Ok! Backend stuff for the remote ocr workflow

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/0023_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", "0022_add_perf_indexes"),
+    ]
+
+    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

@@ -1599,6 +1599,10 @@ class WorkflowAction(models.Model):
             6,
             _("Move to trash"),
         )
+        REMOTE_OCR = (
+            7,
+            _("Remote OCR"),
+        )
 
     type = models.PositiveSmallIntegerField(
         _("Workflow Action Type"),

src/documents/serialisers.py

@@ -3277,6 +3277,26 @@ class WorkflowSerializer(serializers.ModelSerializer[Workflow]):
             "actions",
         ]
 
+    def validate(self, attrs):
+        attrs = super().validate(attrs)
+
+        triggers = attrs.get("triggers") or []
+        actions = attrs.get("actions") or []
+
+        # Remote OCR can only work with consumption triggers
+        if any(
+            action.get("type") == WorkflowAction.WorkflowActionType.REMOTE_OCR
+            for action in actions
+        ) and not any(
+            trigger.get("type") == WorkflowTrigger.WorkflowTriggerType.CONSUMPTION
+            for trigger in triggers
+        ):
+            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 +390,82 @@ 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_create_workflow_trigger_action_empty_fields(self) -> None:
         """
         GIVEN:

src/documents/tests/test_workflows.py

@@ -5360,3 +5360,82 @@ 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))