Fix migration

docs/usage.md

@@ -650,6 +650,19 @@ happened while it was still encrypted, that original version will likewise be mi
 **Current limitation**: Passwords are stored as a simple list without descriptions. To handle
 multiple PDF types with different passwords, create separate workflows for each use case.
 
+##### Remote OCR {#workflow-action-remote-ocr}
+
+"Remote OCR" actions send the document to the configured remote OCR engine instead of processing it
+locally. To use remote OCR selectively, set the [remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE)
+to `workflow_only` then add this action to a workflow that matches only the documents you
+want sent to the remote engine. See [Remote OCR](#remote-ocr) for the engine setup. The action only works with
+a **Consumption Started** trigger.
+
+The action takes no options, its presence is what enables remote OCR for a matching document.
+
+If the remote engine is not configured, or does not support the document's file type, the document is
+processed locally instead and a warning is written to the log.
+
 #### Workflow placeholders
 
 Titles and webhook payloads can be generated by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).
@@ -1094,7 +1107,8 @@ 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.
+unless a [remote OCR workflow action](#workflow-action-remote-ocr) enables it 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.
 

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.html

@@ -455,6 +455,13 @@
           </div>
         </div>
       }
+      @case (WorkflowActionType.RemoteOcr) {
+        <div class="row">
+          <div class="col">
+            <p class="text-muted small" i18n>The document will be sent to the configured remote OCR service. May incur costs.</p>
+          </div>
+        </div>
+      }
     }
   </div>
 </ng-template>

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.spec.ts

@@ -29,6 +29,7 @@ import {
   DocumentSource,
   WorkflowTriggerType,
 } from 'src/app/data/workflow-trigger'
+import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { IfOwnerDirective } from 'src/app/directives/if-owner.directive'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { CorrespondentService } from 'src/app/services/rest/correspondent.service'
@@ -224,7 +225,12 @@ describe('WorkflowEditDialogComponent', () => {
     ).toEqual('Document Added')
     expect(component.getTriggerTypeOptionName(null)).toEqual('')
     expect(component.sourceOptions).toEqual(DOCUMENT_SOURCE_OPTIONS)
-    expect(component.actionTypeOptions).toEqual(WORKFLOW_ACTION_OPTIONS)
+    // Remote OCR is absent until the workflow has a consumption trigger
+    expect(component.actionTypeOptions).toEqual(
+      WORKFLOW_ACTION_OPTIONS.filter(
+        (a) => a.id !== WorkflowActionType.RemoteOcr
+      )
+    )
     expect(
       component.getActionTypeOptionName(WorkflowActionType.Assignment)
     ).toEqual('Assignment')
@@ -237,7 +243,104 @@ describe('WorkflowEditDialogComponent', () => {
     jest.spyOn(settingsService, 'get').mockReturnValue(false)
     component.ngOnInit()
     expect(component.actionTypeOptions).toEqual(
-      WORKFLOW_ACTION_OPTIONS.filter((a) => a.id !== WorkflowActionType.Email)
+      WORKFLOW_ACTION_OPTIONS.filter(
+        (a) =>
+          a.id !== WorkflowActionType.Email &&
+          a.id !== WorkflowActionType.RemoteOcr
+      )
+    )
+  })
+
+  it('should offer remote OCR only for consumption workflows', () => {
+    jest.spyOn(settingsService, 'get').mockReturnValue(true)
+
+    // A consumption trigger makes the action reachable
+    component.object = {
+      name: 'Workflow 1',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.Consumption }],
+      actions: [],
+    } as Workflow
+    component.ngOnInit()
+    expect(component.actionTypeOptions.map((a) => a.id)).toContain(
+      WorkflowActionType.RemoteOcr
+    )
+
+    // Any other trigger type runs after the document has been parsed
+    component.object = {
+      name: 'Workflow 2',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
+      actions: [],
+    } as Workflow
+    component.ngOnInit()
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
+    )
+  })
+
+  it('should offer remote OCR on a trigger added to a new workflow', () => {
+    jest.spyOn(settingsService, 'get').mockReturnValue(true)
+    component.ngOnInit()
+
+    // Nothing for the action to apply to yet
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
+    )
+
+    // addTrigger creates the form field with emitEvent false, so the options
+    // have to be computed on read rather than cached from valueChanges
+    component.addTrigger()
+    expect(component.actionTypeOptions.map((a) => a.id)).toContain(
+      WorkflowActionType.RemoteOcr
+    )
+
+    // Switching that trigger to a type that runs after parsing removes it
+    component.triggerFields
+      .at(0)
+      .get('type')
+      .setValue(WorkflowTriggerType.DocumentAdded)
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
+    )
+  })
+
+  it('should keep remote OCR listed when an action already uses it', () => {
+    jest.spyOn(settingsService, 'get').mockReturnValue(true)
+
+    // Otherwise changing the trigger would silently blank the selection
+    component.object = {
+      name: 'Workflow 1',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
+      actions: [{ type: WorkflowActionType.RemoteOcr }],
+    } as Workflow
+    component.ngOnInit()
+
+    expect(component.actionTypeOptions.map((a) => a.id)).toContain(
+      WorkflowActionType.RemoteOcr
+    )
+  })
+
+  it('should not offer remote OCR when no engine is configured', () => {
+    jest
+      .spyOn(settingsService, 'get')
+      .mockImplementation((key) => key !== SETTINGS_KEYS.REMOTE_OCR_CONFIGURED)
+
+    component.object = {
+      name: 'Workflow 1',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.Consumption }],
+      actions: [],
+    } as Workflow
+    component.ngOnInit()
+
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
     )
   })
 

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts

@@ -148,6 +148,10 @@ export const WORKFLOW_ACTION_OPTIONS = [
     id: WorkflowActionType.MoveToTrash,
     name: $localize`Move to trash`,
   },
+  {
+    id: WorkflowActionType.RemoteOcr,
+    name: $localize`Remote OCR`,
+  },
 ]
 
 export enum TriggerFilterType {
@@ -504,8 +508,6 @@ export class WorkflowEditDialogComponent
 
   expandedItem: number = null
 
-  readonly allowedActionTypes = signal([])
-
   private readonly triggerFilterOptionsMap = new WeakMap<
     FormArray,
     TriggerFilterOption[]
@@ -548,13 +550,40 @@ export class WorkflowEditDialogComponent
       this.checkRemovalActionFields.bind(this)
     )
     this.checkRemovalActionFields(this.objectForm.value)
-    this.allowedActionTypes.set(
+  }
-      this.settingsService.get(SETTINGS_KEYS.EMAIL_ENABLED)
+
-        ? WORKFLOW_ACTION_OPTIONS
+  private allowedActionTypes: typeof WORKFLOW_ACTION_OPTIONS = null
-        : WORKFLOW_ACTION_OPTIONS.filter(
+
-            (a) => a.id !== WorkflowActionType.Email
+  private getAllowedActionTypes() {
-          )
+    let allowed = WORKFLOW_ACTION_OPTIONS
-    )
+
+    if (!this.settingsService.get(SETTINGS_KEYS.EMAIL_ENABLED)) {
+      allowed = allowed.filter((a) => a.id !== WorkflowActionType.Email)
+    }
+
+    // Remote OCR is decided before the document is parsed, so it is only
+    // offered for workflows that run at consumption.
+    const formWorkflow: Workflow = this.objectForm?.value
+    const remoteOcrUsable =
+      this.settingsService.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
+      (formWorkflow?.triggers?.some(
+        (trigger) => trigger.type === WorkflowTriggerType.Consumption
+      ) ||
+        formWorkflow?.actions?.some(
+          (action) => action.type === WorkflowActionType.RemoteOcr
+        ))
+    if (!remoteOcrUsable) {
+      allowed = allowed.filter((a) => a.id !== WorkflowActionType.RemoteOcr)
+    }
+
+    if (
+      this.allowedActionTypes?.length === allowed.length &&
+      this.allowedActionTypes.every((a, i) => a.id === allowed[i].id)
+    ) {
+      return this.allowedActionTypes
+    }
+    this.allowedActionTypes = allowed
+    return allowed
   }
 
   private checkRemovalActionFields(formWorkflow: Workflow) {
@@ -1279,7 +1308,8 @@ export class WorkflowEditDialogComponent
 
   get actionTypeOptions() {
     this.settingsService.trackChanges()
-    return this.allowedActionTypes()
+    // Computed on read rather than cached
+    return this.getAllowedActionTypes()
   }
 
   getActionTypeOptionName(type: WorkflowActionType): string {

src-ui/src/app/data/workflow-action.ts

@@ -7,6 +7,7 @@ export enum WorkflowActionType {
   Webhook = 4,
   PasswordRemoval = 5,
   MoveToTrash = 6,
+  RemoteOcr = 7,
 }
 
 export interface WorkflowActionEmail extends ObjectWithId {

src/documents/consumer.py

@@ -473,6 +473,16 @@ class ConsumerPlugin(
                     f"Unsupported mime type {mime_type}",
                 )
 
+            if self.metadata.remote_ocr and not getattr(
+                parser_class,
+                "uses_remote_service",
+                False,
+            ):
+                self.log.warning(
+                    "Remote OCR was requested for this document but no remote "
+                    "parser is available for it, processing locally instead.",
+                )
+
             # Notify all listeners that we're going to do some work.
 
             document_consumption_started.send(

src/documents/migrations/0024_alter_workflowaction_type.py

@@ -0,0 +1,30 @@
+# Generated by Django 5.2.16 on 2026-08-10 17:27
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0023_savedview_icon"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="workflowaction",
+            name="type",
+            field=models.PositiveSmallIntegerField(
+                choices=[
+                    (1, "Assignment"),
+                    (2, "Removal"),
+                    (3, "Email"),
+                    (4, "Webhook"),
+                    (5, "Password removal"),
+                    (6, "Move to trash"),
+                    (7, "Remote OCR"),
+                ],
+                default=1,
+                verbose_name="Workflow Action Type",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -1668,6 +1668,10 @@ class WorkflowAction(models.Model):
             6,
             _("Move to trash"),
         )
+        REMOTE_OCR = (
+            7,
+            _("Remote OCR"),
+        )
 
     type = models.PositiveSmallIntegerField(
         _("Workflow Action Type"),

src/documents/serialisers.py

@@ -3285,6 +3285,41 @@ class WorkflowSerializer(serializers.ModelSerializer[Workflow]):
             "actions",
         ]
 
+    def validate(self, attrs):
+        attrs = super().validate(attrs)
+
+        if "actions" in attrs:
+            has_remote_ocr_action = any(
+                action.get("type") == WorkflowAction.WorkflowActionType.REMOTE_OCR
+                for action in attrs["actions"]
+            )
+        else:
+            has_remote_ocr_action = self.instance is not None and (
+                self.instance.actions.filter(
+                    type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                ).exists()
+            )
+
+        if "triggers" in attrs:
+            has_consumption_trigger = any(
+                trigger.get("type") == WorkflowTrigger.WorkflowTriggerType.CONSUMPTION
+                for trigger in attrs["triggers"]
+            )
+        else:
+            has_consumption_trigger = self.instance is not None and (
+                self.instance.triggers.filter(
+                    type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+                ).exists()
+            )
+
+        # Remote OCR can only work with consumption triggers
+        if has_remote_ocr_action and not has_consumption_trigger:
+            raise serializers.ValidationError(
+                "Remote OCR actions require a consumption started trigger",
+            )
+
+        return attrs
+
     def update_triggers_and_actions(
         self,
         instance: Workflow,

src/documents/signals/handlers.py

@@ -971,6 +971,17 @@ def run_workflows(
                     )
                 elif action.type == WorkflowAction.WorkflowActionType.MOVE_TO_TRASH:
                     has_move_to_trash_action = True
+                elif action.type == WorkflowAction.WorkflowActionType.REMOTE_OCR:
+                    if use_overrides and overrides:
+                        overrides.remote_ocr = True
+                    else:
+                        # If a workflow has a consumption trigger *and* another type,
+                        # the document has already been parsed by the time the other one fires
+                        logger.debug(
+                            "Remote OCR action only applies to consumption "
+                            "triggers, ignoring",
+                            extra={"group": logging_group},
+                        )
 
             if not use_overrides:
                 # limit title to 128 characters

src/documents/tests/test_api_workflows.py

@@ -390,6 +390,141 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
 
         self.assertEqual(Workflow.objects.count(), 1)
 
+    def test_api_create_remote_ocr_action_requires_consumption_trigger(
+        self,
+    ) -> None:
+        """
+        GIVEN:
+            - API request to create a workflow with a remote OCR action
+            - No consumption started trigger, so the action could never run
+        WHEN:
+            - API is called
+        THEN:
+            - Correct HTTP 400 response
+            - No objects are created
+        """
+        existing_count = Workflow.objects.count()
+
+        response = self.client.post(
+            self.ENDPOINT,
+            json.dumps(
+                {
+                    "name": "Remote OCR too late",
+                    "order": 1,
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+                        },
+                    ],
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertEqual(Workflow.objects.count(), existing_count)
+
+    def test_api_create_remote_ocr_action_with_consumption_trigger(self) -> None:
+        """
+        GIVEN:
+            - API request to create a workflow with a remote OCR action
+            - A consumption started trigger alongside another trigger type
+        WHEN:
+            - API is called
+        THEN:
+            - The workflow is created, the action applies to consumption only
+        """
+        response = self.client.post(
+            self.ENDPOINT,
+            json.dumps(
+                {
+                    "name": "Remote OCR on consume",
+                    "order": 1,
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+                            "filter_filename": "*.pdf",
+                        },
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+                        },
+                    ],
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_201_CREATED)
+
+    def test_api_partial_update_adds_remote_ocr_action(self) -> None:
+        """
+        GIVEN:
+            - An existing workflow with a consumption started trigger
+        WHEN:
+            - A partial update adds a remote OCR action without resubmitting triggers
+        THEN:
+            - The existing trigger is considered and the update succeeds
+        """
+        response = self.client.patch(
+            f"{self.ENDPOINT}{self.workflow.id}/",
+            json.dumps(
+                {
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(
+            self.workflow.actions.get().type,
+            WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+
+    def test_api_partial_update_cannot_remove_remote_ocr_trigger(self) -> None:
+        """
+        GIVEN:
+            - An existing workflow with a remote OCR action
+            - An existing consumption started trigger
+        WHEN:
+            - A partial update replaces the trigger without resubmitting actions
+        THEN:
+            - The existing action is considered and the update is rejected
+        """
+        self.action.type = WorkflowAction.WorkflowActionType.REMOTE_OCR
+        self.action.save()
+
+        response = self.client.patch(
+            f"{self.ENDPOINT}{self.workflow.id}/",
+            json.dumps(
+                {
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertEqual(self.workflow.triggers.get(), self.trigger)
+
     def test_api_create_workflow_trigger_action_empty_fields(self) -> None:
         """
         GIVEN:

src/documents/tests/test_workflows.py

@@ -5409,3 +5409,82 @@ class TestDateWorkflowLocalization(
             document = Document.objects.first()
             assert document is not None
             assert document.title == expected_title
+
+
+class TestRemoteOCRWorkflowAction(DirectoriesMixin, SampleDirMixin, APITestCase):
+    def _make_workflow(self, trigger_type) -> None:
+        trigger = WorkflowTrigger.objects.create(type=trigger_type)
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+        w = Workflow.objects.create(name="Remote OCR", order=0)
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+    def test_consumption_trigger_requests_remote_ocr(self) -> None:
+        """
+        GIVEN:
+            - A consumption workflow with a remote OCR action
+        WHEN:
+            - A matching document is consumed
+        THEN:
+            - The overrides ask for remote OCR, which is what the consumer
+              reads when choosing a parser
+        """
+        self._make_workflow(WorkflowTrigger.WorkflowTriggerType.CONSUMPTION)
+
+        test_file = shutil.copy(
+            self.SAMPLE_DIR / "simple.pdf",
+            self.dirs.scratch_dir / "simple.pdf",
+        )
+        overrides = DocumentMetadataOverrides()
+
+        run_workflows(
+            WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+            ConsumableDocument(
+                source=DocumentSource.ConsumeFolder,
+                original_file=test_file,
+            ),
+            overrides=overrides,
+        )
+
+        self.assertTrue(overrides.remote_ocr)
+
+    def test_other_trigger_types_are_ignored(self) -> None:
+        """
+        GIVEN:
+            - A workflow with a remote OCR action that also has a
+              non-consumption trigger, which is a valid combination
+        WHEN:
+            - The non-consumption trigger fires
+        THEN:
+            - The action is skipped, since the document has already been
+              parsed by this point
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+        )
+        updated_trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+        w = Workflow.objects.create(name="Remote OCR", order=0)
+        w.triggers.add(trigger, updated_trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            original_filename="sample.pdf",
+        )
+
+        with self.assertLogs("paperless.handlers", level="DEBUG") as cm:
+            run_workflows(
+                WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+                doc,
+            )
+
+        self.assertIn("only applies to consumption triggers", "".join(cm.output))