Fix: clamp mailrule max age before migration

Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
Signed-off-by: dependabot[bot] <support@github.com>

.github/workflows/ci-frontend.yml

@@ -191,7 +191,7 @@ jobs:
     runs-on: ubuntu-24.04
     permissions:
       contents: read
-    container: mcr.microsoft.com/playwright:v1.60.0-noble
+    container: mcr.microsoft.com/playwright:v1.61.1-noble
     env:
       PLAYWRIGHT_BROWSERS_PATH: /ms-playwright
       PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: 1

SECURITY.md

@@ -63,6 +63,7 @@ The following are not generally considered vulnerabilities unless accompanied by
 - optional webhook, mail, AI, OCR, or integration behavior described without a product-level vulnerability
 - missing limits or hardening settings presented without concrete impact
 - generic AI or static-analysis output that is not confirmed against the current codebase and a real deployment scenario
+- the ability to attach objects that a user cannot access to a document by ID is an intentional design choice, and not considered a vulnerability
 
 ## Transparency
 

docs/migration-v3.md

@@ -326,3 +326,11 @@ behind a reverse proxy may need to set
 [`PAPERLESS_TRUSTED_PROXIES`](configuration.md#PAPERLESS_TRUSTED_PROXIES),
 [`PAPERLESS_ALLAUTH_TRUSTED_CLIENT_IP_HEADER`](configuration.md#PAPERLESS_ALLAUTH_TRUSTED_CLIENT_IP_HEADER),
 or both, to avoid `403 Forbidden` errors on login.
+
+## Database Migrations
+
+Some integer fields have been changed to smaller types to reduce database size. If you have any `MailRule` records with a `maximum_age` greater than 32767, they will be clamped to 32767 during the migration to avoid errors during migration.
+
+### Action Required
+
+No user action is required. The migration will automatically clamp any `MailRule.maximum_age` values greater than 32767 to 32767 during the migration process.

src-ui/package.json

@@ -33,11 +33,11 @@
     "ngx-device-detector": "^11.0.0",
     "ngx-ui-tour-ng-bootstrap": "^18.0.0",
     "normalize-diacritics": "^5.0.0",
-    "pdfjs-dist": "^5.7.284",
+    "pdfjs-dist": "^6.0.227",
     "rxjs": "^7.8.2",
     "tslib": "^2.8.1",
     "utif": "^3.1.0",
-    "uuid": "^14.0.0",
+    "uuid": "^14.0.1",
     "zone.js": "^0.16.2"
   },
   "devDependencies": {
@@ -54,17 +54,17 @@
     "@angular/cli": "~21.2.12",
     "@angular/compiler-cli": "~21.2.14",
     "@codecov/webpack-plugin": "^2.0.1",
-    "@playwright/test": "^1.60.0",
+    "@playwright/test": "^1.61.1",
     "@types/jest": "^30.0.0",
-    "@types/node": "^25.9.1",
-    "@typescript-eslint/eslint-plugin": "^8.60.0",
-    "@typescript-eslint/parser": "^8.60.0",
-    "@typescript-eslint/utils": "^8.60.0",
-    "eslint": "^10.4.0",
+    "@types/node": "^26.0.0",
+    "@typescript-eslint/eslint-plugin": "^8.62.0",
+    "@typescript-eslint/parser": "^8.62.0",
+    "@typescript-eslint/utils": "^8.62.0",
+    "eslint": "^10.5.0",
     "jest": "30.4.2",
     "jest-environment-jsdom": "^30.4.1",
     "jest-junit": "^17.0.0",
-    "jest-preset-angular": "^16.1.5",
+    "jest-preset-angular": "^17.0.0",
     "jest-websocket-mock": "^2.5.0",
     "prettier-plugin-organize-imports": "^4.3.0",
     "ts-node": "~10.9.1",

src-ui/src/app/components/common/pdf-viewer/pdf-viewer.component.ts

@@ -27,7 +27,6 @@ import {
 } from 'pdfjs-dist/web/pdf_viewer.mjs'
 import {
   PdfRenderMode,
-  PdfSource,
   PdfZoomLevel,
   PdfZoomScale,
   PngxPdfDocumentProxy,
@@ -43,7 +42,8 @@ export class PngxPdfViewerComponent
 {
   private readonly document = inject<Document>(DOCUMENT)
 
-  @Input() src!: PdfSource
+  @Input() src!: string
+  @Input() password?: string
   @Input() page?: number
   @Output() pageChange = new EventEmitter<number>()
   @Input() rotation?: number
@@ -93,7 +93,7 @@ export class PngxPdfViewerComponent
   }
 
   ngOnChanges(changes: SimpleChanges): void {
-    if (changes['src']) {
+    if (changes['src'] || changes['password']) {
       this.resetViewerState()
       if (this.src) {
         this.loadDocument()
@@ -174,8 +174,12 @@ export class PngxPdfViewerComponent
       'assets/js/pdf.worker.min.mjs',
       this.document.baseURI
     ).toString()
-    this.loadingTask = getDocument(this.src)
-
+    let initOptions = {
+      url: this.src,
+      password: this.password,
+      withCredentials: true,
+    }
+    this.loadingTask = getDocument(initOptions)
     try {
       const pdf = await this.loadingTask.promise
       this.pdf = pdf

src-ui/src/app/components/common/pdf-viewer/pdf-viewer.types.ts

@@ -2,8 +2,6 @@ export type PngxPdfDocumentProxy = {
   numPages: number
 }
 
-export type PdfSource = string | { url: string; password?: string }
-
 export enum PdfRenderMode {
   Single = 'single',
   All = 'all',

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

@@ -473,6 +473,7 @@
           <div class="preview-sticky pdf-viewer-container">
             <pngx-pdf-viewer
               [src]="pdfSource"
+              [password]="pdfPassword"
               [renderMode]="PdfRenderMode.All"
               [(page)]="previewCurrentPage"
               [zoomScale]="previewZoomScale"

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

@@ -1530,11 +1530,13 @@ describe('DocumentDetailComponent', () => {
   })
 
   it('should clear pdf source if preview URL is empty', () => {
-    component.pdfSource = { url: '/preview', password: 'secret' } as any
+    component.pdfSource = '/preview'
+    component.pdfPassword = 'secret'
     component.previewUrl = null
     ;(component as any).updatePdfSource()
 
-    expect(component.pdfSource).toEqual({ url: null, password: undefined })
+    expect(component.pdfSource).toEqual(null)
+    expect(component.pdfPassword).toBeUndefined()
   })
 
   it('should close incoming update modal if one is open', () => {
@@ -1871,9 +1873,8 @@ describe('DocumentDetailComponent', () => {
     expect(component.thumbUrl).toBe('thumb-version')
     expect(component.previewText).toBe('version text')
     expect(component.documentForm.get('content').value).toBe('version-content')
-    const pdfSource = component.pdfSource as { url: string; password?: string }
-    expect(pdfSource.url).toBe('preview-version')
-    expect(pdfSource.password).toBeUndefined()
+    expect(component.pdfSource).toBe('preview-version')
+    expect(component.pdfPassword).toBeUndefined()
 
     previewSpy.mockReturnValueOnce('preview-error')
     component.selectVersion(11)

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

@@ -115,7 +115,6 @@ import { PDFEditorComponent } from '../common/pdf-editor/pdf-editor.component'
 import { PngxPdfViewerComponent } from '../common/pdf-viewer/pdf-viewer.component'
 import {
   PdfRenderMode,
-  PdfSource,
   PdfZoomLevel,
   PdfZoomScale,
   PngxPdfDocumentProxy,
@@ -242,7 +241,8 @@ export class DocumentDetailComponent
   title: string
   titleSubject: Subject<string> = new Subject()
   previewUrl: string
-  pdfSource?: PdfSource
+  pdfSource?: string
+  pdfPassword?: string
   thumbUrl: string
   previewText: string
   previewLoaded: boolean = false
@@ -375,10 +375,8 @@ export class DocumentDetailComponent
   }
 
   private updatePdfSource() {
-    this.pdfSource = {
-      url: this.previewUrl,
-      password: this.password,
-    }
+    this.pdfSource = this.previewUrl
+    this.pdfPassword = this.password
   }
 
   private loadMetadataForSelectedVersion() {

src/documents/sanity_checker.py

@@ -45,6 +45,12 @@ class SanityCheckMessages:
 
     def __init__(self) -> None:
         self._messages: dict[int | None, list[MessageEntry]] = defaultdict(list)
+        self._document_pks: set[int] = set()
+        self._document_error_pks: set[int] = set()
+        self._document_warning_pks: set[int] = set()
+        self._document_info_pks: set[int] = set()
+        self._document_error_issue_count: int = 0
+        self._document_warning_issue_count: int = 0
         self.has_error: bool = False
         self.has_warning: bool = False
         self.has_info: bool = False
@@ -56,20 +62,33 @@ class SanityCheckMessages:
 
     # -- Recording ----------------------------------------------------------
 
+    def _add_document_issue(self, doc_pk: int, document_pks: set[int]) -> bool:
+        if doc_pk not in self._document_pks:
+            self._document_pks.add(doc_pk)
+            self.document_count += 1
+
+        if doc_pk in document_pks:
+            return False
+
+        document_pks.add(doc_pk)
+        return True
+
     def error(self, doc_pk: int | None, message: str) -> None:
         self._messages[doc_pk].append({"level": logging.ERROR, "message": message})
         self.has_error = True
         if doc_pk is not None:
-            self.document_count += 1
-            self.document_error_count += 1
+            self._document_error_issue_count += 1
+            if self._add_document_issue(doc_pk, self._document_error_pks):
+                self.document_error_count += 1
 
     def warning(self, doc_pk: int | None, message: str) -> None:
         self._messages[doc_pk].append({"level": logging.WARNING, "message": message})
         self.has_warning = True
 
         if doc_pk is not None:
-            self.document_count += 1
-            self.document_warning_count += 1
+            self._document_warning_issue_count += 1
+            if self._add_document_issue(doc_pk, self._document_warning_pks):
+                self.document_warning_count += 1
         else:
             # This is the only type of global message we do right now
             self.global_warning_count += 1
@@ -78,8 +97,10 @@ class SanityCheckMessages:
         self._messages[doc_pk].append({"level": logging.INFO, "message": message})
         self.has_info = True
 
-        if doc_pk is not None:
-            self.document_count += 1
+        if doc_pk is not None and self._add_document_issue(
+            doc_pk,
+            self._document_info_pks,
+        ):
             self.document_info_count += 1
 
     # -- Iteration / query --------------------------------------------------
@@ -105,8 +126,8 @@ class SanityCheckMessages:
     def total_issue_count(self) -> int:
         """Total number of error and warning messages across all documents and global."""
         return (
-            self.document_error_count
-            + self.document_warning_count
+            self._document_error_issue_count
+            + self._document_warning_issue_count
             + self.global_warning_count
         )
 

src/documents/search/_tokenizer.py

@@ -48,6 +48,9 @@ _LANGUAGE_MAP: dict[str, str] = {
 }
 
 SUPPORTED_LANGUAGES: frozenset[str] = frozenset(_LANGUAGE_MAP)
+# Document.title is max_length=128, so use 129 as the limit for
+# Tantivy's remove_long filter
+_TOKEN_REMOVE_LONG_LIMIT: Final[int] = 129
 
 
 def register_tokenizers(index: tantivy.Index, language: str | None) -> None:
@@ -77,10 +80,10 @@ def register_tokenizers(index: tantivy.Index, language: str | None) -> None:
 
 
 def _paperless_text(language: str | None) -> tantivy.TextAnalyzer:
-    """Main full-text tokenizer for content, title, etc: simple -> remove_long(65) -> lowercase -> ascii_fold [-> stemmer]"""
+    """Main full-text tokenizer for content, title, etc: simple -> remove_long(129) -> lowercase -> ascii_fold [-> stemmer]"""
     builder = (
         tantivy.TextAnalyzerBuilder(tantivy.Tokenizer.simple())
-        .filter(tantivy.Filter.remove_long(65))
+        .filter(tantivy.Filter.remove_long(_TOKEN_REMOVE_LONG_LIMIT))
         .filter(tantivy.Filter.lowercase())
         .filter(tantivy.Filter.ascii_fold())
     )
@@ -119,12 +122,12 @@ def _bigram_analyzer() -> tantivy.TextAnalyzer:
 
 
 def _simple_search_analyzer() -> tantivy.TextAnalyzer:
-    """Tokenizer for simple substring search fields: non-whitespace chunks -> remove_long(65) -> lowercase -> ascii_fold."""
+    """Tokenizer for simple substring search fields: non-whitespace chunks -> remove_long(129) -> lowercase -> ascii_fold."""
     return (
         tantivy.TextAnalyzerBuilder(
             tantivy.Tokenizer.regex(r"\S+"),
         )
-        .filter(tantivy.Filter.remove_long(65))
+        .filter(tantivy.Filter.remove_long(_TOKEN_REMOVE_LONG_LIMIT))
         .filter(tantivy.Filter.lowercase())
         .filter(tantivy.Filter.ascii_fold())
         .build()

src/documents/search/_translate.py

@@ -163,7 +163,12 @@ def scan(query: str) -> list[Token]:
             i += 1
             continue
         token, i = matched
-        _flush(buf, tokens)
+        if buf and buf[-1] == ",":
+            buf.pop()
+            _flush(buf, tokens)
+            tokens.append(Comma())
+        else:
+            _flush(buf, tokens)
         tokens.append(token)
         i = _maybe_comma(query, i, tokens)
     _flush(buf, tokens)

src/documents/tests/search/test_backend.py

@@ -261,6 +261,36 @@ class TestSearch:
             == 1
         )
 
+    @pytest.mark.parametrize(
+        ("search_mode", "query"),
+        [
+            pytest.param(SearchMode.TITLE, "12345", id="title_search"),
+            pytest.param(SearchMode.TEXT, "12345", id="text_search"),
+            pytest.param(SearchMode.QUERY, None, id="query_title_exact"),
+        ],
+    )
+    def test_search_modes_match_model_limit_title_tokens(
+        self,
+        backend: TantivyBackend,
+        search_mode: SearchMode,
+        query: str | None,
+    ) -> None:
+        """Search must keep filename-like title tokens up to the model limit."""
+        long_title = "1234567890" * 12 + "12345678"
+        doc = Document.objects.create(
+            title=long_title,
+            content="ordinary content",
+            checksum="TXT12",
+            pk=18,
+        )
+        backend.add_or_update(doc)
+
+        assert backend.search_ids(
+            query or f"title:{long_title}",
+            user=None,
+            search_mode=search_mode,
+        ) == [doc.pk]
+
     @pytest.mark.parametrize(
         ("mode", "title", "content", "hits", "misses"),
         [

src/documents/tests/search/test_tokenizer.py

@@ -99,6 +99,25 @@ class TestTokenizers:
         )
         assert simple_search_index.searcher().search(q, limit=5).count == 1
 
+    def test_simple_search_analyzer_supports_model_limit_token_substrings(
+        self,
+        simple_search_index: tantivy.Index,
+    ) -> None:
+        """Simple substring search keeps tokens up to Document.title's model limit."""
+        long_token = "abcdefghij" * 12 + "abcdefgh"
+        writer = simple_search_index.writer()
+        doc = tantivy.Document()
+        doc.add_text("simple_content", long_token)
+        writer.add_document(doc)
+        writer.commit()
+        simple_search_index.reload()
+        q = tantivy.Query.regex_query(
+            simple_search_index.schema,
+            "simple_content",
+            ".*cdefg.*",
+        )
+        assert simple_search_index.searcher().search(q, limit=5).count == 1
+
     def test_unsupported_language_logs_warning(self, caplog: LogCaptureFixture) -> None:
         """Unsupported language codes should log a warning and disable stemming gracefully."""
         sb = tantivy.SchemaBuilder()

src/documents/tests/search/test_translate.py

@@ -716,6 +716,12 @@ class TestISODatetimeBounds:
             "added:[2026-05-01T00:00:00Z TO 2026-06-01T00:00:00Z]"
         )
 
+    def test_translate_query_text_before_comma_separated_date_clause(self) -> None:
+        result = translate_query("schäfersee,created:previous year", UTC)
+        assert result == (
+            "schäfersee AND created:[2025-01-01T00:00:00Z TO 2026-01-01T00:00:00Z]"
+        )
+
     def test_invalid_iso_datetime_raises(self) -> None:
         # A token with "T" that is not valid ISO datetime -> raise.
         with pytest.raises(InvalidDateQuery) as exc_info:

src/documents/tests/test_sanity_check.py

@@ -12,6 +12,7 @@ from typing import TYPE_CHECKING
 
 import pytest
 
+from documents.sanity_checker import SanityCheckMessages
 from documents.sanity_checker import check_sanity
 
 if TYPE_CHECKING:
@@ -21,6 +22,26 @@ if TYPE_CHECKING:
     from documents.tests.conftest import PaperlessDirs
 
 
+class TestSanityCheckMessages:
+    def test_document_counts_are_unique_per_severity(self) -> None:
+        messages = SanityCheckMessages()
+
+        messages.error(1, "first error")
+        messages.error(1, "second error")
+        messages.warning(1, "first warning")
+        messages.warning(1, "second warning")
+        messages.info(1, "first info")
+        messages.info(1, "second info")
+        messages.warning(None, "global warning")
+
+        assert messages.document_count == 1
+        assert messages.document_error_count == 1
+        assert messages.document_warning_count == 1
+        assert messages.document_info_count == 1
+        assert messages.global_warning_count == 1
+        assert messages.total_issue_count == 5
+
+
 @pytest.mark.django_db
 class TestCheckSanityNoDocuments:
     """Sanity checks against an empty archive."""

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: 2026-06-03 22:14+0000\n"
+"POT-Creation-Date: 2026-06-23 14:33+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -21,39 +21,39 @@ msgstr ""
 msgid "Documents"
 msgstr ""
 
-#: documents/filters.py:463
+#: documents/filters.py:464
 msgid "Value must be valid JSON."
 msgstr ""
 
-#: documents/filters.py:482
+#: documents/filters.py:483
 msgid "Invalid custom field query expression"
 msgstr ""
 
-#: documents/filters.py:492
+#: documents/filters.py:493
 msgid "Invalid expression list. Must be nonempty."
 msgstr ""
 
-#: documents/filters.py:513
+#: documents/filters.py:514
 msgid "Invalid logical operator {op!r}"
 msgstr ""
 
-#: documents/filters.py:527
+#: documents/filters.py:528
 msgid "Maximum number of query conditions exceeded."
 msgstr ""
 
-#: documents/filters.py:591
+#: documents/filters.py:592
 msgid "{name!r} is not a valid custom field."
 msgstr ""
 
-#: documents/filters.py:628
+#: documents/filters.py:629
 msgid "{data_type} does not support query expr {expr!r}."
 msgstr ""
 
-#: documents/filters.py:743 documents/models.py:136
+#: documents/filters.py:744 documents/models.py:136
 msgid "Maximum nesting depth exceeded."
 msgstr ""
 
-#: documents/filters.py:990
+#: documents/filters.py:1052
 msgid "Custom field not found"
 msgstr ""
 
@@ -1351,49 +1351,49 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:463 documents/serialisers.py:815
-#: documents/serialisers.py:2681 documents/views.py:295 documents/views.py:2468
+#: documents/serialisers.py:503 documents/serialisers.py:855
+#: documents/serialisers.py:2744 documents/views.py:297 documents/views.py:2482
 #: paperless_mail/serialisers.py:155
 msgid "Insufficient permissions."
 msgstr ""
 
-#: documents/serialisers.py:651
+#: documents/serialisers.py:691
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:2175
+#: documents/serialisers.py:2216
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:2219
+#: documents/serialisers.py:2260
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:2226
+#: documents/serialisers.py:2267
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:2243 documents/serialisers.py:2253
+#: documents/serialisers.py:2284 documents/serialisers.py:2294
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:2248
+#: documents/serialisers.py:2289
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2395
+#: documents/serialisers.py:2436
 msgid "Invalid variable detected."
 msgstr ""
 
-#: documents/serialisers.py:2737
+#: documents/serialisers.py:2800
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2767 documents/views.py:4345
+#: documents/serialisers.py:2830 documents/views.py:4429
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1661,32 +1661,36 @@ msgstr ""
 msgid "Unable to parse URI {value}"
 msgstr ""
 
-#: documents/views.py:288 documents/views.py:2465
+#: documents/views.py:290 documents/views.py:2479
 msgid "Invalid more_like_id"
 msgstr ""
 
-#: documents/views.py:1511
+#: documents/views.py:1513
 msgid "Invalid AI configuration."
 msgstr ""
 
-#: documents/views.py:2290 documents/views.py:2606
+#: documents/views.py:1522
+msgid "AI backend request timed out."
+msgstr ""
+
+#: documents/views.py:2304 documents/views.py:2625
 msgid "Specify only one of text, title_search, query, or more_like_id."
 msgstr ""
 
-#: documents/views.py:4357
+#: documents/views.py:4441
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:4403
+#: documents/views.py:4487
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:4463
+#: documents/views.py:4547
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:4473
+#: documents/views.py:4557
 msgid "The share link bundle is unavailable."
 msgstr ""
 
@@ -1935,154 +1939,158 @@ msgid "Sets the LLM output language"
 msgstr ""
 
 #: paperless/models.py:370
+msgid "Sets the LLM timeout in seconds"
+msgstr ""
+
+#: paperless/models.py:376
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings/__init__.py:539
+#: paperless/settings/__init__.py:545
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings/__init__.py:540
+#: paperless/settings/__init__.py:546
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings/__init__.py:541
+#: paperless/settings/__init__.py:547
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings/__init__.py:542
+#: paperless/settings/__init__.py:548
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings/__init__.py:543
+#: paperless/settings/__init__.py:549
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:544
+#: paperless/settings/__init__.py:550
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings/__init__.py:545
+#: paperless/settings/__init__.py:551
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings/__init__.py:546
+#: paperless/settings/__init__.py:552
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings/__init__.py:547
+#: paperless/settings/__init__.py:553
 msgid "German"
 msgstr ""
 
-#: paperless/settings/__init__.py:548
+#: paperless/settings/__init__.py:554
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings/__init__.py:549
+#: paperless/settings/__init__.py:555
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings/__init__.py:550
+#: paperless/settings/__init__.py:556
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings/__init__.py:551
+#: paperless/settings/__init__.py:557
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings/__init__.py:552
+#: paperless/settings/__init__.py:558
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings/__init__.py:553
+#: paperless/settings/__init__.py:559
 msgid "French"
 msgstr ""
 
-#: paperless/settings/__init__.py:554
+#: paperless/settings/__init__.py:560
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:555
+#: paperless/settings/__init__.py:561
 msgid "Indonesian"
 msgstr ""
 
-#: paperless/settings/__init__.py:556
+#: paperless/settings/__init__.py:562
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings/__init__.py:557
+#: paperless/settings/__init__.py:563
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings/__init__.py:558
+#: paperless/settings/__init__.py:564
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings/__init__.py:559
+#: paperless/settings/__init__.py:565
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings/__init__.py:560
+#: paperless/settings/__init__.py:566
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings/__init__.py:561
+#: paperless/settings/__init__.py:567
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings/__init__.py:562
+#: paperless/settings/__init__.py:568
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings/__init__.py:563
+#: paperless/settings/__init__.py:569
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings/__init__.py:564
+#: paperless/settings/__init__.py:570
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings/__init__.py:565
+#: paperless/settings/__init__.py:571
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings/__init__.py:566
+#: paperless/settings/__init__.py:572
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings/__init__.py:567
+#: paperless/settings/__init__.py:573
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings/__init__.py:568
+#: paperless/settings/__init__.py:574
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings/__init__.py:569
+#: paperless/settings/__init__.py:575
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings/__init__.py:570
+#: paperless/settings/__init__.py:576
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings/__init__.py:571
+#: paperless/settings/__init__.py:577
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings/__init__.py:572
+#: paperless/settings/__init__.py:578
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings/__init__.py:573
+#: paperless/settings/__init__.py:579
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings/__init__.py:574
+#: paperless/settings/__init__.py:580
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings/__init__.py:575
+#: paperless/settings/__init__.py:581
 msgid "Chinese Traditional"
 msgstr ""
 

src/paperless_ai/ai_classifier.py

@@ -87,7 +87,7 @@ def build_localization_prompt(suggestions: dict, output_language: str) -> str:
     Return the same JSON schema with all fields present.
 
     Suggestions:
-    {json.dumps(suggestions)}
+    {json.dumps(suggestions, ensure_ascii=False)}
     """.strip()
 
 

src/paperless_ai/tests/test_ai_classifier.py

@@ -239,6 +239,23 @@ def test_get_language_name_falls_back_to_language_code():
     assert get_language_name("zz-zz") == "zz-zz"
 
 
+def test_build_localization_prompt_preserves_unicode_characters():
+    prompt = build_localization_prompt(
+        {
+            "title": "Gebührenbescheid",
+            "tags": [],
+            "correspondents": [],
+            "document_types": [],
+            "storage_paths": [],
+            "dates": [],
+        },
+        output_language="de-de",
+    )
+
+    assert "Gebührenbescheid" in prompt
+    assert "\\u00fc" not in prompt
+
+
 @patch("paperless_ai.ai_classifier.query_similar_documents")
 def test_get_context_for_document(
     mock_query_similar_documents,

src/paperless_mail/migrations/0002_optimize_integer_field_sizes.py

@@ -4,6 +4,12 @@ from django.db import migrations
 from django.db import models
 
 
+def clamp_mailrule_maximum_age(apps, schema_editor):
+    # Clamp the maximum_age field of MailRule because of PositiveIntegerField --> PositiveSmallIntegerField
+    MailRule = apps.get_model("paperless_mail", "MailRule")
+    MailRule.objects.filter(maximum_age__gt=32767).update(maximum_age=32767)
+
+
 class Migration(migrations.Migration):
     dependencies = [
         ("paperless_mail", "0001_squashed"),
@@ -112,6 +118,10 @@ class Migration(migrations.Migration):
                 verbose_name="consumption scope",
             ),
         ),
+        migrations.RunPython(
+            clamp_mailrule_maximum_age,
+            migrations.RunPython.noop,
+        ),
         migrations.AlterField(
             model_name="mailrule",
             name="maximum_age",