fix: Produktions-Crash durch TypeORM-synchronize beheben

NODE_ENV=production deaktiviert synchronize (zerstörerischer ADD/DROP-COLUMN-
Churn auf MariaDB, der die 8126-Byte-Zeilengröße sprengte) und aktiviert
migrationsRun. Neue data-source.ts als einzige Konfigquelle (Laufzeit + CLI),
Migrations-Workflow (generate/run/revert) inkl. dotenv ergänzt.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.env.example

@@ -7,6 +7,13 @@
 # Produktion: VITE_API_URL leer lassen (nginx Reverse-Proxy leitet /api weiter)
 # =============================================================================
 
+# --- Umgebung ---
+# Produktion: NODE_ENV=production -> KEIN TypeORM-synchronize (Schema via Migrationen),
+#             Migrationen werden beim Start automatisch ausgeführt (migrationsRun).
+#             Aktiviert zudem CORS-Schutz (siehe CORS_ORIGIN weiter unten).
+# Entwicklung: NODE_ENV leer lassen -> synchronize ON (Schema folgt den Entities).
+NODE_ENV=production
+
 # --- Ports ---
 BACKEND_PORT=7601
 FRONTEND_PORT=7600

CLAUDE.md

@@ -78,11 +78,37 @@ Use `@Public()` to bypass auth guards entirely.
 
 ### Database
 
-- TypeORM with MySQL 8+, UTF8MB4, `synchronize: true` (schema auto-migrates)
+- TypeORM with MySQL/MariaDB, UTF8MB4
+- Connection config lives in `src/database/data-source.ts` (single source of truth,
+  shared by the NestJS runtime and the TypeORM CLI). `database.module.ts` consumes it.
+- **Schema strategy depends on `NODE_ENV`:**
+  - Dev (`NODE_ENV` unset): `synchronize: true` — schema auto-migrates from entities.
+  - Production (`NODE_ENV=production`): `synchronize: false` + `migrationsRun: true` —
+    pending migrations in `src/database/migrations/` are applied automatically on boot.
+    **Never run `synchronize` against the production DB** — on MariaDB it issues
+    destructive `ADD`/`DROP COLUMN` churn every boot (see caveat below).
 - 23 entities in `src/database/entities/`
 - JSON columns use transformers to normalize empty arrays/objects to `null`
 - Key entities: `InboxDocument`, `Task`, `Email`, `Attachment`, `Postprocessing`, `BarcodeTemplate`, `LabelPrintJob`, `ApiKey`, `Setting`
 
+#### Migrations workflow
+
+```bash
+npm run migration:generate -- src/database/migrations/<Name>   # diff entities → DB
+npm run migration:run                                          # apply pending
+npm run migration:revert                                       # roll back last
+```
+
+The existing production schema is the implicit baseline (no baseline migration); only
+future changes get migration files.
+
+**Caveat — MariaDB reports `json` as `longtext`:** every `@Column({ type: 'json' })`
+is stored as `longtext ... CHECK (json_valid(...))`, so `migration:generate` always
+emits spurious no-op `CHANGE` statements (json↔longtext, nullable/default re-declares).
+**Hand-trim generated migrations** down to the real change before committing. (This same
+false diff is exactly why `synchronize` must stay off in production — left unchecked it
+accumulates `ALGORITHM=INSTANT` drops until a table trips the 8126-byte row-size limit.)
+
 ### Document Processing Pipeline
 
 **Preprocessing** (`preprocessing/document-pipeline.service.ts`):

docker-compose.yml

@@ -8,6 +8,8 @@ services:
     ports:
       - "${BACKEND_PORT:-7601}:3100"
     environment:
+      - NODE_ENV=production
+      - CORS_ORIGIN=${CORS_ORIGIN:-}
       - PORT=3100
       - DB_HOST=${DB_HOST:-db}
       - DB_PORT=${DB_PORT:-3306}

paperless-backend/package-lock.json

@@ -24,6 +24,7 @@
         "axios": "^1.14.0",
         "basic-ftp": "^5.2.1",
         "chokidar": "^4.0.3",
+        "dotenv": "^17.4.2",
         "form-data": "^4.0.5",
         "imapflow": "^1.3.2",
         "jsqr": "^1.4.0",
@@ -3023,6 +3024,18 @@
         "rxjs": "^7.1.0"
       }
     },
+    "node_modules/@nestjs/config/node_modules/dotenv": {
+      "version": "17.2.3",
+      "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz",
+      "integrity": "sha512-JVUnt+DUIzu87TABbhPmNfVdBDt18BLOWjMUFJMSi/Qqg7NTYtabbvSNJGOJ7afbRuv9D/lngizHtP7QyLQ+9w==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://dotenvx.com"
+      }
+    },
     "node_modules/@nestjs/core": {
       "version": "11.1.17",
       "resolved": "https://registry.npmjs.org/@nestjs/core/-/core-11.1.17.tgz",
@@ -6291,9 +6304,9 @@
       }
     },
     "node_modules/dotenv": {
-      "version": "17.2.3",
-      "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz",
-      "integrity": "sha512-JVUnt+DUIzu87TABbhPmNfVdBDt18BLOWjMUFJMSi/Qqg7NTYtabbvSNJGOJ7afbRuv9D/lngizHtP7QyLQ+9w==",
+      "version": "17.4.2",
+      "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.4.2.tgz",
+      "integrity": "sha512-nI4U3TottKAcAD9LLud4Cb7b2QztQMUEfHbvhTH09bqXTxnSie8WnjPALV/WMCrJZ6UV/qHJ6L03OqO3LcdYZw==",
       "license": "BSD-2-Clause",
       "engines": {
         "node": ">=12"

paperless-backend/package.json

@@ -17,7 +17,11 @@
     "test:watch": "jest --watch",
     "test:cov": "jest --coverage",
     "test:debug": "node --inspect-brk -r tsconfig-paths/register -r ts-node/register node_modules/.bin/jest --runInBand",
-    "test:e2e": "jest --config ./test/jest-e2e.json"
+    "test:e2e": "jest --config ./test/jest-e2e.json",
+    "typeorm": "typeorm-ts-node-commonjs -d ./src/database/data-source.ts",
+    "migration:generate": "npm run typeorm -- migration:generate",
+    "migration:run": "npm run typeorm -- migration:run",
+    "migration:revert": "npm run typeorm -- migration:revert"
   },
   "dependencies": {
     "@nestjs/common": "^11.0.1",
@@ -35,6 +39,7 @@
     "axios": "^1.14.0",
     "basic-ftp": "^5.2.1",
     "chokidar": "^4.0.3",
+    "dotenv": "^17.4.2",
     "form-data": "^4.0.5",
     "imapflow": "^1.3.2",
     "jsqr": "^1.4.0",

paperless-backend/src/database/data-source.ts

@@ -0,0 +1,81 @@
+import 'reflect-metadata';
+import { join } from 'path';
+import { config as loadEnv } from 'dotenv';
+import { DataSource, DataSourceOptions } from 'typeorm';
+import {
+  Client,
+  DocumentType,
+  DocumentField,
+  Task,
+  Postprocessing,
+  PostprocessingAction,
+  PostprocessingLog,
+  ExportTarget,
+  Setting,
+  Kontonummer,
+  Document,
+  UserClient,
+  Email,
+  Attachment,
+  Content,
+  ApiKey,
+  CorrespondentSetting,
+  BarcodeTemplate,
+  InboxDocument,
+  InboxPostprocessingAction,
+  CorrespondentEmailMapping,
+  UserSettings,
+  LabelPrintJob,
+} from './entities';
+
+// CLI-Kontext: .env laden (Laufzeit im Container liefert die Variablen via Docker,
+// dotenv ist dort ein No-Op). dotenv überschreibt bereits gesetzte Variablen nicht.
+loadEnv();
+loadEnv({ path: join(process.cwd(), '..', '.env') });
+
+export const entities = [
+  Client,
+  DocumentType,
+  DocumentField,
+  Task,
+  Postprocessing,
+  PostprocessingAction,
+  PostprocessingLog,
+  ExportTarget,
+  Setting,
+  Kontonummer,
+  Document,
+  UserClient,
+  Email,
+  Attachment,
+  Content,
+  ApiKey,
+  CorrespondentSetting,
+  BarcodeTemplate,
+  InboxDocument,
+  InboxPostprocessingAction,
+  CorrespondentEmailMapping,
+  UserSettings,
+  LabelPrintJob,
+];
+
+const isProduction = process.env.NODE_ENV === 'production';
+
+export const dataSourceOptions: DataSourceOptions = {
+  type: 'mysql',
+  host: process.env.DB_HOST ?? 'localhost',
+  port: Number(process.env.DB_PORT ?? 3306),
+  username: process.env.DB_USERNAME ?? 'root',
+  password: process.env.DB_PASSWORD ?? '',
+  database: process.env.DB_DATABASE ?? 'paperlessadd',
+  charset: 'utf8mb4',
+  entities,
+  migrations: [join(__dirname, 'migrations', '*.{ts,js}')],
+  // In Produktion: kein synchronize (zerstörerischer ALTER-Churn), Migrationen
+  // werden beim Start automatisch ausgeführt. In Dev: synchronize wie bisher.
+  synchronize: !isProduction,
+  migrationsRun: isProduction,
+};
+
+// Wird von der TypeORM-CLI verwendet (migration:generate / :run / :revert).
+export default new DataSource(dataSourceOptions);

paperless-backend/src/database/database.module.ts

@@ -1,75 +1,12 @@
 import { Module } from '@nestjs/common';
 import { TypeOrmModule } from '@nestjs/typeorm';
-import { ConfigModule, ConfigService } from '@nestjs/config';
-import {
-  Client,
-  DocumentType,
-  DocumentField,
-  Task,
-  Postprocessing,
-  PostprocessingAction,
-  PostprocessingLog,
-  ExportTarget,
-  Setting,
-  Kontonummer,
-  Document,
-  UserClient,
-  Email,
-  Attachment,
-  Content,
-  ApiKey,
-  CorrespondentSetting,
-  BarcodeTemplate,
-  InboxDocument,
-  InboxPostprocessingAction,
-  CorrespondentEmailMapping,
-  UserSettings,
-  LabelPrintJob,
-} from './entities';
-
-const entities = [
-  Client,
-  DocumentType,
-  DocumentField,
-  Task,
-  Postprocessing,
-  PostprocessingAction,
-  PostprocessingLog,
-  ExportTarget,
-  Setting,
-  Kontonummer,
-  Document,
-  UserClient,
-  Email,
-  Attachment,
-  Content,
-  ApiKey,
-  CorrespondentSetting,
-  BarcodeTemplate,
-  InboxDocument,
-  InboxPostprocessingAction,
-  CorrespondentEmailMapping,
-  UserSettings,
-  LabelPrintJob,
-];
+import { dataSourceOptions, entities } from './data-source';
 
 @Module({
   imports: [
-    TypeOrmModule.forRootAsync({
-      imports: [ConfigModule],
-      inject: [ConfigService],
-      useFactory: (config: ConfigService) => ({
-        type: 'mysql' as const,
-        host: config.get<string>('DB_HOST', 'localhost'),
-        port: config.get<number>('DB_PORT', 3306),
-        username: config.get<string>('DB_USERNAME', 'root'),
-        password: config.get<string>('DB_PASSWORD', ''),
-        database: config.get<string>('DB_DATABASE', 'paperlessadd'),
-        entities,
-        synchronize: config.get<string>('NODE_ENV') !== 'production',
-        charset: 'utf8mb4',
-      }),
-    }),
+    // Eine einzige Konfigurationsquelle (data-source.ts), geteilt zwischen
+    // NestJS-Laufzeit und TypeORM-CLI (Migrationen).
+    TypeOrmModule.forRoot(dataSourceOptions),
     TypeOrmModule.forFeature(entities),
   ],
   exports: [TypeOrmModule],