_key: 'PAPERLESS_REMOTE_OCR_ENDPOINT',
+    category: ConfigCategory.OCR,
+    section: ConfigSection.RemoteOCR,
+    note: $localize`Required when using the Azure AI engine.`,
+  },
+  {
+    key: 'remote_ocr_mode',
+    title: $localize`Remote OCR Mode`,
+    type: ConfigOptionType.Select,
+    choices: mapToItems(RemoteOCRModeConfig),
+    config_key: 'PAPERLESS_REMOTE_OCR_MODE',
+    category: ConfigCategory.OCR,
+    section: ConfigSection.RemoteOCR,
+    note: $localize`Which documents are sent to the remote engine. Use 'workflow_only' to keep remote OCR off unless a workflow enables it for a document.`,
+  },
   {
     key: 'app_logo',
     title: $localize`Application Logo`,
@@ -398,6 +449,10 @@ export interface PaperlessConfig extends ObjectWithId {
   barcode_enable_tag: boolean
   barcode_tag_mapping: object
   barcode_tag_split: boolean
+  remote_ocr_engine: string
+  remote_ocr_api_key: string
+  remote_ocr_endpoint: string
+  remote_ocr_mode: string
   ai_enabled: boolean
   llm_embedding_backend: string
   llm_embedding_model: string

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

@@ -1,5 +1,6 @@
 import { PdfEditorEditMode } from '../components/common/pdf-editor/pdf-editor-edit-mode'
 import { PdfZoomScale } from '../components/common/pdf-viewer/pdf-viewer.types'
+import { RemoteOCRModeConfig } from './paperless-config'
 import { User } from './user'
 
 export interface UiSettings {
@@ -94,6 +95,8 @@ export const SETTINGS_KEYS = {
   OUTLOOK_OAUTH_URL: 'outlook_oauth_url',
   EMAIL_ENABLED: 'email_enabled',
   AI_ENABLED: 'ai_enabled',
+  REMOTE_OCR_CONFIGURED: 'remote_ocr:configured',
+  REMOTE_OCR_MODE: 'remote_ocr:mode',
 }
 
 export const SETTINGS: UiSetting[] = [
@@ -347,4 +350,14 @@ export const SETTINGS: UiSetting[] = [
     type: 'string',
     default: PdfEditorEditMode.Create,
   },
+  {
+    key: SETTINGS_KEYS.REMOTE_OCR_CONFIGURED,
+    type: 'boolean',
+    default: false,
+  },
+  {
+    key: SETTINGS_KEYS.REMOTE_OCR_MODE,
+    type: 'string',
+    default: RemoteOCRModeConfig.ALWAYS,
+  },
 ]

src-ui/src/app/services/rest/document.service.spec.ts

@@ -284,6 +284,21 @@ describe(`DocumentService`, () => {
     expect(req.request.method).toEqual('POST')
     expect(req.request.body).toEqual({
       documents: ids,
+      remote_ocr: false,
+    })
+  })
+
+  it('should request remote OCR when reprocessing with it enabled', () => {
+    const ids = [1, 2, 3]
+    subscription = service
+      .reprocessDocuments({ documents: ids }, true)
+      .subscribe()
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}${endpoint}/reprocess/`
+    )
+    expect(req.request.body).toEqual({
+      documents: ids,
+      remote_ocr: true,
     })
   })
 

src-ui/src/app/services/rest/document.service.ts

@@ -349,9 +349,13 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     })
   }
 
-  reprocessDocuments(selection: DocumentSelectionQuery) {
+  reprocessDocuments(
+    selection: DocumentSelectionQuery,
+    remoteOcr: boolean = false
+  ) {
     return this.http.post(this.getResourceUrl(null, 'reprocess'), {
       ...selection,
+      remote_ocr: remoteOcr,
     })
   }
 

src-ui/src/app/services/settings.service.spec.ts

@@ -13,6 +13,7 @@ import { environment } from 'src/environments/environment'
 import { CustomFieldDataType } from '../data/custom-field'
 import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
 import { SavedView } from '../data/saved-view'
+import { RemoteOCRModeConfig } from '../data/paperless-config'
 import { SETTINGS_KEYS, UiSettings } from '../data/ui-settings'
 import { PermissionsService } from './permissions.service'
 import { CustomFieldsService } from './rest/custom-fields.service'
@@ -434,4 +435,26 @@ describe('SettingsService', () => {
         ).name
     ).toEqual(customFields[0].name)
   })
+  it('should offer remote OCR only when configured and selective', () => {
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, false)
+    settingsService.set(
+      SETTINGS_KEYS.REMOTE_OCR_MODE,
+      RemoteOCRModeConfig.WORKFLOW_ONLY
+    )
+    expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
+
+    // configured, but already handling every document
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, true)
+    settingsService.set(
+      SETTINGS_KEYS.REMOTE_OCR_MODE,
+      RemoteOCRModeConfig.ALWAYS
+    )
+    expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
+
+    settingsService.set(
+      SETTINGS_KEYS.REMOTE_OCR_MODE,
+      RemoteOCRModeConfig.WORKFLOW_ONLY
+    )
+    expect(settingsService.remoteOCRIsSelectable).toBeTruthy()
+  })
 })

src-ui/src/app/services/settings.service.ts

@@ -19,6 +19,7 @@ import {
 } from 'src/app/utils/color'
 import { DEFAULT_APP_TITLE, environment } from 'src/environments/environment'
 import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
+import { RemoteOCRModeConfig } from '../data/paperless-config'
 import { SavedView } from '../data/saved-view'
 import {
   PAPERLESS_GREEN_HEX,
@@ -687,6 +688,17 @@ export class SettingsService {
     return this.settingIsSet(SETTINGS_KEYS.UPDATE_CHECKING_ENABLED)
   }
 
+  /**
+   * Offering remote OCR as a  choice only makes sense when an engine
+   * is configured but is not already handling every document.
+   */
+  get remoteOCRIsSelectable(): boolean {
+    return (
+      this.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
+      this.get(SETTINGS_KEYS.REMOTE_OCR_MODE) !== RemoteOCRModeConfig.ALWAYS
+    )
+  }
+
   offerTour(): boolean {
     return this.dashboardIsEmpty() && !this.get(SETTINGS_KEYS.TOUR_COMPLETE)
   }

src/documents/bulk_edit.py

@@ -394,10 +394,16 @@ def delete(doc_ids: list[int]) -> Literal["OK"]:
     return "OK"
 
 
-def reprocess(doc_ids: list[int]) -> Literal["OK"]:
+def reprocess(doc_ids: list[int], *, remote_ocr: bool = False) -> Literal["OK"]:
+    """
+    Re-run parsing for the given documents.
+
+    Consumption workflows do not run here, so ``remote_ocr`` is how the user
+    asks for the remote engine when it is not configured to handle everything.
+    """
     for document_id in doc_ids:
         update_document_content_maybe_archive_file.apply_async(
-            kwargs={"document_id": document_id},
+            kwargs={"document_id": document_id, "remote_ocr": remote_ocr},
             headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
         )
 

src/documents/consumer.py

@@ -53,6 +53,7 @@ from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
 from paperless.config import OcrConfig
+from paperless.config import RemoteOCRConfig
 from paperless.models import ArchiveFileGenerationChoices
 from paperless.parsers import ParserContext
 from paperless.parsers import ParserProtocol
@@ -451,12 +452,19 @@ class ConsumerPlugin(
                 except Exception as e:
                     self.log.error(f"Error attempting to clean PDF: {e}")
 
+            # Workflows have already run at this point, so the metadata knows
+            # whether this document was singled out for remote OCR
+            allow_remote = (
+                self.metadata.remote_ocr or RemoteOCRConfig().remote_ocr_by_default
+            )
+
             # Based on the mime type, get the parser for that type
             parser_class: type[ParserProtocol] | None = (
                 get_parser_registry().get_parser_for_file(
                     mime_type,
                     self.filename,
                     self.working_copy,
+                    allow_remote=allow_remote,
                 )
             )
             if not parser_class:

src/documents/data_models.py

@@ -34,6 +34,7 @@ class DocumentMetadataOverrides:
     skip_asn_if_exists: bool = False
     version_label: str | None = None
     actor_id: int | None = None
+    remote_ocr: bool = False
 
     def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
         """
@@ -57,6 +58,8 @@ class DocumentMetadataOverrides:
             self.actor_id = other.actor_id
         if other.skip_asn_if_exists:
             self.skip_asn_if_exists = True
+        if other.remote_ocr:
+            self.remote_ocr = True
         if other.version_label is not None:
             self.version_label = other.version_label
 

src/documents/filters.py

@@ -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:

src/documents/permissions.py

@@ -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)
 

src/documents/serialisers.py

@@ -1744,7 +1744,7 @@ class DeleteDocumentsSerializer(DocumentSelectionSerializer):
 
 
 class ReprocessDocumentsSerializer(DocumentSelectionSerializer):
-    pass
+    remote_ocr = serializers.BooleanField(required=False, default=False)
 
 
 class BulkEditSerializer(
@@ -2086,6 +2086,13 @@ class BulkEditSerializer(
                         f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
                     )
 
+    def _validate_parameters_reprocess(self, parameters) -> None:
+        if "remote_ocr" in parameters:
+            if not isinstance(parameters["remote_ocr"], bool):
+                raise serializers.ValidationError("remote_ocr must be a boolean")
+        else:
+            parameters["remote_ocr"] = False
+
     def validate_parameters_remove_password(self, parameters):
         if "password" not in parameters:
             raise serializers.ValidationError("password not specified")
@@ -2150,6 +2157,8 @@ class BulkEditSerializer(
             self._validate_parameters_edit_pdf(parameters, attrs["documents"][0])
         elif method == bulk_edit.remove_password:
             self.validate_parameters_remove_password(parameters)
+        elif method == bulk_edit.reprocess:
+            self._validate_parameters_reprocess(parameters)
 
         return attrs
 

src/documents/tasks.py

@@ -66,6 +66,7 @@ from documents.utils import compute_checksum
 from documents.utils import identity
 from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
+from paperless.config import RemoteOCRConfig
 from paperless.logging import consume_task_id
 from paperless.parsers import ParserContext
 from paperless.parsers.registry import get_parser_registry
@@ -337,10 +338,17 @@ def bulk_update_documents(document_ids) -> None:
 
 
 @shared_task
-def update_document_content_maybe_archive_file(document_id) -> None:
+def update_document_content_maybe_archive_file(
+    document_id,
+    *,
+    remote_ocr: bool = False,
+) -> None:
     """
     Re-creates OCR content and thumbnail for a document, and archive file if
     it exists.
+
+    Remote OCR is used only when the engine is configured to handle everything
+    or if explicitly asked for via ``remote_ocr``.
     """
     document = Document.objects.get(id=document_id)
 
@@ -350,6 +358,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
         mime_type,
         document.original_filename or "",
         document.source_path,
+        allow_remote=remote_ocr or RemoteOCRConfig().remote_ocr_by_default,
     )
 
     if not parser_class:

src/documents/tests/test_api_app_config.py

@@ -72,6 +72,10 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
                 "barcode_enable_tag": None,
                 "barcode_tag_mapping": None,
                 "barcode_tag_split": None,
+                "remote_ocr_engine": None,
+                "remote_ocr_api_key": None,
+                "remote_ocr_endpoint": None,
+                "remote_ocr_mode": None,
                 "ai_enabled": False,
                 "llm_embedding_backend": None,
                 "llm_embedding_model": None,
@@ -870,6 +874,49 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
         config.refresh_from_db()
         self.assertEqual(config.llm_api_key, None)
 
+    def test_update_remote_ocr_api_key(self) -> None:
+        """
+        GIVEN:
+            - Existing config with remote_ocr_api_key specified
+        WHEN:
+            - API to update remote_ocr_api_key is called with all *s
+            - API to update remote_ocr_api_key is called with empty string
+        THEN:
+            - remote_ocr_api_key is unchanged
+            - remote_ocr_api_key is set to None
+        """
+        config = ApplicationConfiguration.objects.first()
+        assert config is not None
+        config.remote_ocr_api_key = "1234567890"
+        config.save()
+
+        # Test with all *
+        response = self.client.patch(
+            f"{self.ENDPOINT}1/",
+            json.dumps(
+                {
+                    "remote_ocr_api_key": "*" * 32,
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        config.refresh_from_db()
+        self.assertEqual(config.remote_ocr_api_key, "1234567890")
+        # Test with empty string
+        response = self.client.patch(
+            f"{self.ENDPOINT}1/",
+            json.dumps(
+                {
+                    "remote_ocr_api_key": "",
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        config.refresh_from_db()
+        self.assertEqual(config.remote_ocr_api_key, None)
+
     def test_enable_ai_index_triggers_update(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_bulk_edit.py

@@ -532,7 +532,29 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertEqual(args[0], [self.doc1.id])
-        self.assertEqual(len(kwargs), 0)
+        self.assertEqual(kwargs, {"remote_ocr": False})
+
+    @mock.patch("documents.views.bulk_edit.reprocess")
+    def test_reprocess_documents_endpoint_remote_ocr(self, m) -> None:
+        """
+        GIVEN:
+            - API data to reprocess a document with remote OCR requested
+        WHEN:
+            - API is called
+        THEN:
+            - reprocess is called with remote_ocr=True
+        """
+        self.setup_mock(m, "reprocess")
+        response = self.client.post(
+            "/api/documents/reprocess/",
+            json.dumps({"documents": [self.doc1.id], "remote_ocr": True}),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertEqual(args[0], [self.doc1.id])
+        self.assertEqual(kwargs, {"remote_ocr": True})
 
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
     def test_api_set_storage_path(self, m) -> None:
@@ -1553,6 +1575,29 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
                             ),
                         )
 
+    def test_legacy_bulk_edit_reprocess_invalid_remote_ocr(self) -> None:
+        """
+        GIVEN:
+            - The deprecated bulk_edit endpoint with a non-boolean remote_ocr
+        WHEN:
+            - API is called
+        THEN:
+            - The request is rejected rather than passed through to the task
+        """
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc1.id],
+                    "method": "reprocess",
+                    "parameters": {"remote_ocr": "yes please"},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
     @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf(self, m) -> None:
         self.setup_mock(m, "edit_pdf")

src/documents/tests/test_api_uisettings.py

@@ -60,6 +60,10 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
                 },
                 "email_enabled": False,
                 "ai_enabled": False,
+                "remote_ocr": {
+                    "configured": False,
+                    "mode": "always",
+                },
             },
         )
 
@@ -154,6 +158,50 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
             str(response.data["settings"]),
         )
 
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY="somekey",
+        REMOTE_OCR_ENDPOINT="https://example.cognitiveservices.azure.com",
+        REMOTE_OCR_MODE="workflow_only",
+    )
+    def test_settings_reports_remote_ocr_when_configured(self) -> None:
+        """
+        GIVEN:
+            - A fully configured remote OCR engine in workflow_only mode
+        WHEN:
+            - The ui_settings endpoint is called
+        THEN:
+            - The UI is told remote OCR is available and selective, so it can
+              offer it where it would actually change something
+        """
+        response = self.client.get(self.ENDPOINT, format="json")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(
+            response.data["settings"]["remote_ocr"],
+            {"configured": True, "mode": "workflow_only"},
+        )
+
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY=None,
+        REMOTE_OCR_ENDPOINT=None,
+    )
+    def test_settings_reports_remote_ocr_incompletely_configured(self) -> None:
+        """
+        GIVEN:
+            - An engine named but missing its endpoint and API key
+        WHEN:
+            - The ui_settings endpoint is called
+        THEN:
+            - It is reported as not configured, matching what the parser
+              registry will actually do
+        """
+        response = self.client.get(self.ENDPOINT, format="json")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertFalse(response.data["settings"]["remote_ocr"]["configured"])
+
     @override_settings(
         OAUTH_CALLBACK_BASE_URL="http://localhost:8000",
         GMAIL_OAUTH_CLIENT_ID="abc123",

src/documents/tests/test_bulk_edit.py

@@ -1782,3 +1782,56 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
         self.assertIn("wrong password", str(exc.exception))
         self.assertIn("Error removing password from document", cm.output[0])
+
+
+class TestBulkEditReprocess(DirectoriesMixin, TestCase):
+    def setUp(self) -> None:
+        super().setUp()
+
+        self.doc = Document.objects.create(
+            title="test",
+            checksum="A",
+            mime_type="application/pdf",
+        )
+
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_defaults_to_local(self, mock_task: mock.Mock) -> None:
+        """
+        GIVEN:
+            - A reprocess request that says nothing about remote OCR
+        WHEN:
+            - reprocess is called
+        THEN:
+            - The task is queued without asking for the remote engine
+        """
+        result = bulk_edit.reprocess([self.doc.id])
+
+        self.assertEqual(result, "OK")
+        mock_task.apply_async.assert_called_once()
+        _, kwargs = mock_task.apply_async.call_args
+        self.assertEqual(
+            kwargs["kwargs"],
+            {"document_id": self.doc.id, "remote_ocr": False},
+        )
+
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_passes_remote_ocr(self, mock_task: mock.Mock) -> None:
+        """
+        GIVEN:
+            - A reprocess request that explicitly asks for remote OCR
+        WHEN:
+            - reprocess is called
+        THEN:
+            - The request is forwarded to the task for every document
+        """
+        other = Document.objects.create(
+            title="test2",
+            checksum="B",
+            mime_type="application/pdf",
+        )
+
+        bulk_edit.reprocess([self.doc.id, other.id], remote_ocr=True)
+
+        self.assertEqual(mock_task.apply_async.call_count, 2)
+        for call in mock_task.apply_async.call_args_list:
+            self.assertTrue(call.kwargs["kwargs"]["remote_ocr"])

src/documents/tests/test_consumer.py

@@ -1559,6 +1559,72 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
                         consumer.run_post_consume_script(doc)
 
 
+class TestConsumerRemoteOCR(
+    DirectoriesMixin,
+    FileSystemAssertsMixin,
+    GetConsumerMixin,
+    TestCase,
+):
+    """
+    The consumer resolves the remote OCR mode and the per-document request from
+    workflows into the allow_remote flag it hands to the parser registry.
+    """
+
+    def setUp(self) -> None:
+        super().setUp()
+
+        patcher = mock.patch("documents.consumer.get_parser_registry")
+        self.mock_registry = patcher.start()
+        self.mock_registry.return_value.get_parser_for_file.return_value = DummyParser
+        self.addCleanup(patcher.stop)
+
+    def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
+        src = (
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf"
+        )
+        dst = self.dirs.scratch_dir / "sample.pdf"
+        shutil.copy(src, dst)
+
+        with self.get_consumer(dst, overrides=overrides) as consumer:
+            consumer.run()
+
+        _, kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
+        return kwargs["allow_remote"]
+
+    @override_settings(REMOTE_OCR_MODE="always")
+    def test_always_mode_allows_remote(self) -> None:
+        """
+        GIVEN: Remote OCR mode is 'always'.
+        WHEN:  A document is consumed without any workflow asking for it.
+        THEN:  The registry is allowed to pick the remote parser.
+        """
+        self.assertTrue(self._consume())
+
+    @override_settings(REMOTE_OCR_MODE="workflow_only")
+    def test_workflow_only_mode_denies_remote_by_default(self) -> None:
+        """
+        GIVEN: Remote OCR mode is 'workflow_only'.
+        WHEN:  A document is consumed and nothing asked for remote OCR.
+        THEN:  The remote parser is excluded.
+        """
+        self.assertFalse(self._consume())
+
+    @override_settings(REMOTE_OCR_MODE="workflow_only")
+    def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
+        """
+        GIVEN: Remote OCR mode is 'workflow_only'.
+        WHEN:  A workflow set remote_ocr on the metadata overrides.
+        THEN:  The registry is allowed to pick the remote parser.
+        """
+        self.assertTrue(
+            self._consume(overrides=DocumentMetadataOverrides(remote_ocr=True)),
+        )
+
+
 class TestMetadataOverrides(TestCase):
     def test_update_skip_asn_if_exists(self) -> None:
         base = DocumentMetadataOverrides()
@@ -1566,6 +1632,20 @@ class TestMetadataOverrides(TestCase):
         base.update(incoming)
         self.assertTrue(base.skip_asn_if_exists)
 
+    def test_update_remote_ocr(self) -> None:
+        base = DocumentMetadataOverrides()
+        base.update(DocumentMetadataOverrides(remote_ocr=True))
+        self.assertTrue(base.remote_ocr)
+
+    def test_update_remote_ocr_is_not_unset(self) -> None:
+        """
+        A later workflow that says nothing must not undo an earlier one that
+        asked for remote OCR.
+        """
+        base = DocumentMetadataOverrides(remote_ocr=True)
+        base.update(DocumentMetadataOverrides())
+        self.assertTrue(base.remote_ocr)
+
     def test_update_actor_and_version_label(self) -> None:
         base = DocumentMetadataOverrides(
             actor_id=1,

src/documents/tests/test_permission_filtering_security.py

@@ -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)

src/documents/tests/test_permitted_objects_filter.py

@@ -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

src/documents/tests/test_tasks.py

@@ -287,6 +287,45 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
 
 
+class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
+    """
+    Consumption workflows do not run on reprocess, so the remote parser is
+    used only in 'always' mode or when the caller explicitly asks for it.
+    """
+
+    def setUp(self) -> None:
+        super().setUp()
+
+        patcher = mock.patch("documents.tasks.get_parser_registry")
+        self.mock_registry = patcher.start()
+        self.mock_registry.return_value.get_parser_for_file.return_value = None
+        self.addCleanup(patcher.stop)
+
+        self.doc = Document.objects.create(
+            title="test",
+            content="my document",
+            checksum="wow",
+            mime_type="application/pdf",
+        )
+
+    def _allow_remote(self, **kwargs) -> bool:
+        tasks.update_document_content_maybe_archive_file(self.doc.pk, **kwargs)
+        _, call_kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
+        return call_kwargs["allow_remote"]
+
+    @override_settings(REMOTE_OCR_MODE="always")
+    def test_always_mode_allows_remote(self) -> None:
+        self.assertTrue(self._allow_remote())
+
+    @override_settings(REMOTE_OCR_MODE="workflow_only")
+    def test_workflow_only_mode_denies_remote_by_default(self) -> None:
+        self.assertFalse(self._allow_remote())
+
+    @override_settings(REMOTE_OCR_MODE="workflow_only")
+    def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
+        self.assertTrue(self._allow_remote(remote_ocr=True))
+
+
 class TestAIIndex(DirectoriesMixin, TestCase):
     @override_settings(
         AI_ENABLED=True,

src/documents/views.py

@@ -236,8 +236,10 @@ from paperless import version
 from paperless.celery import app as celery_app
 from paperless.config import AIConfig
 from paperless.config import GeneralConfig
+from paperless.config import RemoteOCRConfig
 from paperless.models import ApplicationConfiguration
 from paperless.parsers.registry import get_parser_registry
+from paperless.parsers.remote import RemoteEngineConfig
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -4010,6 +4012,11 @@ class UiSettingsView(GenericAPIView[Any]):
 
         ui_settings["auditlog_enabled"] = settings.AUDIT_LOG_ENABLED
 
+        ui_settings["remote_ocr"] = {
+            "configured": RemoteEngineConfig.from_app_config().engine_is_valid(),
+            "mode": RemoteOCRConfig().remote_ocr_mode,
+        }
+
         if settings.GMAIL_OAUTH_ENABLED or settings.OUTLOOK_OAUTH_ENABLED:
             manager = PaperlessMailOAuth2Manager()
             if settings.GMAIL_OAUTH_ENABLED:

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: 2026-08-08 14:28+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"
@@ -53,7 +53,7 @@ msgstr ""
 msgid "Maximum nesting depth exceeded."
 msgstr ""
 
-#: documents/filters.py:1073
+#: documents/filters.py:1079
 msgid "Custom field not found"
 msgstr ""
 

src/paperless/auth.py

@@ -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,

src/paperless/checks.py

@@ -339,16 +339,30 @@ def check_deprecated_v2_ocr_env_vars(
 
 @register()
 def check_remote_parser_configured(app_configs: Any, **kwargs: Any) -> list[Error]:
+    # Import here because checks.py runs before the app registry is ready
+    from paperless.models import RemoteOCRMode
+
+    errors = []
+
     if settings.REMOTE_OCR_ENGINE == "azureai" and not (
         settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
     ):
-        return [
+        errors.append(
             Error(
                 "Azure AI remote parser requires endpoint and API key to be configured.",
             ),
-        ]
+        )
 
-    return []
+    valid_modes = {mode.value for mode in RemoteOCRMode}
+    if settings.REMOTE_OCR_MODE not in valid_modes:
+        errors.append(
+            Error(
+                f"PAPERLESS_REMOTE_OCR_MODE is set to {settings.REMOTE_OCR_MODE!r}, "
+                f"expected one of {sorted(valid_modes)}.",
+            ),
+        )
+
+    return errors
 
 
 def get_tesseract_langs():

src/paperless/config.py

@@ -9,6 +9,7 @@ from paperless.models import CleanChoices
 from paperless.models import ColorConvertChoices
 from paperless.models import ModeChoices
 from paperless.models import OutputTypeChoices
+from paperless.models import RemoteOCRMode
 
 
 @dataclasses.dataclass
@@ -185,6 +186,45 @@ class GeneralConfig(BaseConfig):
         self.app_logo = app_config.app_logo.url if app_config.app_logo else None
 
 
+@dataclasses.dataclass
+class RemoteOCRConfig(BaseConfig):
+    """
+    Settings for the remote (cloud) OCR parser
+    """
+
+    remote_ocr_engine: str | None = dataclasses.field(init=False)
+    remote_ocr_api_key: str | None = dataclasses.field(init=False)
+    remote_ocr_endpoint: str | None = dataclasses.field(init=False)
+    remote_ocr_mode: RemoteOCRMode = dataclasses.field(init=False)
+
+    def __post_init__(self) -> None:
+        app_config = self._get_config_instance()
+
+        self.remote_ocr_engine = (
+            app_config.remote_ocr_engine or settings.REMOTE_OCR_ENGINE
+        )
+        self.remote_ocr_api_key = (
+            app_config.remote_ocr_api_key or settings.REMOTE_OCR_API_KEY
+        )
+        self.remote_ocr_endpoint = (
+            app_config.remote_ocr_endpoint or settings.REMOTE_OCR_ENDPOINT
+        )
+        self.remote_ocr_mode = app_config.remote_ocr_mode or RemoteOCRMode(
+            settings.REMOTE_OCR_MODE,
+        )
+
+    @property
+    def remote_ocr_by_default(self) -> bool:
+        """
+        Whether every supported document goes to the remote engine.
+
+        When False the remote engine is used only for documents that
+        explicitly asked for it, i.e. a workflow matched during consumption or
+        the user ticked the box when reprocessing.
+        """
+        return self.remote_ocr_mode == RemoteOCRMode.ALWAYS
+
+
 @dataclasses.dataclass
 class AIConfig(BaseConfig):
     """

src/paperless/migrations/0014_applicationconfiguration_remote_ocr_api_key_and_more.py

@@ -0,0 +1,44 @@
+# Generated by Django 5.2.16 on 2026-08-10 14:37
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("paperless", "0013_applicationconfiguration_llm_request_timeout"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="applicationconfiguration",
+            name="remote_ocr_api_key",
+            field=models.CharField(
+                blank=True,
+                max_length=1024,
+                null=True,
+                verbose_name="Sets the remote OCR API key",
+            ),
+        ),
+        migrations.AddField(
+            model_name="applicationconfiguration",
+            name="remote_ocr_endpoint",
+            field=models.CharField(
+                blank=True,
+                max_length=256,
+                null=True,
+                verbose_name="Sets the remote OCR endpoint",
+            ),
+        ),
+        migrations.AddField(
+            model_name="applicationconfiguration",
+            name="remote_ocr_engine",
+            field=models.CharField(
+                blank=True,
+                choices=[("azureai", "Azure AI Document Intelligence")],
+                max_length=32,
+                null=True,
+                verbose_name="Sets the remote OCR engine",
+            ),
+        ),
+    ]

src/paperless/migrations/0015_applicationconfiguration_remote_ocr_mode.py

@@ -0,0 +1,27 @@
+# Generated by Django 5.2.16 on 2026-08-10 15:43
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("paperless", "0014_applicationconfiguration_remote_ocr_api_key_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="applicationconfiguration",
+            name="remote_ocr_mode",
+            field=models.CharField(
+                blank=True,
+                choices=[
+                    ("always", "All supported documents"),
+                    ("workflow_only", "Only when a workflow enables it"),
+                ],
+                max_length=32,
+                null=True,
+                verbose_name="Sets which documents are sent to the remote OCR engine",
+            ),
+        ),
+    ]

src/paperless/models.py

@@ -74,6 +74,23 @@ class ColorConvertChoices(models.TextChoices):
     CMYK = ("CMYK", _("CMYK"))
 
 
+class RemoteOCREngine(models.TextChoices):
+    """
+    Matches to PAPERLESS_REMOTE_OCR_ENGINE
+    """
+
+    AZURE_AI = ("azureai", _("Azure AI Document Intelligence"))
+
+
+class RemoteOCRMode(models.TextChoices):
+    """
+    Matches to PAPERLESS_REMOTE_OCR_MODE
+    """
+
+    ALWAYS = ("always", _("All supported documents"))
+    WORKFLOW_ONLY = ("workflow_only", _("Only when a workflow enables it"))
+
+
 class LLMEmbeddingBackend(models.TextChoices):
     OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
     HUGGINGFACE = ("huggingface", _("Huggingface"))
@@ -286,6 +303,44 @@ class ApplicationConfiguration(AbstractSingletonModel):
         null=True,
     )
 
+    """
+    Settings for the remote OCR parser
+    """
+
+    # PAPERLESS_REMOTE_OCR_ENGINE
+    remote_ocr_engine = models.CharField(
+        verbose_name=_("Sets the remote OCR engine"),
+        blank=True,
+        null=True,
+        max_length=32,
+        choices=RemoteOCREngine.choices,
+    )
+
+    # PAPERLESS_REMOTE_OCR_API_KEY
+    remote_ocr_api_key = models.CharField(
+        verbose_name=_("Sets the remote OCR API key"),
+        blank=True,
+        null=True,
+        max_length=1024,
+    )
+
+    # PAPERLESS_REMOTE_OCR_ENDPOINT
+    remote_ocr_endpoint = models.CharField(
+        verbose_name=_("Sets the remote OCR endpoint"),
+        blank=True,
+        null=True,
+        max_length=256,
+    )
+
+    # PAPERLESS_REMOTE_OCR_MODE
+    remote_ocr_mode = models.CharField(
+        verbose_name=_("Sets which documents are sent to the remote OCR engine"),
+        blank=True,
+        null=True,
+        max_length=32,
+        choices=RemoteOCRMode.choices,
+    )
+
     """
     AI related settings
     """

src/paperless/parsers/__init__.py

@@ -134,6 +134,11 @@ class ParserProtocol(Protocol):
         Author or organisation name.
     url : str
         URL for documentation, source code, or issue tracker.
+
+    Parsers that send document content to a remote service should additionally
+    set ``uses_remote_service = True`` so the registry can exclude them when
+    remote processing has not been requested for a document. The attribute is
+    optional so a parser that omits it is treated as fully local.
     """
 
     # ------------------------------------------------------------------
@@ -145,6 +150,10 @@ class ParserProtocol(Protocol):
     author: str
     url: str
 
+    # NOTE: uses_remote_service is not declared here, the registry reads it
+    # with getattr(cls, ..., False) for backwards-compatibility with existing
+    # parsers
+
     # ------------------------------------------------------------------
     # Class methods
     # ------------------------------------------------------------------

src/paperless/parsers/registry.py

@@ -334,6 +334,8 @@ class ParserRegistry:
         mime_type: str,
         filename: str,
         path: Path | None = None,
+        *,
+        allow_remote: bool = True,
     ) -> type[ParserProtocol] | None:
         """Return the best parser class for the given file, or None.
 
@@ -359,6 +361,11 @@ class ParserRegistry:
         path:
             Optional filesystem path to the file. Forwarded to each
             parser's score method.
+        allow_remote:
+            When False, parsers that declare ``uses_remote_service = True``
+            are excluded from consideration, so a document is never sent to
+            a remote service. Parsers that do not declare the attribute
+            are treated as local and are always considered.
 
         Returns
         -------
@@ -374,6 +381,13 @@ class ParserRegistry:
             if mime_type not in parser_class.supported_mime_types():
                 continue
 
+            if not allow_remote and getattr(
+                parser_class,
+                "uses_remote_service",
+                False,
+            ):
+                continue
+
             score = parser_class.score(mime_type, filename, path)
             if score is None:
                 continue

src/paperless/parsers/remote.py

@@ -57,6 +57,18 @@ class RemoteEngineConfig:
         self.api_key = api_key
         self.endpoint = endpoint
 
+    @classmethod
+    def from_app_config(cls) -> Self:
+        """Build the config from the app config, falling back to the env."""
+        from paperless.config import RemoteOCRConfig
+
+        app_config = RemoteOCRConfig()
+        return cls(
+            engine=app_config.remote_ocr_engine,
+            api_key=app_config.remote_ocr_api_key,
+            endpoint=app_config.remote_ocr_endpoint,
+        )
+
     def engine_is_valid(self) -> bool:
         """Return True when the engine is known and fully configured."""
         return (
@@ -83,6 +95,9 @@ class RemoteDocumentParser:
         Maintainer name.
     url : str
         Issue tracker / source URL.
+    uses_remote_service : bool
+        Content is sent to a remote service, True so that the registry
+        can skip this parser if remote processing was not requested.
     """
 
     name: str = "Paperless-ngx Remote OCR Parser"
@@ -90,6 +105,8 @@ class RemoteDocumentParser:
     author: str = "Paperless-ngx Contributors"
     url: str = "https://github.com/paperless-ngx/paperless-ngx"
 
+    uses_remote_service: bool = True
+
     # ------------------------------------------------------------------
     # Class methods
     # ------------------------------------------------------------------
@@ -138,11 +155,7 @@ class RemoteDocumentParser:
             20 when the remote engine is configured and the MIME type is
             supported, otherwise None.
         """
-        config = RemoteEngineConfig(
+        config = RemoteEngineConfig.from_app_config()
-            engine=settings.REMOTE_OCR_ENGINE,
-            api_key=settings.REMOTE_OCR_API_KEY,
-            endpoint=settings.REMOTE_OCR_ENDPOINT,
-        )
         if not config.engine_is_valid():
             return None
         if mime_type not in _SUPPORTED_MIME_TYPES:
@@ -228,11 +241,7 @@ class RemoteDocumentParser:
             Ignored — the remote engine always returns a searchable PDF,
             which is stored as the archive copy regardless of this flag.
         """
-        config = RemoteEngineConfig(
+        config = RemoteEngineConfig.from_app_config()
-            engine=settings.REMOTE_OCR_ENGINE,
-            api_key=settings.REMOTE_OCR_API_KEY,
-            endpoint=settings.REMOTE_OCR_ENDPOINT,
-        )
 
         if not config.engine_is_valid():
             logger.warning(

src/paperless/serialisers.py

@@ -219,6 +219,13 @@ class ApplicationConfigurationSerializer(
         allow_null=True,
         max_length=1024,
     )
+    remote_ocr_api_key = ObfuscatedPasswordField(
+        required=False,
+        allow_null=True,
+        max_length=1024,
+    )
+
+    OBFUSCATED_FIELDS = ("llm_api_key", "remote_ocr_api_key")
 
     def run_validation(self, data):
         # Empty strings treated as None to avoid unexpected behavior
@@ -230,11 +237,13 @@ class ApplicationConfigurationSerializer(
             data["language"] = None
         if "llm_output_language" in data and data["llm_output_language"] == "":
             data["llm_output_language"] = None
-        if "llm_api_key" in data and data["llm_api_key"] is not None:
+        for field in self.OBFUSCATED_FIELDS:
-            if data["llm_api_key"] == "":
+            if field in data and data[field] is not None:
-                data["llm_api_key"] = None
+                if data[field] == "":
-            elif len(data["llm_api_key"].replace("*", "")) == 0:
+                    data[field] = None
-                del data["llm_api_key"]
+                # Not a real value, don't overwrite the stored one
+                elif len(data[field].replace("*", "")) == 0:
+                    del data[field]
         return super().run_validation(data)
 
     def update(self, instance, validated_data):

src/paperless/settings/__init__.py

@@ -1197,6 +1197,7 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = get_bool_from_env(
 REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
 REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
 REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
+REMOTE_OCR_MODE = os.getenv("PAPERLESS_REMOTE_OCR_MODE", "always")
 
 ################################################################################
 # AI Settings                                                                  #

src/paperless/tests/parsers/test_remote_parser.py

@@ -21,6 +21,7 @@ from unittest.mock import Mock
 import pytest
 
 from documents.parsers import ParseError
+from paperless.models import ApplicationConfiguration
 from paperless.parsers import ParserContext
 from paperless.parsers import ParserProtocol
 from paperless.parsers.remote import RemoteDocumentParser
@@ -33,6 +34,10 @@ if TYPE_CHECKING:
     from pytest_mock import MockerFixture
 
 
+# Remote ocr config from ApplicationConfiguration needs DB access
+pytestmark = pytest.mark.django_db
+
+
 # ---------------------------------------------------------------------------
 # Module-local fixtures
 # ---------------------------------------------------------------------------
@@ -227,6 +232,18 @@ class TestRemoteParserScore:
         score = RemoteDocumentParser.score("application/pdf", "doc.pdf")
         assert score is not None and score > 10
 
+    @pytest.mark.usefixtures("no_engine_settings")
+    def test_score_uses_app_config_when_env_unset(self) -> None:
+        """The app config alone is enough to activate the parser."""
+        config = ApplicationConfiguration.objects.first()
+        assert config is not None
+        config.remote_ocr_engine = "azureai"
+        config.remote_ocr_api_key = "app-config-key"
+        config.remote_ocr_endpoint = "https://config.cognitiveservices.azure.com"
+        config.save()
+
+        assert RemoteDocumentParser.score("application/pdf", "doc.pdf") == 20
+
 
 # ---------------------------------------------------------------------------
 # Properties

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -1277,6 +1277,8 @@ class TestParserFileTypes:
 # ---------------------------------------------------------------------------
 
 
+# Remote ocr config from ApplicationConfiguration needs DB access
+@pytest.mark.django_db
 class TestRasterisedDocumentParserRegistry:
     def test_registered_in_defaults(self) -> None:
         from paperless.parsers.registry import ParserRegistry

src/paperless/tests/test_auth_middleware.py

@@ -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)

src/paperless/tests/test_checks.py

@@ -655,6 +655,23 @@ class TestRemoteParserChecks:
             in msg.msg
         )
 
+    def test_valid_mode(self, settings: SettingsWrapper) -> None:
+        settings.REMOTE_OCR_ENGINE = None
+        settings.REMOTE_OCR_MODE = "workflow_only"
+
+        msgs = check_remote_parser_configured(None)
+
+        assert len(msgs) == 0
+
+    def test_invalid_mode(self, settings: SettingsWrapper) -> None:
+        settings.REMOTE_OCR_ENGINE = None
+        settings.REMOTE_OCR_MODE = "sometimes"
+
+        msgs = check_remote_parser_configured(None)
+
+        assert len(msgs) == 1
+        assert "PAPERLESS_REMOTE_OCR_MODE is set to 'sometimes'" in msgs[0].msg
+
 
 class TestTesseractChecks:
     def test_default_language(self) -> None:

src/paperless/tests/test_registry.py

@@ -468,6 +468,124 @@ class TestParserRegistryGetParserForFile:
         assert result is AcceptingBuiltin
 
 
+class TestParserRegistryRemoteParsers:
+    """Verify the allow_remote filter in ParserRegistry.get_parser_for_file()."""
+
+    @staticmethod
+    def _remote_parser_cls() -> type:
+        class RemoteParser:
+            name = "remote"
+            version = "1.0"
+            author = "A"
+            url = "https://example.com/remote"
+            uses_remote_service = True
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 20
+
+        return RemoteParser
+
+    def test_remote_parser_wins_when_remote_allowed(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A remote parser scoring 20 and a local parser scoring 10.
+        WHEN:  get_parser_for_file() is called with allow_remote=True.
+        THEN:  The remote parser is returned.
+        """
+        remote_parser_cls = self._remote_parser_cls()
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+        registry.register_builtin(remote_parser_cls)
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=True,
+        )
+        assert result is remote_parser_cls
+
+    def test_remote_parser_skipped_when_remote_not_allowed(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A remote parser scoring 20 and a local parser scoring 10.
+        WHEN:  get_parser_for_file() is called with allow_remote=False.
+        THEN:  The local parser is returned despite its lower score.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+        registry.register_builtin(self._remote_parser_cls())
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=False,
+        )
+        assert result is dummy_parser_cls
+
+    def test_no_parser_when_only_remote_available_and_not_allowed(self) -> None:
+        """
+        GIVEN: A registry whose only candidate declares uses_remote_service.
+        WHEN:  get_parser_for_file() is called with allow_remote=False.
+        THEN:  None is returned — the remote parser is never used as a
+               fallback when remote processing was not requested.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(self._remote_parser_cls())
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=False,
+        )
+        assert result is None
+
+    def test_parser_without_attribute_treated_as_local(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A third-party parser predating uses_remote_service, so it does
+               not declare the attribute at all.
+        WHEN:  get_parser_for_file() is called with allow_remote=False.
+        THEN:  It is still considered, i.e. treated as fully local, rather
+               than raising AttributeError.
+        """
+        assert not hasattr(dummy_parser_cls, "uses_remote_service")
+
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=False,
+        )
+        assert result is dummy_parser_cls
+
+    def test_remote_allowed_by_default(self) -> None:
+        """
+        GIVEN: A registry containing only a remote parser.
+        WHEN:  get_parser_for_file() is called without allow_remote.
+        THEN:  The remote parser is returned — callers that do not opt in to
+               the filter keep the previous behaviour.
+        """
+        remote_parser_cls = self._remote_parser_cls()
+        registry = ParserRegistry()
+        registry.register_builtin(remote_parser_cls)
+
+        result = registry.get_parser_for_file("text/plain", "readme.txt")
+        assert result is remote_parser_cls
+
+
 class TestDiscover:
     """Verify entrypoint discovery in ParserRegistry.discover()."""
 

src/paperless/tests/test_remote_ocr_config.py

@@ -0,0 +1,113 @@
+"""Tests for RemoteOCRConfig precedence between app config and Django settings."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+from django.test import override_settings
+
+from paperless.config import RemoteOCRConfig
+from paperless.models import RemoteOCRMode
+
+if TYPE_CHECKING:
+    from unittest.mock import MagicMock
+
+
+@pytest.fixture()
+def null_app_config(mocker) -> MagicMock:
+    """Mock ApplicationConfiguration with all fields None → falls back to Django settings."""
+    return mocker.MagicMock(
+        remote_ocr_engine=None,
+        remote_ocr_api_key=None,
+        remote_ocr_endpoint=None,
+        remote_ocr_mode=None,
+    )
+
+
+@pytest.fixture()
+def make_remote_ocr_config(mocker):
+    def _make(app_config, **django_settings_overrides):
+        mocker.patch(
+            "paperless.config.BaseConfig._get_config_instance",
+            return_value=app_config,
+        )
+        with override_settings(**django_settings_overrides):
+            return RemoteOCRConfig()
+
+    return _make
+
+
+class TestRemoteOCRConfig:
+    def test_falls_back_to_settings(
+        self,
+        make_remote_ocr_config,
+        null_app_config,
+    ) -> None:
+        cfg = make_remote_ocr_config(
+            null_app_config,
+            REMOTE_OCR_ENGINE="azureai",
+            REMOTE_OCR_API_KEY="env-key",
+            REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
+            REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
+        )
+        assert cfg.remote_ocr_engine == "azureai"
+        assert cfg.remote_ocr_api_key == "env-key"
+        assert cfg.remote_ocr_endpoint == "https://env.cognitiveservices.azure.com"
+        assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
+
+    def test_app_config_takes_precedence(
+        self,
+        make_remote_ocr_config,
+        mocker,
+    ) -> None:
+        app_config = mocker.MagicMock(
+            remote_ocr_engine="azureai",
+            remote_ocr_api_key="db-key",
+            remote_ocr_endpoint="https://db.cognitiveservices.azure.com",
+            remote_ocr_mode=RemoteOCRMode.WORKFLOW_ONLY,
+        )
+        cfg = make_remote_ocr_config(
+            app_config,
+            REMOTE_OCR_ENGINE=None,
+            REMOTE_OCR_API_KEY="env-key",
+            REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
+            REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
+        )
+        assert cfg.remote_ocr_engine == "azureai"
+        assert cfg.remote_ocr_api_key == "db-key"
+        assert cfg.remote_ocr_endpoint == "https://db.cognitiveservices.azure.com"
+        assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
+
+    def test_unset_everywhere(
+        self,
+        make_remote_ocr_config,
+        null_app_config,
+    ) -> None:
+        cfg = make_remote_ocr_config(
+            null_app_config,
+            REMOTE_OCR_ENGINE=None,
+            REMOTE_OCR_API_KEY=None,
+            REMOTE_OCR_ENDPOINT=None,
+        )
+        assert cfg.remote_ocr_engine is None
+        assert cfg.remote_ocr_api_key is None
+        assert cfg.remote_ocr_endpoint is None
+
+
+class TestRemoteOCRByDefault:
+    def test_always_mode(self, make_remote_ocr_config, null_app_config) -> None:
+        cfg = make_remote_ocr_config(
+            null_app_config,
+            REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
+        )
+
+        assert cfg.remote_ocr_by_default is True
+
+    def test_workflow_only_mode(self, make_remote_ocr_config, null_app_config) -> None:
+        cfg = make_remote_ocr_config(
+            null_app_config,
+            REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
+        )
+
+        assert cfg.remote_ocr_by_default is False

uv.lock

@@ -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", 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 = "sys_platform == 'linux'" },
+    { 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", 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 = "sys_platform == 'linux'" },
+    { 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 = "filelock", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
-    { name = "fsspec", marker = "sys_platform == 'darwin'" },
+    { name = "fsspec", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
-    { name = "jinja2", marker = "sys_platform == 'darwin'" },
+    { name = "jinja2", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
-    { name = "networkx", marker = "sys_platform == 'darwin'" },
+    { name = "networkx", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
-    { name = "setuptools", marker = "sys_platform == 'darwin'" },
+    { name = "setuptools", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
-    { name = "sympy", marker = "sys_platform == 'darwin'" },
+    { name = "sympy", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
-    { name = "typing-extensions", marker = "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 = "filelock", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
-    { name = "fsspec", marker = "sys_platform == 'linux'" },
+    { name = "fsspec", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
-    { name = "jinja2", marker = "sys_platform == 'linux'" },
+    { name = "jinja2", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
-    { name = "networkx", marker = "sys_platform == 'linux'" },
+    { name = "networkx", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
-    { name = "setuptools", marker = "sys_platform == 'linux'" },
+    { name = "setuptools", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
-    { name = "sympy", marker = "sys_platform == 'linux'" },
+    { name = "sympy", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
-    { name = "typing-extensions", marker = "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" },