Change: skip documents with empty content in apply AI suggestions WF

docs/usage.md

@@ -684,7 +684,8 @@ It requires [AI features](configuration.md#ai) to be enabled. You can specify:
   never replace the document's existing tags.
 
 The action works with every trigger **except Consumption Started**, because suggestions are made from
-the document's text, which does not exist until after the document has been processed.
+the document's text, which does not exist until after the document has been processed. Documents whose
+processed text is empty or contains only whitespace are skipped.
 
 Because the query to the AI service is slow, the action is queued and runs in the background rather
 than as part of the workflow run itself. The document is updated once the suggestions come back.

pyproject.toml

@@ -66,7 +66,7 @@ dependencies = [
   "python-ipware~=3.0.0",
   "python-magic~=0.4.27",
   "rapidfuzz~=3.14.5",
-  "redis[hiredis]~=6.4.0",
+  "redis[hiredis]~=5.2.1",
   "regex>=2026.7.19",
   "scikit-learn~=1.9.0",
   "sentence-transformers>=5.6.1",

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

@@ -23,30 +23,17 @@
                                     <div class="col">
                                         <div class="card bg-light">
                                             <div class="card-body">
-                                                <div class="card-title d-flex align-items-center flex-wrap">
+                                                <div class="card-title d-flex align-items-center">
                                                     <h6 class="mb-0">
                                                       {{option.title}}
                                                     </h6>
                                                     <a class="btn btn-sm btn-link" title="Read the documentation about this setting" i18n-title [href]="getDocsUrl(option.config_key)" target="_blank" referrerpolicy="no-referrer">
                                                         <i-bs name="info-circle"></i-bs>
                                                     </a>
-                                                    @if (isExternallyConfigured(option.config_key)) {
-                                                      @if (isSet(option.key)) {
-                                                        <span class="badge rounded-pill bg-body-secondary text-dark fw-normal" title="This value overrides {{option.config_key}}, which is set outside Paperless." i18n-title>Overrides external</span>
-                                                      } @else {
-                                                        <span class="badge rounded-pill bg-body-secondary text-dark fw-normal" title="{{option.config_key}} is set outside Paperless. Enter a value here to override it." i18n-title>Set externally</span>
-                                                      }
-                                                    }
                                                     @if (isSet(option.key)) {
-                                                      @if (isExternallyConfigured(option.config_key)) {
+                                                      <button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Reset" i18n-title (click)="resetOption(option.key)">
-                                                        <button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Use the externally configured value" i18n-title (click)="resetOption(option.key)">
+                                                          <i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset</ng-container>
-                                                            <i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset to external</ng-container>
+                                                      </button>
-                                                        </button>
-                                                      } @else {
-                                                        <button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Reset" i18n-title (click)="resetOption(option.key)">
-                                                            <i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset</ng-container>
-                                                        </button>
-                                                      }
                                                     }
                                                 </div>
                                                 <div class="mb-n3">

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

@@ -163,19 +163,6 @@ describe('ConfigComponent', () => {
     expect(component.configForm.get('barcodes_enabled').value).toBeNull()
   })
 
-  it('should identify externally configured options', () => {
-    component.externallyConfiguredVariables = new Set([
-      'PAPERLESS_OCR_LANGUAGE',
-    ])
-
-    expect(
-      component.isExternallyConfigured('PAPERLESS_OCR_LANGUAGE')
-    ).toBeTruthy()
-    expect(
-      component.isExternallyConfigured('PAPERLESS_OCR_OUTPUT_TYPE')
-    ).toBeFalsy()
-  })
-
   it('should group options into sections within a category, or not', () => {
     const sections = component.getCategorySections(ConfigCategory.OCR)
     expect(sections).toEqual([null, ConfigSection.RemoteOCR])

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

@@ -69,7 +69,6 @@ export class ConfigComponent
   public configForm = new FormGroup({})
 
   public errors = {}
-  public externallyConfiguredVariables = new Set<string>()
 
   get optionCategories(): string[] {
     return Object.values(ConfigCategory)
@@ -153,9 +152,6 @@ export class ConfigComponent
   }
 
   private initialize(config: PaperlessConfig) {
-    this.externallyConfiguredVariables = new Set(
-      config.externally_configured_variables ?? []
-    )
     if (!this.store) {
       this.store = new BehaviorSubject(config)
 
@@ -166,9 +162,7 @@ export class ConfigComponent
           this.configForm.patchValue(state, { emitEvent: false })
         })
 
-      this.isDirty$ = dirtyCheck(this.configForm, this.store.asObservable(), {
+      this.isDirty$ = dirtyCheck(this.configForm, this.store.asObservable())
-        excludeKeys: ['externally_configured_variables'],
-      })
     }
     this.configForm.patchValue(config)
 
@@ -233,10 +227,6 @@ export class ConfigComponent
     return this.configForm.get(key).value != null
   }
 
-  public isExternallyConfigured(configKey: string): boolean {
-    return this.externallyConfiguredVariables.has(configKey)
-  }
-
   public resetOption(key: string) {
     this.configForm.get(key).setValue(null)
   }

src-ui/src/app/components/common/pdf-editor/pdf-editor.component.scss

@@ -22,7 +22,7 @@
 }
 
 ::ng-deep .pngx-pdf-viewer-container {
-  overflow: hidden !important;
+  overflow: hidden;
 }
 
 .hover-actions {

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

@@ -422,7 +422,6 @@ export const PaperlessConfigOptions: ConfigOption[] = [
 ]
 
 export interface PaperlessConfig extends ObjectWithId {
-  externally_configured_variables: string[]
   output_type: OutputTypeConfig
   pages: number
   language: string

src/documents/tests/test_api_app_config.py

@@ -35,8 +35,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
         THEN:
             - Existing config
         """
-        with patch.dict("os.environ", {}, clear=True):
+        response = self.client.get(self.ENDPOINT, format="json")
-            response = self.client.get(self.ENDPOINT, format="json")
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
 
@@ -46,7 +45,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
             response.data[0],
             {
                 "id": 1,
-                "externally_configured_variables": [],
                 "output_type": None,
                 "pages": None,
                 "language": None,
@@ -78,7 +76,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
                 "remote_ocr_api_key": None,
                 "remote_ocr_endpoint": None,
                 "remote_ocr_mode": None,
-                "ai_enabled": None,
+                "ai_enabled": False,
                 "llm_embedding_backend": None,
                 "llm_embedding_model": None,
                 "llm_embedding_endpoint": None,
@@ -93,31 +91,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
             },
         )
 
-    def test_api_get_config_reports_external_configuration_without_values(self) -> None:
-        with patch.dict(
-            "os.environ",
-            {
-                "PAPERLESS_OCR_LANGUAGE": "eng",
-                "PAPERLESS_REMOTE_OCR_API_KEY": "secret-value",
-                "PAPERLESS_FUTURE_SETTING": "future-value",
-                "UNRELATED_SETTING": "unrelated-value",
-            },
-            clear=True,
-        ):
-            response = self.client.get(self.ENDPOINT, format="json")
-
-        self.assertCountEqual(
-            response.data[0]["externally_configured_variables"],
-            [
-                "PAPERLESS_FUTURE_SETTING",
-                "PAPERLESS_OCR_LANGUAGE",
-                "PAPERLESS_REMOTE_OCR_API_KEY",
-            ],
-        )
-        self.assertNotContains(response, "secret-value")
-        self.assertNotContains(response, "future-value")
-        self.assertNotContains(response, "UNRELATED_SETTING")
-
     def test_api_get_ui_settings_with_config(self) -> None:
         """
         GIVEN:
@@ -976,26 +949,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
             )
             mock_update.assert_called_once()
 
-    @override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND=None)
-    def test_external_ai_setting_triggers_index_update(self) -> None:
-        config = ApplicationConfiguration.objects.first()
-        assert config is not None
-        config.ai_enabled = None
-        config.llm_embedding_backend = None
-        config.save()
-
-        with (
-            patch("documents.tasks.llmindex_index.apply_async") as mock_update,
-            patch("paperless.views.llm_index_exists", return_value=False),
-        ):
-            self.client.patch(
-                f"{self.ENDPOINT}1/",
-                json.dumps({"llm_embedding_backend": "openai-like"}),
-                content_type="application/json",
-            )
-
-        mock_update.assert_called_once()
-
     def test_update_llm_embedding_chunk_size_triggers_rebuild(self) -> None:
         config = ApplicationConfiguration.objects.first()
         assert config is not None

src/documents/tests/test_workflows.py

@@ -5711,6 +5711,39 @@ class TestApplyAISuggestionsWorkflowAction(
         self.assertEqual(changed, [])
         self.assertIn("AI is not enabled", "".join(cm.output))
 
+    def test_document_without_content_does_nothing(self) -> None:
+        """
+        GIVEN:
+            - A document whose OCR content is empty or whitespace-only
+        WHEN:
+            - AI suggestions are applied by a workflow
+        THEN:
+            - The classifier is not called and the document is left unchanged
+        """
+        action = self.make_action(ai_overwrite_existing=True)
+
+        for content in ("", " \n\t"):
+            with self.subTest(content=content):
+                self.doc.content = content
+                self.doc.save(update_fields=["content"])
+
+                with (
+                    mock.patch(
+                        "documents.workflows.ai.get_ai_document_classification",
+                    ) as get_classification,
+                    self.assertLogs(
+                        "paperless.workflows.ai",
+                        level="WARNING",
+                    ) as cm,
+                ):
+                    changed = apply_ai_suggestions_to_document(action, self.doc)
+
+                self.assertEqual(changed, [])
+                get_classification.assert_not_called()
+                self.assertIn("has no content", "".join(cm.output))
+                self.doc.refresh_from_db()
+                self.assertEqual(self.doc.title, "original.pdf")
+
     def test_invalid_configuration_leaves_document_untouched(self) -> None:
         """
         GIVEN:

src/documents/workflows/ai.py

@@ -138,6 +138,16 @@ def apply_ai_suggestions_to_document(
         )
         return []
 
+    if not document.content.strip():
+        logger.warning(
+            "Document %s has no content, skipping AI suggestions for workflow "
+            "action %s",
+            document.pk,
+            action.pk,
+            extra={"group": logging_group},
+        )
+        return []
+
     # Workflows run without a user, so we use the document owner
     owner = document.owner
 

src/paperless/config.py

@@ -133,27 +133,21 @@ class BarcodeConfig(BaseConfig):
         app_config = self._get_config_instance()
 
         self.barcodes_enabled = (
-            app_config.barcodes_enabled
+            app_config.barcodes_enabled or settings.CONSUMER_ENABLE_BARCODES
-            if app_config.barcodes_enabled is not None
-            else settings.CONSUMER_ENABLE_BARCODES
         )
         self.barcode_enable_tiff_support = (
             app_config.barcode_enable_tiff_support
-            if app_config.barcode_enable_tiff_support is not None
+            or settings.CONSUMER_BARCODE_TIFF_SUPPORT
-            else settings.CONSUMER_BARCODE_TIFF_SUPPORT
         )
         self.barcode_string = (
             app_config.barcode_string or settings.CONSUMER_BARCODE_STRING
         )
         self.barcode_retain_split_pages = (
             app_config.barcode_retain_split_pages
-            if app_config.barcode_retain_split_pages is not None
+            or settings.CONSUMER_BARCODE_RETAIN_SPLIT_PAGES
-            else settings.CONSUMER_BARCODE_RETAIN_SPLIT_PAGES
         )
         self.barcode_enable_asn = (
-            app_config.barcode_enable_asn
+            app_config.barcode_enable_asn or settings.CONSUMER_ENABLE_ASN_BARCODE
-            if app_config.barcode_enable_asn is not None
-            else settings.CONSUMER_ENABLE_ASN_BARCODE
         )
         self.barcode_asn_prefix = (
             app_config.barcode_asn_prefix or settings.CONSUMER_ASN_BARCODE_PREFIX
@@ -166,17 +160,13 @@ class BarcodeConfig(BaseConfig):
             app_config.barcode_max_pages or settings.CONSUMER_BARCODE_MAX_PAGES
         )
         self.barcode_enable_tag = (
-            app_config.barcode_enable_tag
+            app_config.barcode_enable_tag or settings.CONSUMER_ENABLE_TAG_BARCODE
-            if app_config.barcode_enable_tag is not None
-            else settings.CONSUMER_ENABLE_TAG_BARCODE
         )
         self.barcode_tag_mapping = (
             app_config.barcode_tag_mapping or settings.CONSUMER_TAG_BARCODE_MAPPING
         )
         self.barcode_tag_split = (
-            app_config.barcode_tag_split
+            app_config.barcode_tag_split or settings.CONSUMER_TAG_BARCODE_SPLIT
-            if app_config.barcode_tag_split is not None
-            else settings.CONSUMER_TAG_BARCODE_SPLIT
         )
 
 
@@ -258,11 +248,7 @@ class AIConfig(BaseConfig):
     def __post_init__(self) -> None:
         app_config = self._get_config_instance()
 
-        self.ai_enabled = (
+        self.ai_enabled = app_config.ai_enabled or settings.AI_ENABLED
-            app_config.ai_enabled
-            if app_config.ai_enabled is not None
-            else settings.AI_ENABLED
-        )
         self.llm_embedding_backend = (
             app_config.llm_embedding_backend or settings.LLM_EMBEDDING_BACKEND
         )

src/paperless/migrations/0016_alter_applicationconfiguration_ai_enabled.py

@@ -1,28 +0,0 @@
-from django.db import migrations
-from django.db import models
-
-
-def normalize_ai_enabled(apps, schema_editor):
-    application_configuration = apps.get_model(
-        "paperless",
-        "ApplicationConfiguration",
-    )
-    application_configuration.objects.filter(ai_enabled=False).update(ai_enabled=None)
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("paperless", "0015_applicationconfiguration_remote_ocr_mode"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="applicationconfiguration",
-            name="ai_enabled",
-            field=models.BooleanField(
-                null=True,
-                verbose_name="Enables AI features",
-            ),
-        ),
-        migrations.RunPython(normalize_ai_enabled, migrations.RunPython.noop),
-    ]

src/paperless/models.py

@@ -348,6 +348,7 @@ class ApplicationConfiguration(AbstractSingletonModel):
     ai_enabled = models.BooleanField(
         verbose_name=_("Enables AI features"),
         null=True,
+        default=False,
     )
 
     llm_embedding_backend = models.CharField(

src/paperless/serialisers.py

@@ -1,5 +1,4 @@
 import logging
-import os
 from io import BytesIO
 
 import magic
@@ -213,7 +212,6 @@ class ProfileSerializer(PasswordValidationMixin, serializers.ModelSerializer[Use
 class ApplicationConfigurationSerializer(
     serializers.ModelSerializer[ApplicationConfiguration],
 ):
-    externally_configured_variables = serializers.SerializerMethodField()
     user_args = serializers.JSONField(binary=True, allow_null=True)
     barcode_tag_mapping = serializers.JSONField(binary=True, allow_null=True)
     llm_api_key = ObfuscatedPasswordField(
@@ -229,12 +227,6 @@ class ApplicationConfigurationSerializer(
 
     OBFUSCATED_FIELDS = ("llm_api_key", "remote_ocr_api_key")
 
-    def get_externally_configured_variables(
-        self,
-        instance: ApplicationConfiguration,
-    ) -> list[str]:
-        return sorted(name for name in os.environ if name.startswith("PAPERLESS_"))
-
     def run_validation(self, data):
         # Empty strings treated as None to avoid unexpected behavior
         if "user_args" in data and data["user_args"] == "":

src/paperless/tests/test_config_precedence.py

@@ -1,32 +0,0 @@
-from django.test import TestCase
-from django.test import override_settings
-
-from paperless.config import AIConfig
-from paperless.config import BarcodeConfig
-from paperless.models import ApplicationConfiguration
-
-
-class TestBooleanConfigPrecedence(TestCase):
-    @override_settings(CONSUMER_ENABLE_BARCODES=True)
-    def test_database_false_overrides_barcode_environment_setting(self) -> None:
-        config, _ = ApplicationConfiguration.objects.get_or_create()
-        config.barcodes_enabled = False
-        config.save()
-
-        self.assertFalse(BarcodeConfig().barcodes_enabled)
-
-    @override_settings(AI_ENABLED=True)
-    def test_database_false_overrides_ai_environment_setting(self) -> None:
-        config, _ = ApplicationConfiguration.objects.get_or_create()
-        config.ai_enabled = False
-        config.save()
-
-        self.assertFalse(AIConfig().ai_enabled)
-
-    @override_settings(AI_ENABLED=True)
-    def test_null_ai_setting_uses_environment_setting(self) -> None:
-        config, _ = ApplicationConfiguration.objects.get_or_create()
-        config.ai_enabled = None
-        config.save()
-
-        self.assertTrue(AIConfig().ai_enabled)

src/paperless/views.py

@@ -443,13 +443,8 @@ class ApplicationConfigurationViewSet(ModelViewSet[ApplicationConfiguration]):
         new_llm_embedding_backend = (
             new_instance.llm_embedding_backend or settings.LLM_EMBEDDING_BACKEND
         )
-        new_ai_enabled = (
-            new_instance.ai_enabled
-            if new_instance.ai_enabled is not None
-            else settings.AI_ENABLED
-        )
         new_ai_index_enabled = bool(
-            new_ai_enabled and new_llm_embedding_backend,
+            new_instance.ai_enabled and new_llm_embedding_backend,
         )
         new_llm_embedding_chunk_size = (
             new_instance.llm_embedding_chunk_size or settings.LLM_EMBEDDING_CHUNK_SIZE

uv.lock

@@ -3070,7 +3070,7 @@ requires-dist = [
     { name = "python-ipware", specifier = "~=3.0.0" },
     { name = "python-magic", specifier = "~=0.4.27" },
     { name = "rapidfuzz", specifier = "~=3.14.5" },
-    { name = "redis", extras = ["hiredis"], specifier = "~=6.4.0" },
+    { name = "redis", extras = ["hiredis"], specifier = "~=5.2.1" },
     { name = "regex", specifier = ">=2026.7.19" },
     { name = "scikit-learn", specifier = "~=1.9.0" },
     { name = "sentence-transformers", specifier = ">=5.6.1" },
@@ -4150,14 +4150,14 @@ wheels = [
 
 [[package]]
 name = "redis"
-version = "6.4.0"
+version = "5.2.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "async-timeout", marker = "python_full_version < '3.11.3'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0d/d6/e8b92798a5bd67d659d51a18170e91c16ac3b59738d91894651ee255ed49/redis-6.4.0.tar.gz", hash = "sha256:b01bc7282b8444e28ec36b261df5375183bb47a07eb9c603f284e89cbc5ef010", size = 4647399, upload-time = "2025-08-07T08:10:11.441Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/47/da/d283a37303a995cd36f8b92db85135153dc4f7a8e4441aa827721b442cfb/redis-5.2.1.tar.gz", hash = "sha256:16f2e22dff21d5125e8481515e386711a34cbec50f0e44413dd7d9c060a54e0f", size = 4608355, upload-time = "2024-12-06T09:50:41.956Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e8/02/89e2ed7e85db6c93dfa9e8f691c5087df4e3551ab39081a4d7c6d1f90e05/redis-6.4.0-py3-none-any.whl", hash = "sha256:f0544fa9604264e9464cdf4814e7d4830f74b165d52f2a330a760a88dd248b7f", size = 279847, upload-time = "2025-08-07T08:10:09.84Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/5f/fa26b9b2672cbe30e07d9a5bdf39cf16e3b80b42916757c5f92bca88e4ba/redis-5.2.1-py3-none-any.whl", hash = "sha256:ee7e1056b9aea0f04c6c2ed59452947f34c4940ee025f5dd83e6a6418b6989e4", size = 261502, upload-time = "2024-12-06T09:50:39.656Z" },
 ]
 
 [package.optional-dependencies]